Machine Learning Seminar

Cross-domain deep distillation learning for image-guided therapies


Harini Veeraraghavan
Memorial Sloan Kettering Cancer Center

Wednesday, September 9, 2020
3:30–4:30 pm

Video recording can be viewed here

Medical image analysis for oncology applications is plagued by problems of small labeled datasets and the difficulty in analyzing images that often have very low soft-tissue contrast to differentiate foreground and background structures. Deep learning techniques such as deep domain adaptation developed in computer vision, have limited success when applied to medical images. This is due to the wide variations in the images even in the same modalities and even larger variations of the different tissues appearing on multiple imaging modalities. In this talk, I will present some solutions developed by our group for solving these two problems. In brief, I will present an approach that uses joint distribution matching to learn from entirely different imaging modalities to segment on a target modality without any expert labels. Next, I will show how cross-domain adaptation can be combined with distillation learning to train models to segment centrally located lung tumors on CT and more challenging cone-beam CT images. I will also show how these methods are being translated from lab into clinical practice for image-guided radiation treatments in our hospital.

Harini Veeraraghavan is an assistant attending computer scientist at Memorial Sloan Kettering Cancer Center since 2012. Her research interests are in developing deep learning and medical image analysis methods for improving cancer treatments. Her group actively develops automated segmentation methods that are currently used for image-guided radiation therapy treatments at MSKCC. She also leads the development of integrated image-based biomarkers of cancer treatment response from radiological and surgical images for multiple cancers. Harini received her PhD in computer science from the University of Minnesota, Twin-Cities in 2006. Prior to joining MSKCC, she was a computer vision scientist at General Electric Research since 2008, and a postdoctoral fellow at Carnegie Mellon University from 2006 to 2008.