CLCI-Net: Cross-Level Fusion and Context Inference Networks for Lesion Segmentation of Chronic Stroke

Abstract

Segmenting stroke lesions from T1-weighted MR images is of great value for large-scale stroke rehabilitation neuroimaging analyses. Nevertheless, there are great challenges with this task, such as large range of stroke lesion scales and the tissue intensity similarity. The famous encoder-decoder convolutional neural network, which although has made great achievements in medical image segmentation areas, may fail to address these challenges due to the insufficient uses of multi-scale features and context information. To address these challenges, this paper proposes a Cross-Level fusion and Context Inference Network (CLCI-Net) for the chronic stroke lesion segmentation from T1-weighted MR images. Specifically, a Cross-Level feature Fusion (CLF) strategy was developed to make full use of different scale features across different levels; Extending Atrous Spatial Pyramid Pooling (ASPP) with CLF, we have enriched multi-scale features to handle the different lesion sizes; In addition, convolutional long short-term memory (ConvLSTM) is employed to infer context information and thus capture fine structures to address the intensity similarity issue. The proposed approach was evaluated on an open-source dataset, the Anatomical Tracings of Lesions After Stroke (ATLAS) with the results showing that our network outperforms five state-of-the-art methods. We make our code and models available at https://github.com/YH0517/CLCI_Net.

RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation

“…Deep learning, and more specifically convolutional neural networks (ConvNets), has become increasingly popular due to its competitive performance in medical image segmentation. Literature on brain lesion segmentation in MR images with ConvNets is dominated by approaches tested on human-derived data (e.g., Duong et al, 2019 ; Gabr et al, 2019 ; Yang et al, 2019 ). Despite using ConvNets, typical brain lesion segmentation approaches are multi-step, i.e., they rely on preprocessing procedures, such as noise reduction, registration, skull-stripping and inhomogeneity correction.…”

Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning

“…Brain infarct lesions segmentation based on U-Net architecture was the most frequently used method in recent studies [ 19 , 20 , 21 , 22 , 23 , 24 , 25 ]. It is a baseline and famous state-of-the-art deep learning architecture in biomedical image segmentation.…”

“…Depending upon the modification of the U-Net architecture, the names of the segmentation Nets were changed study by study. Among [ 19 , 20 , 21 , 22 , 23 , 24 , 25 ], Cross-Level fusion and Context Inference Network X-Net [ 21 ], (CLCI-Net) [ 22 ], Deep Residual Attention Convolutional Neural Network (DRANet) [ 23 ] used two-dimensional (2D) based U-Net architectures. They segmented the infarct lesions from input 2D slices of the MRI based on a single orientation.…”

Correcting and reweighting false label masks in brain tumor segmentation

“…Medical image segmentation has achieved success due to the development of cascade-structured deep learning networks 9 and multiscale analysis. 10,11 Dilated convolutions with different dilation rates are employed for analysis in various perception fields, such as CLCI-Net, 12 DRN, 13 autofocus CNN 14 and 3D multifiber units, 15 working at the encoder, layer, and unit levels. However, supervised learning is sensitive to the annotation quality.…”