HIVE-Net: Centerline-aware hierarchical view-ensemble convolutional network for mitochondria segmentation in EM images. (March 2021)

• Record Type: Journal Article
• Authors: Yuan, Zhimin; Ma, Xiaofen; Yi, Jiajin; Luo, Zhengrong; Peng, Jialin
• Is Part Of: Computer methods and programs in biomedicine. Volume 200(2021)
• Publication Date: 2021-03
• Subjects: Electron microscopy -- Image segmentation -- Multi-task learning -- Centerline detection; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105925
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Semantic segmentation of mitochondria from electron microscopy (EM) is crucial to obtain reliable morphological statistics for investigating neural dysfunction. We introduce a centerline-aware multitask network by utilizing centerline as intrinsic shape cue of mitochondria to regularize the segmentation. We introduce a novel HVEC module to reduce the number of parameters and facilitate multi-view information aggregation. Experiments show that our architecture can achieve state-of-the-art results on two challenging benchmarks, and shows significantly improved generalization ability even training with quite limited amount of training data. Abstract: Background and objective : With the advancement of electron microscopy (EM) imaging technology, neuroscientists can investigate the function of various intracellular organelles, e.g, mitochondria, at nano-scale. Semantic segmentation of electron microscopy (EM) is an essential step to efficiently obtain reliable morphological statistics. Despite the great success achieved using deep convolutional neural networks (CNNs), they still produce coarse segmentations with lots of discontinuities and false positives for mitochondria segmentation. Methods : In this study, we introduce a centerline-aware multitask network by utilizing centerline as an intrinsic shape cue of mitochondria to regularize the segmentation. Since the application of 3D CNNs on large medical volumes is usually hindered by their substantial computational cost and storage overhead, we introduce a novel hierarchical view-ensemble convolution (HVEC), a simple alternative of 3D convolution to learn 3D spatial contexts using more efficient 2D convolutions. The HVEC enables both decomposing and sharing multi-view information, leading to increased learning capacity. Results : Extensive validation results on two challenging benchmarks show that, the proposed method performs favorably against the state-of-the-art methods in accuracy and visual quality but with a greatly reduced model size. Moreover, the proposed model also shows significantly improved generalization ability, especially when training with quite limited amount of training data. Detailed sensitivity analysis and ablation study have also been conducted, which show the robustness of the proposed model and effectiveness of the proposed modules. Conclusions : The experiments highlighted that the proposed architecture enables both simplicity and efficiency leading to increased capacity of learning spatial contexts. Moreover, incorporating shape cues such as centerline information is a promising approach to improve the performance of mitochondria segmentation.