MétaCan
Menu
← Back to cohort

Automated Detection of Shoulder Rotator Cuff Tendon Tears from Ultrasound Images by CNN-Autoencoder

2024· article· en· W4401748818 on OpenAlexaff
Shrimanti Ghosh, Banafshe Felfeliyan, Yuyue Zhou, Shaobo Liu, Jessica Knight, Natasha Akhlaq, Jessica Küpper, Abhilash Rakkunedeth Hareendranathan, Jacob Jaremko

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldMedicine
TopicShoulder Injury and Treatment
Canadian institutionsUniversity of Alberta
Fundersnot available
KeywordsRotator cuffAutoencoderTearsTendonUltrasoundComputer scienceMedicineArtificial intelligenceRadiologyAnatomySurgeryDeep learning

Abstract

fetched live from OpenAlex

Ultrasound can effectively diagnose rotator cuff muscle tears in the shoulder, one of the most common musculoskeletal injuries. Expertise in performing and interpreting these scans is limited, and in some jurisdictions, it involves months-long wait times. This project aims to provide the core AI process for the assessment of shoulder injuries; specifically identifying full-thickness rotator cuff tears within minutes, rather than months. We propose a two-step approach starting with segmentation of the humeral cortex and subacromial bursa followed by the classification of tears based on these regions. Automatic segmentation using ultrasound is challenging due to speckle noise, low contrast, and artifacts. The proposed segmentation method leverages a CNN-autoencoder, that predicts the boundary contour points of the humeral cortex and subacromial bursa directly from raw images. Compared to an end-to-end black box classifier, our two-stage approach is more explainable and focuses on clinically relevant landmarks. The distinctive feature of this segmentation technique is, it predicts the segmentation contour points rather than the popular pixel-wise semantic segmentation. The study was performed on the dataset acquired from 206 patients. All the methods were trained using 10,080 images and evaluated using 2520 images. Our proposed segmentation method achieved an average Dice coefficient (DC) of 94.2% and a Hausdorff Distance (HD) of 2.8 mm, outperforming the U-Net model, which yielded 90.5% for the DC and 6.8 mm for the HD. After the segmentation, a classification network, VGG-16 achieved 81.0% accuracy (sensitivity 78.5%, specificity 76.2%) in classifying rotator cuff tendons as intact or torn from US images. AI-driven ultrasound for rotator cuff tear detection enhances early, accurate diagnosis and improves patient care, and this automated tool could be used by lightly trained users at initial point-of-care facilities like family physician clinics and emergency rooms.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.010
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.012
GPT teacher head0.302
Teacher spread0.289 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations3
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicShoulder Injury and Treatment→French-language works237,207→