1 code implementation • 10 May 2023 • Matin Hosseinzadeh, Anindo Saha, Joeran Bosma, Henkjan Huisman
Our proposed model outperformed the semi-supervised model in experiments with the ProstateX dataset and an external test set, by leveraging only a subset of unlabeled data rather than the full collection of 4953 cases, our proposed model demonstrated improved performance.
1 code implementation • 25 Oct 2021 • Anindo Saha, Joeran Bosma, Jasper Linmans, Matin Hosseinzadeh, Henkjan Huisman
We hypothesize that probabilistic voxel-level classification of anatomy and malignancy in prostate MRI, although typically posed as near-identical segmentation tasks via U-Nets, require different loss functions for optimal performance due to inherent differences in their clinical objectives.