# Segmentation, Detection and Explanation: A Unified Framework for CT Appearance Reasoning

arXiv: https://arxiv.org/abs/2605.15997 · HTML: https://mlsanity.com/paper/2605.15997/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 36 of its 59 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)
- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 30 of 36)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision](https://mlsanity.com/paper/2102.03334/) (2021)
- [Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling](https://mlsanity.com/paper/2501.17811/) (2025)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Contrastive Learning of Medical Visual Representations from Paired Images and Text](https://mlsanity.com/paper/2010.00747/) (2020)
- [VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model](https://mlsanity.com/paper/2504.07615/) (2025)
- [GLaMM: Pixel Grounding Large Multimodal Model](https://mlsanity.com/paper/2311.03356/) (2023)
- [LAVT: Language-Aware Vision Transformer for Referring Image Segmentation](https://mlsanity.com/paper/2112.02244/) (2021)
- [MM-LLMs: Recent Advances in MultiModal Large Language Models](https://mlsanity.com/paper/2401.13601/) (2024)
- [CoTr: Efficiently Bridging CNN and Transformer for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.03024/) (2021)
- [CLIP-Driven Universal Model for Organ Segmentation and Tumor Detection](https://mlsanity.com/paper/2301.00785/) (2023)
- [M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models](https://mlsanity.com/paper/2404.00578/) (2024)
- [ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts](https://mlsanity.com/paper/2312.00784/) (2023)
- [GSVA: Generalized Segmentation via Multimodal Large Language Models](https://mlsanity.com/paper/2312.10103/) (2023)
- [VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks](https://mlsanity.com/paper/2406.08394/) (2024)
- [LViT: Language meets Vision Transformer in Medical Image Segmentation](https://mlsanity.com/paper/2206.14718/) (2022)
- [MosMedData: Chest CT Scans With COVID-19 Related Findings Dataset](https://mlsanity.com/paper/2005.06465/) (2020)
- [CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging](https://mlsanity.com/paper/2403.06801/) (2024)
- [nnDetection: A Self-configuring Method for Medical Object Detection](https://mlsanity.com/paper/2106.00817/) (2021)
- [TGANet: Text-guided attention for improved polyp segmentation](https://mlsanity.com/paper/2205.04280/) (2022)
- [Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection](https://mlsanity.com/paper/1811.08661/) (2018)
- [MedCLIP-SAM: Bridging Text and Image Towards Universal Medical Image Segmentation](https://mlsanity.com/paper/2403.20253/) (2024)
- [A Comparison of Pre-trained Vision-and-Language Models for Multimodal Representation Learning across Medical Images and Reports](https://mlsanity.com/paper/2009.01523/) (2020)

## Abstract (arXiv)

Recent progress in deep learning has significantly advanced CT image analysis, particularly for segmentation tasks. However, these advances are largely confined to image-level pattern recognition, with most methods lacking explicit anatomical or contextual reasoning. Large vision-language models introduce linguistic context into image analysis, yet most approaches typically focus on a single task, which is insufficient for clinical workflow analysis that requires multiple fine-grained types of analysis, such as anatomy detection and segmentation. In this paper, we propose a unified autoregressive framework that integrates language-guided visual reasoning into CT interpretation. Our method introduces task-routing tokens that trigger detection and segmentation heads conditioned on the hidden states of a large vision-language model, enabling coherent generation of visual outputs (e.g., masks and bounding boxes) and textual reasonings. To progressively enhance localisation accuracy and semantic clarity, we further design a "closer-look" mechanism that allows the model to perform progressive coarse-to-fine visits to regions of interest under refined fields of view. To support model training and evaluation, we curated a new multimodal CT dataset containing pixel-wise masks, bounding boxes, spatial prompts, and structured descriptions for visual objects constructed through an AI-assisted annotation process with human verification. Experiments on public benchmarks demonstrate consistent improvements over the SoTA, achieving up to 1.0% Dice on BTCV and 1.7% Dice on MosMed+, while additionally providing appearance reasoning outputs. The code and dataset will be available.