Automated quality check of corpus callosum segmentation using deep learning

Autor(es)

Herrera, William Javier ; Appenzeller, Simone ; Reis, Fabiano ; Pereira, Danilo Rodrigues ; Bento, Mariana Pinheiro ; Rittner, Leticia ; Colliot, O ; Isgum, I ; Landman, BA ; Loew, MH

• Tipo de documento: Artigo Científico
• Fonte: MEDICAL IMAGING 2022: IMAGE PROCESSING; v. 12032, p. 7-pg., 2022-01-01.

Resumo

The Corpus callosum (CC) is a massive white matter structure in the brain, and changes in its shape and volume are associated with subject characteristics, several diseases, and clinical conditions. The CC is mostly studied in magnetic resonance imaging (MRI), where it is segmented to extract valuable information. With the increasing availability of MRI data and the proliferation of automated algorithms to perform CC segmentation, quality control (QC) verification is mandatory to assure reliability in the entire analysis pipeline. We propose a convolutional neural network (CNN) for QC of CC segmentations. The CNN gets information on the mask and contextual information on the image and performs deep feature extraction using a pre-trained model. The CNN model was fine-tuned using T-1 -weighted MR images with CC masks, in the task of classifying correct or incorrect segmentations. The CNN-based approach got an area under the curve (AUC) of 97.98% on the test set. We used an additional test set of patients with tumor to test generalization capability of the trained model to other domains. (AU)

• Processo FAPESP: 13/07559-3 - Instituto Brasileiro de Neurociência e Neurotecnologia - BRAINN
• Beneficiário: Fernando Cendes
• Modalidade de apoio: Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs