A Two-Stage Multiple Instance Learning Framework for the Detection of Breast Cancer in Mammograms
This work addresses the problem of improving breast cancer screening accuracy for medical practitioners, but it is incremental as it builds on existing multiple instance learning methods with a specific two-stage approach.
The paper tackled automated detection of breast cancer in mammograms by proposing a two-stage multiple instance learning framework, achieving an average AUC of 0.91 for image-level classification and 0.76/0.80 precision/recall for mass localization on the INbreast dataset.
Mammograms are commonly employed in the large scale screening of breast cancer which is primarily characterized by the presence of malignant masses. However, automated image-level detection of malignancy is a challenging task given the small size of the mass regions and difficulty in discriminating between malignant, benign mass and healthy dense fibro-glandular tissue. To address these issues, we explore a two-stage Multiple Instance Learning (MIL) framework. A Convolutional Neural Network (CNN) is trained in the first stage to extract local candidate patches in the mammograms that may contain either a benign or malignant mass. The second stage employs a MIL strategy for an image level benign vs. malignant classification. A global image-level feature is computed as a weighted average of patch-level features learned using a CNN. Our method performed well on the task of localization of masses with an average Precision/Recall of 0.76/0.80 and acheived an average AUC of 0.91 on the imagelevel classification task using a five-fold cross-validation on the INbreast dataset. Restricting the MIL only to the candidate patches extracted in Stage 1 led to a significant improvement in classification performance in comparison to a dense extraction of patches from the entire mammogram.