Evaluating severity of white matter lesions from computed tomography images with convolutional neural network

Johanna Pitkänen (Corresponding Author), Juha Koikkalainen, Tuomas Nieminen, Ivan Marinkovic, Sami Curtze, Gerli Sibolt, Hanna Jokinen, Daniel Rueckert, Frederik Barkhof, Reinhold Schmidt, Leonardo Pantoni, Philip Scheltens, Lars Olof Wahlund, Antti Korvenoja, Jyrki Lötjönen, Timo Erkinjuntti, Susanna Melkas

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Purpose: Severity of white matter lesion (WML) is typically evaluated on magnetic resonance images (MRI), yet the more accessible, faster, and less expensive method is computed tomography (CT). Our objective was to study whether WML can be automatically segmented from CT images using a convolutional neural network (CNN). The second aim was to compare CT segmentation with MRI segmentation. Methods: The brain images from the Helsinki University Hospital clinical image archive were systematically screened to make CT-MRI image pairs. Selection criteria for the study were that both CT and MRI images were acquired within 6 weeks. In total, 147 image pairs were included. We used CNN to segment WML from CT images. Training and testing of CNN for CT was performed using 10-fold cross-validation, and the segmentation results were compared with the corresponding segmentations from MRI. Results: A Pearson correlation of 0.94 was obtained between the automatic WML volumes of MRI and CT segmentations. The average Dice similarity index validating the overlap between CT and FLAIR segmentations was 0.68 for the Fazekas 3 group. Conclusion: CNN-based segmentation of CT images may provide a means to evaluate the severity of WML and establish a link between CT WML patterns and the current standard MRI-based visual rating scale.

Original languageEnglish
Pages (from-to)1257-1263
Number of pages7
JournalNeuroradiology
Volume62
Issue number10
Early online date13 Apr 2020
DOIs
Publication statusPublished - Oct 2020
MoE publication typeA1 Journal article-refereed

Keywords

  • Cerebral small vessel disease
  • Computed tomography
  • Convolutional neural network
  • Machine learning
  • White matter lesions

Fingerprint Dive into the research topics of 'Evaluating severity of white matter lesions from computed tomography images with convolutional neural network'. Together they form a unique fingerprint.

  • Cite this

    Pitkänen, J., Koikkalainen, J., Nieminen, T., Marinkovic, I., Curtze, S., Sibolt, G., Jokinen, H., Rueckert, D., Barkhof, F., Schmidt, R., Pantoni, L., Scheltens, P., Wahlund, L. O., Korvenoja, A., Lötjönen, J., Erkinjuntti, T., & Melkas, S. (2020). Evaluating severity of white matter lesions from computed tomography images with convolutional neural network. Neuroradiology, 62(10), 1257-1263. https://doi.org/10.1007/s00234-020-02410-2