DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 02/24/2026 has been entered.
Response to Amendment
Claims 1-20 were previously pending and subject to final action filed on 09/02/2025. In the response filed 02/24/2026, claims 1-3, 5-6, 11-13 and 16 were amended. Therefore, claims 1-20 are currently pending and subject to the non-final action below.
Response to Arguments
Applicant’s arguments, see page 14, filed 02/24/2026, with respect to claims 1-20 under 35 U.S.C. 112 (b) have been fully considered and are persuasive. The 112 (b) of claims 1-20 has been withdrawn.
Applicant's arguments, see pages 14-17, filed 08/05/2025, with respect to claims 1-20 under 35 U.S.C. 103 have been fully considered but they are not persuasive.
Applicant’s argument 1: This rejection is unsustainable because none of the cited prior art discloses or suggests a method that selects from the recited set of 71 radiomics features a subset of features that distinguishes an X-ray of a COVID patient from an X-ray of a non-COVID patient as required by the present claims nor did it provide a reasonable expectation of success for such a method. Chaganti does not teach the 71 radiomic features which are screened to provide a short subset of radiomics features that distinguish between patients having COVID and those that do not.
While Washko teaches certain radiomics features there is no specific suggestion in any of the references to selective screen the 71 specific radiomics features to identify a subset of distinguishing features characteristic of X-rays from COVID patients. Chaganti differs from the invention in that the invention uses ANOVA to identify specific fixed set of radiomics features that best distinguish COVID-19 from non-COVID-19, see the ANOVA scores for each feature described by Table 2. Unlike in the predictive method of Washko, the inventors determine which subset of radiomics features from the larger set of 71 radiomics features are most useful for distinguishing COVID-19 from non-COVID-19 disorders. Washko, like Chaganti fails to teach the specific subset of radiomics features required by the claims.
Chaganti and Washko also do not suggest deployment of a bagged ensemble applied only to the statistically-determined, fixed radiomics subset with majority voting specifically for distinguishing COVID-19 from non-COVID-19 lung diseases and not merely from distinguishing normal lungs from those with pneumonia. While broad ensemble approaches are taught in the prior art, the inventors developed a pipeline tied to the specific statistically justified features including those not disclosed by the cited art.
Singh was relied upon for teaching classification between COVID-19 and other non- COVID-19 lung diseases using an ensemble bagged model that has a plurality of classifiers. However, Singh does not teach a classifier the employs the combination of the set of 71 radiomics features required by the present claims.
Examiner Response 1: After careful consideration and review of the prior art, the examiner respectfully disagrees with applicant’s arguments. The claim recites the term “comprising” which is an open-ended for the table of radiomic features recited in the independent claim. Because Washko teaches a subset of set of radiomic features. Washko recites in paragraph [0008] that the radiomic features comprises first order, gray level size zone matrix (GLSZM), gray level cooccurrence matrix (GLCM), gray level dependence matrix (GLDM) and several others that are listed in applicant’s claim table. Washko recites selecting a subset, and selecting at least two of the radiomic features is taught by the prior arts of record. Therefore, the examiner maintains that the prior art of record teaches the amendment limitation as recited below.
Chaganti teaches: A method for diagnosis of COVID-19 from at least one chest X-Ray image, comprising: (Chaganti – [abstract] The disease may be COVID-19 (coronavirus disease 2019) or diseases, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), or other types of viral and non-viral pneumonia. [0024] The medical imaging data may be chest CT image 102 of FIG. 1 or input chest CT image 224 of FIG. 2. However, the medical imaging data may be of any suitable modality, such as, e.g., MRI (magnetic resonance imaging), ultrasound, x-ray, or any other modality or combination of modalities.)
imaging, by a chest x-ray machine, a person's chest area to obtain the at least one chest x-ray image; (Chaganti − [0024] an image acquisition device, such as, e.g., a CT scanner,)
performing, by processing circuitry, image segmentation of a human lung in the at least one chest x-ray image; (Chaganti − [0022] A lung segmentation 104 is generated by segmenting the lungs from chest CT 102 and an abnormality segmentation 106 is generated by segmenting abnormality regions associated with COVID-19 from chest CT 102. [0026-0029] At step 304, the lungs are segmented from the medical imaging data. In one example, the lungs are segmented at preprocessing step 202 of FIG. 2 and the segmented lungs may be lung segmentation 104 of FIG. 1.)
extracting, by the processing circuitry, a set of radiomics features from the segmented lung; (Chaganti − [0033] feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
selecting from the set of radiomics features, by the processing circuitry, a subset of the radiomics features for classification ability between two classes of COVID-19 and non- COVID-19 including other lung diseases, (Chaganti − [0033] During the online or testing stage, global classifier 212 receives features of abnormality regions from feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
and outputting, by the processing circuitry, an indication of whether the patient is infected with COVID-19; (Chaganti − [0034] In one embodiment, the assessment of the disease is a diagnosis of the disease for screening. In one example, the diagnosis may be output 222 in FIG. 2 for COVID-19 screening. Global classifier 214 in FIG. 2 is trained with imaging data as well as other patient data, such as, e.g., clinical data, genetic data, lab testing, demographics, DNA data, symptoms, epidemiological factors, etc. During the online or testing stage, global classifier 214 receives patient data 204 and features of abnormality regions from feature extractor 206 to generate a diagnosis as output 222. In one embodiment, global classifier 214 estimates the detection of the disease based on the segmented lung, segmented abnormality regions, and features of the abnormality.)
Washko teaches: wherein said set of radiomics features comprises: (Washko – [0008] In various embodiments, radiomic features comprise one or more of first order statistics, 3D shape based features, 2D shape based features, gray level cooccurrence matrix, gray level run length matrix, gray level size zone matrix, neighboring gray tone difference matrix, and gray level dependence matrix. In various embodiments, radiomic features are extracted from an image that has been transformed by applying a filter, such as a wavelet filter or a gaussian filter.) Washko recites in paragraph [0008] that the radiomic features comprises first order, gray level size zone matrix (GLSZM), gray level cooccurrence matrix (GLCM), gray level dependence matrix (GLDM) and several others that are listed in applicant’s claim table.
PNG
media_image1.png
797
396
media_image1.png
Greyscale
PNG
media_image2.png
543
469
media_image2.png
Greyscale
Singh teaches: classifying, by the processing circuitry, between COVID-19 and non-COVID-19 using an ensemble bagged model having a plurality of classifiers; (Singh – [pdf pages 6-8] 2.7 different classification models are evaluated. (b) bagging ensemble with SVM. 2.7.4 Fig. 5 bagging SVM as the classifier.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Applicant’s argument 2: Claims 3, 8, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Chaganti, Washko, Singh as applied to claims 1,6, 12 above, and further in view of Antoniadis (US PGPUB: 20210374951 Al, Date filed: Sept. 18, 2019). This rejection cannot be sustained for the presently amended claims for the reasons explained above for Chaganti, Washko and Singh. Antoniadis was relied upon for teaching selecting radiomics features to find a subset of features that have a statistically significant difference between means of two classes. However, Antoniadis does not disclose or suggest the selection of the 71 radiomics features required by the pending claims, nor provide a reasonable expectation of success in identifying these specific features.
Examiner response 2: The examiner respectfully disagrees for reasons recited above in examiner response 1. Furthermore, Antoniadis teaches: wherein the selecting of radiomics features includes determining a one-way analysis of variance test to find the subset of features that have a statistically significant difference between means of the two classes., with criteria p<0.05, where p-value is a probability. (Antoniadis − [0208] The 53 stable volume- and orientation-independent radiomic features that were associated with the clinical endpoint above the threshold value (p<0.05; where p is the probability value))
Therefore, the rejection citing Chaganti, Washko, JR, Singh and Antoniadis is maintained.
Applicant’s argument 3: Ahmed was relied upon for teaching that the early stages of COVID-19 are not detectable by chest X-rays and a machine learning algorithm configured to detect COVID-19 with a sensitivity and specificity comparable to RT-PCR but does not remedy the deficiencies in the three primary references. Furthermore, Ahmed did not provide a reasonable expectation of success for a method having a sensitivity equivalent or better than RT-PCR. This rejection cannot be sustained.
The examiner respectfully disagrees for reasons recited above in examiner response 1. Furthermore, Ahmed teaches: wherein the person has an early stage of COVID-19 where signs of COVID-19 are not detectable by a chest x-ray. (Ahmed – [abstract, pdf page 3] ReCoNet (residual image-based COVID-19 detection network) for early COVID-19 detection; assisting professional for CheXpert Dataset used negative dataset. A negative dataset is a chest x-ray that does not show COVID-19 )
Therefore, the rejection citing Chaganti, Washko, JR, Singh and Ahmed is maintained.
Claim Interpretation
Independent claims recites the limitation of “selecting from the set of radiomics features, by the processing circuitry, a subset of the radiomics features…, : wherein said set of radiomics features comprises:”. The examiner is interpreting the claim limitations and the claim term “comprises” as open-ended and does not exclude additional, unrecited elements or methods steps. The claims are not considered a Markush group that requires selection from a closed group “consisting of”. Furthermore, the claims does explicitly a prior art selecting all 71 radiomic features, only a subset. A subset of at the least is two radiomic features under the BRI.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-2, 4-7, and 9-13 are rejected under 35 U.S.C. 103 as being unpatentable over Chaganti (US PGPUB: 20210304408 A1, Filed Date: Apr. 1, 2020) in view of Washko, JR. (US PGPUB: 20210233241 A1, Filed Date: Jan. 15, 2021, hereinafter “Washko”) in further view of Singh (Transfer learning–based ensemble support vector machine model for automated COVID-19 detection using lung computerized tomography scan data, Pub Date: Mar. 18, 2021, hereinafter “Singh”).
Regarding independent claim 1, Chaganti teaches: A method for diagnosis of COVID-19 from at least one chest X-Ray image, comprising: (Chaganti – [abstract] The disease may be COVID-19 (coronavirus disease 2019) or diseases, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), or other types of viral and non-viral pneumonia. [0024] The medical imaging data may be chest CT image 102 of FIG. 1 or input chest CT image 224 of FIG. 2. However, the medical imaging data may be of any suitable modality, such as, e.g., MRI (magnetic resonance imaging), ultrasound, x-ray, or any other modality or combination of modalities.)
imaging, by a chest x-ray machine, a person's chest area to obtain the at least one chest x-ray image; (Chaganti − [0024] an image acquisition device, such as, e.g., a CT scanner,)
performing, by processing circuitry, image segmentation of a human lung in the at least one chest x-ray image; (Chaganti − [0022] A lung segmentation 104 is generated by segmenting the lungs from chest CT 102 and an abnormality segmentation 106 is generated by segmenting abnormality regions associated with COVID-19 from chest CT 102. [0026-0029] At step 304, the lungs are segmented from the medical imaging data. In one example, the lungs are segmented at preprocessing step 202 of FIG. 2 and the segmented lungs may be lung segmentation 104 of FIG. 1.)
extracting, by the processing circuitry, radiomics features from the segmented lung; (Chaganti − [0033] feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
selecting, by the processing circuitry, a subset of the radiomics features for classification ability between two classes of COVID-19 and non-COVID-19 including other lung diseases, (Chaganti − [0033] During the online or testing stage, global classifier 212 receives features of abnormality regions from feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
and outputting, by the processing circuitry, an indication of whether the patient is infected with COVID-19. (Chaganti − [0034] In one embodiment, the assessment of the disease is a diagnosis of the disease for screening. In one example, the diagnosis may be output 222 in FIG. 2 for COVID-19 screening. Global classifier 214 in FIG. 2 is trained with imaging data as well as other patient data, such as, e.g., clinical data, genetic data, lab testing, demographics, DNA data, symptoms, epidemiological factors, etc. During the online or testing stage, global classifier 214 receives patient data 204 and features of abnormality regions from feature extractor 206 to generate a diagnosis as output 222. In one embodiment, global classifier 214 estimates the detection of the disease based on the segmented lung, segmented abnormality regions, and features of the abnormality.)
Chaganti does not explicitly teach: wherein said set of radiomics features comprises: table
However, Washko teaches: wherein said set of radiomics features comprises: wherein said set of radiomics features comprises: (Washko – [0008] In various embodiments, radiomic features comprise one or more of first order statistics, 3D shape based features, 2D shape based features, gray level cooccurrence matrix, gray level run length matrix, gray level size zone matrix, neighboring gray tone difference matrix, and gray level dependence matrix. In various embodiments, radiomic features are extracted from an image that has been transformed by applying a filter, such as a wavelet filter or a gaussian filter.) Washko recites in paragraph [0008] that the radiomic features comprises first order, gray level size zone matrix (GLSZM), gray level cooccurrence matrix (GLCM), gray level dependence matrix (GLDM) and several others
PNG
media_image1.png
797
396
media_image1.png
Greyscale
PNG
media_image2.png
543
469
media_image2.png
Greyscale
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti and Washko as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Washko provide Chaganti with a plurality of radiomic features for extracting features from medical imagery. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Chaganti does not explicitly teach: an ensemble bagged model
However, Singh teaches: classifying, by the processing circuitry, between COVID-19 and non-COVID-19 using an ensemble bagged model having a plurality of classifiers; (Singh – [pdf pages 6-8] 2.7 different classification models are evaluated. (b) bagging ensemble with SVM. 2.7.4 Fig. 5 bagging SVM as the classifier.)
PNG
media_image3.png
391
971
media_image3.png
Greyscale
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 2, depends on claim 1, Chaganti does not explicitly teach: producing a heatmap
However, Singh teaches: wherein the selecting of the set of radiomics features includes producing a heatmap of Z-scores for the radiomics features to identify the subset of radiomics features that significantly classify the two classes of COVID- 19 and other lung diseases. (Singh – [pdf pages 6-8] 2.7.4 Fig. 5 bagging SVM as the classifier.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 4, depends on claim 1, Chaganti does not explicitly teach: wherein the plurality of classifiers for the ensemble bagged model are decision trees
However, Singh teaches: wherein the plurality of classifiers for the ensemble bagged model are decision trees. (Singh – [pdf page 7, 2.7.4 Bagging ensemble with SVM] The individual classifiers are trained independently with the bootstrap technique. Bootstrap technique is decision trees.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 5, depends on claim 1, Chaganti teaches: wherein the imaging, by a chest x-ray machine, is performed for a plurality of different persons to obtain a plurality of chest x-ray images for the different persons, (Chaganti − [0014] FIG. 5 shows a table of details of a dataset used for training and testing a network for the segmentation of lungs, in accordance with one or more embodiments; [0015] FIG. 6 shows a table of details of a dataset used for training and testing a network for the segmentation of abnormality regions, in accordance with one or more embodiments;)
and wherein the plurality of chest x-ray images are grouped by a level of severity based on the extent of involvement by ground glass opacities, (Chaganti − [0005] In one embodiment, the disease may be COVID-19 (coronavirus disease 2019) and the abnormality regions associated with COVID-19 comprise opacities of one or more of ground glass opacities (GGO), consolidation, and crazy-paving pattern.)
and the classifying is separately performed for each group (Chaganti − [0016] FIG. 7 shows a scatter plot comparing ground truth and predicted lung severity scores, in accordance with one or more embodiments;)
and wherein said method further comprises treating a diagnosed patient for COVID-19. (In one embodiment, the disease may be COVID-19 (Chaganti − [0005] coronavirus disease 2019) and the abnormality regions associated with COVID-19 comprise opacities of one or more of ground glass opacities (GGO), consolidation, and crazy-paving pattern. However, the disease may be any other disease, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), other types of viral pneumonia, bacterial pneumonia, fungal pneumonia, mycoplasma pneumonia, and other types of pneumonia.)
Regarding independent claim 6, Chaganti teaches: A [computing device] for diagnosis of COVID-19 from at least one Chest X-Ray image, comprising: (Chaganti – [abstract] The disease may be COVID-19 (coronavirus disease 2019) or diseases, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), or other types of viral and non-viral pneumonia. [0024] The medical imaging data may be chest CT image 102 of FIG. 1 or input chest CT image 224 of FIG. 2. However, the medical imaging data may be of any suitable modality, such as, e.g., MRI (magnetic resonance imaging), ultrasound, x-ray, or any other modality or combination of modalities. [0051] Computer 902 may also include one or more input/output devices 908 that enable user interaction with computer 902 (e.g., display, keyboard, mouse, speakers, buttons, etc.)
a display device; (Chaganti – [0051] Computer 902 may also include one or more input/output devices 908 that enable user interaction with computer 902 (e.g., display, keyboard, mouse, speakers, buttons, etc.)
and processing circuitry configured to: perform image segmentation of a human lung in the at least one Chest X-Ray image; (Chaganti − [0022] A lung segmentation 104 is generated by segmenting the lungs from chest CT 102 and an abnormality segmentation 106 is generated by segmenting abnormality regions associated with COVID-19 from chest CT 102. [0026-0029] At step 304, the lungs are segmented from the medical imaging data. In one example, the lungs are segmented at preprocessing step 202 of FIG. 2 and the segmented lungs may be lung segmentation 104 of FIG. 1.)
extract radiomics features from the segmented lung; (Chaganti − [0033] feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
select a subset of the radiomics features for classification ability between two classes of COVID-19 and non-COVID-19 including other lung diseases, (Chaganti − [0033] During the online or testing stage, global classifier 212 receives features of abnormality regions from feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
and output to the display device an indication of whether the patient is infected with COVID-19. (Chaganti − [0034] In one embodiment, the assessment of the disease is a diagnosis of the disease for screening. In one example, the diagnosis may be output 222 in FIG. 2 for COVID-19 screening. Global classifier 214 in FIG. 2 is trained with imaging data as well as other patient data, such as, e.g., clinical data, genetic data, lab testing, demographics, DNA data, symptoms, epidemiological factors, etc. During the online or testing stage, global classifier 214 receives patient data 204 and features of abnormality regions from feature extractor 206 to generate a diagnosis as output 222. In one embodiment, global classifier 214 estimates the detection of the disease based on the segmented lung, segmented abnormality regions, and features of the abnormality.)
Chaganti does not explicitly teach: wherein said set of radiomics features comprises: table
However, Washko teaches: wherein said set of radiomics features comprises: wherein said set of radiomics features comprises: (Washko – [0008] In various embodiments, radiomic features comprise one or more of first order statistics, 3D shape based features, 2D shape based features, gray level cooccurrence matrix, gray level run length matrix, gray level size zone matrix, neighboring gray tone difference matrix, and gray level dependence matrix. In various embodiments, radiomic features are extracted from an image that has been transformed by applying a filter, such as a wavelet filter or a gaussian filter.) Washko recites in paragraph [0008] that the radiomic features comprises first order, gray level size zone matrix (GLSZM), gray level cooccurrence matrix (GLCM), gray level dependence matrix (GLDM) and several others
PNG
media_image1.png
797
396
media_image1.png
Greyscale
PNG
media_image2.png
543
469
media_image2.png
Greyscale
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti and Washko as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Washko provide Chaganti with a plurality of radiomic features for extracting features from medical imagery. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Chaganti does not explicitly teach: an ensemble bagged model
However, Singh teaches: classify between COVID-19 and non-COVID-19 using an ensemble bagged model having a plurality of classifiers; (Singh – [pdf pages 6-8] 2.7 different classification models are evaluated. (b) bagging ensemble with SVM. 2.7.4 Fig. 5 bagging SVM as the classifier.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 7, depends on claim 6, Chaganti does not explicitly teach: producing a heatmap
However, Singh teaches: wherein the processing circuitry is further configured to produce a heatmap of Z-scores for the radiomics features to identify the subset of radiomics features that significantly classify the two classes of COVID-19 and other lung diseases. (Singh – [pdf pages 6-8] 2.7.4 Fig. 5 bagging SVM as the classifier.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 9, depends on claim 6, Chaganti does not explicitly teach: wherein the plurality of classifiers for the ensemble bagged model are decision trees.
However, Singh teaches: wherein the plurality of classifiers for the ensemble bagged model are decision trees. (Singh – [pdf page 7, 2.7.4 Bagging ensemble with SVM] The individual classifiers are trained independently with the bootstrap technique. Bootstrap technique is decision trees.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 10, depends on claim 6, Chaganti teaches: further comprising: communication circuitry configured to wirelessly communicate with at least one chest x-ray machine to receive the at least one chest x-ray image. (Chaganti – [abstract] The disease may be COVID-19 (coronavirus disease 2019) or diseases, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), or other types of viral and non-viral pneumonia. [0024] The medical imaging data may be chest CT image 102 of FIG. 1 or input chest CT image 224 of FIG. 2. However, the medical imaging data may be of any suitable modality, such as, e.g., MRI (magnetic resonance imaging), ultrasound, x-ray, or any other modality or combination of modalities.)
Regarding dependent claim 11, depends on claim 10, Chaganti teaches: wherein the communication circuitry is configured to wirelessly communicate with a plurality of chest x-ray machines to receive a respective plurality of chest x-ray images for a plurality of patients, (Chaganti − [0055] An image acquisition device 914 can be connected to the computer 902 to input image data (e.g., medical images) to the computer 902. It is possible to implement the image acquisition device 914 and the computer 902 as one device. It is also possible that the image acquisition device 914 and the computer 902 communicate wirelessly through a network. Fig. 5 and Fig. 6 datasets.)
wherein the processing circuitry is further configured to perform image segmentation of a human lung in each of the plurality of chest X-ray images; (Chaganti − [0022] A lung segmentation 104 is generated by segmenting the lungs from chest CT 102 and an abnormality segmentation 106 is generated by segmenting abnormality regions associated with COVID-19 from chest CT 102. [0026-0029] At step 304, the lungs are segmented from the medical imaging data. In one example, the lungs are segmented at preprocessing step 202 of FIG. 2 and the segmented lungs may be lung segmentation 104 of FIG. 1.)
extract radiomics features from the segmented lungs; (Chaganti − [0033] feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
select form a set of radiomic features a subset of the radiomics features for classification ability between two classes of COVID-19 and non-COVID-19; (Chaganti − [0033] During the online or testing stage, global classifier 212 receives features of abnormality regions from feature extractor 206 and abnormality segmentation 208 to generate a classification of the disease as output 220. In one embodiment, the classification of the disease is determined by global classifier 212 based on the volume abnormality regions relative to the volume of the lungs, HU density histogram, texture, and other radiomic features of the abnormalities present in the lungs.)
and output to the display device, while simultaneously storing in a database, an indication for each of the plurality of patients whether the respective patient is infected with COVID-19. (Chaganti − [0034] In one embodiment, the assessment of the disease is a diagnosis of the disease for screening. In one example, the diagnosis may be output 222 in FIG. 2 for COVID-19 screening. Global classifier 214 in FIG. 2 is trained with imaging data as well as other patient data, such as, e.g., clinical data, genetic data, lab testing, demographics, DNA data, symptoms, epidemiological factors, etc. During the online or testing stage, global classifier 214 receives patient data 204 and features of abnormality regions from feature extractor 206 to generate a diagnosis as output 222. In one embodiment, global classifier 214 estimates the detection of the disease based on the segmented lung, segmented abnormality regions, and features of the abnormality. [0035] At step 310, the assessment of the disease is output. For example, the assessment of the disease can be output by displaying the assessment of the disease on a display device of a computer system, storing the assessment of the disease on a memory or storage of a computer system, or by transmitting the assessment of the disease to a remote computer system.)
Chaganti does not explicitly teach: an ensemble bagged model
However, Singh teaches: classify between COVID-19 and non-COVID-19, for each of the plurality of chest x- ray images using the ensemble bagged model having the plurality of classifiers; (Singh – [pdf pages 6-8] 2.7 different classification models are evaluated. (b) bagging ensemble with SVM. 2.7.4 Fig. 5 bagging SVM as the classifier.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding independent claim 12, is directed to a non-transitory computer readable storage medium (Chaganti − [0050]). Claim 12 have similar/same technical features/limitation as claim 1 and claim 12 is rejected under the same rationale.
Regarding dependent claim 13, depends on claim 12, Chaganti does not explicitly teach: producing a heatmap
However, Singh teaches: wherein the diagnostic method further includes producing a heatmap of Z-scores for the set of radiomics features to identify the subset of radiomics features that significantly classify the two classes of COVID- 19 and other lung diseases. (Singh – [pdf pages 6-8] 2.7.4 Fig. 5 bagging SVM as the classifier.)
Accordingly, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teaching of Chaganti, Washko and Singh as each invention teaches predicting lung disease from medical imagery data. Adding the teaching of Singh provide Chaganti and Washko with an ensemble bagging model for classifying lung diseases. One of ordinary skill in the art would have been motivated to improve prediction of lung diseases from region of interest in medical imagery data [abstract].
Claims 3, 8, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Chaganti, Washko, Singh as applied to claims 1, 6, 12 above, and further in view of Antoniadis (US PGPUB: 20210374951 A1, Filed Date: Sept. 18, 2019).
Regarding dependent claim 3, depends on claim 1, Chaganti does not explicitly teach: wherein the selecting of radiomics features includes determining a one-way analysis of variance test to find the subset of features that have a statistically significant difference between means of the two classes., with criteria p<0.05, where p-value is a probability.
However, Antoniadis teaches: wherein the selecting of the set of radiomics features includes determining a one-way analysis of variance test to find the subset of features that have a statistically significant difference between means of the two classes., with criteria p<0.05, where p-value is a probability. (Antoniadis − [0208] The 53 stable volume- and orientation-independent radiomic features that were associated with the clinical endpoint above the threshold value (p<0.05; where p is the probability value))
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Antoniadis in order to develop a system for improving prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 8, depends on claim 6, Chaganti does not explicitly teach: wherein the processing circuitry is further configured to determine a one-way analysis of variance test to find the subset of features that have a statistically significant difference between means of the two classes., with criteria p<0.05, where p-value is a probability.
However, Antoniadis teaches: wherein the processing circuitry is further configured to determine a one-way analysis of variance test to find the subset of features that have a statistically significant difference between means of the two classes., with criteria p<0.05, where p-value is a probability. (Antoniadis − [0208] The 53 stable volume- and orientation-independent radiomic features that were associated with the clinical endpoint above the threshold value (p<0.05; where p is the probability value))
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Antoniadis in order to develop a system for improving prediction of lung diseases from region of interest in medical imagery data [abstract].
Regarding dependent claim 14, depends on claim 12, Chaganti does not explicitly teach: wherein the diagnostic method further includes determining a one-way analysis of variance test to find the subset of features that have a statistically significant difference between means of the two classes., with criteria p<0.05, where p-value is a probability.
However, Antoniadis teaches: wherein the diagnostic method further includes determining a one-way analysis of variance test to find the subset of features that have a statistically significant difference between means of the two classes., with criteria p<0.05, where p-value is a probability. (Antoniadis − [0208] The 53 stable volume- and orientation-independent radiomic features that were associated with the clinical endpoint above the threshold value (p<0.05; where p is the probability value))
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Antoniadis in order to develop a system for improving prediction of lung diseases from region of interest in medical imagery data [abstract].
Claims 15-20 are rejected under 35 U.S.C. 103 as being unpatentable over Chaganti, Washko, Singh as applied to claims 1, 6, 12 above, and further in view of Sabbir Ahmed (ReCoNet: Multi-level Preprocessing of Chest X-rays for COVID-19 Detection Using Convolutional Neural Networks, Pub Date: July 11, 2020, hereinafter “Ahmed”).
Regarding dependent claim 15, depends on claim 1, Chaganti does not explicitly teach: wherein the person has an early stage of COVID-19 where signs of COVID-19 are not detectable by a chest x-ray.
However, Ahmed teaches: wherein the person has an early stage of COVID-19 where signs of COVID-19 are not detectable by a chest x-ray. (Ahmed – [abstract, pdf page 3] ReCoNet (residual image-based COVID-19 detection network) for early COVID-19 detection; assisting professional for CheXpert Dataset used negative dataset. A negative dataset is a chest x-ray that does not show COVID-19 )
PNG
media_image4.png
186
495
media_image4.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Ahmed machine learning algorithm (ReCoNet) for improving accuracy of early detection of lung disease as shown in RT-PCR lab testing for lung disease such as COVID-19 [abstract].
Regarding dependent claim 16, depends on claim 1, Chaganti teaches wherein the subset of radiomics features but does not explicitly teach: and machine learning algorithm are configured to detect COVID-19 directly from chest X-ray (CXR) with a sensitivity and specificity at least comparable to that of RT-PCR.
However, Ahmed teaches: wherein the subset of radiomics features and machine learning algorithm are configured to detect COVID-19 directly from chest X-ray (CXR) with a sensitivity and specificity at least comparable to that of RT-PCR. (Ahmed – [pdf page 7-8] Our proposed method achieves an overall Sensitivity, Specificity, Accuracy and MCC of 97:39%, 97:53%, 97:48% and 92:49%,)
PNG
media_image5.png
298
513
media_image5.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Ahmed machine learning algorithm (ReCoNet) for improving accuracy of early detection of lung disease as shown in RT-PCR lab testing for lung disease such as COVID-19 [abstract].
Regarding dependent claim 17, depends on claim 1, Chaganti does not explicitly teach: wherein the support vector machine (SVM) and ensemble bagged model (EBM) based machine learning has an overall sensitivity of 99.6% and 87.8% respectively; and a specificity of 85% and 97%, respectively.
However, Ahmed teaches: wherein the support vector machine (SVM) and ensemble bagged model (EBM) based machine learning has an overall sensitivity of 99.6% and 87.8% respectively; and a specificity of 85% and 97%, respectively. (Ahmed – [pdf pages 7-8] Another unique characteristic of this study is that ReCoNet achieved a sensitivity result of 100% for COVID-19 detection. Our proposed method achieves an overall Sensitivity, Specificity, Accuracy and MCC of 97:39%, 97:53%, 97:48% and 92:49%,)
PNG
media_image5.png
298
513
media_image5.png
Greyscale
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Ahmed machine learning algorithm (ReCoNet) for improving accuracy of early detection of lung disease as shown in RT-PCR lab testing for lung disease such as COVID-19 [abstract].
Regarding dependent claim 18, depends on claim 6, Chaganti does not explicitly teach: detect COVID- 19 directly from CXR with a sensitivity and specificity at least comparable to that of RT-PCR.
However, Ahmed teaches: detect COVID- 19 directly from CXR with a sensitivity and specificity at least comparable to that of RT-PCR. (Ahmed – [abstract, pdf page 3] ReCoNet (residual image-based COVID-19 detection network) for early COVID-19 detection; assisting professional for CheXpert Dataset used negative dataset. A negative dataset is a chest x-ray that does not show COVID-19. Our proposed method achieves an overall Sensitivity, Specificity, Accuracy and MCC of 97:39%, 97:53%, 97:48% and 92:49%, )
Regarding dependent claim 19, depends on claim 12, Chaganti does not explicitly teach: wherein said method for diagnosis detects COVID-19 directly from CXR with a sensitivity and specificity at least comparable to that of RT-PCR.
However, Ahmed teaches: wherein said method for diagnosis detects COVID-19 directly from CXR with a sensitivity and specificity at least comparable to that of RT-PCR. (Ahmed – [abstract, pdf page 3] ReCoNet (residual image-based COVID-19 detection network) for early COVID-19 detection; assisting professional for CheXpert Dataset used negative dataset. A negative dataset is a chest x-ray that does not show COVID-19. Our proposed method achieves an overall Sensitivity, Specificity, Accuracy and MCC of 97:39%, 97:53%, 97:48% and 92:49%, )
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Ahmed machine learning algorithm (ReCoNet) for improving accuracy of early detection of lung disease as shown in RT-PCR lab testing for lung disease such as COVID-19 [abstract].
Regarding dependent claim 20, depends on claim 15, Chaganti teaches: wherein said method does not require sample collection or other manual intervention. (Chaganti − [0024] The medical imaging data may be of any suitable modality, such as, e.g., MRI (magnetic resonance imaging), ultrasound, x-ray, or any other modality or combination of modalities.)
Chaganti does not explicitly teach: detects COVID-19 directly from CXR with a sensitivity and specificity at least comparable to that of RT-PCR,
However, Ahmed teaches: detects COVID-19 directly from CXR with a sensitivity and specificity at least comparable to that of RT-PCR, (Ahmed – [abstract, pdf page 3] ReCoNet (residual image-based COVID-19 detection network) for early COVID-19 detection; assisting professional for CheXpert Dataset used negative dataset. A negative dataset is a chest x-ray that does not show COVID-19. Our proposed method achieves an overall Sensitivity, Specificity, Accuracy and MCC of 97:39%, 97:53%, 97:48% and 92:49%, )
It would have been obvious to one of ordinary skill in the art before the effective filing date to incorporate the teaching of Ahmed machine learning algorithm (ReCoNet) for improving accuracy of early detection of lung disease as shown in RT-PCR lab testing for lung disease such as COVID-19 [abstract].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
JACOBS, US 20240370997 A1 Detecting and characterizing COVID-19.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CARL E BARNES JR whose telephone number is (571)270-3395. The examiner can normally be reached Monday-Friday 9am-6pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Stephen Hong can be reached at (571) 272-4124. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/CARL E BARNES JR/Examiner, Art Unit 2178
/STEPHEN S HONG/Supervisory Patent Examiner, Art Unit 2178