Towards Automatic Lesion Classification in the Upper Aerodigestive Tract Using OCT and Deep Transfer Learning Methods
This work addresses early cancer detection for patients by proposing a non-invasive method, though it is incremental as it builds on existing OCT studies with deep learning.
The paper tackled the problem of automatic lesion classification in the upper aerodigestive tract using OCT images, addressing challenges from a small and low-quality dataset, and found that deep learning approaches could be trained for decision support.
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.