---
title: "Towards a Radiologist Imitation Framework for 3D CT Diagnosis"
description: "The authors propose a framework that mimics how radiologists read a scan, in three stages. 0.87 F1. 31 references."
authors: ["Kaidi Zhang", "Zhiyuan Yan", "Gao Cheng", "Zhenyang Cai"]
year: 2026
venue: "BioNLP 2026"
source: "https://aclanthology.org/2026.bionlp-1.85/"
doi: "10.18653/v1/2026.bionlp-1.85"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/zhang-2026-radiologist-imitation-framework-3d-ct/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/zhang-2026-radiologist-imitation-framework-3d-ct/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/) / Towards a Radiologist Imitation Framework for 3D CT Diagnosis with Multimodal LLMs

# Towards a Radiologist Imitation Framework for 3D CT Diagnosis with Multimodal LLMs

**Authors:** Kaidi Zhang, Zhiyuan Yan, Gao Cheng and [Zhenyang Cai](https://md.research.elamur.ai/free/en/authors/zhenyang-cai/) · **Year:** 2026 · **Venue:** [BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/) ([BioNLP 2026](https://md.research.elamur.ai/free/en/venues/bionlp/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.bionlp-1.85/) · [PDF](https://aclanthology.org/2026.bionlp-1.85.pdf) · [DOI 10.18653/v1/2026.bionlp-1.85](https://doi.org/10.18653/v1/2026.bionlp-1.85) · [OpenAlex](https://openalex.org/W7166821154)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Most AI systems for 3D CT give every slice equal weight. Yet diagnostically relevant findings are usually concentrated in a few slices, so this uniform treatment wastes compute and can miss subtle lesions. The authors propose a framework that mimics how radiologists read a scan, in three stages. First, a CLIP-based classifier, Screen-CLIP, quickly flags slices that look abnormal. Second, a multimodal LLM examines the top-ranked slices together with a window of neighbouring slices to keep 3D context. Third, the system checks its findings and writes a structured report. A self-refinement loop called MediReflect improves the prompts over time using TextGrad-style reflection and retrieval of past reasoning trajectories. Experiments use the CT-RATE chest CT dataset, including slices newly annotated by doctors. The system beats ViT, ResNet-50, GPT-4o, M3D and RadFM on screening and report metrics, while cutting latency and GPU memory. This points toward cheaper and more clinically plausible volumetric diagnosis.

## Key points
- **Data:** About 12,000 CT slices from 100 CT-RATE patients were annotated by three doctors (Split 1, 70/30 patient-level split). A further 1,000 CT-RATE test volumes were used for report generation (Split 2, 90/10 split).
- **Screening results:** Screen-CLIP reached AUC 0.87, F1 0.82 and recall 0.83, compared with an AUC of 0.84 for ViT-Base. Macro F1 improved by 8.8% relative to the best baseline.
- **Report generation:** The method scored a BLEU-Avg of 29.03 and beat M3D and RadFM on BLEU, METEOR, ROUGE-L and BERTScore. In a preliminary blinded rating by three radiologists, it averaged 6.16/10, versus 5.47–5.89 for the baselines.
- **Efficiency:** Screen-CLIP cut latency from 9.83 s to 3.80 s (−61.3%) and GPU memory from 19.06 to 17.27 GB (−9.4%).
- **Ablations and limitations:**
  - Removing Screen-CLIP lowered F1 by 39.7%.
  - Removing the neighbour window lowered F1 by 32.4%.
  - Removing TextGrad lowered BLEU by 23.2%.
  - The system is weaker on diffuse, texture-based findings such as consolidation and septal thickening.
  - Validation so far covers chest CT only.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Chinese University of Hong Kong, Shenzhen](https://md.research.elamur.ai/free/en/universities/chinese-university-of-hong-kong-shenzhen/) — University, Shenzhen, China · 56 works · 3,212 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 275 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 214 works · [🩺 Radiology, Nuclear Medicine and Imaging](https://md.research.elamur.ai/free/en/shelves/medicine/radiology-nuclear-medicine-and-imaging/) · 5 works

🧭 Topics (2): [🧠 Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/) · 3,894 works · [🖼️ Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/) · 811 works

## Cite

Cite as: Kaidi Zhang, Zhiyuan Yan, Gao Cheng and Zhenyang Cai. 2026. Towards a Radiologist Imitation Framework for 3D CT Diagnosis with Multimodal LLMs. BioNLP 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{zhang2026radiologist,
  title = {{Towards a Radiologist Imitation Framework for 3D CT Diagnosis with Multimodal LLMs}},
  author = {Kaidi Zhang, Zhiyuan Yan, Gao Cheng and Zhenyang Cai},
  booktitle = {BioNLP 2026},
  year = {2026},
  doi = {10.18653/v1/2026.bionlp-1.85},
  url = {https://doi.org/10.18653/v1/2026.bionlp-1.85}
}
```

- [← previous Towards a Gold Standard for Adjectival Hypernymy: Enriching the Open English WordNet with a Hybrid Approach](https://md.research.elamur.ai/free/en/papers/augello-2026-gold-standard-adjectival-hypernymy-enriching/)
- [next → Towards A Scanpath-Conditioned Surprisal Theory: Modeling Reader Information States](https://md.research.elamur.ai/free/en/papers/mooney-2026-scanpath-conditioned-surprisal-theory-modeling/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/53/)

## References

31 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Rawan AlSaad, Alaa Abd-Alrazaq, Sabri Boughorbel, Arfan Ahmed, Max-Antoine Renault, Rafat Damseh, and Javaid Sheikh. 2024. Multimodal large language models in health care: applications, challenges, and future outlook. Journal of medical Internet research, 26:e59505. [find](https://scholar.google.com/scholar?q=Rawan+AlSaad%2C+Alaa+Abd%2DAlrazaq%2C+Sabri+Boughorbel%2C+Arfan+Ahmed%2C+Max%2DAntoine+Renault%2C+Rafat+Damseh%2C+and+Javaid+Sheikh%2E+2024%2E+Multimodal+large+language+models+in+health+care%3A+applications%2C+challenges%2C+an)
2. Fan Bai, Yuxin Du, Tiejun Huang, Max Q-H Meng, and Bo Zhao. 2024. M3d: Advancing 3d medical image analysis with multi-modal large language models. arXiv preprint arXiv:2404.00578. — [arXiv:2404.00578](https://arxiv.org/abs/2404.00578) [find](https://scholar.google.com/scholar?q=Fan+Bai%2C+Yuxin+Du%2C+Tiejun+Huang%2C+Max+Q%2DH+Meng%2C+and+Bo+Zhao%2E+2024%2E+M3d%3A+Advancing+3d+medical+image+analysis+with+multi%2Dmodal+large+language+models%2E+arXiv+preprint+arXiv%3A2404%2E00578%2E+%E2%80%94+%5BarXiv%3A2404%2E00578%5D)
3. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, and 8 others. 2025. [Qwen2.5-vl technical report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/). Preprint, arXiv:2502.13…
4. Cheng Chen, Juzheng Miao, Dufan Wu, Aoxiao Zhong, Zhiling Yan, Sekeun Kim, Jiang Hu, Zhengliang Liu, Lichao Sun, Xiang Li, and 1 others. 2024a. Ma-sam: Modality-agnostic sam adaptation for 3d medical image segmentation. Medical Image Analysis, 98:103310. [find](https://scholar.google.com/scholar?q=Cheng+Chen%2C+Juzheng+Miao%2C+Dufan+Wu%2C+Aoxiao+Zhong%2C+Zhiling+Yan%2C+Sekeun+Kim%2C+Jiang+Hu%2C+Zhengliang+Liu%2C+Lichao+Sun%2C+Xiang+Li%2C+and+1+others%2E+2024a%2E+Ma%2Dsam%3A+Modality%2Dagnostic+sam+adaptation+for+3d+medical+)
5. Junying Chen, Chi Gui, Ruyi Ouyang, Anningzhe Gao, Shunian Chen, Guiming Hardy Chen, Xidong Wang, Zhenyang Cai, Ke Ji, Xiang Wan, and 1 others. 2024b. Towards injecting medical visual knowledge into multimodal llms at scale. In Proceedings of the 2024 conference on empirical methods in natural langu… [find](https://scholar.google.com/scholar?q=Junying+Chen%2C+Chi+Gui%2C+Ruyi+Ouyang%2C+Anningzhe+Gao%2C+Shunian+Chen%2C+Guiming+Hardy+Chen%2C+Xidong+Wang%2C+Zhenyang+Cai%2C+Ke+Ji%2C+Xiang+Wan%2C+and+1+others%2E+2024b%2E+Towards+injecting+medical+visual+knowledge+into+m)
6. Sanuwani Dayarathna, Kh Tohidul Islam, Sergio Uribe, Guang Yang, Munawar Hayat, and Zhaolin Chen. 2024. Deep learning based synthesis of mri, ct and pet: Review and analysis. Medical image analysis, 92:103046. [find](https://scholar.google.com/scholar?q=Sanuwani+Dayarathna%2C+Kh+Tohidul+Islam%2C+Sergio+Uribe%2C+Guang+Yang%2C+Munawar+Hayat%2C+and+Zhaolin+Chen%2E+2024%2E+Deep+learning+based+synthesis+of+mri%2C+ct+and+pet%3A+Review+and+analysis%2E+Medical+image+analysis%2C+9)
7. Ibrahim Ethem Hamamci, Sezgin Er, Chenyu Wang, Furkan Almas, Ayse Gulnihan Simsek, Sevval Nil Esirgun, Irem Dogan, Omer Faruk Durugol, Benjamin Hou, Suprosanna Shit, and 1 others. 2026. Generalist foundation models from a multimodal dataset for 3d computed tomography. Nature Biomedical Engineering,… [find](https://scholar.google.com/scholar?q=Ibrahim+Ethem+Hamamci%2C+Sezgin+Er%2C+Chenyu+Wang%2C+Furkan+Almas%2C+Ayse+Gulnihan+Simsek%2C+Sevval+Nil+Esirgun%2C+Irem+Dogan%2C+Omer+Faruk+Durugol%2C+Benjamin+Hou%2C+Suprosanna+Shit%2C+and+1+others%2E+2026%2E+Generalist+fou)
8. Alessa Hering, Lasse Hansen, Tony CW Mok, Albert CS Chung, Hanna Siebert, Stephanie Häger, Annkristin Lange, Sven Kuckertz, Stefan Heldmann, Wei Shao, and 1 others. 2022. Learn2reg: comprehensive multi-task medical image registration challenge, dataset and evaluation in the era of deep learning. IEE… [find](https://scholar.google.com/scholar?q=Alessa+Hering%2C+Lasse+Hansen%2C+Tony+CW+Mok%2C+Albert+CS+Chung%2C+Hanna+Siebert%2C+Stephanie+H%C3%A4ger%2C+Annkristin+Lange%2C+Sven+Kuckertz%2C+Stefan+Heldmann%2C+Wei+Shao%2C+and+1+others%2E+2022%2E+Learn2reg%3A+comprehensive+mult)
9. Jiaxin Huang, Runnan Chen, Ziwen Li, Zhengqing Gao, Xiao He, Yandong Guo, Mingming Gong, and Tongliang Liu. 2025. Mllm-for3d: Adapting multimodal large language model for 3d reasoning segmentation. arXiv preprint arXiv:2503.18135. — [arXiv:2503.18135](https://arxiv.org/abs/2503.18135) [find](https://scholar.google.com/scholar?q=Jiaxin+Huang%2C+Runnan+Chen%2C+Ziwen+Li%2C+Zhengqing+Gao%2C+Xiao+He%2C+Yandong+Guo%2C+Mingming+Gong%2C+and+Tongliang+Liu%2E+2025%2E+Mllm%2Dfor3d%3A+Adapting+multimodal+large+language+model+for+3d+reasoning+segmentation%2E+ar)
10. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv preprint arXiv:2410.21276.
11. NT Huynh, E Zhang, O Francies, F Kuklis, T Allen, J Zhu, O Abeyakoon, F Lucka, M Betcke, J Jaros, and 1 others. 2025. A fast all-optical 3d photoacoustic scanner for clinical vascular imaging. Nature Biomedical Engineering, 9(5):638–655. [find](https://scholar.google.com/scholar?q=NT+Huynh%2C+E+Zhang%2C+O+Francies%2C+F+Kuklis%2C+T+Allen%2C+J+Zhu%2C+O+Abeyakoon%2C+F+Lucka%2C+M+Betcke%2C+J+Jaros%2C+and+1+others%2E+2025%2E+A+fast+all%2Doptical+3d+photoacoustic+scanner+for+clinical+vascular+imaging%2E+Nature+)
12. Saahil Jain, Ashwin Agrawal, Adriel Saporta, Steven QH Truong, Du Nguyen Duong, Tan Bui, Pierre Chambon, Yuhao Zhang, Matthew P Lungren, Andrew Y Ng, and 1 others. 2021. Radgraph: Extracting clinical entities and relations from radiology reports. arXiv preprint arXiv:2106.14463. — [arXiv:2106.14463](https://arxiv.org/abs/2106.14463) [find](https://scholar.google.com/scholar?q=Saahil+Jain%2C+Ashwin+Agrawal%2C+Adriel+Saporta%2C+Steven+QH+Truong%2C+Du+Nguyen+Duong%2C+Tan+Bui%2C+Pierre+Chambon%2C+Yuhao+Zhang%2C+Matthew+P+Lungren%2C+Andrew+Y+Ng%2C+and+1+others%2E+2021%2E+Radgraph%3A+Extracting+clinical+)
13. Charles Leduc, Frank Detterbeck, James Huang, Anja C Roden, and Moishe Liberman. 2025. Managing thymic malignancies in 2025: Migrating from masaoka to tnm. Journal of Thoracic Oncology, 20(12):1760–1762. [find](https://scholar.google.com/scholar?q=Charles+Leduc%2C+Frank+Detterbeck%2C+James+Huang%2C+Anja+C+Roden%2C+and+Moishe+Liberman%2E+2025%2E+Managing+thymic+malignancies+in+2025%3A+Migrating+from+masaoka+to+tnm%2E+Journal+of+Thoracic+Oncology%2C+20%2812%29%3A1760%E2%80%9317)
14. Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023. [Llava-med: Training a large language-and-vision assistant for biomedicine in one day](https://md.research.elamur.ai/free/en/papers/li-2023-llava-med-training-large-language/). Advances in Neural Information Processing Systems, 36:28541–28564.
15. Weixiong Lin, Ziheng Zhao, Xiaoman Zhang, Chaoyi Wu, Ya Zhang, Yanfeng Wang, and Weidi Xie. 2023. Pmc-clip: Contrastive language-image pre-training using biomedical documents. In International Conference on Medical Image Computing and Computer-Assisted Intervention, pages 525–536. Springer. [find](https://scholar.google.com/scholar?q=Weixiong+Lin%2C+Ziheng+Zhao%2C+Xiaoman+Zhang%2C+Chaoyi+Wu%2C+Ya+Zhang%2C+Yanfeng+Wang%2C+and+Weidi+Xie%2E+2023%2E+Pmc%2Dclip%3A+Contrastive+language%2Dimage+pre%2Dtraining+using+biomedical+documents%2E+In+International+Confere)
16. Domenico Mastrodicasa, Marly Van Assen, Merel Huisman, Tim Leiner, Eric E Williamson, Edward D Nicol, Bradley D Allen, Luca Saba, Rozemarijn Vliegenthart, and Kate Hanneman. 2025. Use of ai in cardiac ct and mri: a scientific statement from the escr, eusomii, nasci, scct, scmr, siim, and rsna. Radio… [find](https://scholar.google.com/scholar?q=Domenico+Mastrodicasa%2C+Marly+Van+Assen%2C+Merel+Huisman%2C+Tim+Leiner%2C+Eric+E+Williamson%2C+Edward+D+Nicol%2C+Bradley+D+Allen%2C+Luca+Saba%2C+Rozemarijn+Vliegenthart%2C+and+Kate+Hanneman%2E+2025%2E+Use+of+ai+in+cardiac)
17. Michael Moor, Qian Huang, Shirley Wu, Michihiro Yasunaga, Yash Dalmia, Jure Leskovec, Cyril Zakka, Eduardo Pontes Reis, and Pranav Rajpurkar. 2023. [Med-flamingo: a multimodal medical few-shot learner](https://md.research.elamur.ai/free/en/papers/moor-2023-med-flamingo-multimodal-medical-few/). In Machine learning for health (ML4H), pages 353–367. PMLR.
18. Chuang Niu, Qing Lyu, Christopher D Carothers, Parisa Kaviani, Josh Tan, Pingkun Yan, Mannudeep K Kalra, Christopher T Whitlow, and Ge Wang. 2025. Medical multimodal multitask foundation model for lung cancer screening. Nature Communications, 16(1):1523. [find](https://scholar.google.com/scholar?q=Chuang+Niu%2C+Qing+Lyu%2C+Christopher+D+Carothers%2C+Parisa+Kaviani%2C+Josh+Tan%2C+Pingkun+Yan%2C+Mannudeep+K+Kalra%2C+Christopher+T+Whitlow%2C+and+Ge+Wang%2E+2025%2E+Medical+multimodal+multitask+foundation+model+for+lun)
19. Cheng Ouyang, Chen Chen, Surui Li, Zeju Li, Chen Qin, Wenjia Bai, and Daniel Rueckert. 2022. Causality-inspired single-source domain generalization for medical image segmentation. IEEE Transactions on Medical Imaging, 42(4):1095–1106. [find](https://scholar.google.com/scholar?q=Cheng+Ouyang%2C+Chen+Chen%2C+Surui+Li%2C+Zeju+Li%2C+Chen+Qin%2C+Wenjia+Bai%2C+and+Daniel+Rueckert%2E+2022%2E+Causality%2Dinspired+single%2Dsource+domain+generalization+for+medical+image+segmentation%2E+IEEE+Transactions+on)
20. Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, and 1 others. 2021. [Learning transferable visual models from natural language supervision](https://md.research.elamur.ai/free/en/papers/radford-2021-learning-transferable-visual-models-natural/). In International conference on machine learning, pages 8748–8…
21. Philippe Raffy, Jean-François Pambrun, Ashish Kumar, David Dubois, Jay Waldron Patti, Robyn Alexandra Cairns, and Ryan Young. 2023. Deep learning body region classification of mri and ct examinations. Journal of Digital Imaging, 36(4):1291–1301. [find](https://scholar.google.com/scholar?q=Philippe+Raffy%2C+Jean%2DFran%C3%A7ois+Pambrun%2C+Ashish+Kumar%2C+David+Dubois%2C+Jay+Waldron+Patti%2C+Robyn+Alexandra+Cairns%2C+and+Ryan+Young%2E+2023%2E+Deep+learning+body+region+classification+of+mri+and+ct+examinations%2E)
22. Guoan Wang, Jin Ye, Junlong Cheng, Tianbin Li, Zhaolin Chen, Jianfei Cai, Junjun He, and Bohan Zhuang. 2024a. Sam-med3d-moe: Towards a non-forgetting segment anything model via mixture of experts for 3d medical image segmentation. In International Conference on Medical Image Computing and Computer-A… [find](https://scholar.google.com/scholar?q=Guoan+Wang%2C+Jin+Ye%2C+Junlong+Cheng%2C+Tianbin+Li%2C+Zhaolin+Chen%2C+Jianfei+Cai%2C+Junjun+He%2C+and+Bohan+Zhuang%2E+2024a%2E+Sam%2Dmed3d%2Dmoe%3A+Towards+a+non%2Dforgetting+segment+anything+model+via+mixture+of+experts+for+)
23. Jinzhuo Wang, Kai Wang, Yunfang Yu, Yuxing Lu, Wenchao Xiao, Zhuo Sun, Fei Liu, Zixing Zou, Yuanxu Gao, Lei Yang, and 1 others. 2025. Self-improving generative foundation model for synthetic medical image generation and clinical applications. Nature Medicine, 31(2):609–617. [find](https://scholar.google.com/scholar?q=Jinzhuo+Wang%2C+Kai+Wang%2C+Yunfang+Yu%2C+Yuxing+Lu%2C+Wenchao+Xiao%2C+Zhuo+Sun%2C+Fei+Liu%2C+Zixing+Zou%2C+Yuanxu+Gao%2C+Lei+Yang%2C+and+1+others%2E+2025%2E+Self%2Dimproving+generative+foundation+model+for+synthetic+medical+i)
24. Yuli Wang, Jian Peng, Yuwei Dai, Craig Jones, Haris Sair, Jinglai Shen, Nicolas Loizou, Jing Wu, Wen-Chi Hsu, Maliha Imami, and 1 others. 2024b. Enhancing vision-language models for medical imaging: bridging the 3d gap with innovative slice selection. Advances in Neural Information Processing System… [find](https://scholar.google.com/scholar?q=Yuli+Wang%2C+Jian+Peng%2C+Yuwei+Dai%2C+Craig+Jones%2C+Haris+Sair%2C+Jinglai+Shen%2C+Nicolas+Loizou%2C+Jing+Wu%2C+Wen%2DChi+Hsu%2C+Maliha+Imami%2C+and+1+others%2E+2024b%2E+Enhancing+vision%2Dlanguage+models+for+medical+imaging%3A+b)
25. Zhaoqing Wang, Tianqing Wan, Sijie Ma, and Yang Chai. 2024c. Multidimensional vision sensors for information processing. Nature Nanotechnology, 19(7):919–930. [find](https://scholar.google.com/scholar?q=Zhaoqing+Wang%2C+Tianqing+Wan%2C+Sijie+Ma%2C+and+Yang+Chai%2E+2024c%2E+Multidimensional+vision+sensors+for+information+processing%2E+Nature+Nanotechnology%2C+19%287%29%3A919%E2%80%93930%2E)
26. Chaoyi Wu, Xiaoman Zhang, Ya Zhang, Hui Hui, Yanfeng Wang, and Weidi Xie. 2025. Towards generalist foundation model for radiology by leveraging web-scale 2d&3d medical data. Nature Communications, 16(1):7866. [find](https://scholar.google.com/scholar?q=Chaoyi+Wu%2C+Xiaoman+Zhang%2C+Ya+Zhang%2C+Hui+Hui%2C+Yanfeng+Wang%2C+and+Weidi+Xie%2E+2025%2E+Towards+generalist+foundation+model+for+radiology+by+leveraging+web%2Dscale+2d%263d+medical+data%2E+Nature+Communications%2C+16%28)
27. Kaidi Zhang, Zimo Zhao, Yan Hu, and Thuy Le. 2026. Ai-driven feature selection using only survey variable descriptions: Large language models identify adolescent vaping predictors. medRxiv, pages 2026–03. [find](https://scholar.google.com/scholar?q=Kaidi+Zhang%2C+Zimo+Zhao%2C+Yan+Hu%2C+and+Thuy+Le%2E+2026%2E+Ai%2Ddriven+feature+selection+using+only+survey+variable+descriptions%3A+Large+language+models+identify+adolescent+vaping+predictors%2E+medRxiv%2C+pages+2026)
28. Gat Rauner, Piyush B Gupta, and Charlotte Kuperwasser. 2025. From 2d to 3d and beyond: the evolution and impact of in vitro tumor models in cancer research. Nature Methods, 22(9):1776–1787. [find](https://scholar.google.com/scholar?q=Gat+Rauner%2C+Piyush+B+Gupta%2C+and+Charlotte+Kuperwasser%2E+2025%2E+From+2d+to+3d+and+beyond%3A+the+evolution+and+impact+of+in+vitro+tumor+models+in+cancer+research%2E+Nature+Methods%2C+22%289%29%3A1776%E2%80%931787%2E)
29. Daniel Reichenpfader, Henning Müller, and Kerstin Denecke. 2024. A scoping review of large language model based approaches for information extraction from radiology reports. npj Digital Medicine, 7(1):222. [find](https://scholar.google.com/scholar?q=Daniel+Reichenpfader%2C+Henning+M%C3%BCller%2C+and+Kerstin+Denecke%2E+2024%2E+A+scoping+review+of+large+language+model+based+approaches+for+information+extraction+from+radiology+reports%2E+npj+Digital+Medicine%2C+7%281%29)
30. Heinz-Peter Schlemmer. 2023. The cancer epidemic : Global significance of cancer and the situation in oncological imaging. Radiologie (Heidelb.), 63(1):49– 56. [find](https://scholar.google.com/scholar?q=Heinz%2DPeter+Schlemmer%2E+2023%2E+The+cancer+epidemic+%3A+Global+significance+of+cancer+and+the+situation+in+oncological+imaging%2E+Radiologie+%28Heidelb%2E%29%2C+63%281%29%3A49%E2%80%93+56%2E)
31. Yiming Shi, Xun Zhu, Kaiwen Wang, Ying Hu, Chenyi Guo, Miao Li, and Ji Wu. 2025. Med-2e3: A 2d-enhanced 3d medical multimodal large language model. In 2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 2754– 2759. IEEE. [find](https://scholar.google.com/scholar?q=Yiming+Shi%2C+Xun+Zhu%2C+Kaiwen+Wang%2C+Ying+Hu%2C+Chenyi+Guo%2C+Miao+Li%2C+and+Ji+Wu%2E+2025%2E+Med%2D2e3%3A+A+2d%2Denhanced+3d+medical+multimodal+large+language+model%2E+In+2025+IEEE+International+Conference+on+Bioinformat)

*Updated 2 November 2026*