{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/real-time-automatic-m-mode-echocardiography","title":"Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels","arxiv_id":"2308.07717","date":"2023-08-15","proceeding":null,"authors":["Ching-Hsun Tseng","Shao-Ju Chien","Po-Shen Wang","Shin-Jye Lee","Wei-Huan Hu","Bin Pu","Xiao-jun Zeng"],"abstract":"Motion mode (M-mode) recording is an essential part of echocardiography to measure cardiac dimension and function. However, the current diagnosis cannot build an automatic scheme, as there are three fundamental obstructs: Firstly, there is no open dataset available to build the automation for ensuring constant results and bridging M-mode echocardiography with real-time instance segmentation (RIS); Secondly, the examination is involving the time-consuming manual labelling upon M-mode echocardiograms; Thirdly, as objects in echocardiograms occupy a significant portion of pixels, the limited receptive field in existing backbones (e.g., ResNet) composed from multiple convolution layers are inefficient to cover the period of a valve movement. Existing non-local attentions (NL) compromise being unable real-time with a high computation overhead or losing information from a simplified version of the non-local block. Therefore, we proposed RAMEM, a real-time automatic M-mode echocardiography measurement scheme, contributes three aspects to answer the problems: 1) provide MEIS, a dataset of M-mode echocardiograms for instance segmentation, to enable consistent results and support the development of an automatic scheme; 2) propose panel attention, local-to-global efficient attention by pixel-unshuffling, embedding with updated UPANets V2 in a RIS scheme toward big object detection with global receptive field; 3) develop and implement AMEM, an efficient algorithm of automatic M-mode echocardiography measurement enabling fast and accurate automatic labelling among diagnosis. The experimental results show that RAMEM surpasses existing RIS backbones (with non-local attention) in PASCAL 2012 SBD and human performances in real-time MEIS tested. The code of MEIS and dataset are available at https://github.com/hanktseng131415go/RAME.","url_abs":"https://arxiv.org/abs/2308.07717v1","url_pdf":"https://arxiv.org/pdf/2308.07717v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"real-time-automatic-m-mode-echocardiography","repo_url":"https://github.com/hanktseng131415go/ramem","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"medical-image-segmentation","task_name":"Medical Image Segmentation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"real-time-instance-segmentation","task_name":"Real-time Instance Segmentation"},{"task_slug":"real-time-instance-measurement","task_name":"Real-time instance measurement"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[{"slug":"meis","name":"MEIS","full_name":"M-mode Echocardiograms for Instance Segmentation"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/real-time-instance-segmentation-on-meis","task":"Real-time Instance Segmentation","dataset":"MEIS","model":"maYOLACT ResNet50","rank_in_archive_order":1,"of":2,"metrics":{"FLOPs (G)":"0.4826","Frame (fps)":"36.13","Size (M)":"30.38","avgAP (mask AP + box AP)":"46.29","boxAP":"49.59","maskAP":"42.99"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-instance-segmentation-on-meis","task":"Real-time Instance Segmentation","dataset":"MEIS","model":"RAMEM UPANet80 V2","rank_in_archive_order":2,"of":2,"metrics":{"FLOPs (G)":"100.85","Frame (fps)":"52.22","Size (M)":"40.28","avgAP (mask AP + box AP)":"47.15","boxAP":"51.2","maskAP":"43.09"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-instance-segmentation-on-pascal-voc","task":"Real-time Instance Segmentation","dataset":"PASCAL VOC 2012","model":"RAMEM UPANet80 V2","rank_in_archive_order":1,"of":3,"metrics":{"FLOPs (G)":"100.85","Frame (fps)":"60.93","Size (M)":"40.32","avgAP (mask AP + box AP)":"42.69","boxAP":"42.96","maskAP":"42.42"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-instance-segmentation-on-pascal-voc","task":"Real-time Instance Segmentation","dataset":"PASCAL VOC 2012","model":"maYOLACT ResNet50","rank_in_archive_order":2,"of":3,"metrics":{"FLOPs (G)":"48.26","Frame (fps)":"81.27","Size (M)":"30.41","avgAP (mask AP + box AP)":"37.39","boxAP":"37.50","maskAP":"37.27"},"uses_additional_data":false},{"leaderboard":"/sota/real-time-instance-segmentation-on-pascal-voc","task":"Real-time Instance Segmentation","dataset":"PASCAL VOC 2012","model":"YOLACT ResNet50","rank_in_archive_order":3,"of":3,"metrics":{"FLOPs (G)":"48.26","Frame (fps)":"81.11","Size (M)":"30.41","avgAP (mask AP + box AP)":"35.73","boxAP":"36.65","maskAP":"35.12"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}