Structure Regularized Attentive Network for Automatic Femoral Head Necrosis Diagnosis and Localization

TL;DR

This paper introduces SRANet, a novel neural network that improves AVNFH diagnosis from CT scans by highlighting necrotic regions and providing detailed localization to aid medical diagnosis.

Contribution

The paper presents a new structure regularized attentive network (SRANet) that enhances AVNFH classification and lesion localization from CT images, incorporating prior knowledge for better generalization.

Findings

SRANet outperforms traditional CNNs in AVNFH classification.

SRANet can accurately localize necrotic regions in CT images.

The method provides additional diagnostic information to doctors.

Abstract

In recent years, several works have adopted the convolutional neural network (CNN) to diagnose the avascular necrosis of the femoral head (AVNFH) based on X-ray images or magnetic resonance imaging (MRI). However, due to the tissue overlap, X-ray images are difficult to provide fine-grained features for early diagnosis. MRI, on the other hand, has a long imaging time, is more expensive, making it impractical in mass screening. Computed tomography (CT) shows layer-wise tissues, is faster to image, and is less costly than MRI. However, to our knowledge, there is no work on CT-based automated diagnosis of AVNFH. In this work, we collected and labeled a large-scale dataset for AVNFH ranking. In addition, existing end-to-end CNNs only yields the classification result and are difficult to provide more information for doctors in diagnosis. To address this issue, we propose the structure regularized attentive network (SRANet), which is able to highlight the necrotic regions during classification based on patch attention. SRANet extracts features in chunks of images, obtains weight via the attention mechanism to aggregate the features, and constrains them by a structural regularizer with prior knowledge to improve the generalization. SRANet was evaluated on our AVNFH-CT dataset. Experimental results show that SRANet is superior to CNNs for AVNFH classification, moreover, it can localize lesions and provide more information to assist doctors in diagnosis. Our codes are made public at https://github.com/tomas-lilingfeng/SRANet.