A Real Use Case of Semi-Supervised Learning for Mammogram Classification in a Local Clinic of Costa Rica

TL;DR

This study demonstrates that semi-supervised deep learning, specifically MixMatch, combined with fine-tuning, improves mammogram classification accuracy in a real-world Costa Rican clinic with limited labeled data, addressing dataset mismatch and imbalance issues.

Contribution

The paper introduces a semi-supervised learning approach using MixMatch for mammogram classification on a new Costa Rican dataset, highlighting its effectiveness in scarce and imbalanced data scenarios.

Findings

Semi-supervised learning improves classification accuracy with limited labels.

Fine-tuning enhances model performance on the target dataset.

The approach is effective despite dataset distribution differences.

Abstract

The implementation of deep learning based computer aided diagnosis systems for the classification of mammogram images can help in improving the accuracy, reliability, and cost of diagnosing patients. However, training a deep learning model requires a considerable amount of labeled images, which can be expensive to obtain as time and effort from clinical practitioners is required. A number of publicly available datasets have been built with data from different hospitals and clinics. However, using models trained on these datasets for later work on images sampled from a different hospital or clinic might result in lower performance. This is due to the distribution mismatch of the datasets, which include different patient populations and image acquisition protocols. The scarcity of labeled data can also bring a challenge towards the application of transfer learning with models trained using these source datasets. In this work, a real world scenario is evaluated where a novel target dataset sampled from a private Costa Rican clinic is used, with few labels and heavily imbalanced data. The use of two popular and publicly available datasets (INbreast and CBIS-DDSM) as source data, to train and test the models on the novel target dataset, is evaluated. The use of the semi-supervised deep learning approach known as MixMatch, to leverage the usage of unlabeled data from the target dataset, is proposed and evaluated. In the tests, the performance of models is extensively measured, using different metrics to assess the performance of a classifier under heavy data imbalance conditions. It is shown that the use of semi-supervised deep learning combined with fine-tuning can provide a meaningful advantage when using scarce labeled observations. We make available the novel dataset for the benefit of the community.