Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Guo, Xiaoqing, Men, Qianhui, Noble, J. Alison
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2408.03761
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914997494349824
author Guo, Xiaoqing
Men, Qianhui
Noble, J. Alison
author_facet Guo, Xiaoqing
Men, Qianhui
Noble, J. Alison
contents We present the first automated multimodal summary generation system, MMSummary, for medical imaging video, particularly with a focus on fetal ultrasound analysis. Imitating the examination process performed by a human sonographer, MMSummary is designed as a three-stage pipeline, progressing from keyframe detection to keyframe captioning and finally anatomy segmentation and measurement. In the keyframe detection stage, an innovative automated workflow is proposed to progressively select a concise set of keyframes, preserving sufficient video information without redundancy. Subsequently, we adapt a large language model to generate meaningful captions for fetal ultrasound keyframes in the keyframe captioning stage. If a keyframe is captioned as fetal biometry, the segmentation and measurement stage estimates biometric parameters by segmenting the region of interest according to the textual prior. The MMSummary system provides comprehensive summaries for fetal ultrasound examinations and based on reported experiments is estimated to reduce scanning time by approximately 31.5%, thereby suggesting the potential to enhance clinical workflow efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2408_03761
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MMSummary: Multimodal Summary Generation for Fetal Ultrasound Video
Guo, Xiaoqing
Men, Qianhui
Noble, J. Alison
Computer Vision and Pattern Recognition
We present the first automated multimodal summary generation system, MMSummary, for medical imaging video, particularly with a focus on fetal ultrasound analysis. Imitating the examination process performed by a human sonographer, MMSummary is designed as a three-stage pipeline, progressing from keyframe detection to keyframe captioning and finally anatomy segmentation and measurement. In the keyframe detection stage, an innovative automated workflow is proposed to progressively select a concise set of keyframes, preserving sufficient video information without redundancy. Subsequently, we adapt a large language model to generate meaningful captions for fetal ultrasound keyframes in the keyframe captioning stage. If a keyframe is captioned as fetal biometry, the segmentation and measurement stage estimates biometric parameters by segmenting the region of interest according to the textual prior. The MMSummary system provides comprehensive summaries for fetal ultrasound examinations and based on reported experiments is estimated to reduce scanning time by approximately 31.5%, thereby suggesting the potential to enhance clinical workflow efficiency.
title MMSummary: Multimodal Summary Generation for Fetal Ultrasound Video
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.03761