Patch-based Carcinoma Detection on Confocal Laser Endomicroscopy Images -- A Cross-Site Robustness Assessment

TL;DR

This study evaluates a deep learning algorithm trained on oral carcinoma images for its ability to generalize to other head and neck carcinoma sites using confocal laser endomicroscopy, demonstrating promising cross-site robustness.

Contribution

First to assess the generalization of a deep learning-based carcinoma detection algorithm across different head and neck locations using CLE images.

Findings

Achieved 89.45% accuracy and 0.955 AUC on vocal cords data with oral cavity trained model.

Concatenating datasets improved accuracy to 90.81% and AUC to 0.970.

Demonstrated potential for examiner-independent, cross-site carcinoma detection in head and neck using deep learning.

Abstract

Deep learning technologies such as convolutional neural networks (CNN) provide powerful methods for image recognition and have recently been employed in the field of automated carcinoma detection in confocal laser endomicroscopy (CLE) images. CLE is a (sub-)surface microscopic imaging technique that reaches magnifications of up to 1000x and is thus suitable for in vivo structural tissue analysis. In this work, we aim to evaluate the prospects of a priorly developed deep learning-based algorithm targeted at the identification of oral squamous cell carcinoma with regard to its generalization to further anatomic locations of squamous cell carcinomas in the area of head and neck. We applied the algorithm on images acquired from the vocal fold area of five patients with histologically verified squamous cell carcinoma and presumably healthy control images of the clinically normal contra-lateral vocal cord. We find that the network trained on the oral cavity data reaches an accuracy of 89.45% and an area-under-the-curve (AUC) value of 0.955, when applied on the vocal cords data. Compared to the state of the art, we achieve very similar results, yet with an algorithm that was trained on a completely disjunct data set. Concatenating both data sets yielded further improvements in cross-validation with an accuracy of 90.81% and AUC of 0.970. In this study, for the first time to our knowledge, a deep learning mechanism for the identification of oral carcinomas using CLE Images could be applied to other disciplines in the area of head and neck. This study shows the prospect of the algorithmic approach to generalize well on other malignant entities of the head and neck, regardless of the anatomical location and furthermore in an examiner-independent manner.