Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation

• URL: http://arxiv.org/abs/2608.16377v1
• Date: Mon, 17 Aug 2026 10:30:51 GMT
• Title: Adaptive Post-Processing Drives Instance-Level Detection in Stroke Lesion Segmentation
• Abstract summary: In our ISLES'26 submission, we found that closing this gap mattered far more in post-processing than in architecture design.<n>Our Volume-Conditioned Adaptive Post-Processing scheme adjusts component-size thresholds to each case's predicted lesion burden.<n>A resolution-aware attention architecture (Viola2Plus) designed for small-lesion segmentation shows why the distinction matters.
• Score: 0.9530026127073782
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Instance-level lesion detection has been an increasingly larger focal point in medical image segmentation besides the more standard voxel-level overlap. Still, most pipelines are trained and post-processed for voxel overlap alone. In particular, the mismatch is most pronounced for small lesions, where a near-miss prediction---substantial overlap that falls just short of the instance-matching threshold---scores the same as a complete miss. In our ISLES'26 submission, we found that closing this gap mattered far more in post-processing than in architecture design. Our Volume-Conditioned Adaptive Post-Processing (VCAP) scheme adjusts component-size thresholds to each case's predicted lesion burden, improving Lesion-F1 by 0.032 (unbiased cross-fold estimate)---approximately 6 times larger than any architectural change we tested. A resolution-aware attention architecture (Viola2Plus), designed for small-lesion segmentation, shows why the distinction matters: it left small-lesion Dice unchanged but raised small-lesion detection rate by 3.7\%, a real effect voxel-overlap metrics alone would have missed. Under 5-fold cross-validation on the 1,453-case training set, our post-processed two-architecture ensemble achieves Dice 0.651 and Lesion-F1 0.614, versus 0.644 and 0.573 for the unprocessed single-model baseline.

Related papers

• Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRI [0.0]
  Deep networks trained on structural MRI for Alzheimer's disease often reach reasonable accuracy while attending to anatomically irrelevant regions.<n>We use FastSurfer segmentations as an anatomical reference.<n>We adapt a CLIP-style image and organize ADNIMERGE variables along a label-leakage spectrum.
  arXiv  Detail & Related papers  (2026-09-14T17:13:12Z)
• Bridging Vision Foundation Model Priors with CLIP for Spatial-aware Few-shot Anomaly Detection in Medical Images [48.646448077284276]
  We propose Spatial-FAD, a framework for effective few-shot medical anomaly detection.<n>It improves lesion localization by combining VFM spatial priors with CLIP semantics.<n>Our method achieves an average improvement of over 11.4% in Dice score and 1.8% in AUC.
  arXiv  Detail & Related papers  (2026-09-11T05:21:01Z)
• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• YOLO26-RD: An End-to-End Road Damage Detection Network With Learnable Contrast Enhancement and Edge-Guided Downsampling [2.274915755738124]
  We present YOLO26-RD, an end-to-end (NMS-free) detector built on YOLO26 with two lightweight novel modules.<n>We subject the design to a data-first audit on a 7,618-image road-survey dataset.<n>Our best screening configuration reaches 0.787 mAP50 on the validation split versus a 0.771 project baseline.
  arXiv  Detail & Related papers  (2026-08-16T12:36:12Z)
• Multi-Granularity 3D Kidney Lesion Characterization from CT Volumes [11.709061205652871]
  We reformulate kidney CT characterization as a per-lesion set-prediction task.<n>We curated 2,619 CT volumes from 788 patients at one academic medical center.<n>We propose textbfLesionDETR, a DETR-style architecture with size-distance Hungarian matching.
  arXiv  Detail & Related papers  (2026-06-03T02:28:57Z)
• Magnification-Invariant Image Classification via Domain Generalization and Stable Sparse Embedding Signatures [0.0]
  Magnification shift is a major obstacle to robust histopathology classification, because models trained on one scale often generalize poorly to another.<n>We evaluated this problem on the BreaKHis dataset using a strict patient-disjoint leave-one-magnification-out protocol.
  arXiv  Detail & Related papers  (2026-04-28T16:26:14Z)
• Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI [0.0]
  We propose a unified objective function, termed CATMIL, that augments the base segmentation loss with two auxiliary supervision terms operating at different levels.<n>We evaluate the proposed objective on the MSLesSeg dataset using a consistent nnU-Net framework and 5-fold cross-validation.<n>Results show that CATMIL achieves the most balanced performance across segmentation accuracy, lesion detection, and error control.
  arXiv  Detail & Related papers  (2026-04-09T09:15:10Z)
• Hybrid Gated Flow (HGF): Stabilizing 1.58-bit LLMs via Selective Low-Rank Correction [0.766310831583367]
  Hybrid Gated Flow (HGF) is a dual-stream architecture that couples a 1.58-bit ternary backbone with a learnable, low-rank FP16 correction path.<n>We show that HGF 5.4 achieves a validation loss of 0.9306 compared to BitNet's 1.0294, recovering approximately 55% of the quality gap between pure ternary quantization and the FP16 baseline.
  arXiv  Detail & Related papers  (2026-02-05T03:47:17Z)
• When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models [55.444604697848426]
  Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF.<n>The standard objective used in reward modeling is the Bradley-Terry (BT) loss, which learns from pairwise data consisting of a pair of chosen and rejected responses.<n>We propose NormBT, an adaptive pair-wise normalization scheme that balances representation-driven effects and focuses learning signals on prediction error.
  arXiv  Detail & Related papers  (2025-12-06T08:15:37Z)
• Cancer-Net PCa-MultiSeg: Multimodal Enhancement of Prostate Cancer Lesion Segmentation Using Synthetic Correlated Diffusion Imaging [55.62977326180104]
  Current deep learning approaches for prostate cancer lesion segmentation achieve limited performance.<n>We investigate synthetic correlated diffusion imaging (CDI$s$) as an enhancement to standard diffusion-based protocols.<n>Our results establish validated integration pathways for CDI$s$ as a practical drop-in enhancement for PCa lesion segmentation tasks.
  arXiv  Detail & Related papers  (2025-11-11T04:16:12Z)
• Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning [48.11265601808718]
  We show that standard self-supervised contrastive learning objectives implicitly approximate a supervised variant we call the negatives-only supervised contrastive loss (NSCL)<n>We prove that the gap between the CL and NSCL losses vanishes as the number of semantic classes increases, under a bound that is both label-agnostic and architecture-independent.
  arXiv  Detail & Related papers  (2025-06-04T19:43:36Z)
• MAPPING: Model Average with Post-processing for Stroke Lesion Segmentation [57.336056469276585]
  We present our stroke lesion segmentation model based on nnU-Net framework, and apply it to the Anatomical Tracings of Lesions After Stroke dataset. Our method took the first place in the 2022 MICCAI ATLAS Challenge with an average Dice score of 0.6667, Lesion-wise F1 score of 0.5643, Simple Lesion Count score of 4.5367, and Volume Difference score of 8804.9102.
  arXiv  Detail & Related papers  (2022-11-11T14:17:04Z)
• Inception Convolution with Efficient Dilation Search [121.41030859447487]
  Dilation convolution is a critical mutant of standard convolution neural network to control effective receptive fields and handle large scale variance of objects. We propose a new mutant of dilated convolution, namely inception (dilated) convolution where the convolutions have independent dilation among different axes, channels and layers. We explore a practical method for fitting the complex inception convolution to the data, a simple while effective dilation search algorithm(EDO) based on statistical optimization is developed.
  arXiv  Detail & Related papers  (2020-12-25T14:58:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.