Decoupled conditional contrastive learning with variable metadata for prostate lesion detection
This work addresses early prostate cancer diagnosis by improving lesion detection accuracy, though it is incremental as it builds on existing contrastive learning methods.
The paper tackled prostate lesion detection from MRI by proposing a contrastive loss function that leverages weak metadata with multiple annotators and variable confidence, resulting in a 3% AUC increase on the PI-CAI challenge dataset.
Early diagnosis of prostate cancer is crucial for efficient treatment. Multi-parametric Magnetic Resonance Images (mp-MRI) are widely used for lesion detection. The Prostate Imaging Reporting and Data System (PI-RADS) has standardized interpretation of prostate MRI by defining a score for lesion malignancy. PI-RADS data is readily available from radiology reports but is subject to high inter-reports variability. We propose a new contrastive loss function that leverages weak metadata with multiple annotators per sample and takes advantage of inter-reports variability by defining metadata confidence. By combining metadata of varying confidence with unannotated data into a single conditional contrastive loss function, we report a 3% AUC increase on lesion detection on the public PI-CAI challenge dataset. Code is available at: https://github.com/camilleruppli/decoupled_ccl