Evaluation of Multi-Scale Multiple Instance Learning to Improve Thyroid Cancer Classification
This work addresses the need for more efficient and objective thyroid cancer diagnosis, but it is incremental as it builds on existing patch-based methods with limited gains.
The authors tackled the problem of automatic thyroid cancer classification from whole slide images by extending a patch-based multiple instance learning method to incorporate multi-scale patch resolutions. They found that only one of three multi-scale combination approaches improved classification performance, while the others decreased scores.
Thyroid cancer is currently the fifth most common malignancy diagnosed in women. Since differentiation of cancer sub-types is important for treatment and current, manual methods are time consuming and subjective, automatic computer-aided differentiation of cancer types is crucial. Manual differentiation of thyroid cancer is based on tissue sections, analysed by pathologists using histological features. Due to the enormous size of gigapixel whole slide images, holistic classification using deep learning methods is not feasible. Patch based multiple instance learning approaches, combined with aggregations such as bag-of-words, is a common approach. This work's contribution is to extend a patch based state-of-the-art method by generating and combining feature vectors of three different patch resolutions and analysing three distinct ways of combining them. The results showed improvements in one of the three multi-scale approaches, while the others led to decreased scores. This provides motivation for analysis and discussion of the individual approaches.