Chest X-rays Classification: A Multi-Label and Fine-Grained Problem

Abstract

The widely used ChestX-ray14 dataset addresses an important medical image classification problem and has the following caveats: 1) many lung pathologies are visually similar, 2) a variant of diseases including lung cancer, tuberculosis, and pneumonia are present in a single scan, i.e. multiple labels and 3) The incidence of healthy images is much larger than diseased samples, creating imbalanced data. These properties are common in medical domain. Existing literature uses stateof- the-art DensetNet/Resnet models being transfer learned where output neurons of the networks are trained for individual diseases to cater for multiple diseases labels in each image. However, most of them don't consider relationship between multiple classes. In this work we have proposed a novel error function, Multi-label Softmax Loss (MSML), to specifically address the properties of multiple labels and imbalanced data. Moreover, we have designed deep network architecture based on fine-grained classification concept that incorporates MSML. We have evaluated our proposed method on various network backbones and showed consistent performance improvements of AUC-ROC scores on the ChestX-ray14 dataset. The proposed error function provides a new method to gain improved performance across wider medical datasets.

References in corpus (5)

• Adam: A Method for Stochastic Optimization
• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Learning to diagnose from scratch by exploiting dependencies among labels
• Learning to Read Chest X-Rays: Recurrent Neural Cascade Model for Automated Image Annotation
• Improved Bilinear Pooling with CNNs

Cited by in corpus (13)

• Query2Label: A Simple Transformer Way to Multi-Label Classification
• Multi-Label Image Recognition with Graph Convolutional Networks
• GM-MLIC: Graph Matching based Multi-Label Image Classification
• Multi-Label Image Classification with Contrastive Learning
• Pathological Retinal Region Segmentation From OCT Images Using Geometric Relation Based Augmentation
• Registration of Histopathogy Images Using Structural Information From Fine Grained Feature Maps
• Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition
• Generative Adversarial Networks And Domain Adaptation For Training Data Independent Image Registration
• Instance-Aware Graph Convolutional Network for Multi-Label Classification
• CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysis
• Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learning
• Classification of COVID-19 from CXR Images in a 15-class Scenario: an Attempt to Avoid Bias in the System
• Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentation