Improving Classification Model Performance on Chest X-Rays through Lung Segmentation

no code implementations • 22 Feb 2022 • Hilda Azimi, Jianxing Zhang, Pengcheng Xi, Hala Asad, Ashkan Ebadi, Stephane Tremblay, Alexander Wong

Our approach is designed in a cascaded manner and incorporates two modules: a deep neural network with criss-cross attention modules (XLSor) for localizing lung region in CXR images and a CXR classification model with a backbone of a self-supervised momentum contrast (MoCo) model pre-trained on large-scale CXR data sets.

Classification Segmentation

Performance or Trust? Why Not Both. Deep AUC Maximization with Self-Supervised Learning for COVID-19 Chest X-ray Classifications

no code implementations • 14 Dec 2021 • Siyuan He, Pengcheng Xi, Ashkan Ebadi, Stephane Tremblay, Alexander Wong

Ablation study is conducted for both the performance and the trust on feature learning methods and loss functions.

Representation Learning Self-Supervised Learning

COVID-19 Detection from Chest X-ray Images using Imprinted Weights Approach

no code implementations • 4 May 2021 • Jianxing Zhang, Pengcheng Xi, Ashkan Ebadi, Hilda Azimi, Stephane Tremblay, Alexander Wong

The COVID-19 pandemic has had devastating effects on the well-being of the global population.