The paper introduces RABR-Net, a two‑stage framework that refines biomedical image segmentation boundaries by combining multiple uncertainty measures into a boundary‑aware representation. A gated residual refiner uses this representation to selectively correct uncertain boundary pixels while preserving confident regions, leading to modest but statistically significant improvements in Dice, Boundary Dice, and HD95 metrics on a held‑out test set. Qualitative results show the refiner focuses on uncertain cytoplasm and nucleus boundaries, though calibration does not automatically improve.
By Anima Kujur
arXiv:2610.08570v1 Announce Type: new
Abstract: Handcrafted preprocessing is widely employed in automated dermoscopic analysis to suppress imaging artifacts and enhance lesion visibility. Nevertheles...
By Truong Viet Vu, Nguyen Chi Hai, Nguyen Phuc Nguyen, Ngo Hoang Tu, Vo Nguyen Quoc Bao, Nguyen Thai Anh
arXiv:2609.28327v1 Announce Type: new
Abstract: We present LightMIS, a scalable family of ultra-lightweight convolutional networks for 2D binary medical image segmentation without a learned stage-wis...
By Andrei Arhire, Mihaela-Elena Breab\u{a}n, Radu Timofte
arXiv:2606. 03069v1 Announce Type: cross Abstract: Generalized segmentation of medical images prevents performance degradation when different imaging devices and clinical protocols are used across multiple domains.
By Aqsa Naseer, Maryam Bibi, Syeda Samiya Urooj, Muhammad Khurram Shahzad
STRADAViT is a self‑supervised continued‑pretraining framework that adapts Vision Transformer (ViT) backbones for radio‑astronomy image analysis. It curates mixed‑survey data, generates radio‑astronomy‑aware training views, and initializes encoders with ViT‑MAE, optionally adding register tokens. Evaluations on three morphology benchmarks (MiraBest, LoTSS DR2, and Radio Galaxy Zoo) show that a register‑based two‑stage checkpoint improves linear‑probe Macro‑F1 scores over the ViT‑MAE baseline and enhances fine‑tuning on MiraBest and RGZ DR1, though performance on LoTSS DR2 fine‑tuning declines; these differences are statistically significant.
By Andrea DeMarco, Ian Fenech Conti, Hayley Camilleri, Ardiana Bushi, Simone Riggi
arXiv:2604. 15271v3 Announce Type: replace-cross Abstract: Reliable uncertainty estimation is critical for medical image segmentation, where automated contours feed downstream quantification and clinical decision support.
By Tianhao Fu, Austin Wang, Charles Chen, Roby Aldave-Garza, Yucheng Chen
arXiv:2608.28706v1 Announce Type: new
Abstract: ViT detectors fix a uniform token grid before any learned stage. A native-resolution aerial detector must then choose between resolving few-pixel objec...
By Khayrul Islam
The study evaluates automatic tooth segmentation on panoramic radiographs using a large annotated corpus of 1,422 images and 42,142 tooth polygons. It finds that increasing input resolution improves boundary precision (mask mAP50‑95 rises from 0.656 to 0.717) while detection performance remains unchanged, and that architectural changes have minimal impact on in‑domain accuracy. Targeted interventions such as LoRA adaptation, promptable foundation models, and anatomical label assignment provide negligible gains, indicating that resolution and acquisition diversity should be prioritized over model novelty.
By Muhammad Rehan, Moaz Amjad, Syed Danial Ahmed, Mariam Adnan, Haider Ali
arXiv:1812.00877v2 Announce Type: replace-cross
Abstract: Segmentation of skin lesion boundaries in dermoscopic imaging is an important prerequisite step for computer-aided diagnosis of malignant mel...
By Glib Kechyn
arXiv:2609.09634v1 Announce Type: new
Abstract: Large networks and ensembles often lead medical image segmentation challenges, but their storage and inference demands complicate deployment. We presen...
By Giorgi Nikvashvili, Hanxue Gu, Jie Bao, Kang Wang, Yang Yang
The study investigates how the choice of annotation used to set a segmentation threshold influences retinal vessel segmentation performance. Using all 28 CHASE DB1 images and two human observers, the authors fit random forests and Extra Trees models, then compare five threshold policies—including fixed, observer‑tuned, mean‑observer, and maximin tuning—on the same score maps. Results show that maximin tuning alters thresholds in most fits but yields negligible changes in worst‑observer Dice scores, suggesting no accuracy advantage in this cohort.
By Wenhao Xu, Yixian Kong, Ting Pan, Changwei Wang, Feilong Wang, Rongtao Xu
Exemplar is a few‑shot segmentation method that combines a frozen DINOv3 backbone with a fixed bank of classical native‑resolution filter responses in a single lightweight head. Trained only from support masks, it achieves a mean foreground intersection‑over‑union of 0.782 across eleven biomedical imaging datasets, outperforming either component alone and surpassing five other few‑shot methods in 54 of 55 comparisons. With a single annotated mask, Exemplar reaches 0.703, higher than a from‑scratch nnU‑Net trained on the same mask, and while nnU‑Net eventually overtakes it with eight masks, it requires 16–77× longer to fit.
By Michal Pr\r{u}\v{s}ek, Adam Novoz\'amsk\'y, Filip \v{S}roubek