Development and Validation of a Multitask Deep Learning Model for                    Severity Grading of Hip Osteoarthritis Features on Radiographs

Schacky, Claudio E. von; Sohn, Jae Ho; Liu, Felix; Ozhinsky, Eugene; Jungmann, Pia M.; Nardo, Lorenzo; Posadzy, Magdalena; Foreman, Sarah C.; Nevitt, Michael C.; Link, Thomas M.; Pedoia, Valentina

doi:10.1148/radiol.2020190925

Cited by 66 publications

(52 citation statements)

References 17 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the images of human extremities, PXRs reveal a more complex anatomical structure and sometimes multiple injury sites. Most of the previous studies on PXRs have focused only on hip fractures [17][18][19][20] or osteoarthritis 15,25 , which emphasize only a specific region or condition in the entire image. It is not practical to create different algorithms for each kind of abnormality that appears in a single image.…”

Section: Discussionmentioning

confidence: 99%

A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs

Cheng

Wang²,

Chen

et al. 2021

Nat Commun

View full text Add to dashboard Cite

Pelvic radiograph (PXR) is essential for detecting proximal femur and pelvis injuries in trauma patients, which is also the key component for trauma survey. None of the currently available algorithms can accurately detect all kinds of trauma-related radiographic findings on PXRs. Here, we show a universal algorithm can detect most types of trauma-related radiographic findings on PXRs. We develop a multiscale deep learning algorithm called PelviXNet trained with 5204 PXRs with weakly supervised point annotation. PelviXNet yields an area under the receiver operating characteristic curve (AUROC) of 0.973 (95% CI, 0.960–0.983) and an area under the precision-recall curve (AUPRC) of 0.963 (95% CI, 0.948–0.974) in the clinical population test set of 1888 PXRs. The accuracy, sensitivity, and specificity at the cutoff value are 0.924 (95% CI, 0.912–0.936), 0.908 (95% CI, 0.885–0.908), and 0.932 (95% CI, 0.919–0.946), respectively. PelviXNet demonstrates comparable performance with radiologists and orthopedics in detecting pelvic and hip fractures.

show abstract

Section: Discussionmentioning

confidence: 99%

A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs

Cheng

Wang²,

Chen

et al. 2021

Nat Commun

View full text Add to dashboard Cite

show abstract

“…Here, with the rise of computing power, deep-learning based CAD systems gained interest recently: for automatic x-ray image classification several approaches have been published 12 – 15 , which may assist radiologists in clinical practice. U-Net like architectures were successfully employed for segmentation tasks 16 , 17 and RetinaNet based detector for object detection tasks in radiographs 18 – 21 . While U-Net based implementations yield a segmentation as output, RetinaNet detectors output bounding boxes which most likely contain the object of interest (in our case a nodule).…”

Section: Introductionmentioning

confidence: 99%

Lung nodule detection in chest X-rays using synthetic ground-truth data comparing CNN-based diagnosis to human performance

Schultheiß

Schmette

Bodden

et al. 2021

Sci Rep

Self Cite

View full text Add to dashboard Cite

We present a method to generate synthetic thorax radiographs with realistic nodules from CT scans, and a perfect ground truth knowledge. We evaluated the detection performance of nine radiologists and two convolutional neural networks in a reader study. Nodules were artificially inserted into the lung of a CT volume and synthetic radiographs were obtained by forward-projecting the volume. Hence, our framework allowed for a detailed evaluation of CAD systems’ and radiologists’ performance due to the availability of accurate ground-truth labels for nodules from synthetic data. Radiographs for network training (U-Net and RetinaNet) were generated from 855 CT scans of a public dataset. For the reader study, 201 radiographs were generated from 21 nodule-free CT scans with altering nodule positions, sizes and nodule counts of inserted nodules. Average true positive detections by nine radiologists were 248.8 nodules, 51.7 false positive predicted nodules and 121.2 false negative predicted nodules. The best performing CAD system achieved 268 true positives, 66 false positives and 102 false negatives. Corresponding weighted alternative free response operating characteristic figure-of-merits (wAFROC FOM) for the radiologists range from 0.54 to 0.87 compared to a value of 0.81 (CI 0.75–0.87) for the best performing CNN. The CNN did not perform significantly better against the combined average of the 9 readers (p = 0.49). Paramediastinal nodules accounted for most false positive and false negative detections by readers, which can be explained by the presence of more tissue in this area.

show abstract

“…We used a multiclass classification model that could predict all classes for each image instead of using multiple binary classifiers. This is similar to the approach used by von Schacky et al [27], who developed a multiclass classification model for osteoarthritis detection. Other studies used network architectures originally developed for object detection.…”

Section: Discussionmentioning

confidence: 83%

Deep learning for accurately recognizing common causes of shoulder pain on radiographs

et al. 2021

View full text Add to dashboard Cite

Objective Training a convolutional neural network (CNN) to detect the most common causes of shoulder pain on plain radiographs and to assess its potential value in serving as an assistive device to physicians. Materials and methods We used a CNN of the ResNet-50 architecture which was trained on 2700 shoulder radiographs from clinical practice of multiple institutions. All radiographs were reviewed and labeled for six findings: proximal humeral fractures, joint dislocation, periarticular calcification, osteoarthritis, osteosynthesis, and joint endoprosthesis. The trained model was then evaluated on a separate test dataset, which was previously annotated by three independent expert radiologists. Both the training and the test datasets included radiographs of highly variable image quality to reflect the clinical situation and to foster robustness of the CNN. Performance of the model was evaluated using receiver operating characteristic (ROC) curves, the thereof derived AUC as well as sensitivity and specificity. Results The developed CNN demonstrated a high accuracy with an area under the curve (AUC) of 0.871 for detecting fractures, 0.896 for joint dislocation, 0.945 for osteoarthritis, and 0.800 for periarticular calcifications. It also detected osteosynthesis and endoprosthesis with near perfect accuracy (AUC 0.998 and 1.0, respectively). Sensitivity and specificity were 0.75 and 0.86 for fractures, 0.95 and 0.65 for joint dislocation, 0.90 and 0.86 for osteoarthrosis, and 0.60 and 0.89 for calcification. Conclusion CNNs have the potential to serve as an assistive device by providing clinicians a means to prioritize worklists or providing additional safety in situations of increased workload.

show abstract

Development and Validation of a Multitask Deep Learning Model for Severity Grading of Hip Osteoarthritis Features on Radiographs

Cited by 66 publications

References 17 publications

A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs

A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs

Lung nodule detection in chest X-rays using synthetic ground-truth data comparing CNN-based diagnosis to human performance

Deep learning for accurately recognizing common causes of shoulder pain on radiographs

Contact Info

Product

Resources

About