Share：
Share this content in WeChat
X
[Chinese] [PDF] 36 2
• Review •
Research progress on the assessment of supraspinatus tendon injury by deep learning method based on magnetic resonance imaging
ZHANG Jian  HOU Juan  YANG Xinguan 

DOI:10.12015/issn.1674-8034.2026.02.031.


[Abstract] Supraspinatus tendon injury represents the most prevalent type of rotator cuff tear, often manifesting as diminished shoulder strength and restricted mobility, significantly impairing patients' quality of life. Magnetic resonance imaging (MRI) serves as the primary imaging modality for preoperative assessment of supraspinatus tendon injuries. However, conventional image interpretation relies heavily on radiologists' subjective judgment and lacks precise evaluation of tear localization. Deep learning-based approaches utilizing MRI, which have brouken through the conventional subjective viewing habits of humans, can facilitate objective quantitative assessment of supraspinatus tendon injuries, enhancing diagnostic accuracy among radiologists, thereby guiding the formulation of individualized treatment strategies and improving patient prognosis. While numerous studies have explored deep learning methodologies for rotator cuff injury assessment, there remains a paucity of comprehensive reviews systematically evaluating existing research. This review synthesizes current literature on deep learning applications for supraspinatus tendon injury assessment, systematically examines clinical and imaging evaluation of supraspinatus tendon injuries, deep learning applications, current research limitations, and future directions. It explicitly identifies core challenges and technical bottlenecks, offers targeted references for clinical translation, and proposes actionable future research directions. The review highlights key areas for potential breakthroughs, aiming to advance the standardization, precision, and clinical applicability of supraspinatus tendon injury assessment, ultimately alleviating the disease burden on patients.
[Keywords] rotator cuff injury；supraspinatus tendon；magnetic resonance imaging；deep learning；artificial intelligence

ZHANG Jian   HOU Juan   YANG Xinguan*  

Department of Radiology, Guilin People's Hospital, Guilin 541002, China

Corresponding author: YANG X G, E-mail: Yang15007739374@163.com

Conflicts of interest   None.

Received  2025-10-24
Accepted  2026-01-15
DOI: 10.12015/issn.1674-8034.2026.02.031
DOI:10.12015/issn.1674-8034.2026.02.031.

[1]
BEDI A, BISHOP J, KEENER J, et al. Rotator cuff tears[J/OL]. Nat Rev Dis Primers, 2024, 10(1): 8 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/38332156/. DOI: 10.1038/s41572-024-00492-3.
[2]
BI A S, MORGAN A M, O'BRIEN M, et al. Partial-thickness rotator cuff tears: current concepts[J/OL]. JBJS Rev, 2024, 12(8) [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/39186569/. . DOI: 10.2106/JBJS.RVW.24.00063.
[3]
ZHAO J L, LUO M H, LIANG G H, et al. Risk factors for supraspinatus tears: A meta-analysis of observational studies[J/OL]. Orthop J Phys Med, 2021, 9(10): 23259671211042826 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/34660827/. DOI: 10.1177/23259671211042826.
[4]
GRIFFITH K M, HAMMER L C, IANNUZZI N P, et al. Review of human supraspinatus tendon mechanics. Part I: fatigue damage accumulation and failure[J]. J Shoulder Elb Surg, 2022, 31(12): 2671-2677. DOI: 10.1016/j.jse.2022.06.017.
[5]
PLANCHER K D, SHANMUGAM J, BRIGGS K, et al. Diagnosis and management of partial thickness rotator cuff tears: A comprehensive review[J]. J Am Acad Orthop Surg, 2021, 29(24): 1031-1043. DOI: 10.5435/JAAOS-D-20-01092.
[6]
ADRIANI M, SACCOMANNO M F, MOTTA M, et al. Reliability of magnetic resonance imaging criteria for the preoperative assessment of rotator cuff tears: a systematic review[J]. Am J Sports Med, 2024, 52(3): 845-858. DOI: 10.1177/03635465231166077.
[7]
CALVO E, REBOLLÓN C, ITOI E, et al. Reliable interobserver and intraobserver agreement of the International Society of Arthroscopy, Knee Surgery and Orthopaedic Sports Medicine (ISAKOS) classification system of rotator cuff tears[J]. J ISAKOS, 2022, 7(2): 56-61. DOI: 10.1016/j.jisako.2021.12.004.
[8]
CHENG P M, MONTAGNON E, YAMASHITA R, et al. Deep learning: an update for radiologists[J]. RadioGraphics, 2021, 41(5): 1427-1445. DOI: 10.1148/rg.2021200210.
[9]
RODRIGUEZ H C, RUST B, HANSEN P Y, et al. Artificial intelligence and machine learning in rotator cuff tears[J]. Sports Med Arthrosc Rev, 2023, 31(3): 67-72. DOI: 10.1097/JSA.0000000000000371.
[10]
LI Z J, REN S Y, ZHOU R, et al. Deep learning-based magnetic resonance imaging image features for diagnosis of anterior cruciate ligament injury[J/OL]. J Healthc Eng, 2021, 2021: 4076175 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/34306588/. DOI: 10.1155/2021/4076175.
[11]
WITTEN A, MIKKELSEN K, WAGENBLAST MAYNTZHUSEN T, et al. Terminology and diagnostic criteria used in studies investigating patients with subacromial pain syndrome from 1972 to 2019: a scoping review[J]. Br J Sports Med, 2023, 57(13): 864-871. DOI: 10.1136/bjsports-2022-106340.
[12]
SHANG X K, ZHENG J, YU Z Y, et al. Interpretation of clinical practice guidelines for the treatment of rotator cuff injury (2019)[J]. Chin J Shoulder Elb Electron Ed, 2021, 9(2): 103-111. DOI: 10.3877/cma.j.issn.2095-5790.2021.02.002.
[13]
ZHANG K B, TANG X, LI J, et al. Interpretation of American College of Orthopedics (AAOS) Clinical Practice Guidelines for rotator cuff injuries in 2019[J]. Chin J Phys Med, 2020, 39(5): 403-412. DOI: 10.16038/j.1000-6710.2020.05.013.
[14]
KIM S C, KIM H G, LEE J H, et al. Deteriorated quality and medial retraction of tendon after acute traumatic rotator cuff tear are predictors of retear after arthroscopic repair[J/OL]. Arthroscopy, 2025, 41(9): 3510-3522.e1 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/40154759/. DOI: 10.1016/j.arthro.2025.03.037.
[15]
YU W T, YU M C. Risk factors and prediction of rotator cuff re-tear after arthroscopic repair[J]. Orthop J China, 2024, 32(23): 2140-2145. DOI: 10.20184/j.cnki.Issn1005-8478.100966.
[16]
FENG Z N, WU S, HU H, et al. Arthroscopic procedures for degenerative rotator cuff disease: a systematic review and network meta-analysis[J/OL]. J Orthop Surg Res, 2024, 19(1): 650 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/39402591/. DOI: 10.1186/s13018-024-05129-5.
[17]
JIN H F, DENG Z H, SUN J F, et al. Surgical management for massive rotator cuff tears: a network meta-analysis of randomized controlled trials[J/OL]. Burns Trauma, 2024, 12: tkad052 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/38343900/. DOI: 10.1093/burnst/tkad052.
[18]
WEBER S C, ABRAMS J S, NOTTAGE W M. Complications associated with arthroscopic shoulder surgery[J]. Arthroscopy, 2002, 18(2Suppl 1): 88-95. DOI: 10.1053/jars.2002.31801.
[19]
CRUZ I A N DA, FAGUNDES M C, SILVA L N M DA, et al. Scapulothoracic disorders: anatomy, kinematics, clinical assessment, and multimodality imaging[J/OL]. RadioGraphics, 2025, 45: e240097 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/39636754/. DOI: 10.1148/rg.240097.
[20]
LUO F, WANG H D, ZENG Y, et al. Imaging diagnosis of erosive calcific tendonitis in the shoulder joint[J]. Chin J CT MRI, 2025, 23(9): 195-197. DOI: 10.3969/j.issn.1672-5131.2025.09.054.
[21]
FAROOQI A S, LEE A, NOVIKOV D, et al. Diagnostic accuracy of ultrasonography for rotator cuff tears: A systematic review and meta-analysis[J/OL]. Orthop J Phys Med, 2021, 9(10): 23259671211035106 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/34660823/. DOI: 10.1177/23259671211035106.
[22]
WU K T, CHEN P C, CHOU W Y, et al. Diagnostic accuracy and interobserver reliability of rotator cuff tear detection with ultrasonography are improved with attentional deep learning[J]. Arthroscopy, 2025, 41(8): 2708-2716. DOI: 10.1016/j.arthro.2024.12.024.
[23]
SCOTT I, CONNELL D, MOULTON D, et al. An automated method for tendon image segmentation on ultrasound using grey-level co-occurrence matrix features and hidden Gaussian Markov random fields[J/OL]. Comput Biol Med, 2024, 169: 107872 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/38160500/. DOI: 10.1016/j.compbiomed.2023.107872.
[24]
QI P, FENG T, JING L, et al. Diagnostic value of high frequency ultrasound combined with ultra-micro blood flow imaging in supraspinatus tendon injury[J]. Shandong Med J, 2021, 61(25): 83-85. DOI: 10.3969/j.issn.1002-266X.2021.25.022.
[25]
WANG Y H, LI P J, MENG L. Diagnostic value of shoulder MRI in supraspinatus muscle injury[J]. Shanxi Med J, 2021, 50(8): 1250-1253. DOI: 10.3969/j.issn.0253-9926.2021.08.005.
[26]
KHODARAHMI I, FRITZ J. The value of 3 tesla field strength for musculoskeletal magnetic resonance imaging[J]. Invest Radiol, 2021, 56(11): 749-763. DOI: 10.1097/RLI.0000000000000801.
[27]
CAO J T, HU M, QIAN P K, et al. Application value of 3.0T MRI 3D-MERGE sequence in evaluating the degree of supraspinatus tendon injury[J]. J Diagn Concepts Pract, 2021, 20(1): 77-81. DOI: 10.16150/j.1671-2870.2021.01.012.
[28]
ISERN-KEBSCHULL J, MECHÓ S, PEDRET C, et al. Muscle healing in sports injuries: MRI findings and proposed classification based on a single institutional experience and clinical observation[J/OL]. Radiographics, 2024, 44(8): e230147 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/39052498/. DOI: 10.1148/rg.230147.
[29]
SUN H T, FENG Y B, ZHAN D P, et al. Comparison of preoperative MRI measurements and intraoperative findings of supraspinatus tendon tear[J]. Orthop J China, 2025, 33(9): 856-860. DOI: 10.20184/j.cnki.Issn1005-8478.120043.
[30]
HE Y N, WANG C J, QU B, et al. Clinical value of magnetic resonance imaging in the diagnosis of rotator cuff injury[J]. J Hebei Med Univ, 2025, 46(1): 108-112. DOI: 10.3969/j.issn.1007-3205.2025.01.018.
[31]
FEUERRIEGEL G C, FRITZ B, MARTH A A, et al. Assessment of the rotator cuff muscles: state-of-the-art MRI and clinical implications[J/OL]. Radiology, 2025, 315(2): e242131 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/40326869/. DOI: 10.1148/radiol.242131.
[32]
TSUCHIYA S, BOIS A J, MATTHEWSON G, et al. The relationship between preoperative Goutallier stage and retear rates following posterosuperior rotator cuff repair: a systematic review[J]. J Shoulder Elbow Surg, 2023, 32(2): 435-443. DOI: 10.1016/j.jse.2022.09.011.
[33]
KUO T J, LEE Y H, LIN L C, et al. Global fatty degeneration index on preoperative magnetic resonance imaging predicts early postoperative shoulder stiffness at 3 months after primary rotator cuff repair[J]. Arthroscopy, 2025, 41(8): 2720-2727. DOI: 10.1016/j.arthro.2024.12.028.
[34]
FEUERRIEGEL G C, MARCUS R P, SOMMER S, et al. Fat fractions of the rotator cuff muscles acquired with 2-point Dixon MRI: predicting outcome after arthroscopic rotator cuff repair[J]. Invest Radiol, 2024, 59(4): 328-336. DOI: 10.1097/RLI.0000000000001024.
[35]
DWIVEDI A, SHARMA R, SHARMA A, et al. Evaluation of shoulder injuries: A comparative study of imaging by magnetic resonance imaging (MRI) and magnetic resonance arthrography (MRA)[J/OL]. J Pharm Bioallied Sci, 2024, 16(Suppl 2): S1494-S1497 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/38882885/. DOI: 10.4103/jpbs.jpbs_1104_23.
[36]
ELBADRY M, ABDELGALIL M S, QAFESHA R M, et al. High sensitivity and specificity of magnetic resonance arthrography for labral tears, rotator cuff tears, hill-Sachs lesions, and bankart lesions: a systematic review and meta-analysis[J/OL]. Arthroscopy, 2025, 41(9): 3622-3638.e18 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/39914604/. DOI: 10.1016/j.arthro.2025.01.048.
[37]
LIU F X, CHENG X Y, DONG J L, et al. Comparison of MRI and MRA for the diagnosis of rotator cuff tears: A meta-analysis[J/OL]. Medicine, 2020, 99(12): e19579 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/32195972/. DOI: 10.1097/MD.0000000000019579.
[38]
AWASTHI P, DWIVEDI A, CHOUDHARY S S. Role of magnetic resonance arthrography (MRA) in the diagnosis of shoulder injuries[J/OL]. Adv Biomed Res, 2025, 14(1): 55 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/40862170/. DOI: 10.4103/abr.abr_347_23.
[39]
AN F P, LI X W, MA X M. Medical image classification algorithm based on visual attention mechanism-MCNN[J/OL]. Oxid Med Cell Longev, 2021, 2021: 6280690 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/33688390/. DOI: 10.1155/2021/6280690.
[40]
D'ANGELO T, CAUDO D, BLANDINO A, et al. Artificial intelligence, machine learning and deep learning in musculoskeletal imaging: Current applications[J]. J Clin Ultrasound, 2022, 50(9): 1414-1431. DOI: 10.1002/jcu.23321.
[41]
KIJOWSKI R, LIU F, CALIVA F, et al. Deep learning for lesion detection, progression, and prediction of musculoskeletal disease[J]. J Magn Reson Imaging, 2020, 52(6): 1607-1619. DOI: 10.1002/jmri.27001.
[42]
WU X Y, HUA M Q, XIA Y F, et al. Research progress of radiomics and artificial intelligence in the growth prediction of pulmonary ground-glass nodules[J]. Chin Comput Med Imag, 2025, 31(1): 141-145. DOI: 10.19627/j.cnki.cn31-1700/th.2025.01.024.
[43]
LI F, ZHAI P H, YANG C, et al. Automated diagnosis of anterior cruciate ligament via a weighted multi-view network[J/OL]. Front Bioeng Biotechnol, 2023, 11: 1268543 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/37885456/. DOI: 10.3389/fbioe.2023.1268543.
[44]
GAO X, XIE X, WANG W T. Research progress of osteoarthritis of the knee using MRI: based on deep learning[J]. Chin J Magn Reson Imaging, 2023, 14(6): 192-197. DOI: 10.12015/issn.1674-8034.2023.06.035.
[45]
HAHN S, YI J, LEE H J, et al. Image quality and diagnostic performance of accelerated shoulder MRI with deep learning–based reconstruction[J]. Am J Roentgenol, 2022, 218(3): 506-516. DOI: 10.2214/ajr.21.26577.
[46]
VOSSHENRICH J, KOERZDOERFER G, FRITZ J. Modern acceleration in musculoskeletal MRI: applications, implications, and challenges[J]. Skeletal Radiol, 2024, 53(9): 1799-1813. DOI: 10.1007/s00256-024-04634-2.
[47]
FRITZ J, GUGGENBERGER R, DEL GRANDE F. Rapid musculoskeletal MRI in 2021: clinical application of advanced accelerated techniques[J]. AJR Am J Roentgenol, 2021, 216(3): 718-733. DOI: 10.2214/AJR.20.22902.
[48]
XIE X L, WANG J W, YAN X H, et al. Application value of intelligent quick magnetic resonance technology in supraspinatus tendon injuries[J]. Chin J Magn Reson Imaging, 2024, 15(10): 148-152, 164. DOI: 10.12015/issn.1674-8034.2024.10.025.
[49]
VOSSHENRICH J, BRUNO M, CANTARELLI RODRIGUES T, et al. Arthroscopy-validated diagnostic performance of 7-minute five-sequence deep learning super-resolution 3-T shoulder MRI[J/OL]. Radiology, 2025, 314(2): e241351 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/39964264/. DOI: 10.1148/radiol.241351.
[50]
DRATSCH T, SIEDEK F, ZÄSKE C, et al. Reconstruction of shoulder MRI using deep learning and compressed sensing: a validation study on healthy volunteers[J/OL]. Eur Radiol Exp, 2023, 7(1): 66 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/37880546/. DOI: 10.1186/s41747-023-00377-2.
[51]
LEE S H, LEE J, OH K S, et al. Automated 3-dimensional MRI segmentation for the posterosuperior rotator cuff tear lesion using deep learning algorithm[J/OL]. PLoS One, 2023, 18(5): e0284111 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/37200275/. DOI: 10.1371/journal.pone.0284111.
[52]
YANG H K, CHEN Q, FU K R, et al. Boosting medical image segmentation via conditional-synergistic convolution and lesion decoupling[J/OL]. Comput Med Imag Graph, 2022, 101: 102110 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/36057184/. DOI: 10.1016/j.compmedimag.2022.102110.
[53]
HESS H, GUSSAROW P, ROJAS J T, et al. Automatic 3-dimensional analysis of posterosuperior full-thickness rotator cuff tear size on magnetic resonance imaging[J/OL]. J Shoulder Elbow Surg, 2025, 34(6): e309-e316 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/39631559/. DOI: 10.1016/j.jse.2024.09.041.
[54]
ALIPOUR E, CHALIAN M, POOYAN A, et al. Automatic MRI-based rotator cuff muscle segmentation using U-Nets[J]. Skeletal Radiol, 2024, 53(3): 537-545. DOI: 10.1007/s00256-023-04447-9.
[55]
LI M Q, FANG J C, HOU H N, et al. Multi-model segmentation algorithm for rotator cuff injury based on MRI images[J/OL]. Bioengineering (Basel), 2025, 12(3): 218 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/40150682/. DOI: 10.3390/bioengineering12030218.
[56]
MEDINA G, BUCKLESS C G, THOMASSON E, et al. Deep learning method for segmentation of rotator cuff muscles on MR images[J]. Skeletal Radiol, 2021, 50(4): 683-692. DOI: 10.1007/s00256-020-03599-2.
[57]
YAO J, CHEPELEV L, NISHA Y, et al. Evaluation of a deep learning method for the automated detection of supraspinatus tears on MRI[J]. Skeletal Radiol, 2022, 51(9): 1765-1775. DOI: 10.1007/s00256-022-04008-6.
[58]
LAVOIE-GAGNE O, FURY M S, MEHTA N, et al. Double-row repair with platelet-rich plasma optimizes retear rates after small to medium full-thickness rotator cuff repair: a systematic review and network meta-analysis of randomized controlled trials[J]. Arthroscopy, 2022, 38(9): 2714-2729. DOI: 10.1016/j.arthro.2022.03.014.
[59]
CEDERQVIST S, FLINKKILÄ T, SORMAALA M, et al. Non-surgical and surgical treatments for rotator cuff disease: a pragmatic randomised clinical trial with 2-year follow-up after initial rehabilitation[J]. Ann Rheum Dis, 2021, 80(6): 796-802. DOI: 10.1136/annrheumdis-2020-219099.
[60]
NI M, ZHAO Y Q, ZHANG L H, et al. MRI-based automated multitask deep learning system to evaluate supraspinatus tendon injuries[J]. Eur Radiol, 2024, 34(6): 3538-3551. DOI: 10.1007/s00330-023-10392-x.
[61]
LIN D J, SCHWIER M, GEIGER B, et al. Deep learning diagnosis and classification of rotator cuff tears on shoulder MRI[J]. Invest Radiol, 2023, 58(6): 405-412. DOI: 10.1097/RLI.0000000000000951.
[62]
VELASQUEZ GARCIA A, HSU K L, MARINAKIS K. Advancements in the diagnosis and management of rotator cuff tears. The role of artificial intelligence[J]. J Orthop, 2024, 47: 87-93. DOI: 10.1016/j.jor.2023.11.011.
[63]
LONGO U G, BANDINI B, MANCINI L, et al. Artificial intelligence in rotator cuff tear detection: A systematic review of MRI-based models[J/OL]. Diagnostics (Basel), 2025, 15(11): 1315 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/40506887/. DOI: 10.3390/diagnostics15111315.
[64]
RIEM L, FENG X, COUSINS M, et al. A deep learning algorithm for automatic 3D segmentation of rotator cuff muscle and fat from clinical MRI scans[J/OL]. Radiol Artif Intell, 2023, 5(2): e220132 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/37035430/. DOI: 10.1148/ryai.220132.
[65]
SHIM E, KIM J Y, YOON J P, et al. Automated rotator cuff tear classification using 3D convolutional neural network[J/OL]. Sci Rep, 2020, 10(1): 15632 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/32973192/. DOI: 10.1038/s41598-020-72357-0.
[66]
MARSILIO L, MARZORATI D, ROSSI M, et al. Cascade learning in multi-task encoder-decoder networks for concurrent bone segmentation and glenohumeral joint clinical assessment in shoulder CT scans[J/OL]. Artif Intell Med, 2025, 165: 103131 [2025-10-23]. https://pubmed.ncbi.nlm.nih.gov/40279875/. DOI: 10.1016/j.artmed.2025.103131.

PREV Research progress on the value of MRI imaging features in the differential diagnosis of hematogenous osteomyelitis and malignant bone tumors of the extremities
NEXT Research progress of routine CT and MRI in opportunistic screening for osteoporosis
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn