Abnormality Detection in Musculoskeletal Radiographs by DenseNet and Inception-v3

authors:

avatar Zahra Rezaei 1 , * , avatar Behnaz Eslami 2 , avatar Hossein Ebrahimpour-Komleh 1 , avatar Kaveh Daneshmand Jahromi 3

Department of Computer and Electrical Engineering, University of Kashan, Kashan, Iran
Department of Computer Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
Industrial Management Institute (IMI), Tehran, Iran

how to cite: Rezaei Z, Eslami B, Ebrahimpour-Komleh H , Daneshmand Jahromi K. Abnormality Detection in Musculoskeletal Radiographs by DenseNet and Inception-v3. I J Radiol. 2019;16(Special Issue):e99144. https://doi.org/10.5812/iranjradiol.99144.

Abstract

Background:

One of the most remarkable applications of deep learning emerges in medical diagnosis. New improvements in this field have shown that with large enough datasets and the right methods, one can achieve results as reliable as diagnoses made by experienced doctors. One of such developments is MURA, which is a dataset of musculoskeletal radiographs consisting of 14863 studies from 12173 patients, resulting in 40561 multi-view radiograph images. Each one of these studies concerns one of the seven standard upper extremity radiographic study types, namely finger, forearm, elbow, hand, shoulder, homeruns, and wrist. Each study was categorized as normal or abnormal by board-certified radiologists in the diagnostic radiology environment between 2001 and 2012. Abnormality detection in muscular radiography is of great clinical application. This gains more importance in cases in which abnormality detection is difficult for physicians. If the proposed model can help us in detection, the process of treatment will precipitate. This model is termed Inception-v3.

Methods:

In this study, we evaluated the MURA dataset through Dense NET and inception-v3 methods.

Results:

The results indicated that the former had better performance and we added a pre-processing module to it to improve the accuracy of the DenseNet method in detecting the abnormality. In this context, we trained the machine to be sensitive to the presence of external objects to be distinguished from actual abnormality such as bone fraction. We achieved this condition by many various radiographs as machine inputs. By this strategy, both techniques (DenseNet and Inception-v3) showed improvements in accuracy. Thus, we sub-grouped abnormality into with or without the presence of external objects.

Conclusion:

Although the average opinion of radiologists still shows better results, in images with delicate fracture detection, such as finger fracture, the proposed model worked more accurately, and it could be a decision support assistant for physicians in the final detection of fracture. The precision of the proposed model will enhance if the image is separated from normal images using Platinum, a new class is made, and pre-processing is done. Therefore, the model can automatically detect abnormality by identifying that part of the image that is detected to be abnormal. An efficient model can interpret images more efficiently, can reduce errors, and can enhance quality. More studies are needed to evaluate the integration of this model with other models of deep learning in clinical settings.