Reconsidering evaluation practices in modular systems: On the propagation of errors in MRI prostate cancer detection

no code implementations • 15 Sep 2023 • Erlend Sortland Rolfsnes, Philip Thangngat, Trygve Eftestøl, Tobias Nordström, Fredrik Jäderling, Martin Eklund, Alvaro Fernandez-Quilez

Magnetic resonance imaging has evolved as a key component for prostate cancer (PCa) detection, substantially increasing the radiologist workload.

Lesion Detection Segmentation

Leveraging multi-view data without annotations for prostate MRI segmentation: A contrastive approach

no code implementations • 12 Aug 2023 • Tim Nikolass Lindeijer, Tord Martin Ytredal, Trygve Eftestøl, Tobias Nordström, Fredrik Jäderling, Martin Eklund, Alvaro Fernandez-Quilez

Further, our approach shows good external volumetric generalization in an in-house dataset when tested with multi-view data (2. 76+-1. 89% compared to 3. 92+-3. 31%, P=. 002), showing the feasibility of exploiting non-annotated multi-view data through contrastive learning whilst providing flexibility at deployment in the event of missing views.

Contrastive Learning MRI segmentation

Prostate Age Gap (PAG): An MRI surrogate marker of aging for prostate cancer detection

no code implementations • 10 Aug 2023 • Alvaro Fernandez-Quilez, Tobias Nordström, Fredrik Jäderling, Svein Reidar Kjosavik, Martin Eklund

Assessment: Chronological age was defined as the age of the participant at the time of the visit and used to train the deep learning model to predict the age of the patient.