EM-NET: Centerline-Aware Mitochondria Segmentation in EM Images via Hierarchical View-Ensemble Convolutional Network
This work addresses segmentation challenges in biomedical imaging for researchers, offering improved accuracy and efficiency, though it is incremental as it builds on existing deep encoder-decoder networks.
The paper tackled the problem of coarse and discontinuous mitochondria segmentation in EM images by introducing EM-Net, a multi-task network with an auxiliary centerline detection task and a hierarchical view-ensemble convolution module, achieving state-of-the-art performance on a public benchmark with promising results even with reduced training data.
Although deep encoder-decoder networks have achieved astonishing performance for mitochondria segmentation from electron microscopy (EM) images, they still produce coarse segmentations with lots of discontinuities and false positives. Besides, the need for labor intensive annotations of large 3D dataset and huge memory overhead by 3D models are also major limitations. To address these problems, we introduce a multi-task network named EM-Net, which includes an auxiliary centerline detection task to account for shape information of mitochondria represented by centerline. Therefore, the centerline detection sub-network is able to enhance the accuracy and robustness of segmentation task, especially when only a small set of annotated data are available. To achieve a light-weight 3D network, we introduce a novel hierarchical view-ensemble convolution module to reduce number of parameters, and facilitate multi-view information aggregation.Validations on public benchmark showed state-of-the-art performance by EM-Net. Even with significantly reduced training data, our method still showed quite promising results.