期刊
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
卷 27, 期 1, 页码 121-130出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JBHI.2022.3209551
关键词
Microorganisms; Microscopy; Feature extraction; Deep learning; Random forests; Iterative methods; Standards; medical imaging; microorganisms; microscopy; neural networks
Preliminary microbiological diagnosis is time-consuming, but deep learning methods based on microscopic images have been introduced to replace bacteriological examination. In this study, we propose using multi-MIL, a multi-label classification method, to analyze polyculture images and further shorten the diagnosis time. We evaluate our approach using a dataset of microscopic images for four considered bacteria species, achieving an ROC AUC above 0.9 and proving the feasibility for future experiments.
Preliminary microbiological diagnosis usually relies on microscopic examination and, due to the routine culture and bacteriological examination, lasts up to 11 days. Hence, many deep learning methods based on microscopic images were recently introduced to replace the time-consuming bacteriological examination. They shorten the diagnosis by 1-2 days but still require iterative culture to obtain monoculture samples. In this work, we present a feasibility study for further shortening the diagnosis time by analyzing polyculture images. It is possible with multi-MIL, a novel multi-label classification method based on multiple instance learning. To evaluate our approach, we introduce a dataset containing microscopic images for all combinations of four considered bacteria species. We obtain ROC AUC above 0.9, proving the feasibility of the method and opening the path for future experiments with a larger number of species.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据