The Need for Medically Aware Video Compression in Gastroenterology

TL;DR

This paper investigates how classical video codecs negatively impact the quality of gastroenterology videos, especially for medical tasks, and proposes learned compression methods to improve preservation of medically relevant information.

Contribution

It highlights deficiencies of classical codecs in medical video compression and introduces ongoing work on learned compression models tailored for gastroenterology videos.

Findings

Classical codecs compress medically relevant frames worse than nonrelevant ones.

Polyp detector performance drops rapidly with increased compression.

Learned compression could allocate bits to important regions for better performance.

Abstract

Compression is essential to storing and transmitting medical videos, but the effect of compression on downstream medical tasks is often ignored. Furthermore, systems in practice rely on standard video codecs, which naively allocate bits between medically relevant frames or parts of frames. In this work, we present an empirical study of some deficiencies of classical codecs on gastroenterology videos, and motivate our ongoing work to train a learned compression model for colonoscopy videos. We show that two of the most common classical codecs, H264 and HEVC, compress medically relevant frames statistically significantly worse than medically nonrelevant ones, and that polyp detector performance degrades rapidly as compression increases. We explain how a learned compressor could allocate bits to important regions and allow detection performance to degrade more gracefully. Many of our proposed techniques generalize to medical video domains beyond gastroenterology