Abstract:
|
Given the wide variety of AI tools currently being deployed in radiology and pathlogy, it is feasible to bring AI to clinical care. However, the calibration of these tools (i.e, the data, the models and inference) for cost-sensitive situations like healthcare is an important point. Using the example of tumr segmentation task, we will review a few algorithms and describe their potential modes of failure in addition to scoring rubrics related to data and model veracity. Joint work with Snehal Prabhudesai, Vinayak Ahluwalia and Nick Wang.
|