S. E. A. Raza

TIAToolbox provides an end-to-end Python toolbox for computational pathology, enabling efficient and accessible use of deep learning algorithms for tissue image analysis.

The paper investigates immune surveillance in pre-invasive squamous cell lung cancer, finding that regressive lesions have more immune infiltration and distinct molecular profiles compared to progressive lesions.

This paper develops a deep learning pipeline to detect and segment DCIS ducts, revealing that pure DCIS has more TILs but less co-localization with ducts compared to adjacent DCIS.