Automatic Segmentation of Stroke Lesions in Non-Contrast Computed Tomography Datasets With Convolutional Neural Networks

Abstract

Non-contrast computed tomography (NCCT) is commonly used for volumetric follow-up assessment of ischemic strokes. However, manual lesion segmentation is time-consuming and subject to high inter-observer variability. The aim of this study was to develop and establish a baseline convolutional neural network (CNN) model for automatic NCCT lesion segmentation. A total of 252 multi-center clinical NCCT datasets, acquired from 22 centers, and corresponding manual segmentations were used to train (204 datasets) and validate (48 datasets) a 3D multi-scale CNN model for lesion segmentation. Post-processing methods were implemented to improve the CNN-based lesion segmentations. The final CNN model and post-processing method was evaluated using 39 out-of-distribution holdout test datasets, acquired at seven centers that did not contribute to the training or validation datasets. Each test image was segmented by two or three neuroradiologists. The Dice similarity coefficient (DSC) and predicted lesion volumes were used to evaluate the segmentations. The CNN model achieved a mean DSC score of 0.47 on the validation NCCT datasets. Post-processing significantly improved the DSC to 0.50 (P < 0.01). On the holdout test set, the CNN model achieved a mean DSC score of 0.42, which was also significantly improved to 0.45 (P < 0.05) by post-processing. Importantly, the automatically segmented lesion volumes were not significantly different from the lesion volumes determined by the expert observers (P > 0.05) and showed excellent agreement with manual lesion segmentation volumes (intraclass correlation coefficient, ICC = 0.88). The proposed CNN model can automatically and reliably segment ischemic stroke lesions in clinical NCCT datasets. Post-processing techniques can further improve accuracy. As the model was trained and evaluated on datasets from multiple centers, it is broadly applicable and is publicly available. INDEX TERMS Artificial neural networks, brain, computed tomography, computer-assisted image analysis, convolutional neural networks, deep learning, machine learning, stroke.

Automated Cerebral Infarct Detection on Computed Tomography Images Based on Deep Learning

“…A literature review has found few papers similar to this work that applied deep learning with CNN for cerebral infarct detection on brain CT. Tuladhar et al [ 21 ] developed a CNN-based infarct segmentation method and attained a Dice similarity coefficient (DSC) of 0.45%. The generalization of their model was strengthened by using independent multi-center datasets for training, test and validation, as well as using ground truth segmentations by multiple expert observers.…”

Privatsphärefreundliches maschinelles Lernen

“…Dennoch können neuronale Netze auf vielfältige Weise in der Medizin eingesetzt werden. Einsatzgebiete sind die Erkennung von Auffälligkeiten im Rahmen der bildgebenden Diagnostik [34] oder die Filterung von Stör-und Hintergrundgeräuschen in Hörgeräten [12]. Aktuelle Projekte beschäftigen sich mit der Erkennung von Gefäßen in Schnittbildgebungen ohne Kontrastmittel, was zu einer Vermeidung von kontrastmittelassoziierten Komplikationen im Rahmen dieser Standardbildgebung führen könnte.…”

Segmentation of Tissues and Proliferating Cells in Light-Sheet Microscopy Images of Mouse Embryos Using Convolutional Neural Networks

“…The original U-net architecture was proposed to automatically segment neuronal structures on 2D electron microscopy images [32]. Since then, this CNN model has been extended to segment other types of structures and data, such as the prostate [33] and ischemic strokes [34] in 3D MRI volumes. In this work, Unets are used to solve segmentation problems in LSM images of mouse embryos, which present unique challenges.…”