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 .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on September 7th, 2023 and January 10th, 2024 was reviewed and the listed references were noted.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1 and 2 are rejected under 35 U.S.C. 103 as being unpatentable over Miyamoto (JP 2017093879 A) in view of Hu (KR 20210028559 A).
Regarding Claim 1, Miyamoto discloses (Miyamoto, Paragraph [0027], discloses “The measuring apparatus 10 has a bed 14 as an examination table. The subject 16 is placed on the bed 14. The position and posture of the examinee 16 are adjusted so that the measurement target site (test site) is included in the X-ray irradiation area at a predetermined position and posture. In this embodiment, the part to be measured is a soft tissue present on the proximal end of the femur and its surroundings. In other words, it is the hip joint and its vicinity. In practice, X-ray measurements are performed on a two-dimensional range centered on the femoral head. Measurements may be made on other sites including bone and soft tissue.”); “generating a bone tissue image by excluding the soft tissue from the hip joint radiographic image obtained in the obtaining of the hip joint radiographic image, (Miyamoto, Paragraph [0034], discloses “The bone density image forming unit 32 is a module for forming a bone density image as a two-dimensional bone density distribution according to the DEXA method based on the L detection value array and the H detection value array obtained by the X-ray beam scanning. In doing so, it can be obtained by detecting the L air detection value (or the L air detection value sequence) obtained by detecting the low energy X-ray transmitted only through the air layer and the high energy X-ray transmitted only through the air layer The H air detection value sequence (or H air detection value sequence) is also used. As described below, the bone density image forming unit 32 functions as a bone pixel determination unit.”; Miyamoto, Paragraph [0035], discloses “In the bone density calculation, a histogram is created based on a plurality of bone densities calculated for a plurality of pixels (those before bone discrimination). Histograms usually have mountains corresponding to bones and mountains corresponding to soft tissue. A threshold is specified between the two mountains. In the bone density pixel array, it is determined that each pixel having a bone density equal to or larger than the threshold value is a bone pixel (original bone pixel). In general, the pixel to be imaged is a bone pixel and pixels corresponding to soft tissue or air are not imaged. As described above, the bone density image forming unit 32 determines the bone pixel group (raw bone pixel group) in the process of forming the bone density image. In the illustrated configuration example, the determination result is registered in the pixel type table 40. The entity of the pixel type table 40 is a memory. Bone density image data is sent from the bone density image forming unit 32 to the display processing unit 52.”; It is important to note here that although it says a bone density image is formed and analyzed in these paragraphs, a bone tissue image is still needed in order to acquire the bone density image, making this closely related to this limitation. Also, as seen in Paragraph [0035], the soft tissue areas within the image are removed in order to make room for the bone tissue specifically through measuring the pixels based off of specific threshold values); and “detecting regions of interest (ROIs) by detecting a plurality of predetermined ROIs from the bone tissue image generated in the generating of the bone tissue image” (Miyamoto, Paragraph [0030], discloses “In the present embodiment, the initial region of interest is set on the bone density image automatically (or by user's coordinate designation) prior to the setting of the region of interest. In the present embodiment, the initial region of interest is a region including a region of interest for bone analysis and a region of interest for soft tissue. As will be described later, in the pixel correction step on the bone density image, addition (or filling) of bone pixels and deletion (or elimination) of bone pixels can be performed using a pointing device within the initial region of interest. The result of the automatic bone pixel determination and the result of the manual correction thereto are used as exclusive conditions in the determination of the soft tissue pixel group. That is, the determination result of the bone is handed over to the calculation of the soft tissue. On the display unit 30, various images and various measurement results are displayed.”); “extracting image information by extracting image information corresponding to each of the ROIs detected in the detecting of the ROIs” (Miyamoto, Paragraph [0046], discloses: “In the present embodiment, the ROI setting unit 44 has a function of setting an initial ROI (common ROI for bone and soft tissues) on a bone density image based on automatically decided or user-specified coordinate information, a function of designating a user A function of setting an ROI for bone density analysis on a bone density image on the basis of coordinate information (or automatically decided) on the soft tissue image on the basis of the user specified (or automatically decided) coordinate information, And a function of setting an ROI. In the present embodiment, the ROI for bone density analysis and the ROI for soft tissue analysis are set in the initial ROI. In the present embodiment, the initial ROI is automatically set so as to include the head of the femur and its surroundings by automatic analysis of the bone density image. It should be noted that a single ROI or two ROIs may be set.”); and “deriving the examinee's bone density by using the image information extracted in the extracting of the image information.” (Miyamoto, Paragraph [0030], discloses: “In the bone density calculation to be described later, the L attenuation amount is specified from the L detection value and the L air detection value (the detection value obtained when the air region is irradiated with the low-energy X-rays), the H attenuation amount is specified from the H detection value and the H air detection value (the detection value obtained when the air region is irradiated with the low-energy X-rays), and the bone density is calculated from the L attenuation amount and the H attenuation amount in pixel units. Such operations are well known.”; Paragraph [0031], discloses “The calculation device 12 includes a calculation unit 26, an input unit 28, and a display unit 30. As will be described later with reference to FIG. 2, the calculation unit 26 has a bone density image forming function, a soft tissue image forming function, a soft tissue analysis function, and the like.”).
Miyamoto does not explicitly disclose “A machine learning-based bone density measuring method using an X-ray image, the method comprising”. However, in an analogous field of endeavor, Hu discloses “In an image of a region including a femur of a subject while using machine learning as a means of segmentation, an image analysis method comprises the processes of: creating an image for a teacher that at least a neck region of the femur and a background region can be identified with a label; and creating a learning model of machine learning by learning processing using the image of the region including the femur of the subject and the created image for teacher.” (Hu, Abstract). Hu also discloses “The bone density measuring device 100 is a device for diagnosing bone diseases such as osteoporosis. The bone density measuring apparatus 100 of the present embodiment is an apparatus for measuring bone density using a DXA (Dual Energy X-ray Absorptiometry) method. The DXA method is a method of irradiating two types of X-rays of different energies, calculating the amount of unabsorbed X-rays due to the difference in the absorption rate of X-rays of soft tissues other than bone and bone, and measuring bone density. Bone Mineral Density is the bone mass per square centimeter and expressed in g/cm 2.” (Hu, Paragraph [0016]). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the techniques of acquiring the hip joint/bone tissue images, detecting and extracting image information from ROIs, and deriving the examinee’s bone density seen in Miyamoto with the technique of measuring the bone density using machine learning seen in Hu to achieve a complete machine-learning bone density measuring method. By combining the techniques seen by both Miyamoto and Hu, one of ordinary skill in the art can effectively isolate various areas (such as bone or soft tissue) to calculate the bone density adequately without having the noise of other less-important segments of the X-Ray image (such as muscles or organs). Thus, it would have been obvious to combine the Miyamoto and Hu references to achieve the same bone density measuring method as seen in Claim 1.
Regarding Claim 2, the combination of Miyamoto and Hu discloses “The method of claim 1 wherein, in the detecting of the ROIs, the plurality of predetermined ROIs comprise” (Please refer to the above-described analysis for Claim 1); and “the femoral neck, the femoral trochanteric region, and the femoral intertrochanteric region of the hip joint.” (Hu, Paragraphs [0017]-[0019], disclose the following:
PNG
media_image1.png
219
712
media_image1.png
Greyscale
PNG
media_image2.png
772
709
media_image2.png
Greyscale
Hu, Paragraph [0024], also discloses “As shown in Figure 5, the analysis image (6) acquires the cervix domain (53) of the femur (50) with the prepared learning model (7) and it is used it acquires the interest area (4) based on the cervix domain (53) of the femur (50) acquired it is the image for the analysis of being used for the measurement of the bone mineral density. Moreover, in Figures 4 and 5, for convenience, and the analysis image (6) and input image (5) are appointed as the same image and input image (5) have. However the generally is the dissimilar image.”; As shown in the aforementioned paragraphs, the femoral neck (cervix domain of the femur) and trochanteric/intertrochanteric (condylar ball) region of the hip joint are all shown (as seen in Paragraphs [0017] - [0019]) in the X-Ray image, while a region of interest is acquired from those areas. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to use the technique of acquiring regions of interest from the femoral neck, trochanteric, and intertrochanteric region of the hip joint seen in the combination of Miyamoto and Hu to improve the bone density measuring method seen in Claim 2 in the same way.
Claim 3 is rejected under 35 U.S.C. 103 as being unpatentable over Miyamoto in view of Hu, and further in view of Arnaud (US 20110040168 A1) and Zhu (CN 113487587 A)
Regarding Claim 3, the combination of Miyamoto and Hu discloses “The method of claim 1 wherein the extracting of the image information comprises” (Please refer to the above-described analysis for Claim 3) segment were then measured. The regions were also superimposed on the original gray level image and average gray level within each region was measured. The cortex was identified as those segments connected to the boundary of the proximal femur mask with the greatest area, longest major axis length and a mean gray level about the average gray level of all enclosed segments within the proximal femur mask.” (Arnaud, Paragraph [0126]). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the bone density measurement method seen in the combination of Miyamoto and Hu with the Arnaud technique of extracting average grayscale values of images corresponding to their ROIs to improve the bone density measurement method in the same way. By using the extraction technique seen in Arnaud with the bone density measurement method described in the combination of Miyamoto and Hu, one of ordinary skill in the art can effectively analyze how the grayscale values relate closely with the type of bone or tissue they want to observe to get a clearer picture of the condition of the hip. Thus, it would have been obvious for one of ordinary skill in the art to combine the Miyamoto, Hu, and Arnaud references to achieve the above-described limitation seen in Claim 3.
The combination of Miyamoto, Hu, and Arnaud does not explicitly disclose “the deriving of the examinee's bone density comprises deriving the examinee's bone density by inputting the extracted average grayscale values to a linear regression model”. However, in an analogous field of endeavor, Zhu discloses “after the model is divided, counting the average grey value of the result area; based on the average grey value, using linear regression method to predict bone density t value. The invention automatically divides the spine part in the CT image, so as to use the area gray value to predict the bone density t value of the patient” (Zhu, Abstract). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the bone density measurement method seen in the combination of Miyamoto, Hu, and Arnaud with the Zhu technique of deriving bone density through inputting the extracted average grayscale values into a linear regression model to improve the bone density measurement method seen in Claim 3 in the same way.
Claim 4 is rejected under 35 U.S.C. 103 as being unpatentable over Miyamoto in view of Hu, and further in view of Kudo (US 20220005233 A1)
Regarding Claim 4, the combination of Miyamoto and Hu discloses “The method of claim 1” (Please refer to the above-described analysis for Claim 1); “wherein, in the generating of the bone tissue image, the machine learning algorithm comprises an artificial neural network algorithm to perform” (Hu, Paragraph [0033], discloses “In step 22, the control unit 2 sets a learning model 7 for specifying the neck region 53 of the femur 50 by machine learning that learns to output the teacher image 8 from the input image 5 Control to create. As the machine learning method, any method such as Fully Convolutional Networks (FCN), neural network, support vector machine (SVM), and boosting can be used. In addition, step 22 is an example of "the process of creating a learning model for machine learning" described in the claims.”) generating a new image on the basis of the features extracted in the image compression process”. However, in an analogous field of endeavor, Kudo discloses for the image compression process that “The feature amount extraction unit 110 acquires the input image and the compression parameter from an external device. The feature amount extraction unit 110 extracts a feature amount of the input image based on the acquired input image and compression parameter. Here, the feature amount extraction unit 110 performs extraction of the feature amount so that features of the input image are concentrated on a predetermined region and a magnitude based on the compression parameter.” (Kudo, Paragraph [0031]). Kudo also discloses for the same process that “when the encoding apparatus 100 and the decoding apparatus 200 compress an image (transforms into low-dimension), the learning is performed so that the parameter expressing a main feature of the image becomes dense in a desired data range in the compressed data” (Kudo, Paragraph [0077]). For the image generation process, Kudo discloses “The reconfiguration unit 240 (a decoded image acquisition unit) acquires the provisional encoded data output from the encoded data decompression unit 220. The reconfiguration unit 240 acquires the compression parameter output from the compression parameter calculation unit 230. The reconfiguration unit 240 reconfigures the decoded image based on the provision encoded data and the compression parameter. The reconfiguration unit 240 outputs the reconfigured decoded image to the external device.” (Kudo, Paragraph [0049]). Kudo finally discloses for the same process that “the provisional encoded data transmitted from the encoding apparatus 100 is data that expresses only a region on which the features of the input image are concentrated. In other words, in order for the reconfiguration unit 240 of the decoding apparatus 200 to obtain the decoded image, it is necessary to supplement the region deleted by the encoded data extraction unit 130 of the encoding apparatus 100. Since the region deleted by the encoded data extraction unit 130 is not a feature of the input image, the size expansion unit 241 of the reconfiguration unit 240 of the decoding apparatus 200 assigns the pre-decided value of “0” or the like to the provisional encoded data, as described above, and thus the reconfiguration unit 240 can obtain the decoded image from the provisional encoded data”. It is important to note that since the decoded image is created via the features of the image compression process such as the encoded data and the compression parameter, this can be analogous to a new image. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the bone density measurement method with a neural network machine learning algorithm seen in the combination of Miyamoto and Hu with the image compression and generation processes seen in Kudo to improve the bone density measuring method in the same way. By using both the image compression and generation processes seen in Kudo with the bone density measurement method with an artificial neural network, one of ordinary skill in the art can effectively create new images that reflect the features that are important for understanding the X-Ray image. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Miyamoto, Hu, and Kudo references to achieve the same method described in Claim 4.
Claims 5 and 6 are rejected under 35 U.S.C. 103 as being unpatentable over Miyamoto in view of Hu, and further in view of Takahashi (US 20230096694 A1).
Regarding Claim 5, the combination of Miyamoto and Hu discloses “The method of claim 1 wherein the generating of the bone tissue image comprises” (Please refer to the above-described analysis for Claim 1); and “generating a bone tissue image by excluding a soft tissue image from the hip joint radiographic image obtained in the obtaining of the hip joint radiographic image” (Miyamoto, Paragraph [0034] discloses “The bone density image forming unit 32 is a module for forming a bone density image as a two-dimensional bone density distribution according to the DEXA method based on the L detection value array and the H detection value array obtained by the X-ray beam scanning. In doing so, it can be obtained by detecting the L air detection value (or the L air detection value sequence) obtained by detecting the low energy X-ray transmitted only through the air layer and the high energy X-ray transmitted only through the air layer The H air detection value sequence (or H air detection value sequence) is also used. As described below, the bone density image forming unit 32 functions as a bone pixel determination unit.”; Miyamoto, Paragraph [0035], discloses “In the bone density calculation, a histogram is created based on a plurality of bone densities calculated for a plurality of pixels (those before bone discrimination). Histograms usually have mountains corresponding to bones and mountains corresponding to soft tissue. A threshold is specified between the two mountains. In the bone density pixel array, it is determined that each pixel having a bone density equal to or larger than the threshold value is a bone pixel (original bone pixel). In general, the pixel to be imaged is a bone pixel and pixels corresponding to soft tissue or air are not imaged. As described above, the bone density image forming unit 32 determines the bone pixel group (raw bone pixel group) in the process of forming the bone density image. In the illustrated configuration example, the determination result is registered in the pixel type table 40. The entity of the pixel type table 40 is a memory. Bone density image data is sent from the bone density image forming unit 32 to the display processing unit 52.”; Please refer to Claim 1 in regards to why the bone density image is classified as a bone image. However, in terms of excluding the soft-tissue image from the hip joint image, Paragraph [0035] best describes this due to the fact that the soft tissue from the image is omitted from the hip joint image. If we consider that the pixels omitted that represented the soft tissue could be reconstructed to form a soft tissue image, this is analogous to the exclusion of the soft tissue image from the original hip joint radiographic image); Paragraphs [0057]-[0059]:
PNG
media_image3.png
307
337
media_image3.png
Greyscale
PNG
media_image4.png
43
345
media_image4.png
Greyscale
PNG
media_image5.png
238
322
media_image5.png
Greyscale
Here, we can see that a machine learning algorithm is being used to derive both the bone and soft tissue images (specifically in Paragraph [0059]). Takahashi also discloses that “In addition, in some cases, muscle that supports the bone is evaluated. For example, in a case in which muscle around the hip joint is well developed, dislocation of the hip joint is unlikely to occur, and thus muscle around the hip joint is evaluated in some cases. In this case, the synthesis unit 25 need only derive the composite image GC0 at a ratio of artificial object image Ga: bone part image Gb: muscle image Gm: fat image Gf=0%:100%:100%:0%. Note that, in this case, the muscle tissue can be easily seen by lowering the synthesis ratio of the bone part image Gb. In this case, the synthesis unit 25 need only derive the composite image GC0 at a ratio of artificial object image Ga: bone part image Gb: muscle image Gm: fat image Gf=0%:50%:100%:0%.” (Takahashi, Paragraph [0079]). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have combined technique of excluding the soft tissue image from the hip-joint x-ray image seen in the combination of Miyamoto and Hu with the technique of forming the soft tissue image using a machine learning algorithm seen in Takahashi to achieve a more complete bone density measuring method. By combining both the Miyamoto and Hu technique of the excluding soft tissue image and the Takahashi technique of using machine learning to form the soft tissue image, one of ordinary skill in the art can effectively analyze the differences between both the bone and soft tissue images to come to an appropriate diagnostic conclusion when assessing an examinee. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Miyamoto, Hu, and Takahashi references to achieve the same bone density measurement method described in Claim 5.
Regarding Claim 6, the combination of Miyamoto, Hu, and Takahashi discloses “The method of claim 5, wherein, in the generating of the bone tissue image,” (Please refer to the above-described analysis for Claim 5) and “the machine learning algorithm builds a training data set for generating a soft tissue image on the basis of the hip joint radiographic image input thereto.” (Takahashi, Paragraph [0059], discloses “…In this case, the derivation model that derives the bone part image Gb and the soft part image Gs from the first removal radiation image Gr1 and the second removal radiation image Gr2 can be constructed by training a neural network using teacher data including the first and second radiation images G1 and G2 that do not include the artificial object acquired by the energy subtraction imaging, and the bone part image and the soft part image derived from the first and second radiation images G1 and G2 that do not include the artificial object by the energy subtraction processing.”). Takahashi also discloses that “In addition, in some cases, muscle that supports the bone is evaluated. For example, in a case in which muscle around the hip joint is well developed, dislocation of the hip joint is unlikely to occur, and thus muscle around the hip joint is evaluated in some cases. In this case, the synthesis unit 25 need only derive the composite image GC0 at a ratio of artificial object image Ga: bone part image Gb: muscle image Gm: fat image Gf=0%:100%:100%:0%. Note that, in this case, the muscle tissue can be easily seen by lowering the synthesis ratio of the bone part image Gb. In this case, the synthesis unit 25 need only derive the composite image GC0 at a ratio of artificial object image Ga: bone part image Gb: muscle image Gm: fat image Gf=0%:50%:100%:0%.” (Takahashi, Paragraph [0079]). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to use the technique of building a training data set for generating the soft tissue image seen in the combination of Miyamoto, Hu, and Takahashi to improve the current bone density measurement method. By using this technique of generating a training data set, one of ordinary skill in the art would have enabled the machine learning model to more accurately identify bone tissue from soft tissue within the hip joint X-Ray Image to effectively measure the bone density of the hip-joint. Thus, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to use the technique of generating a training data set to improve the bone density measuring method seen in Claim 6.
Claims 7 and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Miyamoto in view of Hu, and further in view Takahashi and Yamamoto (US 20210027430 A1)
Regarding Claim 7, the combination of Miyamoto, Hu, and Takahashi discloses “The method of claim 6” (Please refer to the above-described analysis for Claim 6) image, the input image including synthetic images obtained by synthesizing soft tissue images and bone tissue images collected from different hip joint radiographic images taken by X-ray, and the output image including the soft tissue images”. However, in an analogous field of endeavor, Yamamoto discloses for the training data set including an input and an output image that “it is preferable to construct a learned network in accordance with an image to be subjected to noise reduction processing or its noise. For example, when it is desired to reduce noise caused by metal, a learned network is constructed using learning data in which an image including noise caused by metal is an input image and an image with reduced noise caused by metal is an output image.” (Yamamoto, Paragraph [0066]). For the input image including synthetic images obtained by synthesizing both soft tissue and bone tissue images from different hip joint X-Ray images, Yamamoto first discloses that “the four input images generated by the preprocessing unit 321 are input to the learning data generation unit 322. In the next step S102, the conversion execution unit 630 performs region division processing for dividing the four images into regions, such as air, soft tissue, and bone tissue, to generate a region divided image”. Yamamoto further discloses that “The conversion number k is associated in advance with the purpose and a learned network appropriate for performing noise reduction processing corresponding to the purpose, and the preprocessing unit and the learning application unit with the same conversion number k all have a correspondence relationship therebetween. FIG. 11 shows a correspondence table showing an example of the correspondence relationship between a series of processes represented by k and the purpose.” (Yamamoto, Paragraph [0138] and Figure 11 (see below)).
PNG
media_image6.png
438
317
media_image6.png
Greyscale
Paragraph [0140] and Figure 11 demonstrate the fact that the different input images seen in Paragraph [0103] can associate with specific areas of the skeleton of the examinee. We can see here that the hip joint is one of them, where one would use a conversion number to further conduct noise-processing on the images to make them easier to see. However, the important part is the fact that these four input X-Ray images described can be taken from multiple angles of the hip joint. Yamamoto expands on what is seen in Figure 11 by mentioning “In addition, the purpose and the conversion number do not need to correspond to each other in a one-to-one manner. As shown in the example of the hip joint of the conversion number 9 in FIG. 11, when the same noise reduction processing is effective for the bone tissue and the soft tissue, the same processing may be performed. Therefore, the bone tissue and the soft tissue can be associated with the same conversion number.” (Yamamoto, Paragraph [0140]).
Finally, for the output image including soft tissue images, Yamamoto discloses that “Specifically, in the known noise reduction processing, all the soft tissue regions are set to a fixed value, for example, 1000 HU. However, in the noise reduction processing for soft tissue in this example, a basic image is specified and a composite image 1 (low frequency component) is generated and a composite image 2 (high frequency component) is generated, and a composite region, a low frequency filter, and a high frequency filter are specified and noise reduction processing is performed on the soft tissue region…” (Yamamoto, Paragraph [0108]). Yamamoto further discloses “The noise reduction processing images of respective regions of the soft tissue region, the bone tissue region, the air region, and the metal region obtained in step S312 are combined to generate a region-specific noise-reduced image” (Yamamoto, Paragraph [0111]). Here, we can clearly see that the soft tissue region is considered as an output image after noise reduction is performed to generate an output image of just the soft tissue, therefore making analogous to this limitation. Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to combine the bone density measuring method seen in the combination of Miyamoto, Hu, and Takashi with the input image and output soft tissue image acquisition techniques seen in Yamamoto to improve the bone density measurement method in the same way. By using the Yamamoto technique of utilizing a training data set with a unique input and output image, one of ordinary skill in the art can continuously train the machine learning bone density measurement method to develop a stronger accuracy when analyzing hip-joint X-Ray images for calculating the bone mineral density. Therefore, it would have been obvious for one of ordinary skill in the art to combine the Miyamoto, Hu, Takahashi, and Yamamoto references to achieve the same bone density measuring method as Claim 7.
Regarding Claim 8, the combination of Miyamoto, Hu, Takahashi, and Yamamoto discloses “The method of claim 7” (Please refer to the above-described analysis for Claim 7) and “wherein the input image and the soft tissue images of the output image are collected from a soft tissue region including no bone tissue of the hip joint radiographic image.” (Yamamoto, Paragraph [0135], discloses: “In the present embodiment, the image processing unit 133 of the X-ray CT apparatus recognizes the purpose of the input image and performs noise reduction processing according to the purpose. Here, the purpose of the image is specified by an imaging part, such as a head, a jaw, a chest, an abdomen, a lumbar spine, and a hip joint, and an imaging tissue, such as a soft tissue and a bone tissue. When the imaging tissue is a soft tissue, the CT image is used for diagnosis of a soft tissue disease, such as an internal disease or a malignant tumor. When the imaging tissue is a bone tissue, the CT image is used for diagnosis of an orthopedic disease, such as a fracture.”; As seen in Paragraph [0135], the input image can focus solely on the soft tissue of the hip joint without including any bone tissue within the radiographic image.
Paragraph [0108] discloses: “Specifically, in the known noise reduction processing, all the soft tissue regions are set to a fixed value, for example, 1000 HU. However, in the noise reduction processing for soft tissue in this example, a basic image is specified and a composite image 1 (low frequency component) is generated and a composite image 2 (high frequency component) is generated, and a composite region, a low frequency filter, and a high frequency filter are specified and noise reduction processing is performed on the soft tissue region…”; Yamamoto, Paragraph [0111], discloses: “The noise reduction processing images of respective regions of the soft tissue region, the bone tissue region, the air region, and the metal region obtained in step S312 are combined to generate a region-specific noise-reduced image”; As mentioned before in the analysis for Claim 7, the soft tissue image is clearly one of the output images in this scenario after noise reduction processing is finalized, as seen in Paragraph [0111]). Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to use the technique of including input and output soft tissue images without any bone tissue seen in the combination of Miyamoto, Hu, Takahashi, and Yamamoto to adequately assess both tissues to make an accurate quantitative and qualitative analysis with the bone density measuring method. By using the input and output images seen in the combination of Miyamoto, Hu, Takahashi, and Yamamoto, one of ordinary skill in the art can make an effective diagnosis for an examinee through evaluating every main area seen in and around their hip joint in the radiographic image. Thus, it would have been obvious for one of ordinary skill in the art to use the Miyamoto, Hu, Takahashi, and Yamamoto references to achieve the same bone density measuring method described in Claim 8.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Miyamoto in view of Hu, and further in view of Lin (US 20230029674 A1)
Regarding Claim 10, the combination of Miyamoto and Hu discloses “The method of claim 1” (Please refer to the above-described analysis for Claim 1) bone density on the basis of at least one information among the examinee's age, height, and weight”. However, in an analogous field of endeavor, Lin discloses “In step 14, an overall bone status may further be generated based on the skeletal characteristic values. The bone status represents the final evaluation of the bone quality of the subject. The final evaluation may be an integrated result (e.g. a score) of bone strength, a predicted risk of fracture, or a diagnosed osteoporosis status. Since some health conditions are not available from the X-ray image, some non-image features from medical records may also be incorporate into the evaluation of bone status, as shown in step 15. Those non-image features include but are not limited to age, weight, height, gender, smoking habit, alcohol use, and existence of previous fractures of the subject. The Fracture Risk Assessment Tool (FRAX) provides an example of integrating image features and non-image features to evaluate total fracture risk within 10 years.” (Lin, Paragraph [0049]). Therefore, it would have been obvious for one of ordinary skill in the art to combine the bone density measuring method seen in the combination of Miyamoto and Hu with the technique of deriving the bone density based on either the examinee’s age, height, and weight seen in Lin to offer a holistic analysis of the examinee when using the bone density measuring method. By combining the bone density measuring method seen in Miyamoto and Hu with the technique of deriving the bone density based off of non-image parameters seen in Lin, one of ordinary skill in the art allows for a doctor or radiographic technician to assess the healing or injury of the hip joint to make a more tailored treatment plan associated with their current stage in life. Thus, it would have been obvious to combine the Miyamoto, Hu, and Lin references to achieve the same bone density measuring method as Claim 10.
Allowable Subject Matter
Claim 9 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims. The following is a statement of reasons for the indication of allowable subject matter. For Claim 9, the combination of Miyamoto, Hu, Takahashi, and Yamamoto does not explicitly disclose bone tissue images of the input image being collected from low-effect soft tissue images that do not include a partition region or a partition line due to the interference of the soft tissue among the hip joint radiographic images. None of the cited prior art references provide a motivation to teach the ordered combination of the limitations recited in the claim in combination with the claim limitations of Claim 9.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Bae et al. (KR 20210054925 A) teaches a system for extracting a region of interest for bone mineral density calculation includes: an image acquisition unit for acquiring a CT image used for calculating patient's bone density; an image processing unit for extracting a region of interest for calculating bone density by an artificial intelligence algorithm from a CT image acquired by the image acquisition unit; and an image display unit for visualizing an analysis result by the image processing unit.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SORIE I KOROMA JR whose telephone number is (571)272-9259. The examiner can normally be reached Monday - Friday 8AM-6:00PM; Alternate Fridays Off.
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, Amandeep Saini can be reached at 571-272-3382. 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.
/SORIE I KOROMA JR/Examiner, Art Unit 2662
/AMANDEEP SAINI/Supervisory Patent Examiner, Art Unit 2662
Prosecution Insights