Pub Date : 2022-07-06DOI: 10.1109/SPMB55497.2022.10014968
S. Rizvi, P. Cicalese, S. Seshan, S. Sciascia, J. U.Becker, H. Nguyen
Deep learning-based methods have powered recent advancements in medical image segmentation, accelerating the field past previous statistical and Machine Learning-based methods [1]. This, however, has simultaneously created a need for large quantities of labeled data, which is difficult in domains such as medical imaging where labeling is expensive and requires expert knowledge. Semi-supervised learning (SSL) addresses these limitations by augmenting labeled data with large quantities of more widely available unlabeled data. Existing semi-supervised frameworks based on pseudo-labeling [2] or contrastive methods [3], however, struggle to scale to the high resolution of medical image datasets. In this work, we propose the Histopathology DatasetGAN (HDGAN) framework, an extension of the DatasetGAN framework for image generation and segmentation that scales well to large-resolution histopathology images. We make several adaptations on the original framework, including updating the generative backbone, selectively extracting latent features from the generator, and switching to memory-mapped arrays. These changes reduce the memory consumption of the framework, improving its applicability to medical imaging domains.
{"title":"Histopathology DatasetGAN: Synthesizing Large-Resolution Histopathology Datasets","authors":"S. Rizvi, P. Cicalese, S. Seshan, S. Sciascia, J. U.Becker, H. Nguyen","doi":"10.1109/SPMB55497.2022.10014968","DOIUrl":"https://doi.org/10.1109/SPMB55497.2022.10014968","url":null,"abstract":"Deep learning-based methods have powered recent advancements in medical image segmentation, accelerating the field past previous statistical and Machine Learning-based methods [1]. This, however, has simultaneously created a need for large quantities of labeled data, which is difficult in domains such as medical imaging where labeling is expensive and requires expert knowledge. Semi-supervised learning (SSL) addresses these limitations by augmenting labeled data with large quantities of more widely available unlabeled data. Existing semi-supervised frameworks based on pseudo-labeling [2] or contrastive methods [3], however, struggle to scale to the high resolution of medical image datasets. In this work, we propose the Histopathology DatasetGAN (HDGAN) framework, an extension of the DatasetGAN framework for image generation and segmentation that scales well to large-resolution histopathology images. We make several adaptations on the original framework, including updating the generative backbone, selectively extracting latent features from the generator, and switching to memory-mapped arrays. These changes reduce the memory consumption of the framework, improving its applicability to medical imaging domains.","PeriodicalId":261445,"journal":{"name":"2022 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124655826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-04-01DOI: 10.1109/SPMB55497.2022.10014819
T. Möller, Martin Voss, Laura Kaltwasser
This technical paper provides a tutorial to build a low-cost (10–100 USD) and easy to assemble ECG device (ArdMob-ECG) that can be easily used for a variety of different scientific studies. The advantage of this device is that it automatically stores the data and has a built-in detection algorithm for heartbeats. Compared to a clinical ECG, this device entails a serial interface that can send triggers via USB directly to a computer and software (e.g. Unity, Matlab) with minimal delay due to its architecture. Its software and hardware is open-source and publicly available. The performance of the device regarding sensitivity and specificity is comparable to a professional clinical ECG and is assessed in this paper. Due to the open-source software, a variety of different research questions and individual alterations can be adapted using this ECG. The code as well as the circuit is publicly available and accessible for everyone to promote a better health system in remote areas, Open Science, and to boost scientific progress and the development of new paradigms that ultimately foster innovation.
{"title":"An Arduino Based Heartbeat Detection Device (ArdMob-ECG) for Real-Time ECG Analysis","authors":"T. Möller, Martin Voss, Laura Kaltwasser","doi":"10.1109/SPMB55497.2022.10014819","DOIUrl":"https://doi.org/10.1109/SPMB55497.2022.10014819","url":null,"abstract":"This technical paper provides a tutorial to build a low-cost (10–100 USD) and easy to assemble ECG device (ArdMob-ECG) that can be easily used for a variety of different scientific studies. The advantage of this device is that it automatically stores the data and has a built-in detection algorithm for heartbeats. Compared to a clinical ECG, this device entails a serial interface that can send triggers via USB directly to a computer and software (e.g. Unity, Matlab) with minimal delay due to its architecture. Its software and hardware is open-source and publicly available. The performance of the device regarding sensitivity and specificity is comparable to a professional clinical ECG and is assessed in this paper. Due to the open-source software, a variety of different research questions and individual alterations can be adapted using this ECG. The code as well as the circuit is publicly available and accessible for everyone to promote a better health system in remote areas, Open Science, and to boost scientific progress and the development of new paradigms that ultimately foster innovation.","PeriodicalId":261445,"journal":{"name":"2022 IEEE Signal Processing in Medicine and Biology Symposium (SPMB)","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116286539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：