Instance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CT

• URL: http://arxiv.org/abs/2609.00447v1
• Date: Mon, 31 Aug 2026 22:38:11 GMT
• Title: Instance-Guided Report Anchoring for Text-Free 3D Abnormality Segmentation in Chest CT
• Abstract summary: We propose Instance-Guided Report Anchoring (IGRA), a model-agnostic module that preserves the correspondence between each annotated abnormality instance and the report finding that describes it.<n>IGRA improves Dice by 22.5% over the strongest image-only baseline (30.93 vs. 25.25) and is comparable to VoxTell on the single-finding subset (30.29 vs. 30.43)
• Score: 1.3890393030771435
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate 3D abnormality segmentation in chest CT requires dense spatial supervision, but obtaining expert voxel-level labels is costly. Radiology reports, however, are routinely generated during clinical interpretation and contain instance-specific descriptions that can provide additional guidance without new dense annotation. Existing vision-language grounding methods typically require report-derived findings at inference, making localization dependent on paired text and limiting each forward pass to a queried finding. We propose Instance-Guided Report Anchoring (IGRA), a model-agnostic module that preserves the correspondence between each annotated abnormality instance and the report finding that describes it. IGRA pools each instance representation and anchors it to the corresponding finding embedding during training; all text-related components are discarded at inference. We further reformulate free-text grounding on ReXGroundingCT as multi-label volumetric segmentation by merging same-category instances, allowing all abnormality categories to be predicted in one image-only forward pass. IGRA improves Dice by 22.5% over the strongest image-only baseline (30.93 vs. 25.25) and is comparable to VoxTell on the single-finding subset (30.29 vs. 30.43). Applied unchanged to four standard 3D segmentation backbones, IGRA improves Dice and hit rate across all architectures. Zero-shot evaluation on LIDC-IDRI, PleThora, and a private in-house dataset further shows consistent gains over image-only baselines.

Related papers

• Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection [52.986874008247554]
  We propose ReCAP, a language-free framework that replaces static anchors with input-conditioned visual prototypes.<n>ReCAP re-centers separated normal and abnormal prototypes for each image through a bounded gated modulation.<n>It achieves the best image-level AUROC on all zero-shot and 23 of 24 few-shot settings, and the best zero-shot pixel-level AUROC on all three segmentation datasets.
  arXiv  Detail & Related papers  (2026-08-01T04:46:55Z)
• When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment [0.5721241882795979]
  Graph-text retrieval typically maps a graph and its description to a single embedding, even when a query concerns only one semantic aspect.<n>We show that architectural channelization, not necessarily semantic routing, can be resolved.
  arXiv  Detail & Related papers  (2026-07-29T23:49:37Z)
• Open-Ended CT Volume Segmentation with Weak Supervision from Language [60.690380060745134]
  We introduce a method for training a text-conditioned segmentation model for CT scans, which combines voxel-level supervision with coarse but scalable slice-level supervision from reports.<n>We finetune a general-purpose 2D image segmentation model, SAM3, with standard segmentation losses from strongly labeled data and with a slice-level classification loss from the extracted weak supervision.<n>Our results on the ReXGroundingCT dataset illustrate that this strategy improves the segmentation dice score: from an 8% relative gain when there are 1000 fully labeled volumes to 22% when there are 250 fully labeled volumes.
  arXiv  Detail & Related papers  (2026-07-28T15:29:12Z)
• GLINT: Sparsely Gated Vision-Language Alignment for Fine-Grained Radiology Representations [1.2679579476597642]
  We present GLINT (Gated Language-Image alignmeNT), a framework that explicitly models this sparse correspondence.<n> GLINT enables zero-shot classification, grounding, and segmentation from free-text queries.<n>It is the first to demonstrate zero-shot segmentation on 3D CT volumes without mask supervision.
  arXiv  Detail & Related papers  (2026-06-02T05:40:51Z)
• SegRAG: Training-Free Retrieval-Augmented Semantic Segmentation [13.665861251747144]
  SegRAG is a training-free retrieval-augmented segmentation framework.<n>It grounds SAM3 with class-specific point prompts derived from a curated DINOv3 feature bank.<n>On four standard benchmarks, SegRAG consistently outperforms the text-only baseline.
  arXiv  Detail & Related papers  (2026-05-17T19:51:32Z)
• Exploring Efficient Open-Vocabulary Segmentation in the Remote Sensing [55.291219073365546]
  Open-Vocabulary Remote Sensing Image (OVRSIS) is an emerging task that adapts Open-Vocabulary (OVS) to the remote sensing (RS) domain.<n>textbfRSKT-Seg is a novel open-vocabulary segmentation framework tailored for remote sensing.<n> RSKT-Seg consistently outperforms strong OVS baselines by +3.8 mIoU and +5.9 mACC, while achieving 2x faster inference through efficient aggregation.
  arXiv  Detail & Related papers  (2025-09-15T15:24:49Z)
• ReXGroundingCT: A 3D Chest CT Dataset for Segmentation of Findings from Free-Text Reports [23.716614736159034]
  We introduce ReXGroundingCT, the first publicly available dataset linking free-text findings to pixel-level 3D segmentations in chest CT scans.<n>The dataset includes 3,142 non-contrast chest CT scans paired with standardized radiology reports from CT-RATE.<n>About 79% of findings are focal abnormalities and 21% are non-focal.
  arXiv  Detail & Related papers  (2025-07-29T17:27:15Z)
• NSegment : Label-specific Deformations for Remote Sensing Image Segmentation [10.585761836168409]
  Labeling errors in remote sensing (RS) image segmentation datasets often remain implicit and subtle.<n>The scarcity of annotated RS data due to the high cost of labeling complicates training noise-robust models.<n>We propose NSegment-a simple yet effective data augmentation solution to mitigate this issue.
  arXiv  Detail & Related papers  (2025-04-28T09:49:35Z)
• LESS: Label-Efficient and Single-Stage Referring 3D Segmentation [55.06002976797879]
  Referring 3D is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. We propose a novel Referring 3D pipeline, Label-Efficient and Single-Stage, dubbed LESS, which is only under the supervision of efficient binary mask. We achieve state-of-the-art performance on ScanRefer dataset by surpassing the previous methods about 3.7% mIoU using only binary labels.
  arXiv  Detail & Related papers  (2024-10-17T07:47:41Z)
• SegVG: Transferring Object Bounding Box to Segmentation for Visual Grounding [56.079013202051094]
  We present SegVG, a novel method transfers the box-level annotation as signals to provide an additional pixel-level supervision for Visual Grounding. This approach allows us to iteratively exploit the annotation as signals for both box-level regression and pixel-level segmentation.
  arXiv  Detail & Related papers  (2024-07-03T15:30:45Z)
• Instance Consistency Regularization for Semi-Supervised 3D Instance Segmentation [50.51125319374404]
  We propose a novel self-training network InsTeacher3D to explore and exploit pure instance knowledge from unlabeled data. Experimental results on multiple large-scale datasets show that the InsTeacher3D significantly outperforms prior state-of-the-art semi-supervised approaches.
  arXiv  Detail & Related papers  (2024-06-24T16:35:58Z)

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.