Automated Muscle Segmentation from Clinical CT Using Bayesian U-Net for Personalized Musculoskeletal Modeling
Open accessThe DOI matches its Crossref record; 43 of the 45 references it cites were found in a registry or an index.
Abstract
We propose a method for automatic segmentation of individual muscles from a clinical CT. The method uses Bayesian convolutional neural networks with the U-Net architecture, using Monte Carlo dropout that infers an uncertainty metric in addition to the segmentation label. We evaluated the performance of the proposed method using two data sets: 20 fully annotated CTs of the hip and thigh regions and 18 partially annotated CTs that are publicly available from The Cancer Imaging Archive (TCIA) database. The experiments showed a Dice coefficient (DC) of 0.891±0.016 (mean±std) and an average symmetric surface distance (ASD) of 0.994±0.230 mm over 19 muscles in the set of 20 CTs. These results were statistically significant improvements compared to the state-of-the-art hierarchical multi-atlas method which resulted in 0.845 ± 0.031 DC and 1.556 ± 0.444 mm ASD. We evaluated validity of the uncertainty metric in the multi-class organ segmentation problem and demonstrated a correlation between the pixels with high uncertainty and the segmentation failure. One application of the uncertainty metric in active-learning is demonstrated, and the proposed query pixel selection method considerably reduced the manual annotation cost for expanding the training data set. The proposed method allows an accurate patient-specific analysis of individual muscle shapes in a clinical routine. This would open up various applications including personalization of biomechanical simulation and quantitative evaluation of muscle atrophy.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Xue al. [685] | et | 2019 | BNN and U-Net | Classification | Gigapixel phase im- ages | 1 | MC dropout and ensembles”
From A review of uncertainty quantification in deep learning: Techniques, applications and challenges (2021) · cites this paper as [685]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 4×
“the weights in the same way as in [9], and then trained the networks using adaptive moment estimation (Adam) [16] for 1×105 iterations at the learning rate of 0.”
MethodInfluentialFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
(2014) · Cited by 33,419
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
He, K., Zhang, X., Ren, S., & Sun, J. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.123 · Cited by 19,741 · cited 1×
“We initialized the weights in the same way as in [9], and then trained the networks using adaptive moment estimation (Adam) [16] for 1 × 10 5 iterations at the learning rate of 0.0001.”
MethodInfluentialMeasures of the Amount of Ecologic Association Between Species
Dice, L. R. (1945) · Ecology · doi:10.2307/1932409 · Cited by 11,874 · cited 1×
“We used the Dice coefficient (DC) [5] and the average symmetric surface distance (ASD) [31] as the error metrics.”
MethodDropout as a bayesian approximation: Representing model uncertainty in deep learning
Gal, Y., & Ghahramani, Z. (2015) · arXiv · doi:10.48550/arxiv.1506.02142 · Cited by 6,471 · cited 6×
“Below, we briefly summarize the theoretical background described in [7], formulate the specific metric that we employed in this paper, and propose a new structure-wise”
BackgroundMethodInfluential(2009) · Minds at UW (University of Wisconsin) · Cited by 4,791
What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
Kendall, A., & Gal, Y. (2017) · arXiv · doi:10.48550/arxiv.1703.04977 · Cited by 3,088 · cited 1×
“It measures the degree of difference of each test sample from the training data set, originated from the deficiency of training data, namely epistemic uncertainty [15].”
BackgroundSeth, A., Hicks, J. L., Uchida, T. K., Habib, A., Dembia, C. L., Dunne, J. J., Ong, C. F., DeMers, M. S., Rajagopal, A., Millard, M., et al. (2018) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1006223 · Cited by 1,322 · cited 1×
“The computational simulation of human motion using musculoskeletal modeling has been performed in a number of studies to investigate musculo-tendon forces and joint contact forces, which cannot be easily achieved by physical measurements [25], [27], [29].”
BackgroundFull-Body Musculoskeletal Model for Muscle-Driven Simulation of Human Gait
Rajagopal, A., Dembia, C. L., DeMers, M. S., Delp, D. D., Hicks, J. L., & Delp, S. L. (2016) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2586891 · Cited by 1,053
Research works printed but not linked: 2
- hiasa, 2018, Surgical tools segmentation in laparoscopic images using convolutional neural networks with uncertainty estimation and semi-supervised learning, Proc Int Conf CARS, 14
- hiasa, 2018, Cross-modality image synthesis from unpaired data using CycleGAN, Proc Int Workshop SASHIMI, 31
Cited by
A review of uncertainty quantification in deep learning: Techniques, applications and challenges
Abdar, M., Pourpanah, F., Hussain, S., Rezazadegan, D., Liu, L., Ghavamzadeh, M., Fieguth, P., Cao, X., Khosravi, A., Acharya, U. R., et al. (2021) · Information Fusion · doi:10.1016/j.inffus.2021.05.008 · Cited by 3,111
U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications
Siddique, N., Paheding, S., Elkin, C. P., & Devabhaktuni, V. (2021) · IEEE Access · doi:10.1109/access.2021.3086020 · Cited by 1,960
Lambert, B., Forbes, F., Doyle, S., Dehaene, H., & Dojat, M. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102830 · Cited by 269
Modality specific U-Net variants for biomedical image segmentation: a survey
Punn, N. S., & Agarwal, S. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10152-1 · Cited by 246
“(2018) Improved U-Net CT - X X - BU Mini-residual connections within encoder-decoder phases Janssens et al. (2018) Two stage U-Net model CT - X X - EU 3D FCN LocalizationNet followed by SegmentationNet Kumar et al. (2018) U-SegNet MRI X - X - BU Integration of skip connections with SegNet Kermi et al. (2018) Residual…”
MethodInfluentialSeoni, S., Jahmunah, V., Salvi, M., Barua, P. D., Molinari, F., & Acharya, U. R. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107441 · Cited by 239
A Review on Bayesian Deep Learning in Healthcare: Applications and Challenges
Abdullah, A. A., Hassan, M. M., & Mustafa, Y. T. (2022) · IEEE Access · doi:10.1109/access.2022.3163384 · Cited by 193
“Hiasa et al. [58] used Bayesian-CNN based U-Net for muscle segmentation from Musculoskeletal for CT scan images.”
MethodA comprehensive survey on deep active learning in medical image analysis
Wang, H., Jin, Q., Li, S., Liu, S., Wang, M., & Song, Z. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103201 · Cited by 210
“In muscle segmentation of CT images, Hiasa et al. (2020) selected key slices and key regions.”
Medical Image Segmentation With Limited Supervision: A Review of Deep Network Models
Peng, J., & Wang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3062380 · Cited by 132
“guidance to maintain reliable predictions [158]–[165].”
Brain stroke lesion segmentation using consistent perception generative adversarial network
Wang, S., Chen, Z., You, S., Wang, B.-C., Shen, Y., & Lei, B. (2022) · Neural Computing and Applications · doi:10.1007/s00521-021-06816-8 · Cited by 86
“It has become a popular neural network architecture for biomedical image segmentation tasks [12, 19, 31, 62].”
BackgroundDeep Learning Enables Superior Photoacoustic Imaging at Ultralow Laser Dosages
Zhao, H., Ke, Z., Yang, F., Li, K., Chen, N., Song, L., Zheng, C., Liang, D., & Liu, C. (2020) · Advanced Science · doi:10.1002/advs.202003097 · Cited by 76
Alzubaidi, L., Al-Dulaimi, K., Salhi, A., Alammar, Z., Fadhel, M. A., Albahri, A. S., Alamoodi, A. H., Albahri, O. S., Hasan, A. F., Bai, J., et al. (2024) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2024.102935 · Cited by 84
Liu, J., Gao, Q., Tang, Z., Xie, Y., Gui, W., Ma, T., & Niyoyita, J. P. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3006629 · Cited by 69
“Since then, FullConNet and U-Net with their variants, e.g., SegAN [15], have been widely used [16].”
Defect Inspection in Tire Radiographic Image Using Concise Semantic Segmentation
Zheng, Z., Zhang, S., Yu, B., Li, Q., & Zhang, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3003089 · Cited by 55
“Even though U-net has a good performance in the segmentation of medical images [27], the effect of using it in the detection of tire defects is unsatisfactory, especially for the”
BackgroundMethodInfluentialRozynek, M., Kucybała, I., Urbanik, A., & Wojciechowski, W. (2021) · Nutrition · doi:10.1016/j.nut.2021.111227 · Cited by 50
Deep Learning for Orthopedic Disease Based on Medical Image Analysis: Present and Future
Lee, J. H., & Chung, S. W. (2022) · Applied Sciences · doi:10.3390/app12020681 · Cited by 48
“Therefore, U-net is expected to be widely used for segmentation of medical images [67].”
MethodAutomated Segmentation of Abdominal Skeletal Muscle on Pediatric CT Scans Using Deep Learning
Castiglione, J., Somasundaram, E., Gilligan, L. A., Trout, A. T., & Brady, S. L. (2021) · Radiology Artificial Intelligence · doi:10.1148/ryai.2021200130 · Cited by 49
“To this end, Bayesian convolutional neural networks with Monte Carlo dropout as proposed by Hiasa et al (30) could be used to provide an uncertainty metric for each output prediction made by the U-Net model and can be incorporated in the future models to identify outlier predictions for the larger datasets without gro…”
MethodNishio, M., Noguchi, S., & Fujimoto, K. (2020) · Applied Sciences · doi:10.3390/app10103360 · Cited by 49
Image-based biomechanical models of the musculoskeletal system
Galbusera, F., Cina, A., Panico, M., Albano, D., & Messina, C. (2020) · European Radiology Experimental · doi:10.1186/s41747-020-00172-3 · Cited by 41
“[28], a Bayesian convolutional network with the U-Net architecture was implemented to automatically extract muscle segmentation from clinical CT scans.”
MethodUncertainty-based Active Learning by Bayesian U-Net for Multi-label Cone-beam CT Segmentation
Huang, J., Farpour, N., Yang, B. J., Mupparapu, M., Lure, F. Y. M., Li, J., Yan, H., & Setzer, F. C. (2023) · Journal of Endodontics · doi:10.1016/j.joen.2023.11.002 · Cited by 42
Coronary artery segmentation in angiographic videos utilizing spatial-temporal information
Wang, L., Liang, D., Yin, X., Qiu, J., Yang, Z., Xing, J., Dong, J., & Ma, Z. (2020) · BMC Medical Imaging · doi:10.1186/s12880-020-00509-9 · Cited by 44
Zhu, J., Bolsterlee, B., Chow, B. V. Y., Cai, C., Herbert, R., Song, Y., & Meijering, E. H. W. (2021) · NMR in Biomedicine · doi:10.1002/nbm.4609 · Cited by 36
Kim, H. S., Kim, H., Kim, S., Cha, Y., Kim, J.-T., Kim, J.-W., Ha, Y., & Yoo, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-53707-8 · Cited by 33
“Nevertheless, achieving precise voxel-level segmentation is essential for accurately quantifying each individual muscle’s volume and gaining comprehensive insights into muscle performance 9 .”
BackgroundMethodBayesian U-Net for Segmenting Glaciers in Sar Imagery
Hartmann, A., Davari, A., Seehaus, T., Braun, M., Maier, A., & Christlein, V. (2021) · IEEE International Geoscience and Remote Sensing Symposium (IGARSS) · doi:10.1109/igarss47720.2021.9554292 · Cited by 35
“[9], who themselves followed the proposal by Gal and Ghahramani [7].”
BackgroundMethodLarge-scale analysis of iliopsoas muscle volumes in the UK Biobank
Fitzpatrick, J. A., Basty, N., Cule, M., Liu, Y., Bell, J. D., Thomas, E. L., & Whitcher, B. J. (2020) · Scientific Reports · doi:10.1038/s41598-020-77351-0 · Cited by 37
Bonaldi, L., Pretto, A., Pirri, C., Uccheddu, F., Fontanella, C. G., & Stecco, C. (2023) · Bioengineering · doi:10.3390/bioengineering10020137 · Cited by 31
Uemura, K., Otake, Y., Takao, M., Makino, H., Soufi, M., Iwasa, M., Sugano, N., & Sato, Y. (2022) · Archives of Osteoporosis · doi:10.1007/s11657-022-01063-3 · Cited by 29
“For all four parameters, femur segmentation from the CT images was first performed using a Bayesian U-Net model, a convolutional neural network for semantic segmentation that has been reported and validated elsewhere [14]”
MethodSelf-citationvan Rooij, W., Verbakel, W. F. A. R., Slotman, B. J., & Dahele, M. R. (2021) · Advances in Radiation Oncology · doi:10.1016/j.adro.2021.100658 · Cited by 29
Deep-learning-based automatic facial bone segmentation using a two-dimensional U-Net
Morita, D., Soufi, M., Tsujiko, S., Otake, Y., Sato, Y., & Numajiri, T. (2022) · International Journal of Oral and Maxillofacial Surgery · doi:10.1016/j.ijom.2022.10.015 · Cited by 28
Self-citationActive learning for segmentation based on Bayesian sample queries
Özdemir, F., Peng, Z., Fürnstahl, P., Tanner, C., & Göksel, O. (2020) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106531 · Cited by 34
Wu, D., Zhi, X., Liu, X., Zhang, Y., & Chai, W. (2022) · Journal of Orthopaedic Surgery and Research · doi:10.1186/s13018-022-02932-w · Cited by 25
“V-Net and U-Net), have been successfully applied in hip segmentation [11].”
MethodBoosting Personalized Musculoskeletal Modeling With Physics-Informed Knowledge Transfer
Zhang, J., Zhao, Y., Bao, T., Li, Z., Qian, K., Frangi, A. F., Xie, S. Q., & Zhang, Z. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3227604 · Cited by 80
“However, when we study the musculoskeletal function of the specific subject, musculoskeletal model with the unique anatomy and neurophysiology of the subject is necessary [26], [27].”
BackgroundA Deep Convolutional Gated Recurrent Unit for CT Image Reconstruction
Ikuta, M., & Zhang, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3169569 · Cited by 26
Lee, S. H., Lee, J. H., Oh, K.-S., Yoon, J. P., Seo, A., Jeong, Y., & Chung, S. W. (2023) · PLoS ONE · doi:10.1371/journal.pone.0284111 · Cited by 24
Morita, D., Kawarazaki, A., Koimizu, J., Tsujiko, S., Soufi, M., Otake, Y., Sato, Y., & Numajiri, T. (2023) · Journal of Cranio-Maxillofacial Surgery · doi:10.1016/j.jcms.2023.09.003 · Cited by 23
Self-citationDiao, Z., Jiang, H., & Shi, T. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108739 · Cited by 25
Uemura, K., Otake, Y., Takashima, K., Hamada, H., Imagama, T., Takao, M., Sakai, T., Sato, Y., Okada, S., & Sugano, N. (2023) · Bone and Joint Research · doi:10.1302/2046-3758.129.bjr-2023-0115.r1 · Cited by 24
Self-citationIwasa, M., Takao, M., Soufi, M., Uemura, K., Otake, Y., Hamada, H., Sato, Y., Sugano, N., & Okada, S. (2022) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02797-8 · Cited by 23
Self-citationGu, Y., Otake, Y., Uemura, K., Soufi, M., Takao, M., Talbot, H., Okada, S., Sugano, N., & Sato, Y. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102970 · Cited by 24
Self-citationUemura, K., Otake, Y., Takao, M., Soufi, M., Kawasaki, A., Sugano, N., & Sato, Y. (2021) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-021-02345-w · Cited by 18
Self-citationCheng, R., Crouzier, M., Hug, F., Tucker, K. J., Juneau, P. L., McCreedy, E. S., Gandler, W., McAuliffe, M., & Sheehan, F. T. (2021) · Medical Physics · doi:10.1002/mp.15335 · Cited by 19
Deep generative models for automated muscle segmentation in computed tomography scanning
Nishiyama, D., Iwasaki, H., Taniguchi, T., Fukui, D., Yamanaka, M., Harada, T., & Yamada, H. (2021) · PLoS ONE · doi:10.1371/journal.pone.0257371 · Cited by 17
“[14] proposed a method using Bayesian convolutional neural networks with U-Net and Monte Carlo dropout for the automatic segmentation of individual muscles from clinical CT images; their results showed significant improvements compared to the hierarchical multiatlas method.”
MethodYoo, H. J., Kim, Y. J., Hong, H., Hong, S. H., Chae, H. D., & Choi, J.-Y. (2022) · European Radiology · doi:10.1007/s00330-022-08770-y · Cited by 18
“Image segmentation of individual muscles is timeconsuming and labor-intensive, severely limiting the application of CT in quantifying skeletal muscle mass [20, 21].”
BackgroundTang, X., Zhu, J., Zhong, P., Yu, C., Zhang, B., & Hu, H. (2022) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2022.107281 · Cited by 17
Sakamoto, M., Hiasa, Y., Otake, Y., Takao, M., Suzuki, Y., Sugano, N., & Sato, Y. (2020) · Journal of Signal Processing Systems · doi:10.1007/s11265-019-01507-z · Cited by 24
“Among several previous CNN-based methods [2–4] on segmentation of musculoskeletal structures from CT, our Bayesian U-net [5] showed improved accuracy and provided uncertainty in segmentation.”
BackgroundMethodInfluentialSelf-citationvon Haxthausen, F., Ipsen, S., Schwegmann, H., Bruder, R., Ernst, F., & García‐Vázquez, V. (2020) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-020-02171-6 · Cited by 18
Soufi, M., Otake, Y., Iwasa, M., Uemura, K., Hakotani, T., Hashimoto, M., Yamada, Y., Yamada, M., Yokoyama, Y., Jinzaki, M., et al. (2025) · Scientific Reports · doi:10.1038/s41598-024-83793-7 · Cited by 21
Self-citationGuo, J., Wang, J., Chen, J., Ren, G., Tian, Q., & Guo, C. (2023) · Multibody System Dynamics · doi:10.1007/s11044-023-09876-x · Cited by 16
“Based on high-fidelity imaging data [85], a more detailed mandibular model could be built by considering a tumor model in the preoperative stage and the scar tissue biomechanics [86] in the postoperative stage.”
MethodArtificial intelligence in healthcare and medicine technology development review
Chung, D. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109801 · Cited by 22
Learning trustworthy model from noisy labels based on rough set for surface defect detection
Niu, T., Wang, Z., Li, W., Li, K., Li, K., Xu, G., & Li, Y. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112138 · Cited by 21
Zhang, R., He, A., Xia, W., Su, Y., Jian, J., Liu, Y., Guo, Z., Shi, W., Zhang, Z., He, B., et al. (2023) · Academic Radiology · doi:10.1016/j.acra.2023.06.009 · Cited by 15
Kawamoto, M., Kamiya, N., Zhou, X., Kato, H., Hara, T., & Fujita, H. (2023) · IEEE Access · doi:10.1109/access.2023.3335948 · Cited by 14
Li, G., Otake, Y., Soufi, M., Taniguchi, M., Yagi, M., Ichihashi, N., Uemura, K., Takao, M., Sugano, N., & Sato, Y. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03065-7 · Cited by 16
“In order to further identify the informative instances, we implement a Bayesian active learning (BAL) framework based on Bayesian U-net [10] for uncertainty estimation and sampling.”
BackgroundMethodInfluentialSelf-citationBreaking the Barrier: Selective Uncertainty-Based Active Learning for Medical Image Segmentation
Ma, S., Wu, H., Lawlor, A., & Dong, R. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10446026 · Cited by 28
“Furthermore, in the context of segmentation, contemporary AL meth-ods continue to employ conventional classification-oriented techniques, such as entropy and Bayesian, through cumulative pixel-level metric aggregation [9, 10, 11].”
MethodKomura, N., Matsumoto, K., Igari, S., Ogawa, T., Fujita, S., & NAKAMOTO, K. (2023) · International Journal of Automation Technology · doi:10.20965/ijat.2023.p0120 · Cited by 13
Self-citationAshino, K., Kamiya, N., Zhou, X., Kato, H., Hara, T., & Fujita, H. (2024) · Radiological Physics and Technology · doi:10.1007/s12194-024-00839-1 · Cited by 12
“In addition, data augmentation was applied to the training images, which is effective in the skeletal muscle segmentation of the lower and upper legs [25].”
Kono, K., Kinoshita, T., Soufi, M., Otake, Y., Masaki, Y., Uemura, K., Kutsuna, T., Hino, K., Miyamoto, T., Tanaka, Y., et al. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03284-y · Cited by 12
“A deep learning-based AI model built from a fully convolutional neural network with a U-Net architecture (Bayesian U-Net), which has a high reliability in bone and muscle assessment in hip-to-knee CTs [19], was used in this study.”
Self-citationGu, Y., Otake, Y., Uemura, K., Soufi, M., Takao, M., Sugano, N., & Sato, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-16446-0_61 · Cited by 14
Self-citationKamiya, N., Oshima, A., Zhou, X., Kato, H., Hara, T., Miyoshi, T., Matsuo, M., & Fujita, H. (2020) · Applied Sciences · doi:10.3390/app10134477 · Cited by 12
“Hiasa and Sakamoto proposed a site-specific segmentation method for a total of 19 skeletal muscles, in the thigh and hip regions, using deep learning [8,9].”
MethodArtificial Intelligence in Musculoskeletal Radiology: Past, Present, and Future
Pankhania, M. (2020) · Indian Journal of Musculoskeletal Radiology · doi:10.25259/ijmsr_62_2020 · Cited by 13
A Bayesian network for simultaneous keyframe and landmark detection in ultrasonic cine
Feng, Y., Yang, J., Li, M., Tang, L.-Z., Sun, S., & Wang, Y. (2024) · Medical Image Analysis · doi:10.1016/j.media.2024.103228 · Cited by 12
Zhang, X., Xiang, Y., Yao, J., Hu, X., Wang, Y., Liu, L., Wang, Y., & Wu, Y. (2023) · Quantitative Imaging in Medicine and Surgery · doi:10.21037/qims-22-1198 · Cited by 12
“This may also be the reason why many studies (39-41) choose to automatically segment the larger limb muscles instead of the pelvic floor muscles.”
Uemura, K., Takashima, K., Otake, Y., Li, G., Mae, H., Okada, S., Hamada, H., & Sugano, N. (2025) · The Journal of Arthroplasty · doi:10.1016/j.arth.2025.05.126 · Cited by 10
Self-citationYang, Z., Choi, I., Choi, J., Jung, J., Ryu, M., & Yong, H. S. (2023) · PLoS ONE · doi:10.1371/journal.pone.0290950 · Cited by 12
Gomariz, Á., Portenier, T., Nombela‐Arrieta, C., & Göksel, O. (2022) · Science Advances · doi:10.1126/sciadv.abi8295 · Cited by 13
“Bayesian regression networks for calibrated detections Motivated by the advantages in calibration with the use of different Bayesian DL techniques reported for different domains (52, 57, 58, 61), we adapt our framework to take into account any uncertainties in DM regression.”
MethodZhang, L., Guo, Z., Zhang, H., van der Plas, E. A. A., Koscik, T. R., Nopoulos, P., & Sonka, M. (2023) · Medical Physics · doi:10.1002/mp.16284 · Cited by 13
“Hiasa et al. 14 proposed a general automated segmentation of individual muscles by using Bayesian convolutional neural networks with the U-Net architecture.”
Li, L., Liu, H., Li, Q., Tian, Z., Li, Y., Geng, W., & Wang, S. (2023) · Bioengineering · doi:10.3390/bioengineering10060726 · Cited by 10
Schmid, J., Assassi, L., & Chênes, C. (2023) · European Radiology Experimental · doi:10.1186/s41747-023-00357-6 · Cited by 11
“As our THA training dataset contains several pathological cases with sometimes significant bone deformations and the presence of several implants, this distribution may have impacted the performance of the segmentation approach in the presence of healthy bones.”
BackgroundInfluentialMasuda, M., Soufi, M., Otake, Y., Uemura, K., Kono, S., Takashima, K., Hamada, H., Gu, Y., Takao, M., Okada, S., et al. (2024) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-024-03087-1 · Cited by 9
“Model uncertainty was also correlated with the prediction accuracy in image segmentation problems [17].”
BackgroundSelf-citationFedZaCt: Federated Learning with Z Average and Cross-Teaching on Image Segmentation
Yang, T., Xu, J., Zhu, M., An, S., Gong, M., & Zhu, H. (2022) · Electronics · doi:10.3390/electronics11203262 · Cited by 12
Kang, H., Zhang, W., Li, S., Wang, X., Sun, Y., Sun, X., Li, F.-X., Hou, C., Lam, S., & Zheng, Y. (2024) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2024.108494 · Cited by 12
Andrzejewski, K., Domżalski, M. E., Komorowski, P., Poszepczyński, J., Rokita, B., & Elgalal, M. T. (2023) · Diagnostics · doi:10.3390/diagnostics13152516 · Cited by 10
An Uncertainty-based Neural Network for Explainable Trajectory Segmentation
Bi, X., Zhang, C., Wang, F., Liu, Z., Zhao, X., Yuan, Y., & Wang, G. (2021) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3467978 · Cited by 8
Teikari, P., & Pietrusz, A. (2021) · SportRxiv (OSF Preprints) · doi:10.31236/osf.io/w734a · Cited by 17
Jalal, N., Śliwińska, M., Wojciechowski, W., Kucybała, I., Rozynek, M., Krupa, K., Matusik, P. S., Jarczewski, J. D., & Tabor, Z. (2024) · Applied Sciences · doi:10.3390/app142110020 · Cited by 12
Iwasa, M., Uemura, K., Soufi, M., Otake, Y., Kinoshita, T., Kutsuna, T., Takashima, K., Hamada, H., Sato, Y., Sugano, N., et al. (2025) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-025-03321-4 · Cited by 8
“The images were automatically extracted using the artificial intelligence system (Bayesian U-Net) previously developed by us [14].”
Self-citationImani, M., Buratto, J., Dao, T., Meijering, E. H. W., Vogrin, S., Kwok, T. C. Y., ORWOLL, E. S., Cawthon, P. M., & Duque, G. (2025) · Journal of Cachexia Sarcopenia and Muscle · doi:10.1002/jcsm.13728 · Cited by 11
Ahmed, M. R., & Lasserre, P. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103399 · Cited by 8
Yan, C., Lu, J., Chen, K., Wang, L., Lu, H., Yu, L., Sun, M., & Xu, J. (2021) · Magnetic Resonance in Medicine · doi:10.1002/mrm.28939 · Cited by 7
Translation of Cellular Protein Localization Using Convolutional Networks
Shigene, K., Hiasa, Y., Otake, Y., Soufi, M., Janewanthanakul, S., Nishimura, T., Sato, Y., & Suetsugu, S. (2021) · Frontiers in Cell and Developmental Biology · doi:10.3389/fcell.2021.635231 · Cited by 7
“The detailed methodology is described in the Conditional GAN subsection of the “Materials and Methods” section (Hiasa et al., 2019).”
MethodSelf-citationAn Enhanced U-Net Approach for Segmentation of Aeroengine Hollow Turbine Blade
Zheng, J., Tang, C. Y., Sun, Y., Feng, M., & Wang, C. (2022) · Mathematics · doi:10.3390/math10224230 · Cited by 8
Pool-UNet: Ischemic Stroke Segmentation from CT Perfusion Scans Using Poolformer UNet
Liu, R., Pu, W., Zou, Y., Jiang, L., & Ye, Z. (2022) · Asian Conference on Artificial Intelligence Technology (ACAIT) · doi:10.1109/acait56212.2022.10137834 · Cited by 9
“The classical image segmentation algorithm can learn the local features of images well and has been extensively used by research scholars in medical image segmentation tasks [20]– [25].”
BackgroundUemura, K., Takao, M., Otake, Y., Iwasa, M., Hamada, H., Ando, W., Sato, Y., & Sugano, N. (2022) · Calcified Tissue International · doi:10.1007/s00223-022-01012-9 · Cited by 7
“175 mm [15], and the accuracy of calibration segmentation had a median Dice coefficient of 0.”
BackgroundSelf-citationSkeletal muscle shape influences joint torque exertion through the mechanical advantages
Umehara, J., Taniguchi, M., Yagi, M., Li, G., Soufi, M., Otake, Y., Sato, Y., Fukumoto, Y., Yamagata, M., Nakai, R., et al. (2025) · Journal of Applied Physiology · doi:10.1152/japplphysiol.00997.2024 · Cited by 6
Self-citationNozaki, T., Hashimoto, M., Ueda, D., Fujita, S., Fushimi, Y., Kamagata, K., Matsui, Y., Ito, R., Tsuboyama, T., Tatsugami, F., et al. (2025) · La radiologia medica · doi:10.1007/s11547-024-01947-z · Cited by 7
Quintero, P., Cerviño, L., Zhang, H., & Harris, W. (2025) · Medical Physics · doi:10.1002/mp.17721 · Cited by 8
“16,27 To match the ten sub-models from the ensemble models M1 and M3, ten outputs were randomly taken from the MC integration loop for the testing dataset predictions.”
Artifact estimation network for MR images: effectiveness of batch normalization and dropout layers
Maruyama, T., Hayashi, N., Sato, Y., Ogura, T., Uehara, M., Watanabe, H., & Kitoh, Y. (2025) · BMC Medical Imaging · doi:10.1186/s12880-025-01663-8 · Cited by 6
Self-citation(2022) · International Journal of Computer Assisted Radiology and Surgery · doi:10.1007/s11548-022-02635-x · Cited by 6
Yang, T., Zhang, Y., Zhu, M., Wang, Y., An, S., Gu, X., Liu, X., Han, J., He, Y., & Zhu, H. (2022) · IET Image Processing · doi:10.1049/ipr2.12597 · Cited by 6
Huang, Y. Y., Holcombe, S. A., Wang, S. C., & Tang, J. (2024) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2024.102456 · Cited by 5
Robust semi-automatic segmentation method: an expert assistant tool for muscles in CT and MR data
Azimbagirad, M., Dardenne, G., Salem, D. B., Werthel, J.-D., de Casson, F. B., Stindel, É., Garraud, C., Rémy‐Néris, O., & Burdin, V. (2024) · Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization · doi:10.1080/21681163.2023.2301403 · Cited by 5
“In another study Hiasa et al. (2020) used a U-Net DL model to segment muscles in hip and thigh regions.”
MethodSide-to-side differences in hip bone mineral density in patients with unilateral hip osteoarthritis
Uemura, K., Kono, S., Takashima, K., Tamura, K., Higuchi, R., Mae, H., NAKAMURA, N., Otake, Y., Sato, Y., Sugano, N., et al. (2025) · Bone · doi:10.1016/j.bone.2025.117456 · Cited by 7
Self-citationMizoe, S., Otake, Y., Miyamoto, T., Soufi, M., Nakao, S., Tanaka, Y., & Sato, Y. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-87202-1_18 · Cited by 5
Self-citationKono, S., Takashima, K., Uemura, K., Mae, H., Takagi, K., Soufi, M., Otake, Y., Sato, Y., Sugano, N., Okada, S., et al. (2025) · Bone and Joint Research · doi:10.1302/2046-3758.148.bjr-2024-0216.r2 · Cited by 4
“17 - - - -”
InfluentialSelf-citationSuzuki, M., Kinoshita, T., Kono, K., Soufi, M., Otake, Y., Uemura, K., Kutsuna, T., Hino, K., Murakami, Y., Watanabe, Y., et al. (2025) · Journal of Experimental Orthopaedics · doi:10.1002/jeo2.70518 · Cited by 5
“Recent deep ‐ learning developments have enabled the automatic segmentation of muscle groups, allowing precise 3D analysis of individual muscles using CT or MRI images [15, 19, 22, 43].”
Self-citationChoi, I., Choi, J., Yong, H. S., & Yang, Z. (2024) · PLoS ONE · doi:10.1371/journal.pone.0306789 · Cited by 4
Wohlfarth, V., Kway, Y. M., Sood, A., Jeon, Y. S., Chong, L. R., Marx, U. C., Tay, J., Eriksson, J. G., Bendahan, D., Michel, C. P., et al. (2025) · Magnetic Resonance Materials in Physics Biology and Medicine · doi:10.1007/s10334-025-01308-5 · Cited by 8
Pei, T., Lei, Y., Gao, Y., Zhang, M., Xu, T., Yang, W., Wen, Q., & Liu, Q. (2026) · Frontiers in Endocrinology · doi:10.3389/fendo.2026.1779448 · Cited by 5
“Deep-learning models address modality variation through transfer learning and domain adaptation (34).”
InfluentialBi-Graph Reasoning for Masticatory Muscle Segmentation From Cone-Beam Computed Tomography
Zhong, Y., Pei, Y., Nie, K., Zhang, Y., Xu, T., & Zha, H. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3304557 · Cited by 5
Kim, H. S., Kim, S., Kim, H., Song, S.-Y., Cha, Y., Kim, J.-T., Kim, J. W., Ha, Y., & Yoo, J. (2024) · PeerJ · doi:10.7717/peerj.17509 · Cited by 4
“The volume of each individual muscle, obtained by calculating the annotated segmentation mask, can overcome these limitations ( Hiasa et al., 2019 ).”
BackgroundFalcinelli, C., Cheong, V. S., Ellingsen, L. M., & Helgason, B. (2024) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2024.1446829 · Cited by 6
Metadata
- Authors
- Hiasa, Y., Otake, Y., Takao, M., Ogawa, T., Sugano, N., & Sato, Y.
- Affiliations
- Nara Institute of Science and Technology (JP)
- The University of Osaka (JP)
- Venue
- IEEE Transactions on Medical Imaging
- Published
- 2020-04
- Volume
- 39
- Issue
- 4
- Pages
- 1030-1040
- ISSN
- 0278-0062 (ISSN-L)
- 1558-254X
- OpenAlex
- W2972629588
- Cited by
- 157
- References
- 45
- Citations by year
- 2026: 16 · 2025: 27 · 2024: 26 · 2023: 24 · 2022: 26 · 2021: 22 · 2020: 16
- FWCI
- 7.16
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Medical Imaging (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Ministry of Education, Culture, Sports, Science and Technology (19H01176, 26108004)
- Japan Society for the Promotion of Science (20407)
- AMED/ETH Strategic Japanese-Swiss Cooperative Program
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Engineering › Biomedical Engineering › Medical Imaging and Analysis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- muscle segmentation, Monte Carlo dropout, uncertainty estimation, musculoskeletal modeling, active learning (machine learning), muscle atrophy, biomechanical simulation, multi-atlas segmentation
- MeSH terms
- Deep Learning, Bayes Theorem, Female, Hip, Humans, Image Processing, Computer-Assisted, Male, Thigh, Tomography, X-Ray Computed, Neural Networks, Computer, Muscle, Skeletal, Arthroplasty, Replacement, Hip, Patient-Specific Modeling
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.