Deep Hiearchical Multi-Label Classification Applied to Chest X-Ray Abnormality Taxonomies

09/11/2020
by   Haomin Chen, et al.
0

CXRs are a crucial and extraordinarily common diagnostic tool, leading to heavy research for CAD solutions. However, both high classification accuracy and meaningful model predictions that respect and incorporate clinical taxonomies are crucial for CAD usability. To this end, we present a deep HMLC approach for CXR CAD. Different than other hierarchical systems, we show that first training the network to model conditional probability directly and then refining it with unconditional probabilities is key in boosting performance. In addition, we also formulate a numerically stable cross-entropy loss function for unconditional probabilities that provides concrete performance improvements. Finally, we demonstrate that HMLC can be an effective means to manage missing or incomplete labels. To the best of our knowledge, we are the first to apply HMLC to medical imaging CAD. We extensively evaluate our approach on detecting abnormality labels from the CXR arm of the PLCO dataset, which comprises over 198,000 manually annotated CXRs. When using complete labels, we report a mean AUC of 0.887, the highest yet reported for this dataset. These results are supported by ancillary experiments on the PadChest dataset, where we also report significant improvements, 1.2 and AP, respectively over strong "flat" classifiers. Finally, we demonstrate that our HMLC approach can much better handle incompletely labelled data. These performance improvements, combined with the inherent usefulness of taxonomic predictions, indicate that our approach represents a useful step forward for CXR CAD.

READ FULL TEXT
research
12/23/2020

Diabetic Retinopathy Grading System Based on Transfer Learning

Much effort is being made by the researchers in order to detect and diag...
research
09/30/2022

Did You Get What You Paid For? Rethinking Annotation Cost of Deep Learning Based Computer Aided Detection in Chest Radiographs

As deep networks require large amounts of accurately labeled training da...
research
05/15/2019

Multi-task Learning for Chest X-ray Abnormality Classification on Noisy Labels

Chest X-ray (CXR) is the most common X-ray examination performed in dail...
research
04/07/2021

Soft-Label Anonymous Gastric X-ray Image Distillation

This paper presents a soft-label anonymous gastric X-ray image distillat...
research
09/14/2021

How Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?

As NLP models are increasingly deployed in socially situated settings su...
research
06/22/2021

Gradient-based Label Binning in Multi-label Classification

In multi-label classification, where a single example may be associated ...

Please sign up or login with your details

Forgot password? Click here to reset