Improving the detection of new lesions in multiple sclerosis with a cascaded 3D fully convolutional neural network approach
dc.contributor.author
dc.date.accessioned
2022-12-01T12:41:28Z
dc.date.available
2022-12-01T12:41:28Z
dc.date.issued
2022-11-24
dc.identifier.issn
1662-4548
dc.identifier.uri
dc.description.abstract
Longitudinal magnetic resonance imaging (MRI) has an important role in multiple sclerosis (MS) diagnosis and follow-up. Specifically, the presence of new lesions on brain MRI scans is considered a robust predictive biomarker for the disease progression. New lesions are a high-impact prognostic factor to predict evolution to MS or risk of disability accumulation over time. However, the detection of this disease activity is performed visually by comparing the follow-up and baseline scans. Due to the presence of small lesions, misregistration, and high inter-/intra-observer variability, this detection of new lesions is prone to errors. In this direction, one of the last Medical Image Computing and Computer Assisted Intervention (MICCAI) challenges was dealing with this automatic new lesion quantification. The MSSEG-2: MS new lesions segmentation challenge offers an evaluation framework for this new lesion segmentation task with a large database (100 patients, each with two-time points) compiled from the OFSEP (Observatoire français de la sclérose en plaques) cohort, the French MS registry, including 3D T2-w fluid-attenuated inversion recovery (T2-FLAIR) images from different centers and scanners. Apart from a change in centers, MRI scanners, and acquisition protocols, there are more challenges that hinder the automated detection process of new lesions such as the need for large annotated datasets, which may be not easily available, or the fact that new lesions are small areas producing a class imbalance problem that could bias trained models toward the non-lesion class. In this article, we present a novel automated method for new lesion detection of MS patient images. Our approach is based on a cascade of two 3D patch-wise fully convolutional neural networks (FCNNs). The first FCNN is trained to be more sensitive revealing possible candidate new lesion voxels, while the second FCNN is trained to reduce the number of misclassified voxels coming from the first network. 3D T2-FLAIR images from the two-time points were pre-processed and linearly co-registered. Afterward, a fully CNN, where its inputs were only the baseline and follow-up images, was trained to detect new MS lesions. Our approach obtained a mean segmentation dice similarity coefficient of 0.42 with a detection F1-score of 0.5. Compared to the challenge participants, we obtained one of the highest precision scores (PPVL = 0.52), the best PPVL rate (0.53), and a lesion detection sensitivity (SensL of 0.53)
dc.description.sponsorship
This work has been supported by DPI2020-114769RB-I00
from the Ministerio de Ciencia, Innovación y Universidades.
The authors gratefully acknowledge the support of the NVIDIA Corporation with their donation of the TITAN X GPU used
in this research. This work has been also supported by ICREA
Academia program
dc.format.mimetype
application/pdf
dc.language.iso
eng
dc.publisher
Frontiers Media
dc.relation
DPI2020-114769RB-I00
dc.relation.isformatof
Reproducció digital del document publicat a: https://doi.org/10.3389/fnins.2022.1007619
dc.relation.ispartof
Frontiers in Neuroscience, 2022, vol. 16, art. núm. 1007619
dc.relation.ispartofseries
Articles publicats (D-ATC)
dc.rights
Attribution 4.0 International
dc.rights.uri
dc.subject
dc.title
Improving the detection of new lesions in multiple sclerosis with a cascaded 3D fully convolutional neural network approach
dc.type
info:eu-repo/semantics/article
dc.rights.accessRights
info:eu-repo/semantics/openAccess
dc.type.version
info:eu-repo/semantics/publishedVersion
dc.identifier.doi
dc.type.peerreviewed
peer-reviewed
dc.relation.FundingProgramme
dc.identifier.eissn
1662-453X