Towards Automatic Lesion Classification in the Upper Aerodigestive Tract Using OCT and Deep Transfer Learning Methods

TL;DR

This paper explores the feasibility of using deep transfer learning on OCT images for automatic lesion classification in the upper aerodigestive tract, aiming to assist clinicians despite limited data quality and size.

Contribution

It demonstrates the potential of deep transfer learning methods to classify lesions in OCT images with small datasets, advancing non-invasive cancer detection techniques.

Findings

Deep learning can be effective even with small, limited-quality datasets.

Transfer learning improves classification accuracy in OCT-based lesion detection.

The approach supports non-invasive, early cancer diagnosis in clinical settings.

Abstract

Early detection of cancer is crucial for treatment and overall patient survival. In the upper aerodigestive tract (UADT) the gold standard for identification of malignant tissue is an invasive biopsy. Recently, non-invasive imaging techniques such as confocal laser microscopy and optical coherence tomography (OCT) have been used for tissue assessment. In particular, in a recent study experts classified lesions in the UADT with respect to their invasiveness using OCT images only. As the results were promising, automatic classification of lesions might be feasible which could assist experts in their decision making. Therefore, we address the problem of automatic lesion classification from OCT images. This task is very challenging as the available dataset is extremely small and the data quality is limited. However, as similar issues are typical in many clinical scenarios we study to what extent deep learning approaches can still be trained and used for decision support.