A Comparative Study of Existing and New Deep Learning Methods for Detecting Knee Injuries using the MRNet Dataset

Azcona, David; McGuinness, Kevin; Smeaton, Alan F.

doi:10.1109/idsta50958.2020.9264030

Cited by 17 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy achieved by the radiologists (92%) was higher than the one achieved by the AI model (86.7%). Azcona et al [ 52 ] proposed and evaluated the performance of four architectures: (i) deep residual network with transfer learning; (ii) custom deep residual network using a fixed number of slices; (iii) multi-plane deep residual network; and (iv) multi-plane multi-objective deep residual network. They found that transfer learning combined with a carefully tuned data augmentation strategy were the crucial factors in achieving best performance.…”

Section: Resultsmentioning

confidence: 99%

Knee Injury Detection Using Deep Learning on MRI Studies: A Systematic Review

Siouras

Moustakidis²,

Giannakidis

et al. 2022

Diagnostics

View full text Add to dashboard Cite

The improved treatment of knee injuries critically relies on having an accurate and cost-effective detection. In recent years, deep-learning-based approaches have monopolized knee injury detection in MRI studies. The aim of this paper is to present the findings of a systematic literature review of knee (anterior cruciate ligament, meniscus, and cartilage) injury detection papers using deep learning. The systematic review was carried out following the PRISMA guidelines on several databases, including PubMed, Cochrane Library, EMBASE, and Google Scholar. Appropriate metrics were chosen to interpret the results. The prediction accuracy of the deep-learning models for the identification of knee injuries ranged from 72.5–100%. Deep learning has the potential to act at par with human-level performance in decision-making tasks related to the MRI-based diagnosis of knee injuries. The limitations of the present deep-learning approaches include data imbalance, model generalizability across different centers, verification bias, lack of related classification studies with more than two classes, and ground-truth subjectivity. There are several possible avenues of further exploration of deep learning for improving MRI-based knee injury diagnosis. Explainability and lightweightness of the deployed deep-learning systems are expected to become crucial enablers for their widespread use in clinical practice.

show abstract

Section: Resultsmentioning

confidence: 99%

Knee Injury Detection Using Deep Learning on MRI Studies: A Systematic Review

Siouras

Moustakidis²,

Giannakidis

et al. 2022

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Our study, by employing the efficiently-layered network (ELNet) rather than the ResNet50 model in the Model 3 section, can be re-evaluated. The study by Azcona et al [18] employed a logistic regression-based ensemble learning approach. The ROC-AUC values acquired from the study were 0.9557 for ACL, 0.9081 for meniscus, and 0.9381 for abnormality diagnosis.…”

Section: Discussionmentioning

confidence: 99%

“…Each image is 256 × 256, and the number of slices ranges from 17 to 61. There are 1104 abnormal, 319 ACLs, and 508 menisci in the dataset [18]. The dataset contains 1130 trains, 120 valid, and 120 test datasets.…”

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

Detection and Classification of Knee Injuries from MR Images Using the MRNet Dataset with Progressively Operating Deep Learning Methods

Kara

Hardalaç

2021

MAKE

View full text Add to dashboard Cite

This study aimed to build progressively operating deep learning models that could detect meniscus injuries, anterior cruciate ligament (ACL) tears and knee abnormalities in magnetic resonance imaging (MRI). The Stanford Machine Learning Group MRNet dataset was employed in the study, which included MRI image indexes in the coronal, sagittal, and axial axes, each having 1130 trains and 120 validation items. The study is divided into three sections. In the first section, suitable images are selected to determine the disease in the image index based on the disturbance under examination. It is also used to identify images that have been misclassified or are noisy and/or damaged to the degree that they cannot be utilised for diagnosis in the first section. The study employed the 50-layer residual networks (ResNet50) model in this section. The second part of the study involves locating the region to be focused on based on the disturbance that is targeted to be diagnosed in the image under examination. A novel model was built by integrating the convolutional neural networks (CNN) and the denoising autoencoder models in the second section. The third section is dedicated to making a diagnosis of the disease. In this section, a novel ResNet50 model is trained to identify disease diagnoses or abnormalities, independent of the ResNet50 model used in the first section. The images that each model selects as output after training are referred to as progressively operating deep learning methods since they are supplied as an input to the following model.

show abstract

“…Tsai et al (2020) proposed a so-called “Efficiently-Layered Network” for detection of meniscal tears, reaching an AUC of 0.904 and 0.913 for two different datasets. Azcona et al (2020) demonstrated the use of a 2D CNN as a pseudo-3D variant for detection of torn menisci. Their method relies on transfer learning while using data augmentation and reaches an AUC of 0.934.…”

Section: Introductionmentioning

confidence: 99%

A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database

Tack

Shestakov

Lüdke

et al. 2021

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

We present a novel and computationally efficient method for the detection of meniscal tears in Magnetic Resonance Imaging (MRI) data. Our method is based on a Convolutional Neural Network (CNN) that operates on complete 3D MRI scans. Our approach detects the presence of meniscal tears in three anatomical sub-regions (anterior horn, body, posterior horn) for both the Medial Meniscus (MM) and the Lateral Meniscus (LM) individually. For optimal performance of our method, we investigate how to preprocess the MRI data and how to train the CNN such that only relevant information within a Region of Interest (RoI) of the data volume is taken into account for meniscal tear detection. We propose meniscal tear detection combined with a bounding box regressor in a multi-task deep learning framework to let the CNN implicitly consider the corresponding RoIs of the menisci. We evaluate the accuracy of our CNN-based meniscal tear detection approach on 2,399 Double Echo Steady-State (DESS) MRI scans from the Osteoarthritis Initiative database. In addition, to show that our method is capable of generalizing to other MRI sequences, we also adapt our model to Intermediate-Weighted Turbo Spin-Echo (IW TSE) MRI scans. To judge the quality of our approaches, Receiver Operating Characteristic (ROC) curves and Area Under the Curve (AUC) values are evaluated for both MRI sequences. For the detection of tears in DESS MRI, our method reaches AUC values of 0.94, 0.93, 0.93 (anterior horn, body, posterior horn) in MM and 0.96, 0.94, 0.91 in LM. For the detection of tears in IW TSE MRI data, our method yields AUC values of 0.84, 0.88, 0.86 in MM and 0.95, 0.91, 0.90 in LM. In conclusion, the presented method achieves high accuracy for detecting meniscal tears in both DESS and IW TSE MRI data. Furthermore, our method can be easily trained and applied to other MRI sequences.

show abstract

A Comparative Study of Existing and New Deep Learning Methods for Detecting Knee Injuries using the MRNet Dataset

Cited by 17 publications

References 10 publications

Knee Injury Detection Using Deep Learning on MRI Studies: A Systematic Review

Knee Injury Detection Using Deep Learning on MRI Studies: A Systematic Review

Detection and Classification of Knee Injuries from MR Images Using the MRNet Dataset with Progressively Operating Deep Learning Methods

A Multi-Task Deep Learning Method for Detection of Meniscal Tears in MRI Data from the Osteoarthritis Initiative Database

Contact Info

Product

Resources

About