BG-YOLO11s: Boundary-Guided YOLO11 with Bézier Contour Augmentation for Brain Tumour Segmentation in T1-CE MRI.
Authors
Affiliations (5)
Affiliations (5)
- Department of Computer Engineering, Kırıkkale University, Kırıkkale 71450, Türkiye.
- Department of Electronics and Information Technologies, Faculty of Architecture and Engineering, Nakhchivan State University, AZ 7012 Nakhchivan, Azerbaijan.
- Department of Computer Engineering, İstanbul Topkapı University, İstanbul 34394, Türkiye.
- Department of Computer Engineering, Iğdır University, Iğdır 76000, Türkiye.
- Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Fenerbahce University, Istanbul 34758, Türkiye.
Abstract
<b>Background/Objectives:</b> Accurate delineation of brain tumours on contrast-enhanced MRI remains difficult because lesions can be small, irregular, and weakly separated from adjacent tissue. This study developed BG-YOLO11s, a boundary-guided single-stage instance-segmentation model for T1 contrast-enhanced MRI. <b>Methods:</b> The public Figshare/Cheng dataset, comprising 3064 slices from 233 patients, was converted to YOLO polygon annotations and evaluated using a fixed 70/15/15 image-level split (2144/459/461 slices). Because patient identifiers were not retained in the exported image-and-polygon data, the split was not guaranteed to be patient-disjoint. Bézier Contour Augmentation generated two contour-perturbed training samples per original slice while leaving validation and test data unchanged. BG-YOLO11s extended YOLO11s-seg with dilated context aggregation in the backbone, boundary-enhanced feature fusion in the neck, and a prototype refinement module with differentiable boundary-aware supervision in the segmentation head. <b>Results:</b> In a single run on the held-out image-level test split, BG-YOLO11s achieved 92.4% precision, 88.7% recall, 94.6% mask mAP@50, 68.9% mAP@50-95, and 86.5% IoU. Relative to YOLO11s-seg, the corresponding gains were 3.8 points in mAP@50, 5.8 points in mAP@50-95, and 4.1 points in IoU. A progressive ablation produced incremental gains along the fixed module-addition sequence, but it did not isolate all component interactions or quantify run-to-run uncertainty. <b>Conclusions:</b> BG-YOLO11s improved single-run mask-overlap estimates under the present image-level benchmark. Patient-disjoint retraining, repeated-seed statistics, boundary-specific metrics, complete failure pattern auditing, and external multi-sequence validation are required before broader clinical or deployment claims can be made.