Ultrasound Video Summarization using Deep Reinforcement Learning
This addresses the challenge for clinicians in handling raw diagnostic video data, which is time-consuming to process, though it is incremental as it applies existing reinforcement learning to a specific medical domain.
The paper tackles the problem of efficiently summarizing ultrasound videos to reduce processing time, introducing a novel deep reinforcement learning method that preserves diagnostic information and outperforms alternative methods on fetal ultrasound screening data.
Video is an essential imaging modality for diagnostics, e.g. in ultrasound imaging, for endoscopy, or movement assessment. However, video hasn't received a lot of attention in the medical image analysis community. In the clinical practice, it is challenging to utilise raw diagnostic video data efficiently as video data takes a long time to process, annotate or audit. In this paper we introduce a novel, fully automatic video summarization method that is tailored to the needs of medical video data. Our approach is framed as reinforcement learning problem and produces agents focusing on the preservation of important diagnostic information. We evaluate our method on videos from fetal ultrasound screening, where commonly only a small amount of the recorded data is used diagnostically. We show that our method is superior to alternative video summarization methods and that it preserves essential information required by clinical diagnostic standards.