arXiv Machine Learning
5d ago
A small HER2 reader for routine H&E slides: real-world deployment
arXiv:2610. 40662v1 Announce Type: cross Abstract: HER2 status decides who receives HER2-targeted therapy.
SWIFT-Cell: Segmentation Without Iterative Flow Tracking
Related stories
arXiv AI
Sep 4
TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation Models
TAP-Path is a task‑adaptive compression framework that restructures a pretrained Virchow2 encoder for histopathology. It selectively removes transformer blocks, prunes patch tokens, and adds a lightweight gated task head, reducing parameters by 24.96% and FLOPs by 35.20% while maintaining high accuracy on a 32‑class benchmark. The method achieves competitive test metrics and improved rare‑class performance, with strong external validation on CPTAC samples.
arXiv AI
Aug 5
MalariAI: A Label-Resilient Decoupled Framework for Annotation-Agnostic Cell Segmentation and Explainable Stage Classification in Dense Malaria Blood Smears
arXiv:2607. 00385v2 Announce Type: replace-cross Abstract: Automated malaria diagnosis from blood smear microscopy is a critical global health AI challenge; expert scarcity remains the primary diagnostic bottleneck.
arXiv Computer Vision
2d ago
Anchored Slice Propagation with Boundary Transport for 3D CT Segmentation from Three Orthogonal Annotated Slices
arXiv:2611.05693v1 Announce Type: new Abstract: Sli2Vol propagates a binary mask through affinities between adjacent slices, but an error can persist because each prediction becomes the input to the...
arXiv Computer Vision
Oct 28
Readout and Operating-Point Sensitivity in Event-Stream Candidate Selection
The paper evaluates how readout settings and operating points affect event-stream candidate selection in event-triggered recording. Using 520 DailyDVS‑200 clips and 47 participants, the authors compare several encoder configurations—including DINO‑CLS, patch mean, and MobileNetV3‑Small—across different accumulation durations and view counts, reporting metrics such as target capture, false triggers, and partial AUC. The study finds that lightweight baselines and specific operating points significantly influence performance, while no clear advantage is observed for the JEPA‑specific method.
arXiv AI
Oct 21
When PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text Embedders
The paper investigates when post‑training quantization (PTQ) calibration helps or hurts text embedders, focusing on the amount of calibration (dose) and whether to calibrate at all. Across three models and 161 calibration runs at 4‑bit weight quantization, the effect ranges from significant gains to catastrophic degradation, driven mainly by the functional displacement of the quantized model. A validation‑gated abstention rule is proposed that avoids harmful calibrations while capturing most benefits, highlighting the trade‑off between safety and opportunity.
arXiv Computer Vision
Oct 12
CoRef-DETR: Decoupled Global Context and Selective Boundary-Category Refinement for Underwater Instance Segmentation
CoRef-DETR is a compact detection transformer designed for underwater instance segmentation, addressing errors from context, boundaries, and categories. It uses a decoupled global context detector with 33.4 M parameters, a lightweight boundary refiner of 47.7 k parameters, and a crop‑probe category branch that revises up to three mask categories per image. The method achieves state‑of‑the‑art mask AP on multiple UIIS datasets and runs in 26–37 ms on an NVIDIA T4 GPU, outperforming larger models.
arXiv Machine Learning
Sep 21
Detection is solved, delineation is not: what governs tooth segmentation on panoramic radiographs
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.
arXiv Computer Vision
Oct 27
NucShare: A Shared-Decoder Framework for Lightweight Nuclei Instance Segmentation
arXiv:2609.35203v2 Announce Type: replace Abstract: Nuclei instance segmentation underpins quantitative pathology, yet its accuracy currently comes at a large parameter cost, and both the encoder and...
arXiv Computer Vision
Sep 23
Initialization and Stopping Tolerance in CPU Dermoscopic Segmentation
The study investigates how contour initialization and stopping tolerance jointly influence active‑contour segmentation performance on dermoscopic images. Using scikit‑image’s Chan‑Vese implementation on a resized ISIC 2017 dataset, the authors compare Otsu, checkerboard, disk, and Otsu‑initialized contours under default and tighter level‑set tolerances. Results show that Otsu initialization improves mean Dice scores at default tolerance but the advantage diminishes with tighter tolerance, and that evaluation metrics can vary across lesion size strata, underscoring the need to report initial fields, tolerances, and iteration counts.
arXiv Computation and Language
Sep 15
Occlusal Geometry in Closed Form for Orthodontic Report Generation
arXiv:2609.13237v1 Announce Type: cross Abstract: Orthodontic report generation from intraoral data is normally cast as multimodal captioning, yet the released Bite2Text scan pairs are supplied alrea...
arXiv AI
Aug 5
A Deployment-Friendly Foundational Framework for Efficient Computational Pathology
arXiv:2602. 14010v2 Announce Type: replace-cross Abstract: Pathology foundation models (PFMs) generalize well across computational pathology tasks but remain costly for gigapixel whole-slide image analysis.