Search

PURPOSE Automated analysis of skeletal muscle in whole-body computed tomography (CT) images uses bone information, but bone segmentation including the epiphysis is not achieved. The purpose of this research was the semantic segmentation of eight regions of upper and lower limb bones including the epiphysis in whole-body CT images. Our targets were left and right upper arms, forearms, thighs, and lower legs. METHOD We connected two 3D U-Nets in cascade for segmentation of eight upper and lower limb bones in whole-body CT images. The first 3D U-Net was used for skeleton segmentation in whole-body CT images, and the second 3D U-Net was used for eight upper and lower limb bones' segmentation in skeleton segmentation results. Thirty cases of whole-body CT images were used in the experiment, and the segmentation results were evaluated using Dice coefficient with 3-fold cross-validation. RESULT The mean Dice coefficient was 93% in the left and right upper arms, 89% in the left and right forearms, 95% in the left and right thighs, and 94% in the left and right lower legs. CONCLUSION Although the accuracy of the segmentation results of relatively small bones remains a challenge, the semantic segmentation of eight regions of upper and lower limb bones including the epiphysis in whole-body CT images has been achieved.

Nondestructive analysis of historical materials, such as paper, is vital in the elucidation of history and culture. This is because it is possible to elucidate the background of a book’s origin using information obtained from other sources, such as paper making methods and paper’s fiber composition. Herein, we propose a patch classification method for Japanese paper kozo using EfficientNet-B0. We integrate the results classified using patch images to estimate the origin of the kozo fiber in the entire paper. Consequently, the average success rate of our method was 93.1 % for two classifications and 87.5 % for four classifications of the production areas of kozo. In addition, the classification accuracy for the entire paper was evaluated from the patch image obtained after classification using the reconstructed image in which the position was rearranged on the original image. As a result, the classification of four production areas of kozo, from which the entire macro image was made, could be classified in all macro images, although the number of experiments was limited. In the future, we will investigate a multi-scale technique to consider the fiber continuity between patches in macro images reconstructed from patch images.

Advancements in musculoskeletal analysis have been achieved by adopting deep learning technology in image recognition and analysis. Unlike musculoskeletal modeling based on computational anatomy, deep learning-based methods can obtain muscle information automatically. Through analysis of image features, both approaches can obtain muscle characteristics such as shape, volume, and area, and derive additional information by analyzing other image textures. In this chapter, we first discuss the necessity of musculoskeletal analysis and the required image processing technology. Then, the limitations of skeletal muscle recognition based on conventional handcrafted features are discussed, and developments in skeletal muscle recognition using machine learning and deep learning technology are described. Next, a technique for analyzing musculoskeletal systems using whole-body computed tomography (CT) images is shown. This study aims to achieve automatic recognition of skeletal muscles throughout the body and automatic classification of atrophic muscular disease using only image features, to demonstrate an application of whole-body musculoskeletal analysis driven by deep learning. Finally, we discuss future development of musculoskeletal analysis that effectively combines deep learning with handcrafted feature-based modeling techniques.

The Elucidation of the spread of paper is an important research that reveals historical culture. In particular, clarifying the paper fibers contained in paper is one of the important issues involved in elucidating the propagation of paper. The target of our research is an image of the Samarkand paper acquired from historical cultural properties. In this research, images of the paper were acquired by macro photography with a commercially available digital camera that can obtain samples nondestructively. By using the VGG-16, which is a deep convolutional neural network (DCNN), we easily determined whether the paper from which the macro image was obtained has a hemp or cotton fiber. In addition, as the piece of paper to be photographed is a cultural property, data acquisition through simple photography is required. However, one macro shot with a digital camera causes blurring at the periphery of the image. Therefore, the DCNN-based classification performance was compared using two datasets of the input image and the image obtained by trimming the periphery. As a result of trimming of the image periphery prone to blur in macro photography of digital images, classification results of up to 95.8% were obtained.

The skeletal muscle exists in the whole body and can be observed in many cross sections in various tomographic images. Skeletal muscle atrophy is due to aging and disease, and the abnormality is difficult to distinguish visually. In addition, although skeletal muscle analysis requires a technique for accurate site-specific measurement of skeletal muscle, it is only realized in a limited region. We realized automatic site-specific recognition of skeletal muscle from whole-body CT images using model-based methods. Three-dimensional texture analysis revealed imaging features with statistically significant differences between amyotrophic lateral sclerosis (ALS) and other muscular diseases accompanied by atrophy. In recent years, deep learning technique is also used in the field of computer-aided diagnosis. Therefore, in this initial study, we performed automatic classification of amyotrophic diseases using deep learning for the upper extremity and lower limb regions. The classification accuracy was highest in the right forearm, which was 0.960 at the maximum (0.903 on average). In the future, methods for differentiating more kinds of muscular atrophy and clinical application of ALS detection by analyzing muscular regions must be considered.

Erector spinae muscle (ESM) is an important muscle in the torso region. Changes of sizes, shapes and densities in the cross section of the spinal column muscles have been found in chronic low back pain, degenerative lumbar sclerosis and chronic obstructive pulmonary disease. However, the image features of the ESM are measured manually by the physician. Therefore, automatic recognition in three dimensions (3D) not only for the limited two-dimensional (2D) section but also for the whole ESM is required. In this study, we realize automatic recognition of the ESMs and its attachment region on the skeleton using a 2D deep convolutional neural network. Each cross section of the 3D computed tomography (CT) image is input as a 2D image to the fully convolutional network. Then, the obtained result is reconstructed into a 3D image to obtain the recognition result of the ESM and its attachment region on the skeleton. ESM and attached area are extracted manually from the CT images of 11 cases and used for evaluation. In the experiments, automatic recognition was performed for each case using the leave-one-out method. The mean recognition accuracy of ESM and attached area was \(89.9\%\) and \(65.5\%\), respectively for the Dice coefficient. In this study, although there is over-extraction in the recognition of the attachment region, the initial region has been acquired successfully and it is the first study to simultaneously recognize the ESMs and its attachment region on the skeleton.

This study aimed to develop and validate an automated segmentation method for surface muscles using a three-dimensional (3D) U-Net based on selective voxel patches from whole-body computed tomography (CT) images. Our method defined a voxel patch (VP) as the input images, which consisted of 56 slices selected at equal intervals from the whole slices. In training, one VP was used for each case. In the test, multiple VPs were created according to the number of slices in the test case. Segmentation was then performed for each VP and the results of each VP merged. The proposed method achieved a segmentation accuracy mean dice coefficient of 0.900 for 8 cases. Although challenges remain in muscles adjacent to visceral organs and in small muscle areas, VP is useful for surface muscle segmentation using whole-body CT images with limited annotation data. The limitation of our study is that it is limited to cases of muscular disease with atrophy. Future studies should address whether the proposed method is effective for other modalities or using data with different imaging ranges.

To develop and validate a fully automatic method for segmentation of paraspinal muscles from 3D torso CT images. We propose a novel learning-based method to address this challenging problem. Multi-scale iterative random forest classifications with multi-source information are employed in this study to speed up the segmentation and to improve the accuracy. Here, multi-source images include the original torso CT images and later also the iteratively estimated and refined probability maps of the paraspinal muscles. We validated our method on 20 torso CT data with associated manual segmentation. We randomly partitioned the 20 CT data into two evenly distributed groups and took one group as the training data and the other group as the test data. The proposed method achieved a mean Dice coefficient of 93.0%. It took on average 46.5 s to segment a 3D torso CT image with the size ranging from $$512 \times 512 \times 802$$ voxels to $$512 \times 512 \times 1031$$ voxels. Our fully automatic, learning-based method can accurately segment paraspinal muscles from 3D torso CT images. It generates segmentation results that are better than those achieved by the state-of-the-art methods.

Skeletal muscle segmentation techniques can help orthopedic interventions in various scenes. In this chapter, we describe two methods of skeletal muscle segmentation on 3D CT images. The first method is based on a computational anatomical model, and the second method is a deep learning-based method. The computational anatomy-based methods are modeling the muscle shape with its running and use it for segmentation. In the deep learning-based methods, the muscle regions are directly acquired automatically. Both approaches can obtain muscle regions including shape, area, volume, and some other image texture features. And it is desirable that the method be selected by the required orthopedic intervention. Here, we show each design philosophy and features of a representative method. We discuss the various examples of site-specific segmentation of skeletal muscle in non-contrast images using torso CT and whole-body CT including in cervical, thoracoabdominal, surface and deep muscles. And we also mention the possibility of application to orthopedic intervention.

Amyotrophic lateral sclerosis (ALS) causes functional disorders such as difficulty in breathing and swallowing through the atrophy of voluntary muscles. ALS in its early stages is difficult to diagnose because of the difficulty in differentiating it from other muscular diseases. In addition, image inspection methods for aggressive diagnosis for ALS have not yet been established. The purpose of this study is to develop an automatic analysis system of the whole skeletal muscle to support the early differential diagnosis of ALS using whole-body CT images. In this study, the muscular atrophy parts including ALS patients are automatically identified by recognizing and segmenting whole skeletal muscle in the preliminary steps. First, the skeleton is identified by its gray value information. Second, the initial area of the body cavity is recognized by the deformation of the thoracic cavity based on the anatomical segmented skeleton. Third, the abdominal cavity boundary is recognized using ABM for precisely recognizing the body cavity. The body cavity is precisely recognized by non-rigid registration method based on the reference points of the abdominal cavity boundary. Fourth, the whole skeletal muscle is recognized by excluding the skeleton, the body cavity, and the subcutaneous fat. Additionally, the areas of muscular atrophy including ALS patients are automatically identified by comparison of the muscle mass. The experiments were carried out for ten cases with abnormality in the skeletal muscle. Global recognition and segmentation of the whole skeletal muscle were well realized in eight cases. Moreover, the areas of muscular atrophy including ALS patients were well identified in the lower limbs. As a result, this study indicated the basic technology to detect the muscle atrophy including ALS. In the future, it will be necessary to consider methods to differentiate other kinds of muscular atrophy as well as the clinical application of this detection method for early ALS detection and examine a large number of cases with stage and disease type.

This chapter presents examples of medical image understanding algorithms using computational anatomy models explained in Chap. 2. After the introductory in Sect. 3.1, Sect. 3.2 shows segmentation algorithms for vertebrae, ribs, and hip joints. Segmentation algorithms for skeletal muscle and detection algorithms for lymph nodes are explained in Sects. 3.3 and 3.4, respectively. Section 3.5 deals with algorithms for understanding organs/tissues in the head and neck regions and starts with computational neuroanatomy, followed by analysis and segmentation algorithms for white matter, brain CT, oral regions, fundus oculi, and retinal optical coherence tomography (OCT). Algorithms useful in the thorax, specifically for the lungs, tracheobronchial tree, vessels, and interlobar fissures from a thoracic CT volume, are presented in Sect. 3.6. Section 3.7 provides algorithms for breast ultrasound imaging, i.e., mammography and breast MRI. Cardiac imaging algorithms in an echocardiographic image sequence and MR images as well as coronary arteries in a CT volume are explained in Sect. 3.8. Section 3.9 deals with segmentation algorithms of abdominal organs, including the liver, pancreas, spleen, kidneys, gastrointestinal tract, and abdominal blood vessels, followed by anatomical labeling of segmented vessels.

In many products, the visual impressions of the product are extremely important components—sight accounts for 83 % of the five senses (An education apparatus editing committee in An industrial education apparatus system manual. JUS Press 1972). However, manufacturers still depend on the aspect of the effectiveness, efficiency, and usability for the design evaluation of products; yet, consumer emotion is hard to measure because the mental side of users such as visual impressions cannot be observed directly and the index to measure them has not been established. The function, performance, and usability can be measured by the behavioral index of users (e.g., operation time and error rate) (Nagashima and Kubo in The sensitivity and information for the new manufacturing. Morikita Shuppan Co., Ltd, 2007). In this study, we experimentally searched for indices to objectively detect the impression of appearance with car images as targets. We observed that MPFC activation is related to high “familiarity” and low “mechanical” features.

Consumers expect mature products such as cars to provide value in addition to conventional features such as safety and usability. Hence, introducing methods to evaluate consumer perceptions of the worth of new features during the design process benefits manufacturers. Consequently, increasing attention has been recently focused on user experience (UX). This project examined three aspects of UX, namely, the “desire to try using” during an encounter, the “goodness of using,” and the “desire to continue to use” after the initial usage. Then, a method for introducing these aspects into the product design process was developed. Thus, the factors that influence user desire to continue the product usage were obtained. The relation between the user requirements and the design elements was examined, and a method that quantitatively evaluates user desires based on the design elements during the design process was proposed.

The iliac muscle is an important skeletal muscle related to ambulatory function. The muscles related to ambulatory function are the psoas major and iliac muscles, collectively defined as the iliopsoas muscle. We have proposed an automated recognition method of the iliac muscle. Muscle fibers of the iliac muscle have a characteristic running pattern. Therefore, we used 20 cases from a training database to model the movement of the muscle fibers of the iliac muscle. In the recognition process, the existing position of the iliac muscle was estimated by applying the muscle fiber model. To generate an approximation mask by using a muscle fiber model, a candidate region of the iliac muscle was obtained. Finally, the muscle region was identified by using values from the gray value and boundary information. The experiments were performed by using the 20 cases without abnormalities in the skeletal muscle for modeling. The recognition result in five cases obtained a 76.9% average concordance rate. In the visual evaluation, overextraction of other organs was not observed in 85% of the cases. Therefore, the proposed method is considered to be effective in the recognition of the initial region of the iliac muscle. In the future, we will integrate the recognition method of the psoas major muscle in developing an analytical technique for the iliopsoas area. Furthermore, development of a sophisticated muscle function analysis method is necessary.

Our motivation was to provide an automatic tool for radiologists and orthopedic surgeons for improving the quality of life of an aging population. We propose a method for generating a shape model and a fully automated segmenting scheme for the psoas major muscle in X-ray CT images by using the shape model. Our approach consists of two steps: (1) The generation of a shape model and its application to muscle segmentation. The shape model describes the muscle's outer shape and has two parameters, an outer shape parameter and a fitting parameter. The former was determined by approximating of the outer shape of the muscle region in training cases. The latter was determined for each test case in the recognition process. (2) Finally, the psoas major muscle was segmented by use of the shape model. To evaluate the performance of the method, we applied it to CT images for constructing the shape models by using 20 cases as training samples; 80 cases were used for testing. The accuracy of this method was measured by comparison of the extracted muscle regions with regions that were identified manually by an expert radiologist. The experimental results of the segmentation of the psoas major muscle gave a mean Jaccard similarity coefficient of 72.3%. The mean true segmentation coefficient was 76.2%. The proposed method can be used for the analysis of cross-sectional area and muscular thickness in a transverse section, offering radiologists an alternative to manual measurement for saving their time and improving the reproducibility of segmentation.

Recently, a dramatic increase in pregnancies complicated by mental disorders has been observed in Tokyo, Japan [1, 2]. In 2014, the estimated number of deliveries complicated by mental disorders was 1,800 [2]. The rate of general hospital with psychiatric inpatient beds is only about 16% of the delivery facilities in Tokyo; however, about 36% of the deliveries with mental disorders were managed by these general hospitals. These rates are feared to lead to the tremendous burden of both obstetrics and psychiatric staffs of the general hospitals in Tokyo. To know the reason why many deliveries with mild mental disorders are managed in a small number of general hospitals, we requested 85 private obstetric clinics to provide the reason why they introduced even deliveries with mild mental disorders to the general hospitals. Because many of the deliveries with mental disorders managed at the general hospital seemed to be not severe as necessary to be managed at the higher-order facilities. A total of 57 (67%) of them responded. The most common reason (26/57, 46%) was “We cannot examine the severity of mental disorders” and the second common reason was “It is difficult to take reservation of psychiatric clinics for pregnant women”. Therefore, they seemed to introduce all pregnant women suspected having mental disorders to the general hospitals. On the other hand, about 60% of the staffs of the psychiatric clinics in Tokyo seemed to be worried excessively about the influence of medications on both fetuses and pregnant women (Takeuchi and Okano, unpublished data). Therefore, some psychiatrists also seemed to introduce all pregnant women with mental disorders to the general hospitals. For the proper management of perinatal psychosis, it is necessary to build a smooth cooperation system of obstetricians and psychiatrists. As the first step of the cooperation, the guidelines for the determination of severity of mental disorders by obstetricians those obtained a consensus between the obstetricians and psychiatrists are needed.

Since September 2010, in Japan serological screening for the detection of human T-cell leukemia virus type 1 (HTLV-1) antibodies can be performed for all women during pregnancy with the Japanese public funds for strategies for prevention of HTLV-1 vertical transmission, because Japan, especially Kyushu area, has been reported to be one of the areas of highest prevalence of HTLV-1 in the world [1, 2]. In our previous study [3], we examined the prevalence of HTLV-1 carrier in Japanese pregnant women according to the implement rate and results of HTLV-1 screening and confirmation tests of women who gave births in Japan in 2011. The total rates of positive HTLV-1 screening tests and positive western blot (WB) test in positive screening tests were 0.32% and 49.8%, respectively in 2011. Considering the response rate and the rate of implementation of WB test, the number of HTLV-1 carrier in Japanese pregnant women in 2011 was estimated to be 1,560 (0.15%). In addition, although the number of delivery in Kyushu area was only 14% of Japanese deliveries, 53% of HTLV-1 carrier of Japanese pregnant women was present in Kyushu area. Recently, the migration of Japanese people from Kyushu area to the metropolitan areas has been thought to contribute to a significant decrease of HTLV-1 carriers in Kyushu area and an increase in Kanto (including Tokyo) area in Japan [1, 4]. To confirm this migration in Japanese pregnant women, on December 2014, we requested again 2,544 obstetrical facilities that are members of Japan Association of Obstetricians and Gynecologists (JAOG) to provide information of HTLV-1 tests in pregnant women who delivered at ≥ 22 weeks’ gestation in 2013. A total of 1,356 (53.3%) of 2,544 obstetrical facilities responded and information on a total of 538,167 women, accounting for approximately 54% of all deliveries that occurred in Japan during the study period (approximately 1,001,800 births) was provided. In 2013, the total rates of positive HTLV-1 screening tests and positive WB test in positive screening tests were 0.35% and 50.8%, respectively. Considering the response rate and the rate of implementation of WB test, the number of HTLV-1 carrier in Japanese pregnant women in 2013 was estimated to be 1,780 (0.18%). Table 1 shows the difference in the estimated number of HTLV-1 carrier based on positive WB test by area in Japan between 2011 and 2013. The estimated number of HTLV-1 carrier in 2013 seemed to be more than that in 2011, especially in the northeast and southwest (Kyushu) areas. In addition, 51% of HTLV-1 carrier of Japanese pregnant women was present in Kyushu area, although the number of delivery in Kyushu area was only 13% of Japanese deliveries in 2013. Although the migration of Japanese people from Kyushu area to the metropolitan areas has been supposed to contribute to a significant decrease of HTLV-1 carriers in Kyushu area, the estimated number of HTLV-1 carrier of pregnant women seemed to be increased in Kyushu area. In addition, the estimated rate of HTLV-1 carrier in pregnant women in Kyushu area was still significantly higher than that in the other areas (P < 0.01 by the Chi-square test). Therefore, there are still remaining problems concerning the locality for strategies for prevention of HTLV-1 vertical transmission in Japan.

We examined the current status of human T-cell leukemia virus type 1 (HTLV-1) carrier in Japanese pregnant women, according to the results of HTLV-1 screening and confirmation tests of women who gave birth in Japan in 2011. We requested 2642 obstetrical facilities to provide information of HTLV-1 tests and 71.3% of them responded. Considering the response rate and the rate of implementation of confirmation tests, the number of HTLV-1 carrier in Japanese pregnant women was estimated to be 1620 (0.16%) per year.

Purpose The maximum limit of MR scanner noise and necessity of ear protection is defined in the IEC standard (IEC60601-2-33) of MR safety. With improvements in MR scanner performance, pulse sequences generating higher scanning noise have been used clinically. In this study, we investigated the factors significantly related to potential acoustic trauma cases (PATC) after MR examinations. To consider the future direction for MR safety and prevention of acoustic trauma, issues related to noise generation by MR scanners and acoustic trauma were systematically reviewed. Methods A statistical analysis was performed using the data set from a survey (n=974) conducted in 2010 by the JSMRM safety committee. Hierarchical clustering analysis was used to extract the characteristics of the responders. With this classification as a reference, tests of independence and a residual analysis were employed to evaluate the factors related to PATC. Results No significant relationship was observed between the ear protection policy and the incidence or the reported outcome of PATC. While the two main clusters out of the six clusters extracted were associated with who reported the PATC and the confirmation process of the acoustic noise level of MR scanners, no cluster was associated with the frequency of PATC. An absence of PATC was significantly less reported (p=0.03) and more PATC was reported (p=0.04) by facilities with 3T MR systems. Discussion Although the total frequency was 4 cases, it should be noted that persistent hearing disturbances are a possible consequence of MR examinations. Neither the condition of the subjects nor the ear protection method was significantly related to the probability of PATC, suggesting the difficulty of predicting the potential risk of acoustic trauma. It is recommended to more systematically follow up PATC cases and clarify the risk factors.

きわめてまれな腟壁のVerrucous squamous cell carcinomaを経験し, その細胞診, 組織学的特徴を透過型電顕, 光顕およびHPV感染を含めて検討した.腫瘍表面の擦過細胞診で, 腫瘍細胞はライトグリーン好性の細胞質, perinuclear haloを持つ中層型から旁基底型のdysplastic cellと軽度のクロマチン増量を示す裸核細胞を散在性に認めた.組織像では表層に軽度角化を伴った乳頭状の腫瘍細胞の増殖と核分裂像を多く認めたが, koilocytosisは少なかった.基底膜側の大部分は扁平の圧排像を示し, 一部に間質部への乳頭状侵入を認めVerrucous carcinomaと診断した.またin situハイブリッド法によるHPVの検索では6, 11型の陽性所見を認め, 本症とHPV感染が示唆された.電顕による観察では核の不整が目立ち, 細胞質organellaの発達は幼若型と成熟型の扁平上皮型細胞が混在していたが, viral particleは認められなかった.以上の所見より尖型コンジロームおよびパピローマとの鑑別が可能であった.

In this paper we propose a new multi-functional steering wheel switch for HVAC and audio systems. This new switch has five buttons on the front side of the spoke area and one button with vibration on the backside of it. Drivers can operate either HVAC or audio functions with the front switches, and HVAC or audio mode can be alternatively selected by pressing the back switch. Since different vibration modes are assigned for the HVAC and audio mode, drivers can also easily recognize which function can be operated. By changing the assignment of the mode in this way, the switch can operate more than 10 functions with 6 buttons allocated on the spoke area. Several kinds of evaluations were performed in order to develop this multi-functional switch. At first, to optimize the positions of the buttons, the behaviors of thumbs and fingers were measured. Also the physical workload of the thumb motion and middle fingers' postures was evaluated when subjects operated the switches. Secondly, tactile sensibility of humans was investigated, and sensory evaluations concerned with vibration sensitivity were performed to decide the specification of the vibration. Thirdly, functions for operating the HVAC and audio systems with this switch were selected by considering driving situations. Finally, the switch that was developed based on the results of these evaluations was re-evaluated by using a driving simulator to verify the operability of the switch. As a result of this evaluation, it was shown that the new switch with the functions for both the HVAC and audio systems performs well compared to the conventional switches.

Japan has been reported to be one of the areas of highest prevalence of human T-cell leukemia virus type 1 (HTLV-1) in the world [1,2]. For example, our earlier study indicated that about 1620 of H...

The purpose of this study is to recognize the psoas major muscle on X-ray CT images. For this purpose, we propose a novel recognition method. The recognition process in this method involves three steps: the generation of a shape model for the psoas major muscle, recognition of anatomical points such as the origin and insertion, and the recognition of the psoas major muscles by the use of the shape model. We generated the shape model using 20 CT cases and tested the model for recognition in 20 other CT cases. The average Jaccard similarity coefficient (JSC) and reproducibility rate were 0.704 and 0.783, respectively. Experimental results indicate that our method was effective for a 2-D cross-sectional area (CSA) analysis.