TY - GEN
T1 - Adaptive feature aggregation network for nuclei segmentation
AU - Geng, Ruizhe
AU - Huang, Zhongyi
AU - Chen, Jie
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/3/7
Y1 - 2021/3/7
N2 - Nuclei instance segmentation is essential for cell morphometrics and analysis, playing a crucial role in digital pathology. The problem of variability in nuclei characteristics among diverse cell types makes this task more challenging. Recently, proposal-based segmentation methods with feature pyramid network (FPN) has shown good performance because FPN integrates multi-scale features with strong semantics. However, FPN has information loss of the highest-level feature map and sub-optimal feature fusion strategies. This paper proposes a proposal-based adaptive feature aggregation methods (AANet) to make full use of multi-scale features. Specifically, AANet consists of two components: Context Augmentation Module (CAM) and Feature Adaptive Selection Module (ASM). In feature fusion, CAM focus on exploring extensive contextual information and capturing discriminative semantics to reduce the information loss of feature map at the highest pyramid level. The enhanced features are then sent to ASM to get a combined feature representation adaptively over all feature levels for each RoI. The experiments show our model's effectiveness on two publicly available datasets: the Kaggle 2018 Data Science Bowl dataset and the Multi-Organ nuclei segmentation dataset.
AB - Nuclei instance segmentation is essential for cell morphometrics and analysis, playing a crucial role in digital pathology. The problem of variability in nuclei characteristics among diverse cell types makes this task more challenging. Recently, proposal-based segmentation methods with feature pyramid network (FPN) has shown good performance because FPN integrates multi-scale features with strong semantics. However, FPN has information loss of the highest-level feature map and sub-optimal feature fusion strategies. This paper proposes a proposal-based adaptive feature aggregation methods (AANet) to make full use of multi-scale features. Specifically, AANet consists of two components: Context Augmentation Module (CAM) and Feature Adaptive Selection Module (ASM). In feature fusion, CAM focus on exploring extensive contextual information and capturing discriminative semantics to reduce the information loss of feature map at the highest pyramid level. The enhanced features are then sent to ASM to get a combined feature representation adaptively over all feature levels for each RoI. The experiments show our model's effectiveness on two publicly available datasets: the Kaggle 2018 Data Science Bowl dataset and the Multi-Organ nuclei segmentation dataset.
KW - histopathology images
KW - neural networks
KW - nuclei segmentation
UR - http://www.scopus.com/inward/record.url?scp=85105877498&partnerID=8YFLogxK
U2 - 10.1145/3444685.3446271
DO - 10.1145/3444685.3446271
M3 - Conference contribution
AN - SCOPUS:85105877498
T3 - Proceedings of the 2nd ACM International Conference on Multimedia in Asia, MMAsia 2020
BT - Proceedings of the 2nd ACM International Conference on Multimedia in Asia, MMAsia 2020
PB - Association for Computing Machinery, Inc
T2 - 2nd ACM International Conference on Multimedia in Asia, MMAsia 2020
Y2 - 7 March 2021
ER -