arXiv:2607. 26090v1 Announce Type: cross Abstract: Glioma grading from tumor contours is often treated as a pixel problem even when the signal of interest is shape.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2512. 14937v2 Announce Type: replace-cross Abstract: Gliomas are the most common malignant brain tumors in adults and are among the most lethal.
arXiv:2607. 22749v1 Announce Type: cross Abstract: Tracking residual tumor after surgery is essential for catching recurrence early, but automating post-operative glioma segmentation remains a difficult task.
ME^2FDiff is a single‑model architecture for post‑treatment glioma segmentation that uses an attention‑conditioned spectral diffusion block to refine the bottleneck and a multiscale expert‑enhanced feature block to fuse intermediate encoder scales. On the BraTS 2024 post‑treatment dataset it outperforms all single‑model baselines and a three‑expert ensemble, achieving 91.23% Dice and 84.52% IOU for the whole tumor while using roughly one‑third the inference cost of the ensemble. The design eliminates the need for auxiliary losses and large ensembles, demonstrating that a compact network can match or exceed state‑of‑the‑art performance with fewer parameters.
VGG16-MCA UNet is a hybrid neural network that combines an ImageNet‑pretrained VGG16 encoder with a decoder enhanced by a Multi‑Channel Attention module, trained using Focal Tversky loss to address class imbalance. The model was evaluated as a 2‑D, FLAIR‑only whole‑tumor segmenter on BraTS 2020 and LGG datasets, achieving a pixel‑level Dice of 95.10 % on BraTS and 88.32 % on LGG in a 5‑fold cross‑validation setting. Inference time is 66.32 ms per 256×256 slice on a single RTX 2060, only slightly slower than a VGG16‑UNet without attention. whyItMatters":"The study provides a reproducible 2‑D FLAIR baseline for whole‑tumor segmentation, demonstrating high Dice scores and detailed reporting of training and evaluation protocols."
arXiv:2610.34529v1 Announce Type: cross Abstract: Background/Objectives: Rapid differentiation of ischemic and hemorrhagic stroke subtypes is vital for acute management. Although current deep learnin...
Automated segmentation of post-treatment glioma from MRI is essential for accurate diagnosis and treatment planning, yet remains difficult. Surgery and chemoradiotherapy cause structural changes in br...