Learning to diagnose from scratch by exploiting dependencies among labels

Abstract

The field of medical diagnostics contains a wealth of challenges which closely resemble classical machine learning problems; practical constraints, however, complicate the translation of these endpoints naively into classical architectures. Many tasks in radiology, for example, are largely problems of multi-label classification wherein medical images are interpreted to indicate multiple present or suspected pathologies. Clinical settings drive the necessity for high accuracy simultaneously across a multitude of pathological outcomes and greatly limit the utility of tools which consider only a subset. This issue is exacerbated by a general scarcity of training data and maximizes the need to extract clinically relevant features from available samples -- ideally without the use of pre-trained models which may carry forward undesirable biases from tangentially related tasks. We present and evaluate a partial solution to these constraints in using LSTMs to leverage interdependencies among target labels in predicting 14 pathologic patterns from chest x-rays and establish state of the art results on the largest publicly available chest x-ray dataset from the NIH without pre-training. Furthermore, we propose and discuss alternative evaluation metrics and their relevance in clinical practice.

include the link for the dataset split

References in corpus (1)

• A Survey on Deep Learning in Medical Image Analysis

Cited by in corpus (46)

• CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning
• Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification
• CovidAID: COVID-19 Detection Using Chest X-Ray
• Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays
• Augmenting the Pathology Lab: An Intelligent Whole Slide Image Classification System for the Real World
• Machine-Learning-Based Multiple Abnormality Prediction with Large-Scale Chest Computed Tomography Volumes
• ChestNet: A Deep Neural Network for Classification of Thoracic Diseases on Chest Radiography
• Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions
• Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans
• Large Scale Automated Reading of Frontal and Lateral Chest X-Rays using Dual Convolutional Neural Networks
• Towards Evaluating the Robustness of Deep Diagnostic Models by Adversarial Attack
• Early Diagnosis of Pneumonia with Deep Learning
• Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks
• Chest X-rays Classification: A Multi-Label and Fine-Grained Problem
• A Weakly Supervised Adaptive DenseNet for Classifying Thoracic Diseases and Identifying Abnormalities
• Multi-task Learning for Chest X-ray Abnormality Classification on Noisy Labels
• Deep learning classification of chest x-ray images
• Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification
• DeepRadiologyNet: Radiologist Level Pathology Detection in CT Head Images
• Automated diagnosis of pneumothorax using an ensemble of convolutional neural networks with multi-sized chest radiography images
• Using Radiomics as Prior Knowledge for Thorax Disease Classification and Localization in Chest X-rays
• Automatic Diagnosis of Pneumothorax from Chest Radiographs: A Systematic Literature Review
• Quantifying the Value of Lateral Views in Deep Learning for Chest X-rays
• Towards Radiologist-Level Accurate Deep Learning System for Pulmonary Screening
• Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs
• Deep Mining External Imperfect Data for Chest X-ray Disease Screening
• Deep Learning for Automated Classification of Tuberculosis-Related Chest X-Ray: Dataset Specificity Limits Diagnostic Performance Generalizability
• Bias Field Poses a Threat to DNN-based X-Ray Recognition
• MUXConv: Information Multiplexing in Convolutional Neural Networks
• Vulnerability Analysis of Chest X-Ray Image Classification Against Adversarial Attacks
• Dynamic Routing on Deep Neural Network for Thoracic Disease Classification and Sensitive Area Localization
• Deformable Gabor Feature Networks for Biomedical Image Classification
• Automated Radiological Report Generation For Chest X-Rays With Weakly-Supervised End-to-End Deep Learning
• Learning Image Labels On-the-fly for Training Robust Classification Models
• Extracting and Leveraging Nodule Features with Lung Inpainting for Local Feature Augmentation
• Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
• Weighing Features of Lung and Heart Regions for Thoracic Disease Classification
• Dynamic Graph Correlation Learning for Disease Diagnosis with Incomplete Labels
• Learning to estimate label uncertainty for automatic radiology report parsing
• Multi-label Thoracic Disease Image Classification with Cross-Attention Networks
• SCALP -- Supervised Contrastive Learning for Cardiopulmonary Disease Classification and Localization in Chest X-rays using Patient Metadata
• Deep Generative Classifiers for Thoracic Disease Diagnosis with Chest X-ray Images
• Deep Hiearchical Multi-Label Classification Applied to Chest X-Ray Abnormality Taxonomies
• Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs
• Interpretation of smartphone-captured radiographs utilizing a deep learning-based approach
• A Computer Vision Approach to Combat Lyme Disease