Weakly-Supervised Localization and Classification of Proximal Femur Fractures

In this paper, we target the problem of fracture classification from clinical X-Ray images towards an automated Computer Aided Diagnosis (CAD) system. Although primarily dealing with an image classification problem, we argue that localizing the fracture in the image is crucial to make good class predictions. Therefore, we propose and thoroughly analyze several schemes for simultaneous fracture localization and classification. We show that using an auxiliary localization task, in general, improves the classification performance. Moreover, it is possible to avoid the need for additional localization annotations thanks to recent advancements in weakly-supervised deep learning approaches. Among such approaches, we investigate and adapt Spatial Transformers (ST), Self-Transfer Learning (STL), and localization from global pooling layers. We provide a detailed quantitative and qualitative validation on a dataset of 1347 femur fractures images and report high accuracy with regard to inter-expert correlation values reported in the literature. Our investigations show that i) lesion localization improves the classification outcome, ii) weakly-supervised methods improve baseline classification without any additional cost, iii) STL guides feature activations and boost performance. We plan to make both the dataset and code available.

[1]  Hyo-Eun Kim,et al.  Self-Transfer Learning for Fully Weakly Supervised Object Localization , 2016, ArXiv.

[2]  Yu Cao,et al.  Fracture detection in x-ray images through stacked random forests feature fusion , 2015, 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).

[3]  Ismail Hmeidi,et al.  Detecting Hand Bone Fractures in X-Ray Images , 2013, J. Multim. Process. Technol..

[4]  G. Roukema,et al.  The comparison of two classifications for trochanteric femur fractures: the AO/ASIF classification and the Jensen classification. , 2010, Injury.

[5]  L. Dai,et al.  Reliability of classification systems for intertrochanteric fractures of the proximal femur in experienced orthopaedic surgeons. , 2005, Injury.

[6]  Shadi Albarqouni,et al.  Automatic Classification of Proximal Femur Fractures Based on Attention Models , 2017, MLMI@MICCAI.

[7]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[8]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[11]  Ronald M. Summers,et al.  Deep convolutional networks for automated detection of posterior-element fractures on spine CT , 2016, SPIE Medical Imaging.

[12]  W. Leow,et al.  DETECTION OF FEMUR AND RADIUS FRACTURES IN X-RAY IMAGES , 2004 .

[13]  Kayvan Najarian,et al.  Fracture Detection in Traumatic Pelvic CT Images , 2012, Int. J. Biomed. Imaging.

[14]  R. West,et al.  New classification system for long-bone fractures supplementing the AO/OTA classification. , 2012, Orthopedics.

[15]  Tim Cootes,et al.  Detection of Wrist Fractures in X-Ray Images , 2016, CLIP@MICCAI.

[16]  Murat Cakiroglu,et al.  DIFFRACT: DIaphyseal Femur FRActure Classifier SysTem , 2016 .

[17]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[18]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[19]  Lior Wolf,et al.  Compression fractures detection on CT , 2017, Medical Imaging.

[20]  Joseph E. Burns,et al.  Automated Detection, Localization, and Classification of Traumatic Vertebral Body Fractures in the Thoracic and Lumbar Spine at CT. , 2016, Radiology.

[21]  Ronald M. Summers,et al.  ChestX-ray: Hospital-Scale Chest X-ray Database and Benchmarks on Weakly Supervised Classification and Localization of Common Thorax Diseases , 2019, Deep Learning and Convolutional Neural Networks for Medical Imaging and Clinical Informatics.