Search

Skeletal muscle segmentation of the L3 slice can be used to estimate total body skeletal muscle mass. However, site-specific three-dimensional (3D) segmentation of each region, such as the erector spinae, quadratus lumborum, psoas major, oblique muscle, and rectus abdominis, in the L3 slice has not yet been achieved for the accurate measurement of skeletal muscle mass. Herein, we propose a method for site-specific 3D segmentation of skeletal muscles in the L3 slice from body CT images. We focused on the characteristics of the erector spinae muscle (ESM), which can be simultaneously observed with other skeletal muscles on craniocaudal slices and can be accurately segmented using machine learning. We introduce a segmentation method with ESM (w/ESM) using 2D U-Net for the simultaneous learning of the erector spinae and skeletal muscles, which are recognized as targets. In a three-fold cross-validation using 30 CT image cases, the mean Dice value of the baseline method, without ESM (wo/ESM), was 0.637, whereas that for the segmentation of skeletal muscles by w/ESM was 0.864, an improvement of 0.227. Our method improves the accuracy of site-specific segmentation of skeletal muscles within the L3 slice and helps evaluate the skeletal muscles through 3D imaging. This effect of w/ESM was confirmed for the skeletal muscles within the L3 slice as well as the trapezius and supraspinatus muscles. These results demonstrate the effectiveness of simultaneously learning the erector spinae and skeletal muscles in improving the accuracy of site-specific segmentation of skeletal muscles.

Currently, staging the degree of liver fibrosis predominantly relies on liver biopsy, a method fraught with potential risks, such as bleeding and infection. With the rapid development of medical imaging devices, quantification of liver fibrosis through image processing technology has become feasible. Stacking technology is one of the effective ensemble techniques for potential usage, but precise tuning to find the optimal configuration manually is challenging. Therefore, this paper proposes a novel EVO-MS model—a multiple stacking ensemble learning model optimized by the energy valley optimization (EVO) algorithm to select most informatic features for fibrosis quantification. Liver contours are profiled from 415 biopsied proven CT cases, from which 10 shape features are calculated and inputted into a Support Vector Machine (SVM) classifier to generate the accurate predictions, then the EVO algorithm is applied to find the optimal parameter combination to fuse six base models: K-Nearest Neighbors (KNNs), Decision Tree (DT), Naive Bayes (NB), Extreme Gradient Boosting (XGB), Gradient Boosting Decision Tree (GBDT), and Random Forest (RF), to create a well-performing ensemble model. Experimental results indicate that selecting 3–5 feature parameters yields satisfactory results in classification, with features such as the contour roundness non-uniformity (Rmax), maximum peak height of contour (Rp), and maximum valley depth of contour (Rm) significantly influencing classification accuracy. The improved EVO algorithm, combined with a multiple stacking model, achieves an accuracy of 0.864, a precision of 0.813, a sensitivity of 0.912, a specificity of 0.824, and an F1-score of 0.860, which demonstrates the effectiveness of our EVO-MS model in staging the degree of liver fibrosis.

The supraspinatus tendon is the most frequently torn tendon in the rotator cuff. Rotator cuff reconstruction is more likely to result in retear if the muscle has atrophy or fatty degeneration. Thus, atrophy and fatty degeneration of the supraspinatus muscle are predictors of the postoperative course, and volume analysis using three-dimensional segmentation of the supraspinatus muscle is necessary. The supraspinatus muscle is attached to the scapula, making it possible to estimate the region of the muscle based on the position of the scapula. In this paper, we propose a supraspinatus muscle segmentation method based on the scapula position in torso computed tomography (CT) images. Our proposed method consists of supraspinatus muscle localization using a scapula segmentation result and supraspinatus muscle segmentation based on the localization result. U-Net is used for scapula and supraspinatus muscle segmentation. In this experiment, we used torso CT images and pseudo-chest CT images which were generated from the scans of the same patient. The mean Dice values of the segmentation results obtained by applying the proposed method to the torso and pseudo-chest CT images were both 0.881. When localization was not used, the mean Dice values of the segmentation results in the torso and pseudo-chest CT images were 0.000 and 0.850, respectively. The experimental results demonstrate the effectiveness of bone-based localization in supraspinatus muscle segmentation using U-Net.

Abstract Background The induction of chronic inflammation, perforation, and abscess by foreign bodies (FBs) in adults is uncommon. We present a delayed diagnosis case for a patient who had a fishbone stuck in the duodenal bulb, resulting in chronic abdominal pain for nearly 3 months. We present the diagnosis and treatment procedures for chronic patients, which differ from those for acute and emergency FB ingestion, and also summarize the characteristics of such patients through a systematic literature review. Case presentation A 68-year-old woman was brought to our hospital with repeated right upper abdominal pain lasting for 3 months and aggravation for 9 h. Computed tomography (CT) showed a streaky high-density shadow (approximately 3 cm in length) on the posterior wall of the gastric antrum extending outside the wall. Endoscopic ultrasonography showed hyperechoic space with a cross-section of approximately 0.1 × 0.1 cm in the deep submucosal layer of the local stomach, accompanied by an acoustic shadow in the rear. The possibility of a fishbone as well as perforation was considered and the object was removed using FB forceps. Fasting as well as acid inhibition and anti-infection medication were prescribed for the patient. She eventually recovered and was discharged from the hospital. Conclusion Endoscopic intervention can be recommended as the first option for patients with gastrointestinal FBs.

Given the fact that many software projects are closed-source, analyzing security-related vulnerabilities at the binary level is quintessential to protect computer systems from attacks of malware. Binary code similarity detection is a potential solution for detecting malware from the binaries generated by the processor. In this paper, we proposed a malware detection mechanism based on the binaries using machine learning techniques. Through utilizing the Recurrent Neural Network (RNN), more specifically Long Short-Term Memory (LSTM) network, we generate the uniformed feature embedding of each binary file and further take advantage of the Siamese Neural Network to compute the similarity measure of the extracted features. Therefore, the security risks of the software projects can be evaluated through the similarity measure of the corresponding binaries with existing trained malware. Our real-world experimental results demonstrate a convincing performance indistinguishing out the outliers, and achieved slightly better performance compared with existing state-of-the-art methods.

A fusion image combining both anatomical and functional information obtained by registering medical images of two different modalities, Positron Emission Tomography (PET) and Computed Tomography (CT), is of great significance for medical image analysis and diagnosis. Medical image registration relies on similarity measure which is low between PET/CT image voxels and therefore PET/CT registration is a challenging task. To address this issue, this paper presents an unsupervised end-to-end method, DenseRegNet, for deformable 3D PET/CT image registration. The method consists of two stages: (1) predicting 3D displacement vector field (DVF); and (2) registering 3D image. In the 3D DVF prediction stage, a two-level similarity measure together with a deformation regularization is proposed as loss function to optimize network training.In the image registration stage, a resampler and a spatial transformer are utilized to obtain the registration results. In this paper, 663 pairs of Uptake Value (SUV) and Hounsfield Unit (Hu) patches of 106 patients, 227 pairs of SUV and Hu patches of 35 patients and 259 pairs of SUV and Hu patches of 35 patients are randomly selected as training, validation and test set, respectively. Normalized cross correlation (NCC), intersection over union (IoU) of liver bounding box and euclidean distance (ED) on landmark points are used to evaluate the registration results. Experiment results show that the proposed method, DenseRegNet, achieves the best results in terms of liver bounding box IoU and ED, and the second highest value of NCC. For a trained model, given a new pair of PET/CT images, the registration result can be obtained with only one forward calculation within 10 seconds. Through qualitative and quantitative analyses, we demonstrate that, compared with other deep learning registration models, the proposed DenseRegNet achieves improved results in the challenging deformable PET/CT registration task.

High-resolution CT images can clearly display anatomical structures but does not display functional information, while blurred PET images can display molecular and functional information of lesions but cannot clearly display morphological structures. Therefore, accurate PET-CT image registration, which is used for anatomical structure and functional information fusion, is a prerequisite for early stage cancer diagnosis. However, some hypermetabolic anatomical structures, such as brain and bladder, have low registration accuracy. To solve this problem, a 3D unsupervised network based on a metabolic constraint function and a multi-domain similarity measure (3D MC-MDS Net) is proposed for 3D PET-CT image registration. Specifically, a metabolic constraint model is established based on the standard uptake value (SUV) distribution of hypermetabolic regions such as brain, bladder, liver and heart, which reduces the excessive distortion on displacement vector field (DVF) caused by hypermetabolic anatomical structures in PET images. A DVF estimator is built based on 3D unsupervised convolutional neural networks and a spatial transformer is used for warping 3D PET images to 3D CT images. The generated registration results (PET image patches) and the original 3D CT image patches are used for calculating the spatial domain similarity (SD similarity) and frequency domain similarity (FD similarity). Finally, the loss function of the entire registration network is constructed by a weighted sum of SD similarity, FD similarity and a smoothness of DVF. A dataset consisted of 170 whole-body PET-CT images is used for registration accuracy evaluation. The proposed unsupervised registration network, 3D MC-MDS Net, can accurately learn the 3D registration model by using the training dataset with the metabolic constraint model, which significantly improves the registration accuracy.

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 date, the measurement of the stiffness of liver requires a special vibrational tool that limits its application in many hospitals. In this study, we developed a novel method for automatically assessing the elasticity of the liver without any use of contrast agents or mechanical devices. By calculating the non-rigid deformation of the liver from magnetic resonance (MR) tagging images, the stiffness was quantified as the displacement of grids on the liver image during a forced exhalation cycle. Our methods include two major processes: (1) quantification of the non-rigid deformation as the bending energy (BE) based on the thin-plate spline method in the spatial domain and (2) calculation of the difference in the power spectrum from the tagging images, by using fast Fourier transform in the frequency domain. By considering 34 cases (17 normal and 17 abnormal liver cases), a remarkable difference between the two groups was found by both methods. The elasticity of the liver was finally analyzed by combining the bending energy and power spectral features obtained through MR tagging images. The result showed that only one abnormal case was misclassified in our dataset, which implied our method for non-invasive assessment of liver fibrosis has the potential to reduce the traditional liver biopsy.

Understanding of standardized uptake value (SUV) of 2-deoxy-2-[18F]fluoro-d-glucose positron emission tomography (FDG-PET) depends on the background accumulations of glucose because the SUV often varies the status of patients. The purpose of this study was to develop a new method for quantitative analysis of SUV of FDG-PET scan images. The method included an anatomical standardization and a statistical comparison with normal cases by using Z-score that are often used in SPM or 3D-SSP approach for brain function analysis. Our scheme consisted of two approaches, which included the construction of a normal model and the determination of the SUV scores as Z-score index for measuring the abnormality of an FDG-PET scan image. To construct the normal torso model, all of the normal images were registered into one shape, which indicated the normal range of SUV at all voxels. The image deformation process consisted of a whole body rigid registration of shoulder to bladder region and liver registration and a non-linear registration of body surface by using the thin-plate spline technique. In order to validate usefulness of our method, we segment suspicious regions on FDG-PET images manually, and obtained the Z-scores of the regions based on the corresponding voxels that stores the mean and the standard deviations from the normal model. We collected 243 (143 males and 100 females) normal cases to construct the normal model. We also extracted 432 abnormal spots from 63 abnormal cases (73 cancer lesions) to validate the Z-scores. The Z-scores of 417 out of 432 abnormal spots were higher than 2.0, which statistically indicated the severity of the spots. In conclusions, the Z-scores obtained by our computerized scheme with anatomical standardization of torso region would be useful for visualization and detection of subtle lesions on FDG-PET scan images even when the SUV may not clearly show an abnormality.

The elderly population has substantially increased worldwide. Aging is a complex process, and the effects of aging are myriad and insidious, leading to progressive deterioration of various organs, including the skeleton. Age-related bone loss and resultant osteoporosis in the elderly population increase the risk for fractures and morbidity. Osteoporosis is one of the most common conditions associated with aging, and age is an independent risk factor for osteoporotic fractures. With the development of noninvasive imaging techniques such as computed tomography (CT), micro-CT, and high resolution peripheral quantitative CT (HR-pQCT), imaging of the bone architecture provides important information about age-related changes in bone microstructure and estimates of bone strength. In the past two decades, studies of human specimens using imaging techniques have revealed decreased bone strength in older adults compared with younger adults. The present paper addresses recently studied age-related changes in trabecular and cortical bone microstructure based primarily on HR-pQCT and micro-CT. We specifically focus on the three-dimensional microstructure of the vertebrae, femoral neck, and distal radius, which are common osteoporotic fracture sites.