Curriculum learning for improved femur fracture classification: scheduling data with prior knowledge and uncertainty

Abstract

An adequate classification of proximal femur fractures from X-ray images is crucial for the treatment choice and the patients' clinical outcome. We rely on the commonly used AO system, which describes a hierarchical knowledge tree classifying the images into types and subtypes according to the fracture's location and complexity. In this paper, we propose a method for the automatic classification of proximal femur fractures into 3 and 7 AO classes based on a Convolutional Neural Network (CNN). As it is known, CNNs need large and representative datasets with reliable labels, which are hard to collect for the application at hand. In this paper, we design a curriculum learning (CL) approach that improves over the basic CNNs performance under such conditions. Our novel formulation reunites three curriculum strategies: individually weighting training samples, reordering the training set, and sampling subsets of data. The core of these strategies is a scoring function ranking the training samples. We define two novel scoring functions: one from domain-specific prior knowledge and an original self-paced uncertainty score. We perform experiments on a clinical dataset of proximal femur radiographs. The curriculum improves proximal femur fracture classification up to the performance of experienced trauma surgeons. The best curriculum method reorders the training set based on prior knowledge resulting into a classification improvement of 15%. Using the publicly available MNIST dataset, we further discuss and demonstrate the benefits of our unified CL formulation for three controlled and challenging digit recognition scenarios: with limited amounts of data, under class-imbalance, and in the presence of label noise. The code of our work is available at: https://github.com/ameliajimenez/curriculum-learning-prior-uncertainty.

arXiv commentMedical Image Analysis

References in corpus (10)

• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• NiftyNet: a deep-learning platform for medical imaging
• Evidential Deep Learning to Quantify Classification Uncertainty
• Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks
• Automatic CAD-RADS Scoring Using Deep Learning
• On The Power of Curriculum Learning in Training Deep Networks
• Integration of Convolutional Neural Networks for Pulmonary Nodule Malignancy Assessment in a Lung Cancer Classification Pipeline
• Curriculum semi-supervised segmentation
• Precise Proximal Femur Fracture Classification for Interactive Training and Surgical Planning
• Medical-based Deep Curriculum Learning for Improved Fracture Classification

Cited by in corpus (3)

• Memory-aware curriculum federated learning for breast cancer classification
• CLOG-CD: Curriculum Learning based on Oscillating Granularity of Class Decomposed Medical Image Classification
• GIT-CXR: End-to-End Transformer for Chest X-Ray Report Generation