no code implementations • 16 Sep 2022 • Banafshe Felfeliyan, Abhilash Hareendranathan, Gregor Kuntze, Stephanie Wichuk, Nils D. Forkert, Jacob L. Jaremko, Janet L. Ronsky
The aim of this paper was to develop and evaluate a method to generate probabilistic labels based on multi-rater annotations and anatomical knowledge of the lesion features in MRI and a method to train segmentation models using probabilistic labels using normalized active-passive loss as a "noise-tolerant loss" function.
no code implementations • 17 Jul 2022 • Banafshe Felfeliyan, Abhilash Hareendranathan, Gregor Kuntze, David Cornell, Nils D. Forkert, Jacob L. Jaremko, Janet L. Ronsky
The effectiveness of the proposed method for segmentation tasks in different pre-training and fine-tuning scenarios is evaluated based on the Osteoarthritis Initiative dataset.
no code implementations • 27 Jul 2021 • Banafshe Felfeliyan, Abhilash Hareendranathan, Gregor Kuntze, Jacob L. Jaremko, Janet L. Ronsky
The iMaskRCNN led to improved bone and cartilage segmentation compared to Mask RCNN as indicated with the increase in dice score from 95% to 98% for the femur, 95% to 97% for tibia, 71% to 80% for femoral cartilage, and 81% to 82% for tibial cartilage.
no code implementations • 3 Jan 2020 • Jacky C. K. Chow, Steven K. Boyd, Derek D. Lichti, Janet L. Ronsky
It was found that using a smoothed kNN regression can automatically model the systematic errors in fluoroscopy with similar accuracy as a human expert using a small training dataset.