Hard Spatial Gating for Precision-Driven Brain Metastasis Segmentation: Addressing the Over-Segmentation Paradox in Deep Attention Networks

• URL: http://arxiv.org/abs/2511.22606v1
• Date: Thu, 27 Nov 2025 16:41:27 GMT
• Title: Hard Spatial Gating for Precision-Driven Brain Metastasis Segmentation: Addressing the Over-Segmentation Paradox in Deep Attention Networks
• Abstract summary: We introduce the Spatial Gating Network (SG-Net), a precision-first architecture employing hard spatial gating mechanisms.<n> SG-Net enforces strict feature selection to aggressively suppress background artifacts while preserving tumor features.<n>These findings establish hard spatial gating as a robust solution for precision-driven lesion detection.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Brain metastasis segmentation in MRI remains a formidable challenge due to diminutive lesion sizes (5-15 mm) and extreme class imbalance (less than 2% tumor volume). While soft-attention CNNs are widely used, we identify a critical failure mode termed the "over-segmentation paradox," where models achieve high sensitivity (recall > 0.88) but suffer from catastrophic precision collapse (precision < 0.23) and boundary errors exceeding 150 mm. This imprecision poses significant risks for stereotactic radiosurgery planning. To address this, we introduce the Spatial Gating Network (SG-Net), a precision-first architecture employing hard spatial gating mechanisms. Unlike traditional soft attention, SG-Net enforces strict feature selection to aggressively suppress background artifacts while preserving tumor features. Validated on the Brain-Mets-Lung-MRI dataset (n=92), SG-Net achieves a Dice Similarity Coefficient of 0.5578 +/- 0.0243 (95% CI: 0.45-0.67), statistically outperforming Attention U-Net (p < 0.001) and ResU-Net (p < 0.001). Most critically, SG-Net demonstrates a threefold improvement in boundary precision, achieving a 95% Hausdorff Distance of 56.13 mm compared to 157.52 mm for Attention U-Net, while maintaining robust recall (0.79) and superior precision (0.52 vs. 0.20). Furthermore, SG-Net requires only 0.67M parameters (8.8x fewer than Attention U-Net), facilitating deployment in resource-constrained environments. These findings establish hard spatial gating as a robust solution for precision-driven lesion detection, directly enhancing radiosurgery accuracy.

Related papers

• A Few Neurons Reveal When LLMs Misuse Tools: Sparse Detection and Selective Steering for Reliable Tool Use [28.57781785937644]
  We introduce PRISMS (Probing Representations In Support of Monitoring and Steering), a closed-loop framework that shares a failure-specific neuron basis between sparse detection and activation.<n>Across six models, PRISMS reduces pooled over-calling rate by 80% while increasing tool-required accuracy by 14.2 percentage points.
  arXiv  Detail & Related papers  (2026-07-31T19:03:44Z)
• RadiomicNet: A Hybrid Radiomics-Guided Lightweight Architecture for Interpretable Medical Image Segmentation [0.0]
  We propose RadiomicNet, a novel two-stream hybrid architecture that enhances standard deep learning by integrating handcrafted radiomics features directly into the segmentation learning process.<n>We show that RadiomicNet achieves a Dice Similarity Coefficient (DSC) of 0.763 +/- 0.231 on the Breast Ultrasound Images (BUSI) dataset and 0.854 +/- 0.112 on Kvasir-SEG, with only 3.27M parameters, 9.5x fewer than standard U-Net and 4.3x fewer than U-KAN.
  arXiv  Detail & Related papers  (2026-07-02T13:54:33Z)
• Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis [26.831715552066694]
  The lateral ventricle choroid plexus (LVCP) is gaining recognition as a key imaging biomarker for multiple sclerosis (MS) related to physical disability and neuroinflammation.<n>This research aims to develop a SwinUNETR-driven pipeline that automatically segment the LVCP in MS from both standalone and multi-modal MRI inputs.
  arXiv  Detail & Related papers  (2026-06-02T12:32:43Z)
• Cross-Stage Attention Multi-Expert Network for Radiologist-Inspired Breast Ultrasound Diagnosis [6.727825549527392]
  This paper proposes the Cross-Stage Attention Mixture-of-Experts Network (CSA-MoE-Net) to improve feature representation and classification accuracy.<n>It adopts a Cross-Stage Attention-enhanced ResNet-18 as the backbone, in which the Cross-Stage Attention module adaptively recalibrates multi-level features.<n> Experiments on a balanced dataset of 2,129 breast ultrasound images show that, averaged over 20 independent runs, the model achieves an accuracy of 96.33%, precision of 94.09%, recall of 98.53%, F1-score of 96.25%, and
  arXiv  Detail & Related papers  (2026-05-25T07:20:13Z)
• Annotation-free deep learning for detection and segmentation of fetal germinal matrix-intraventricular hemorrhage in brain MRI [35.75434967398725]
  Prenatal germinal matrix-intraventricular hemorrhage (GMH-IVH) is a leading cause of infant mortality and neurodevelopmental impairment.<n>Deep learning models offer potential for automation but typically require large annotated datasets.<n>FreeHemoSeg was developed and trained using pseudo GMH-IVH images synthesized from normal fetal data.
  arXiv  Detail & Related papers  (2026-05-10T14:39:30Z)
• Improving Generalization of Deep Learning for Brain Metastases Segmentation Across Institutions [5.4585656405659195]
  The goal of this work is to create a domain adaptation framework that will allow for BM segmentation to be used across multiple institutions.<n>We propose a VAE-MMD preprocessing pipeline that combines variational autoencoders (VAE) with maximum mean discrepancy (MMD) loss.
  arXiv  Detail & Related papers  (2026-04-01T02:25:25Z)
• An Explainable AI-Driven Framework for Automated Brain Tumor Segmentation Using an Attention-Enhanced U-Net [0.6087515951830486]
  We present a new segmentation technique based on a U-Net model augmented with executed attention gates to focus on the most significant regions of images.<n>To counter class imbalance, we employ manually designed loss functions like Dice Loss and Categorical Dice Loss, in conjunction with standard categorical cross-entropy.<n>Our approach achieved superior performance with accuracy of 0.9919, Dice coefficient of 0.9901, mean IoU of 0.9873, sensitivity of 0.9908, and specificity of 0.9974.
  arXiv  Detail & Related papers  (2026-03-24T15:42:49Z)
• Margin-Consistent Deep Subtyping of Invasive Lung Adenocarcinoma via Perturbation Fidelity in Whole-Slide Image Analysis [15.00702842825464]
  Whole-slide image classification for invasive lung adenocarcinoma subtyping remains vulnerable to real-world imaging perturbations.<n>We propose a margin consistency framework evaluated on 203,226 patches from 143 whole-slide images.<n>Our approach achieves robust feature-logit space alignment measured by Kendall correlations of 0.88 during training and 0.64 during validation.
  arXiv  Detail & Related papers  (2026-02-27T20:47:15Z)
• Towards Reliable Pediatric Brain Tumor Segmentation: Task-Specific nnU-Net Enhancements [13.880771870415616]
  We present an advanced nnU-Net framework tailored for BraTS 2025 Task-6 (PED), the largest public dataset of pre-treatment pediatric high-grade gliomas.
  arXiv  Detail & Related papers  (2025-11-01T08:33:21Z)
• Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation [30.94379425064039]
  We introduce the Predictive-Corrective (PC) paradigm, a framework that decouples the modeling task to fundamentally accelerate learning.<n>PCambaNet is composed of two synergistic modules. First, the Predictive Prior Module (PPM) generates a coarse approximation at low computational cost.<n>Next, the Corrective Residual Network (CRN) learns to model the residual error, focusing the network's full capacity on refining these challenging regions.
  arXiv  Detail & Related papers  (2025-10-17T08:51:33Z)
• DRBD-Mamba for Robust and Efficient Brain Tumor Segmentation with Analytical Insights [54.87947751720332]
  Accurate brain tumor segmentation is significant for clinical diagnosis and treatment.<n>Mamba-based State Space Models have demonstrated promising performance.<n>We propose a dual-resolution bi-directional Mamba that captures multi-scale long-range dependencies with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-10-16T07:31:21Z)
• MobileDenseAttn:A Dual-Stream Architecture for Accurate and Interpretable Brain Tumor Detection [0.0]
  We introduce MobileDenseAttn, a fusion model of MobileNetV2 and DenseNet201.<n>MobileDenseAttn is trained on an augmented dataset of 6,020 MRI scans representing glioma, meningioma, pituitary tumors, and normal samples.<n>It provides a training accuracy of 99.75%, a testing accuracy of 98.35%, and a stable F1 score of 0.9835.
  arXiv  Detail & Related papers  (2025-08-22T13:24:38Z)
• HANS-Net: Hyperbolic Convolution and Adaptive Temporal Attention for Accurate and Generalizable Liver and Tumor Segmentation in CT Imaging [2.7205074719266062]
  Accurate liver and tumor segmentation on abdominal CT images is critical for reliable diagnosis and treatment planning.<n>We introduce Hyperbolic-convolutions Adaptive-temporal-attention with Neural-representation and Synaptic-plasticity Network (HANS-Net)<n>HANS-Net combines hyperbolic convolutions for hierarchical geometric representation, a wavelet-inspired decomposition module for multi-scale texture learning, and an implicit neural representation branch.
  arXiv  Detail & Related papers  (2025-07-15T13:56:37Z)
• Cancer-Net PCa-Seg: Benchmarking Deep Learning Models for Prostate Cancer Segmentation Using Synthetic Correlated Diffusion Imaging [65.83291923029985]
  Prostate cancer (PCa) is the most prevalent cancer among men in the United States, accounting for nearly 300,000 cases, 29% of all diagnoses and 35,000 total deaths in 2024.<n>Traditional screening methods such as prostate-specific antigen (PSA) testing and magnetic resonance imaging (MRI) have been pivotal in diagnosis, but have faced limitations in specificity and generalizability.<n>We employ several state-of-the-art deep learning models, including U-Net, SegResNet, Swin UNETR, Attention U-Net, and LightM-UNet, to segment prostate glands from a 200 CDI$
  arXiv  Detail & Related papers  (2025-01-15T22:23:41Z)
• Exploiting Precision Mapping and Component-Specific Feature Enhancement for Breast Cancer Segmentation and Identification [0.0]
  We propose novel Deep Learning (DL) frameworks for breast lesion segmentation and classification.<n>We introduce a precision mapping mechanism (PMM) for a precision mapping and attention-driven LinkNet (PMAD-LinkNet) segmentation framework.<n>We also introduce a component-specific feature enhancement module (CSFEM) for a component-specific feature-enhanced classifier (CSFEC-Net)
  arXiv  Detail & Related papers  (2024-07-03T06:40:26Z)
• MTS-Net: Dual-Enhanced Positional Multi-Head Self-Attention for 3D CT Diagnosis of May-Thurner Syndrome [31.032250821769747]
  May-Thurner Syndrome (MTS) is a vascular condition that affects over 20% of the population and significantly increases the risk of iliofemoral deep venous thrombosis.<n> Accurate and early diagnosis of MTS using computed tomography (CT) remains a clinical challenge due to the subtle anatomical compression and variability across patients.<n>We propose MTS-Net, an end-to-end 3D deep learning framework designed to capture spatial-temporal patterns from CT volumes for reliable MTS diagnosis.
  arXiv  Detail & Related papers  (2024-06-07T06:51:09Z)
• SEDNet: Shallow Encoder-Decoder Network for Brain Tumor Segmentation [0.0]
  This paper proposes a tumor segmentation framework including a novel shallow encoder and decoder network named SEDNet. The highlights of SEDNet include sufficiency in hierarchical convolutional downsampling and selective skip mechanism for cost-efficient and effective brain tumor semantic segmentation. With about 1.3 million parameters and impressive performance in comparison to the state-of-the-art, SEDNet(X) is shown to be computationally efficient for real-time clinical diagnosis.
  arXiv  Detail & Related papers  (2024-01-24T11:57:25Z)
• Weakly supervised segmentation of intracranial aneurysms using a novel 3D focal modulation UNet [0.5106162890866905]
  We propose FocalSegNet, a novel 3D focal modulation UNet, to detect an aneurysm and offer an initial, coarse segmentation of it from time-of-flight MRA image patches. We trained and evaluated our model on a public dataset, and in terms of UIA detection, our model showed a low false-positive rate of 0.21 and a high sensitivity of 0.80.
  arXiv  Detail & Related papers  (2023-08-06T03:28:08Z)
• EMT-NET: Efficient multitask network for computer-aided diagnosis of breast cancer [58.720142291102135]
  We propose an efficient and light-weighted learning architecture to classify and segment breast tumors simultaneously. We incorporate a segmentation task into a tumor classification network, which makes the backbone network learn representations focused on tumor regions. The accuracy, sensitivity, and specificity of tumor classification is 88.6%, 94.1%, and 85.3%, respectively.
  arXiv  Detail & Related papers  (2022-01-13T05:24:40Z)
• Neural Network Virtual Sensors for Fuel Injection Quantities with Provable Performance Specifications [71.1911136637719]
  We show how provable guarantees can be naturally applied to other real world settings. We show how specific intervals of fuel injection quantities can be targeted to maximize robustness for certain ranges.
  arXiv  Detail & Related papers  (2020-06-30T23:33:17Z)

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.