no code implementations • 9 Nov 2021 • Nishanjan Ravin, Sourajit Saha, Alan Schweitzer, Ameena Elahi, Farouk Dako, Daniel Mollura, David Chapman
We show that without domain adaptation, ResNet-50 has difficulty in generalizing between imaging distributions from a number of public Tuberculosis screening datasets with imagery from geographically distributed regions.
no code implementations • 10 Feb 2016 • Hoo-chang Shin, Holger R. Roth, Mingchen Gao, Le Lu, Ziyue Xu, Isabella Nogues, Jianhua Yao, Daniel Mollura, Ronald M. Summers
Another effective method is transfer learning, i. e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks.