Pitfalls with Anomaly Detection for Breast Cancer Risk Prediction

Breast cancer has the highest prevalence in the world, and thus, most countries have screening programs which aim to detect the cancer onset early. In these screening programs, negative studies dominate the dataset. Unsupervised anomaly detection promises to take advantage of the negative studies by using it to detect abnormalities as cancer or signs of cancer onset. In this study, we evaluate an anomaly detection method for cancer prediction (1-year ahead) on a MRI dataset of a high risk cohort with BRCA1 and BRCA2 gene mutations. As the approach fails to predict cancer risk on the dataset, we investigate the intrinsic behavior of the method. Our analysis reveals, that the reconstruction based method might only detect high intensity anomalies and that the reconstruction quality is highly correlated with noisy patterns in the image patches.