Feng, Linqing Song, Jun Ho Kim, Jiwon Jeong, Soomin Park, Jin Sung Kim, Jinhyun 2024-01-19T19:00:59Z 2024-01-19T19:00:59Z 2021-09-05 2019-11 2169-3536 https://pubs.kist.re.kr/handle/201004/119377 Quantitative analysis of cell nuclei in microscopic images is an essential yet challenging source of biological and pathological information. The major challenge is accurate detection and segmentation of densely packed nuclei in images acquired under a variety of conditions. Mask R-CNN-based methods have achieved state-of-the-art nucleus segmentation. However, the current pipeline requires fully annotated training images, which are time consuming to create and sometimes noisy. Importantly, nuclei often appear similar within the same image. This similarity could be utilized to segment nuclei with only partially labeled training examples. We propose a simple yet effective region-proposal module for the current Mask R-CNN pipeline to perform few-exemplar learning. To capture the similarities between unlabeled regions and labeled nuclei, we apply decomposed self-attention to learned features. On the self-attention map, we observe strong activation at the centers and edges of all nuclei, including unlabeled nuclei. On this basis, our region-proposal module propagates partial annotations to the whole image and proposes effective bounding boxes for the bounding box-regression and binary mask-generation modules. Our method effectively learns from unlabeled regions thereby improving detection performance. We test our method with various nuclear images. When trained with only 1/4 of the nuclei annotated, our approach retains a detection accuracy comparable to that from training with fully annotated data. Moreover, our method can serve as a bootstrapping step to create full annotations of datasets, iteratively generating and correcting annotations until a predetermined coverage and accuracy are reached. The source code is available at <uri>https://github.com/feng-lab/nuclei</uri>. English IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC SEGMENTATION TRACKING CELLS INFORMATION Robust Nucleus Detection With Partially Labeled Exemplars Article 10.1109/ACCESS.2019.2952098 1 IEEE ACCESS, v.7, pp.162169 - 162178 IEEE ACCESS 7 162169 162178 scie scopus 000497169800098 2-s2.0-85078698821 Computer Science, Information Systems Engineering, Electrical & Electronic Telecommunications Computer Science Engineering Telecommunications Article SEGMENTATION TRACKING CELLS INFORMATION Training Image segmentation Task analysis Pipelines Proposals Head Image edge detection Nucleus segmentation deep learning convolutional neural networks few-exemplar learning semisupervised learning computer-assisted annotating