Pixel Club: Why is it So Difficult to Obtain Medical Images for R&D ?!

Nahum Kiryati (Tel-Aviv University)
Sunday, 18.3.2018, 11:30
Room 337 Taub Bld.

Research in medical image analysis, especially after the deep-learning revolution, relies on access to medical image databases. Specific categories of medical images have been made available as “challenges” to facilitate scientific benchmarking. Nevertheless, R&D of real-world clinical technologies usually requires data acquired while diagnosing and treating particular classes of patients using specific protocols and equipment. Such data cannot be normally found in common challenges, and can only be obtained from hospitals and health care providers. In practice, getting that clinical data is notoriously difficult.

In this non-technical talk, I review the legal and ethical framework regulating access to patients’ data in Israel and abroad. I discuss thorny conundrums, such as “who owns a medical record”, and consider various approaches, old and new, for clearing the access-to-data bottleneck.

Back to the index of events