no code implementations • 25 Apr 2024 • Subrata Mukherjee, Thibaud Coroller, Craig Wang, Ravi K. Samala, Tingting Hu, Didem Gokcay, Nicholas Petrick, Berkman Sahiner, Qian Cao
The algorithm employs a sequential two-step pipeline: (a) Firstly, an adaptive Hungarian algorithm is used to establish correspondence among lesions within a single volumetric image series which have been annotated by multiple radiologists at a specific timepoint.
1 code implementation • 16 Apr 2024 • Mélodie Monod, Peter Krusche, Qian Cao, Berkman Sahiner, Nicholas Petrick, David Ohlssen, Thibaud Coroller
TorchSurv is a Python package that serves as a companion tool to perform deep survival modeling within the PyTorch environment.
no code implementations • 8 Aug 2023 • Yuanhan Mo, Yao Chen, Aimee Readie, Gregory Ligozio, Thibaud Coroller, Bartłomiej W. Papież
In this study, we address this challenge by prototyping a 2-step auto-grading pipeline, called VertXGradeNet, to automatically predict mSASSS scores for the cervical and lumbar vertebral units (VUs) in X-ray spinal imaging.
no code implementations • 7 Feb 2023 • Yao Chen, Yuanhan Mo, Aimee Readie, Gregory Ligozio, Indrajeet Mandal, Faiz Jabbar, Thibaud Coroller, Bartlomiej W. Papiez
Our experimental results have shown that the proposed pipeline outperformed two SOTA segmentation models on our test dataset (MEASURE 1) with a mean Dice of 0. 90, vs. a mean Dice of 0. 73 for Mask R-CNN and 0. 72 for U-Net.
no code implementations • 12 Jul 2022 • Yao Chen, Yuanhan Mo, Aimee Readie, Gregory Ligozio, Thibaud Coroller, Bartlomiej W. Papiez
Manual annotation of vertebrae on spinal X-ray imaging is costly and time-consuming due to bone shape complexity and image quality variations.
1 code implementation • 24 Jun 2021 • Hanxi Sun, Jason Plawinski, Sajanth Subramaniam, Amir Jamaludin, Timor Kadir, Aimee Readie, Gregory Ligozio, David Ohlssen, Mark Baillie, Thibaud Coroller
An alternative to anonymization is sharing a synthetic dataset that bears a behaviour similar to the real data but preserves privacy.