Auto-outlier Fusion Technique for Chest X-ray classification with Multi-head Attention Mechanism

TL;DR

This paper introduces an auto-outlier fusion technique to improve chest X-ray classification by addressing outliers and multi-label impacts, enhancing dataset quality for better deep learning performance.

Contribution

The study proposes a novel auto-outlier fusion method to mitigate outliers and analyze multi-label effects in chest X-ray datasets, which has not been explored before.

Findings

Improved dataset quality after outlier removal.

Enhanced performance of multi-head attention mechanisms.

Better disease classification accuracy.

Abstract

A chest X-ray is one of the most widely available radiological examinations for diagnosing and detecting various lung illnesses. The National Institutes of Health (NIH) provides an extensive database, ChestX-ray8 and ChestXray14, to help establish a deep learning community for analysing and predicting lung diseases. ChestX-ray14 consists of 112,120 frontal-view X-ray images of 30,805 distinct patients with text-mined fourteen disease image labels, where each image has multiple labels and has been utilised in numerous research in the past. To our current knowledge, no previous study has investigated outliers and multi-label impact for a single X-ray image during the preprocessing stage. The effect of outliers is mitigated in this paper by our proposed auto-outlier fusion technique. The image label is regenerated by concentrating on a particular factor in one image. The final cleaned dataset will be used to compare the mechanisms of multi-head self-attention and multi-head attention with generalised max-pooling.