Predicting breast cancer with AI for individual risk-adjusted MRI screening and early detection

no code implementations • 29 Nov 2023 • Lukas Hirsch, Yu Huang, Hernan A. Makse, Danny F. Martinez, Mary Hughes, Sarah Eskreis-Winkler, Katja Pinker, Elizabeth Morris, Lucas C. Parra, Elizabeth J. Sutton

Reevaluating these regions in 10% of all cases with higher AI-predicted risk could have resulted in up to 33% early detections by a radiologist.

Radiologist-level Performance by Using Deep Learning for Segmentation of Breast Cancers on MRI Scans

no code implementations • 21 Sep 2020 • Lukas Hirsch, Yu Huang, Shaojun Luo, Carolina Rossi Saccarelli, Roberto Lo Gullo, Isaac Daimiel Naranjo, Almir G. V. Bitencourt, Natsuko Onishi, Eun Sook Ko, Doris Leithner, Daly Avendano, Sarah Eskreis-Winkler, Mary Hughes, Danny F. Martinez, Katja Pinker, Krishna Juluru, Amin E. El-Rowmeim, Pierre Elnajjar, Elizabeth A. Morris, Hernan A. Makse, Lucas C Parra, Elizabeth J. Sutton

Conclusion: When trained on a sufficiently large dataset, the developed 3D U-Net performed as well as fellowship-trained radiologists in detailed 2D segmentation of breast cancers at routine clinical MRI.

Tumor Segmentation

Segmentation of MRI head anatomy using deep volumetric networks and multiple spatial priors

1 code implementation • 24 May 2019 • Lukas Hirsch, Yu Huang, Lucas C. Parra

The benefit of adding a TPM is generic in that it can boost the performance of established segmentation networks such as the DeepMedic and a UNet.

Anatomy