IVCVMar 19, 2020

End-to-End Deep Diagnosis of X-ray Images

arXiv:2003.08605v116 citations
Originality Incremental advance
AI Analysis

This work addresses the need for efficient and accurate medical image analysis for healthcare professionals, though it is incremental as it builds on existing architectures like DenseNet-121.

The paper tackles the problem of automated diagnosis from X-ray images by developing an end-to-end deep learning framework that sequentially identifies X-rays, classifies their type, and detects abnormalities, achieving an end-to-end accuracy of 0.91 with task-specific accuracies up to 0.987.

In this work, we present an end-to-end deep learning framework for X-ray image diagnosis. As the first step, our system determines whether a submitted image is an X-ray or not. After it classifies the type of the X-ray, it runs the dedicated abnormality classification network. In this work, we only focus on the chest X-rays for abnormality classification. However, the system can be extended to other X-ray types easily. Our deep learning classifiers are based on DenseNet-121 architecture. The test set accuracy obtained for 'X-ray or Not', 'X-ray Type Classification', and 'Chest Abnormality Classification' tasks are 0.987, 0.976, and 0.947, respectively, resulting into an end-to-end accuracy of 0.91. For achieving better results than the state-of-the-art in the 'Chest Abnormality Classification', we utilize the new RAdam optimizer. We also use Gradient-weighted Class Activation Mapping for visual explanation of the results. Our results show the feasibility of a generalized online projectional radiography diagnosis system.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes