Automatic segmentation and reconstruction of intracellular compartments in volumetric electron microscopy data

MADR-Net: multi-level attention dilated residual neural network for segmentation of medical images

Medical image segmentation has made a significant contribution towards delivering affordable healthcare by facilitating the automatic identification of anatomical structures and other regions of interest. Although convolution neural networks have become prominent in the field of medical image segmentation, they suffer from certain limitations. In this study, we present a reliable framework for producing performant outcomes for the segmentation of pathological structures of 2D medical images. Our framework consists of a novel deep learning architecture, called deep multi-level attention dilated residual neural network (MADR-Net), designed to improve the performance of medical image segmentation. MADR-Net uses a U-Net encoder/decoder backbone in combination with multi-level residual blocks and atrous pyramid scene parsing pooling. To improve the segmentation results, channel-spatial attention blocks were added in the skip connection to capture both the global and local features and superseded the bottleneck layer with an ASPP block. Furthermore, we introduce a hybrid loss function that has an excellent convergence property and enhances the performance of the medical image segmentation task. We extensively validated the proposed MADR-Net on four typical yet challenging medical image segmentation tasks: (1) Left ventricle, left atrium, and myocardial wall segmentation from Echocardiogram images in the CAMUS dataset, (2) Skin cancer segmentation from dermoscopy images in ISIC 2017 dataset, (3) Electron microscopy in FIB-SEM dataset, and (4) Fluid attenuated inversion recovery abnormality from MR images in LGG segmentation dataset. The proposed algorithm yielded significant results when compared to state-of-the-art architectures such as U-Net, Residual U-Net, and Attention U-Net. The proposed MADR-Net consistently outperformed the classical U-Net by 5.43%, 3.43%, and 3.92% relative improvement in terms of dice coefficient, respectively, for electron microscopy, dermoscopy, and MRI. The experimental results demonstrate superior performance on single and multi-class datasets and that the proposed MADR-Net can be utilized as a baseline for the assessment of cross-dataset and segmentation tasks.

Machine learning-based 3D segmentation of mitochondria in polarized epithelial cells

Mitochondria are dynamic organelles that alter their morphological characteristics in response to functional needs. Therefore, mitochondrial morphology is an important indicator of mitochondrial function and cellular health. Reliable segmentation of mitochondrial networks in microscopy images is a crucial initial step for further quantitative evaluation of their morphology. However, 3D mitochondrial segmentation, especially in cells with complex network morphology, such as in highly polarized cells, remains challenging. To improve the quality of 3D segmentation of mitochondria in super-resolution microscopy images, we took a machine learning approach, using 3D Trainable Weka, an ImageJ plugin. We demonstrated that, compared with other commonly used methods, our approach segmented mitochondrial networks effectively, with improved accuracy in different polarized epithelial cell models, including differentiated human retinal pigment epithelial (RPE) cells. Furthermore, using several tools for quantitative analysis following segmentation, we revealed mitochondrial fragmentation in bafilomycin-treated RPE cells.

Deep neural network automated segmentation of cellular structures in volume electron microscopy

Volume electron microscopy is an important imaging modality in contemporary cell biology. Identification of intracellular structures is a laborious process limiting the effective use of this potentially powerful tool. We resolved this bottleneck with automated segmentation of intracellular substructures in electron microscopy (ASEM), a new pipeline to train a convolutional neural network to detect structures of a wide range in size and complexity. We obtained dedicated models for each structure based on a small number of sparsely annotated ground truth images from only one or two cells. Model generalization was improved with a rapid, computationally effective strategy to refine a trained model by including a few additional annotations. We identified mitochondria, Golgi apparatus, endoplasmic reticulum, nuclear pore complexes, caveolae, clathrin-coated pits, and vesicles imaged by focused ion beam scanning electron microscopy. We uncovered a wide range of membrane-nuclear pore diameters within a single cell and derived morphological metrics from clathrin-coated pits and vesicles, consistent with the classical constant-growth assembly model.