TY - JOUR
T1 - Position-based anchor optimization for point supervised dense nuclei detection
AU - Yao, Jieru
AU - Han, Longfei
AU - Guo, Guangyu
AU - Zheng, Zhaohui
AU - Cong, Runmin
AU - Huang, Xiankai
AU - Ding, Jin
AU - Yang, Kaihui
AU - Zhang, Dingwen
AU - Han, Junwei
N1 - Publisher Copyright:
© 2023
PY - 2024/3
Y1 - 2024/3
N2 - Nuclei detection is one of the most fundamental and challenging problems in histopathological image analysis, which can localize nuclei to provide effective computer-aided cancer diagnosis, treatment decision, and prognosis. The fully-supervised nuclei detector requires a large number of nuclei annotations on high-resolution digital images, which is time-consuming and needs human annotators with professional knowledge. In recent years, weakly-supervised learning has attracted significant attention in reducing the labeling burden. However, detecting dense nuclei of complex crowded distribution and diverse appearances remains a challenge. To solve this problem, we propose a novel point-supervised dense nuclei detection framework that introduces position-based anchor optimization to complete morphology-based pseudo-label supervision. Specifically, we first generate cellular-level pseudo labels (CPL) for the detection head via a morphology-based mechanism, which can help to build a baseline point-supervised detection network. Then, considering the crowded distribution of the dense nuclei, we propose a mechanism called Position-based Anchor-quality Estimation (PAE), which utilizes the positional deviation between an anchor and its corresponding point label to suppress low-quality detections far from each nucleus. Finally, to better handle the diverse appearances of nuclei, an Adaptive Anchor Selector (AAS) operation is proposed to automatically select positive and negative anchors according to morphological and positional statistical characteristics of nuclei. We conduct comprehensive experiments on two widely used benchmarks, MO and Lizard, using ResNet50 and PVTv2 as backbones. The results demonstrate that the proposed approach has superior capacity compared with other state-of-the-art methods. In particularly, in dense nuclei scenarios, our method can achieve 95.1% performance of the fully-supervised approach. The code is available at https://github.com/NucleiDet/DenseNucleiDet.
AB - Nuclei detection is one of the most fundamental and challenging problems in histopathological image analysis, which can localize nuclei to provide effective computer-aided cancer diagnosis, treatment decision, and prognosis. The fully-supervised nuclei detector requires a large number of nuclei annotations on high-resolution digital images, which is time-consuming and needs human annotators with professional knowledge. In recent years, weakly-supervised learning has attracted significant attention in reducing the labeling burden. However, detecting dense nuclei of complex crowded distribution and diverse appearances remains a challenge. To solve this problem, we propose a novel point-supervised dense nuclei detection framework that introduces position-based anchor optimization to complete morphology-based pseudo-label supervision. Specifically, we first generate cellular-level pseudo labels (CPL) for the detection head via a morphology-based mechanism, which can help to build a baseline point-supervised detection network. Then, considering the crowded distribution of the dense nuclei, we propose a mechanism called Position-based Anchor-quality Estimation (PAE), which utilizes the positional deviation between an anchor and its corresponding point label to suppress low-quality detections far from each nucleus. Finally, to better handle the diverse appearances of nuclei, an Adaptive Anchor Selector (AAS) operation is proposed to automatically select positive and negative anchors according to morphological and positional statistical characteristics of nuclei. We conduct comprehensive experiments on two widely used benchmarks, MO and Lizard, using ResNet50 and PVTv2 as backbones. The results demonstrate that the proposed approach has superior capacity compared with other state-of-the-art methods. In particularly, in dense nuclei scenarios, our method can achieve 95.1% performance of the fully-supervised approach. The code is available at https://github.com/NucleiDet/DenseNucleiDet.
KW - Cancer histopathology image
KW - Dense nuclei detection
KW - Morphology-based pseudo label
KW - Point-supervised learning
KW - Position-based anchor optimization
UR - http://www.scopus.com/inward/record.url?scp=85179620100&partnerID=8YFLogxK
U2 - 10.1016/j.neunet.2023.12.006
DO - 10.1016/j.neunet.2023.12.006
M3 - 文章
C2 - 38091760
AN - SCOPUS:85179620100
SN - 0893-6080
VL - 171
SP - 159
EP - 170
JO - Neural Networks
JF - Neural Networks
ER -