LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation

• URL: http://arxiv.org/abs/2609.09477v1
• Date: Tue, 08 Sep 2026 21:49:56 GMT
• Title: LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation
• Abstract summary: Fine-tuning SAM 3 on lung tumours raises the Dice obtained from a single point prompt from 0.298 to 0.757, and seven rounds of corrections raise it further to 0.765.<n>We propose LeCor, which performs test-time training on a small set of case adapters that are reset for every case.<n>LeCor raises the Dice reached after seven correction rounds from 0.787 with the fine-tuned model to 0.827, reduces the number of cases that never reach a Dice of 0.80 from 47 to 27, and reaches in three correction rounds the accuracy that the fine-tuned model attains in seven.
• Score: 45.86925813888675
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Delineating lung tumours on computed tomography (CT) takes a considerable share of the time spent on radiotherapy planning, and a contour proposed by a model can be refined interactively by the clinician. Promptable foundation models such as SAM 3 support this workflow by writing each correction into a session memory that conditions the remaining slices, while the model weights stay fixed. On 690 test cases from five public CT cohorts, fine-tuning SAM 3 on lung tumours raises the Dice obtained from a single point prompt from 0.298 to 0.757, and seven rounds of corrections raise it further to 0.765, but under memory conditioning alone the accuracy on slices the annotator has not touched stops improving after six rounds. We therefore treat each correction as a training signal and propose LeCor, which performs test-time training on a small set of case adapters that are reset for every case and meta-learned such that a single gradient step driven by a click improves the slices that were not clicked. On the 133 test cases that span at least eight slices, LeCor raises the Dice reached after seven correction rounds from 0.787 with the fine-tuned model to 0.827, reduces the number of cases that never reach a Dice of 0.80 from 47 to 27, and reaches in three correction rounds the accuracy that the fine-tuned model attains in seven.

Related papers

• Two-Stage Personalized Gait Phase Estimation in Stroke Survivors During Exoskeleton-Assisted Walking: An Offline Feasibility Study [0.7734726150561086]
  This study evaluated personalized gait phase estimation for stroke survivors using functional inertial measurement unit (IMU) alignment and two-stage sequential adaptation.<n>The Transformer achieved the lowest final error (2.90 +- 1.13$% of the gait cycle) and heel-strike timing error (23.7 +- 4.5ms)<n>Results support the offline feasibility and embedded computational timing of the proposed framework for exoskeleton-assisted walking.
  arXiv  Detail & Related papers  (2026-09-14T03:42:40Z)
• Parameter-Efficient Fine-Tuning of Foundation Models for Liver Tumor Segmentation in CT [1.9403818519796712]
  We evaluated parameter-efficient fine-tuning (PEFT) of the Segment Anything Model (SAM) for liver tumor segmentation in abdominal CT of colorectal liver metastases.<n>We compared Low-Rank Adaptation (LoRA), 4-bit Quantized LoRA (QLoRA), a convolutional adapter (Conv-Adapter), and our Directional Spectral Top-K adapter (DiSCo)<n>Conv-Adapter and LoRA achieved the highest accuracy (overall Dice 0.793 and 0.792); single-point Dice 0.795 and 0.792; 95th-percentile Hausdorff distance (HD95) 32
  arXiv  Detail & Related papers  (2026-09-12T19:07:51Z)
• Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention [46.03321798937855]
  We show that the standard Generalized Dice Loss (GDL) is unstable under domain shift.<n>We propose a Subspace-Aware Class Attention (SACA) module that re-calibrates the bottleneck features and raises Enhancing Tumor (ET) sensitivity by 8%.
  arXiv  Detail & Related papers  (2026-07-23T09:59:30Z)
• Parameter-Efficient Adaptation of SAM 3 for Automated ITV Generation from 4DCT Images [0.0]
  Four-dimensional computed tomography (4DCT) captures the full respiratory cycle of thoracic anatomy.<n>Current Internal Target Volume contouring process each phase in isolation, discarding temporal coherence and leaving vulnerable to phase-specific artifacts.<n>We present a framework that applies parameter-efficient fine-tuning to the Segment Anything Model 3 (SAM 3) via low-rank adaptation (LoRA)<n>With only seven annotated volumes, the framework retains over 95% of full-data accuracy, and the entire pipeline is trainable on a single consumer-grade GPU.
  arXiv  Detail & Related papers  (2026-06-14T05:12:57Z)
• TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT [49.93685997940356]
  We describe the TriALS challenge for automated liver lesion segmentation under contrast-limited conditions.<n>The top-performing method achieved a mean venous-phase Dice of 0.754, consistent with human-level performance, yet dropped to 0.57 on NCCT.<n>Algorithm performance was most strongly predicted by training data scale and pre-training strategy.
  arXiv  Detail & Related papers  (2026-05-15T19:23:35Z)
• TEMPO: Scaling Test-time Training for Large Reasoning Models [87.61789183311856]
  Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time.<n>We propose TEMPO, a TTT framework that interleaves policy refinement on unlabeled questions with periodic critic recalibration on a labeled dataset.
  arXiv  Detail & Related papers  (2026-04-21T10:01:04Z)
• C2W-Tune: Cavity-to -Wall Transfer Learning for Thin Atrial Wall Segmentation in 3D Late Gadolinium-enhanced Magnetic Resonance [1.452875650827562]
  C2W-Tune is a two-stage cavity-to-wall transfer framework.<n>It uses a high-accuracy LA cavity model as an anatomical prior to improve thin-wall delineation.<n>C2W-Tune achieved a Dice score of 0.78 and an HD95 of 3.15 mm, exceeding multi-class benchmarks.
  arXiv  Detail & Related papers  (2026-03-26T03:35:35Z)
• Pillar-0: A New Frontier for Radiology Foundation Models [41.640120966890954]
  We introduce Pillar-0, a radiology foundation model pretrained on 42,990 abdomen-pelvis CTs, 86,411 chest CTs, 14,348 head CTs, and 11,543 breast MRIs.<n>Pillar-0 achieves mean AUROCs of 86.4, 88.0, 90.1, and 82.9, outperforming MedGemma (Google), MedImageInsight (Microsoft), Lingshu (Alibaba), and Merlin (Stanford) by 7.8-15.8 AUROC points and ranking best in 87.2% (319/366) tasks.
  arXiv  Detail & Related papers  (2025-11-21T21:50:34Z)
• Click, Predict, Trust: Clinician-in-the-Loop AI Segmentation for Lung Cancer CT-Based Prognosis within the Knowledge-to-Action Framework [0.7340285482623061]
  Lung cancer remains the leading cause of cancer mortality, with CT imaging central to screening, prognosis, and treatment.<n>Deep learning (DL) offers automation but faces barriers to clinical adoption.<n>This study develops a clinician-in-the-loop DL pipeline to enhance, prognostic accuracy, and clinical trust.
  arXiv  Detail & Related papers  (2025-10-19T23:02:43Z)
• DINOv3 with Test-Time Training for Medical Image Registration [3.9576638237437183]
  We propose a training-free pipeline that relies on a frozen DINOv3 encoder and test-time optimization of the deformation field in feature space.<n>Across two representative benchmarks, the method is accurate and yields regular deformations.
  arXiv  Detail & Related papers  (2025-08-20T15:58:19Z)
• Pretrained hybrid transformer for generalizable cardiac substructures segmentation from contrast and non-contrast CTs in lung and breast cancers [3.704003490598663]
  AI automated segmentations for radiation treatment planning (RTP) can deteriorate when applied in clinical cases with different characteristics than training dataset.<n>We refined a pretrained transformer into a hybrid transformer convolutional network (HTN) to segment cardiac substructures lung and breast cancer patients.<n>A HTN demonstrated robustly accurate (geometric and dose metrics) cardiac substructures segmentation from CTs with varying imaging and patient characteristics.
  arXiv  Detail & Related papers  (2025-05-16T04:48:33Z)
• Correcting Class Imbalances with Self-Training for Improved Universal Lesion Detection and Tagging [43.06199185109424]
  Universal lesion detection and tagging (ULDT) in CT studies is critical for tumor burden assessment and tracking the progression of lesion status (growth/shrinkage) over time.<n>Prior work used the DeepLesion dataset (4,427 patients, 10,594 studies, 32,120 CT slices, 32,735 lesions, 8 body part labels) for algorithmic development, but this dataset is not completely annotated and contains class imbalances.<n>We developed a self-training pipeline for ULDT using a limited 11.5% subset of DeepLesion.
  arXiv  Detail & Related papers  (2025-04-07T15:57:03Z)

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.