guest ::
| Home > Workflow collections > In process > NeuroFocusNet: An Attention-Enhanced 3-D U-Net for Multimodal MRI Brain Tumor Segmentation |
| Home > Workflow collections > In process > NeuroFocusNet: An Attention-Enhanced 3-D U-Net for Multimodal MRI Brain Tumor Segmentation |
| Journal Article | FZJ-2026-04335 |
; ; ; ; ;
2026
IEEE
New York, NY
This record in other databases:
Please use a persistent id in citations: doi:10.1109/ACCESS.2026.3728214
Abstract: Manual delineation is time-consuming, and inter-reader variability is high, making accuratedelineation of glioma subregions in multimodal magnetic resonance imaging (MRI) important for treatmentplanning and longitudinal assessment. Current automatic techniques have limitations in identifying smallenhancing regions, maintaining irregular tumor boundaries, and maintaining performance in the eventof changes in image quality or input availability. This study proposes a 3D U-Net-based segmentationframework, NeuroFocusNet, which synchronizes spatial attention, channel recalibration, and attention-gatedskip connections within a single volumetric encoder-decoder model. The framework also features intensitypreprocessing using standardization, tumor-biased patch sampling, and a composite loss function comprisingDice, cross-entropy, focal, and boundary-aware loss terms. On the BraTS 2023 dataset, NeuroFocusNetachieved Dice scores across the whole tumor (WT), tumor core (TC), and enhancing tumor (ET) regionsof 0.9268, 0.9081, and 0.8707, respectively, with corresponding mean Hausdorff-95 distances of 1.68 mm,1.36 mm, and 2.10 mm, respectively. A performance reduction was demonstrated when adding simulatedGaussian noise to the input, and was further demonstrated when a modality mask was applied duringinference. Furthermore, 27 randomly selected cases were submitted to 3 different neuroradiologists for apreliminary evaluation of anatomical plausibility and correction requirements. This reader study is not meantto be a prospective or multicentre clinical validation of the framework. The results are encouraging whenconsidering the feasibility of using NeuroFocusNet as a technically promising segmentation framework,and the need for externally controlled benchmarking, multicentre assessment, and prospective clinicalassessment.
; 
; Article Processing Charges ; Clarivate Analytics Master Journal List ; Current Contents - Electronics and Telecommunications Collection ; Current Contents - Engineering, Computing and Technology ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF < 5 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection
|