Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears

Santomartino, Samantha M; Kung, Justin; Yi, Paul H.

doi:10.1007/s00256-023-04416-2

Cited by 4 publications

(4 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first group of items (1)(2)(3)(4)(5)(6)(7)(8)(9)(10)(11)(12)(13) refers to the quality of the title, abstract, introduction, methods section, study design, and data. The next group (14)(15)(16)(17)(18)(19)(20)(21)(22)(23)(24) examines the quality of ground truth, data partitions, and model; items (25)(26)(27)(28)(29)(30)(31)(32)(33)(34)(35)(36)(37) refer to the training, evaluation, and results section with data and model performance; and items (38)(39)(40)(41)(42) examine the discussion section and other information [33]. Item 41 states that readers can access the full study protocol, which is essential for further investigations and the overall credibility of the study.…”

Section: Quality Assessmentmentioning

confidence: 99%

“…Furthermore, despite the focus on DL model performance regarding meniscal tear localization, description, or classification, the number of studies addressing these aspects remains relatively small, potentially restricting the depth of analysis. Although several similar reviews [ 30 , 31 , 32 , 52 ] exist in the literature, the primary limitations remain the heterogeneity and number of included studies, preventing thorough statistical comparisons of output modes. Addressing these limitations in future research endeavors would enhance the comprehensive evaluation of DL’s role in detecting meniscal tears on MRI scans.…”

Section: Study Limitationsmentioning

confidence: 99%

“…This systematic review introduces novel approaches compared to similar previous studies: (i) focus is exclusively on meniscal tears, and while previous reviews have explored DL models in conjunction with various knee injuries, none have explicitly outlined meniscal lesion classifications [ 30 , 31 , 32 ]; (ii) the accuracy of the DL model is studied through meta-analyses that previous reviews have not conducted to the best of our knowledge [ 30 , 31 , 32 ]; (iii) evaluation of whether the presented DL models outperform radiologist interpretations; (iv) evaluation of the DL model’s performance in classifying meniscal tears and detecting their various types, providing an updated comparison with human understanding; and, most notably, (v) introduction of the novelty of assessing DL model performance against arthroscopic surgery as the standard reference. Previous reviews reported that due to the heterogeneity of the included studies, it was impossible to achieve in-depth statistical comparisons of the output mode [ 30 , 31 ]; (vi) compared to previous reviews, this one assesses the quality of the studies, considering the guidelines set forth by the CLAIM checklist [ 33 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Evaluation of Deep Learning Models on Knee MRIs for the Diagnosis and Classification of Meniscal Tears: A Systematic Review and Meta-Analysis

Botnari,

Kadar,

Patrascu

2024

Diagnostics

View full text Add to dashboard Cite

Objectives: This study delves into the cutting-edge field of deep learning techniques, particularly deep convolutional neural networks (DCNNs), which have demonstrated unprecedented potential in assisting radiologists and orthopedic surgeons in precisely identifying meniscal tears. This research aims to evaluate the effectiveness of deep learning models in recognizing, localizing, describing, and categorizing meniscal tears in magnetic resonance images (MRIs). Materials and methods: This systematic review was rigorously conducted, strictly following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Extensive searches were conducted on MEDLINE (PubMed), Web of Science, Cochrane Library, and Google Scholar. All identified articles underwent a comprehensive risk of bias analysis. Predictive performance values were either extracted or calculated for quantitative analysis, including sensitivity and specificity. The meta-analysis was performed for all prediction models that identified the presence and location of meniscus tears. Results: This study’s findings underscore that a range of deep learning models exhibit robust performance in detecting and classifying meniscal tears, in one case surpassing the expertise of musculoskeletal radiologists. Most studies in this review concentrated on identifying tears in the medial or lateral meniscus and even precisely locating tears—whether in the anterior or posterior horn—with exceptional accuracy, as demonstrated by AUC values ranging from 0.83 to 0.94. Conclusions: Based on these findings, deep learning models have showcased significant potential in analyzing knee MR images by learning intricate details within images. They offer precise outcomes across diverse tasks, including segmenting specific anatomical structures and identifying pathological regions. Contributions: This study focused exclusively on DL models for identifying and localizing meniscus tears. It presents a meta-analysis that includes eight studies for detecting the presence of a torn meniscus and a meta-analysis of three studies with low heterogeneity that localize and classify the menisci. Another novelty is the analysis of arthroscopic surgery as ground truth. The quality of the studies was assessed against the CLAIM checklist, and the risk of bias was determined using the QUADAS-2 tool.

show abstract

Section: Quality Assessmentmentioning

confidence: 99%

Section: Study Limitationsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Evaluation of Deep Learning Models on Knee MRIs for the Diagnosis and Classification of Meniscal Tears: A Systematic Review and Meta-Analysis

Botnari,

Kadar,

Patrascu

2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Injuries to the ACL, as well as other ligaments and menisci, are highly prevalent and are commonly diagnosed using knee MRI [22]. AI, particularly DL, has become a widely studied tool to enhance the capabilities of radiologists in various clinical applications [23,24].…”

Section: Diagnosismentioning

confidence: 99%

The Role of Artificial Intelligence in Anterior Cruciate Ligament Injuries: Current Concepts and Future Perspectives

Andriollo,

Picchi,

Sangaletti

et al. 2024

Healthcare

View full text Add to dashboard Cite

The remarkable progress in data aggregation and deep learning algorithms has positioned artificial intelligence (AI) and machine learning (ML) to revolutionize the field of medicine. AI is becoming more and more prevalent in the healthcare sector, and its impact on orthopedic surgery is already evident in several fields. This review aims to examine the literature that explores the comprehensive clinical relevance of AI-based tools utilized before, during, and after anterior cruciate ligament (ACL) reconstruction. The review focuses on current clinical applications and future prospects in preoperative management, encompassing risk prediction and diagnostics; intraoperative tools, specifically navigation, identifying complex anatomic landmarks during surgery; and postoperative applications in terms of postoperative care and rehabilitation. Additionally, AI tools in educational and training settings are presented. Orthopedic surgeons are showing a growing interest in AI, as evidenced by the applications discussed in this review, particularly those related to ACL injury. The exponential increase in studies on AI tools applicable to the management of ACL tears promises a significant future impact in its clinical application, with growing attention from orthopedic surgeons.

show abstract

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade

Ruitenbeek,

Oei,

Visser

et al. 2024

Skeletal Radiol

View full text Add to dashboard Cite

Systematic review of artificial intelligence development and evaluation for MRI diagnosis of knee ligament or meniscus tears

Cited by 4 publications

References 40 publications

A Comprehensive Evaluation of Deep Learning Models on Knee MRIs for the Diagnosis and Classification of Meniscal Tears: A Systematic Review and Meta-Analysis

A Comprehensive Evaluation of Deep Learning Models on Knee MRIs for the Diagnosis and Classification of Meniscal Tears: A Systematic Review and Meta-Analysis

The Role of Artificial Intelligence in Anterior Cruciate Ligament Injuries: Current Concepts and Future Perspectives

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade

Contact Info

Product

Resources

About