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

arXiv: https://arxiv.org/abs/2609.09477 · HTML: https://mlsanity.com/paper/2609.09477/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 8 Sep 2026.

## Builds on (most cited first, 27 of 27)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [Reviving Iterative Training with Mask Guidance for Interactive Segmentation](https://mlsanity.com/paper/2102.06583/) (2021)
- [Medical SAM 2: Segment medical images as video via Segment Anything Model 2](https://mlsanity.com/paper/2408.00874/) (2024)
- [f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation](https://mlsanity.com/paper/2001.10331/) (2020)
- [SimpleClick: Interactive Image Segmentation with Simple Vision Transformers](https://mlsanity.com/paper/2210.11006/) (2022)
- [SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images](https://mlsanity.com/paper/2310.15161/) (2023)
- [FocalClick: Towards Practical Interactive Image Segmentation](https://mlsanity.com/paper/2204.02574/) (2022)
- [MedSAM2: Segment Anything in 3D Medical Images and Videos](https://mlsanity.com/paper/2504.03600/) (2025)
- [SegVol: Universal and Interactive Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2311.13385/) (2023)
- [Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model](https://mlsanity.com/paper/2401.17868/) (2024)
- [End-to-End Test-Time Training for Long Context](https://mlsanity.com/paper/2512.23675/) (2025)
- [Segment Anything in Medical Images and Videos: Benchmark and Deployment](https://mlsanity.com/paper/2408.03322/) (2024)
- [Continuous Adaptation for Interactive Object Segmentation by Learning from Corrections](https://mlsanity.com/paper/1911.12709/) (2019)
- [Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation](https://mlsanity.com/paper/2601.10880/) (2026)
- [Interactive 3D Medical Image Segmentation with SAM 2](https://mlsanity.com/paper/2408.02635/) (2024)
- [Adapting the Segment Anything Model During Usage in Novel Situations](https://mlsanity.com/paper/2404.08421/) (2024)
- [SAM3-Adapter: Efficient Adaptation of Segment Anything 3 for Camouflage Object Segmentation, Shadow Detection, and Medical Image Segmentation](https://mlsanity.com/paper/2511.19425/) (2025)
- [You Point, I Learn: Online Adaptation of Interactive Segmentation Models for Handling Distribution Shifts in Medical Imaging](https://mlsanity.com/paper/2503.06717/) (2025)
- [Accelerating Volumetric Medical Image Annotation via Short-Long Memory SAM 2](https://mlsanity.com/paper/2505.01854/) (2025)

## Abstract (arXiv)

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.