Few Shot Learning for the Classification of Confocal Laser Endomicroscopy Images of Head and Neck Tumors
This work addresses the challenge of automated analysis for surgeons in interpreting difficult CLE images, but it is incremental as it evaluates existing few-shot learning methods on new data.
The study tackled the problem of classifying confocal laser endomicroscopy images of head and neck tumors using few-shot learning to generalize across unseen anatomical domains, achieving median accuracies of 79.6% on vocal folds and 61.6% on sinunasal tumors.
The surgical removal of head and neck tumors requires safe margins, which are usually confirmed intraoperatively by means of frozen sections. This method is, in itself, an oversampling procedure, which has a relatively low sensitivity compared to the definitive tissue analysis on paraffin-embedded sections. Confocal laser endomicroscopy (CLE) is an in-vivo imaging technique that has shown its potential in the live optical biopsy of tissue. An automated analysis of this notoriously difficult to interpret modality would help surgeons. However, the images of CLE show a wide variability of patterns, caused both by individual factors but also, and most strongly, by the anatomical structures of the imaged tissue, making it a challenging pattern recognition task. In this work, we evaluate four popular few shot learning (FSL) methods towards their capability of generalizing to unseen anatomical domains in CLE images. We evaluate this on images of sinunasal tumors (SNT) from five patients and on images of the vocal folds (VF) from 11 patients using a cross-validation scheme. The best respective approach reached a median accuracy of 79.6% on the rather homogeneous VF dataset, but only of 61.6% for the highly diverse SNT dataset. Our results indicate that FSL on CLE images is viable, but strongly affected by the number of patients, as well as the diversity of anatomical patterns.