Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks

By Liang Chen, Paul Bentley, Daniel Rueckert. 2017

278 citations recorded by the source corpus.

Stroke is an acute cerebral vascular disease, which is likely to cause long-term disabilities and death. Acute ischemic lesions occur in most stroke patients. These lesions are treatable under accurate diagnosis and treatments. Although diffusion-weighted MR imaging (DWI) is sensitive to these lesions, localizing and quantifying them manually is costly and challenging for clinicians. In this paper, we propose a novel framework to automatically segment stroke lesions in DWI. Our framework consists of two convolutional neural networks (CNNs): one is an ensemble of two DeconvNets (Noh et al., 2015), which is the EDD Net; the second CNN is the multi-scale convolutional label evaluation net (MUSCLE Net), which aims to evaluate the lesions detected by the EDD Net in order to remove potential false positives. To the best of our knowledge, it is the first attempt to solve this problem and using both CNNs achieves very good results. Furthermore, we study the network architectures and key configurations in detail to ensure the best performance. It is validated on a large dataset comprising clinical acquired DW images from 741 subjects. A mean accuracy of Dice coefficient obtained is 0.67 in total. The mean Dice scores based on subjects with only small and large lesions are 0.61 and 0.83, respectively. The lesion detection rate achieved is 0.94.

Subfields: Biomedical Engineering, Epidemiology, Radiology, Nuclear Medicine and Imaging

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Epidemiology

Arvid Lundervold

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, background): “While machine learning methods, artificial neural networks, brain-machine interfaces and related subfields have recently demonstrated promising performance in performing medical tasks, they are hardly perfect [1] [2] [3] [4] [5] [6] [7] [8].”
An overview of deep learning in medical imaging focusing on MRI (2018, background): “Tested on 105 subjects from the Human Connectome Project Brain age [273] Chronological age prediction from raw brain T1-MRI data, also testing the heritability of brain-predicted age using a sample of 62 monozygotic and dizygotic twins Alzheimer’s disease [274] Landmark-based deep multi-instance lea”
Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory and Practice (2019, methodology): “Nevertheless, training with the pixel-wise cross-entropy loss, or its weighted variant, remains highly popular, even when the evaluation is performed using the Dice score or Jaccard index [11,6].”
Brain tumor detection and classification using machine learning: a comprehensive survey (2021, methodology): “The classiﬁcation of brain tumors has been done using two different types of networks, i.e., visual attention network and CNN are utilized for classiﬁcation of different types of brain tumor i.e., glioma, pituitary I and meningioma [234].”
Deep into the Brain: Artificial Intelligence in Stroke Imaging (2017, methodology): “More recently, the CNN deep learning technique has been applied to lesion segmentation of acute ischemic stroke with diffusion-weighted imaging (DWI).(19) Two already available CNNs were used together to develop their model: one CNN Figure 3.”
Deep Learning in Neuroradiology (2018, methodology): “Chen et al 27 used DWI as input to a 2-stage deep learning algorithm and were able to detect 94% of all acute infarcts.”
Optimization for Medical Image Segmentation: Theory and Practice When Evaluating With Dice Score or Jaccard Index (2020, methodology): “Pixel-wise (weighted) cross-entropy loss is still frequently used in these papers [1], [8].”
DRINet for Medical Image Segmentation (2018, methodology): “Inspired by the DeepLab [17], the deconvolution with a 5 × 5 kernel is replaced by a dilated deconvolution with a 3 × 3 kernel, which is more efﬁcient in memory.”
Deep learning based brain tumor segmentation: a survey (2020, methodology): “[80] used one set of DeconvNets [81] to generate the primary segmentation probability map”