The DOI matches its Crossref record; 68 of the 72 references it cites were found in a registry or an index.
3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation
Open accessAbstract
Despite that the segment anything model (SAM) achieved impressive results on general-purpose semantic segmentation with strong generalization ability on daily images, its demonstrated performance on medical image segmentation is less precise and unstable, especially when dealing with tumor segmentation tasks that involve objects of small sizes, irregular shapes, and low contrast. Notably, the original SAM architecture is designed for 2D natural images and, therefore would not be able to extract the 3D spatial information from volumetric medical data effectively. In this paper, we propose a novel adaptation method for transferring SAM from 2D to 3D for promptable medical image segmentation. Through a holistically designed scheme for architecture modification, we transfer the SAM to support volumetric inputs while retaining the majority of its pre-trained parameters for reuse. The fine-tuning process is conducted in a parameter-efficient manner, wherein most of the pre-trained parameters remain frozen, and only a few lightweight spatial adapters are introduced and tuned. Regardless of the domain gap between natural and medical data and the disparity in the spatial arrangement between 2D and 3D, the transformer trained on natural images can effectively capture the spatial patterns present in volumetric medical images with only lightweight adaptations. We conduct experiments on four open-source tumor segmentation datasets, and with a single click prompt, our model can outperform domain state-of-the-art medical image segmentation models and interactive segmentation models. We also compared our adaptation method with existing popular adapters and observed significant performance improvement on most datasets. Our code and models are available at: https://github.com/med-air/3DSAM-adapter.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Most promptable medical segmentation methods, however, are still developed and evaluated around clean-prompt protocols.”
From Correction-aware interactive 3D tumor segmentation with sparse and revisable prompts (2026) · cites this paper as [5]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“3DSAM-Adapter [5] and SAM-Med3D [29] adapt SAM-style prompting to 3D medical images, while ProMISe [17] is a prompt-driven 3D medical segmenta-tion method based on pretrained image foundation models.”
From Correction-aware interactive 3D tumor segmentation with sparse and revisable prompts (2026) · cites this paper as [5]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., & Guo, B. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00986 · Cited by 35,534
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
LoRA: Low-Rank Adaptation of Large Language Models
Hu, E. J., Shen, Y., Wallis, P., Allen-Zhu, Z., Li, Y., Wang, S., Wang, L., & Chen, W. (2021) · arXiv · doi:10.48550/arxiv.2106.09685 · Cited by 13,453
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation
Isensee, F., Jaeger, P. F., Kohl, S. A. A., Petersen, J., & Maier-Hein, K. H. (2021) · Nature Methods · doi:10.1038/s41592-020-01008-z · Cited by 10,477
Emerging Properties in Self-Supervised Vision Transformers
Caron, M., Touvron, H., Misra, I., Jegou, H., Mairal, J., Bojanowski, P., & Joulin, A. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00951 · Cited by 5,638 · cited 1×
“…foundation models have seen significant interest in computer vision, benefit from pre-training techniques comprising self-supervised learning [25, 26], contrastive learning [27, 28], language-vision pre-training [29, 30], etc. Recently, SAM [4] pre-trained on over 11M images stands out as a…”
BackgroundLiu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352 · cited 2×
“The success of SAM can be partly ascribed to the powerful prompt engineering, which originates from large language models [12] with recent variants improving model generalizability across tasks.”
BackgroundMethod
Cited by
Sorted by citations
Items 101–158 of 158
Review of generative AI for lesion localization and automatic report generation
Sun, K., Wang, Y., Huang, S., Liu, Y., Chen, H., Lian, Z., Tan, M., Lin, X., Zhou, W., Qiu, Z., et al. (2026) · Med-X · doi:10.1007/s44258-026-00076-8 · Cited by 1
Segment anything model-drive boundary-aware network for surgical instrument segmentation
Song, M., Li, Y., Liu, Y., Yang, L., & Bian, G. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132041 · Cited by 1
Xu, G., Udupa, J. K., Yu, Y., Shao, H., Zhao, S., Liu, W., & Zhang, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133439 · Cited by 1
HFP-SAM: Hierarchical Frequency Prompted SAM for Efficient Marine Animal Segmentation
Zhang, P., Yan, T., Wang, Y., Liu, Y., Tang, T., Ma, Y., Lv, L., Tian, F., Sun, W., & Lu, H. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3674678 · Cited by 1
Robust lesion segmentation based on segment anything model
Gu, Y., Shu, H., Li, B., & Chen, Y. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110156 · Cited by 1
Language-Guided Segmentation of Medical Images: A Review of Foundation Models
Qamar, S. (2026) · Bioengineering · doi:10.3390/bioengineering13070803 · Cited by 1
Qing, Z., Liu, Y., Xu, Q., & Li, H. (2024) · IEEE International Symposium on Biomedical Imaging (ISBI) · doi:10.1109/isbi56570.2024.10635248 · Cited by 1
Xu, Z., Chen, C., Lu, D., Sun, J., Wei, D., Zheng, Y., Li, Q., & Tong, R. K. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3596850 · Cited by 2
AMLP: Adjustable Masking Lesion Patches for Self-Supervised Medical Image Segmentation
Wang, X., Wang, R., Lukasiewicz, T., & Xu, Z. (2025) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2025.3636922 · Cited by 1
Correction-aware interactive 3D tumor segmentation with sparse and revisable prompts
Li, H., & Li, H. (2026) · The Visual Computer · doi:10.1007/s00371-026-04560-5
“3DSAM-Adapter [5] and SAM-Med3D [29] move the promptable formulation into volumetric medical images.”
InfluentialAdapting segment anything model for 3D pancreas tumor segmentation
Yang, F., & Wang, B. (2024) · International Conference on Image Processing and Artificial Intelligence (ICIPAI) · doi:10.1117/12.3035136
Interactive Segmentation Model for Placenta Segmentation from 3D Ultrasound Images
Li, H., Oguz, B. U., Arenas, G. A., Yao, X., Wang, J., Pouch, A. M., Byram, B. C., Schwartz, N., & Oğuz, İ. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-73647-6_13
Taming Large Vision Model for Medical Image Segmentation Via Dual Visual PromptingPreprint
Cui, R., Liu, L., Zou, J., Hu, X., Pei, J., & Qin, J. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5050537
Epicardial Adipose Tissue Segmentation in MRIs Using Text-Prompted Pretraining Model
Ye, H., Deng, Y., & Hong, Y. (2024) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm62325.2024.10822506 · Cited by 1
LiteSCTransNet: Lightweight CNN-Transformer for 3D Medical Image Segmentation
Sheng, Y., Hong, Y., Jia, Y., & Duan, G. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-0695-8_29
Gong, S., Wang, H., Zhang, X., & Dou, Q. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-96625-5_1 · Cited by 1
Self-citationZhu, Z., Yu, W., Ma, X., Liu, S., Dong, J., Du, Y., Wang, C., & Yu, G. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-04965-0_31
OG-SAM: Enhancing Multi-organ Segmentation with Organogenesis-Based Adaptive Modeling
Wu, X., Chen, H., Li, Z., & Li, C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06624-4_9
Advancing Efficiency and Accuracy: A Dynamic Anatomy-Aware 3D Vessel Segmentation Framework
Zhao, H.-N., Liu, S.-Q., Luo, J., Zhou, X.-H., Wang, J., Hou, Z., Wang, T., Jiao, L., Ma, X., & Xie, X. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3627397
Unsupervised Cross-Modality MR Image Segmentation via Prompt-Driven Foundation Model
Ma, W., He, K., Zhang, J., Wang, H., Zhang, L., Zhang, K., Yang, Q., Wong, L. Y., Shen, W., Zhang, H., et al. (2025) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2025.3628499
Self-citationGaze-Guided Medical Image Segmentation: A Training-Free Approach using SAM Foundation Model
Pötgens, G. G., Hendrix, R., Scannell, C. M., Bağcı, U., Spampinato, C., & Salanitri, F. P. (2025) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc58623.2025.11253157
DBNet: A Dual-Branch Network with Boundary Awareness for Few-Shot 3D Medical Image Segmentation
Li, Y., He, H., Wang, X., Zhang, Z., He, W., & Shi, W. (2025) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads67057.2025.11323007
Feng, Y., Liu, F., Shan, Z., Wang, L., & Cheng, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5631-1_13
DPA-SAM: Enhancing Medical Image Segmentation with 3D-DCAF and PGAttention
Li, L., He, K., Luo, G., Zhang, H., He, Y., & Xu, D. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5631-1_20
Kabika, T. B., Hongsen, C., Jingxian, D., Li, Y., Wang, M., Zhu, H., Wang, Y., & Hou, W. W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5631-1_14
Zhang, E., Iwasawa, J., Oda, K., & Tokuoka, Y. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343367
ProtoSAM: Semi-Supervised Prototypical Guidance for 3D Medical Image Segmentation with SAM
Yu, Z., Ding, Z., Qing, Z., Xu, Q., Zhao, B., Cui, J., Li, H., & Liu, Y. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356525
OSHMAMBA: One-Scan Hybrid Mamba with Dynamic Chunking for 3D Medical Image Segmentation
Zhang, Y., Jie, B., Wu, J., & Shen, Y. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356421
Multi-prior-guided deep learning framework for hepatic vessel segmentation
Zhang, Q., Chen, X., Fan, Y., & Zhang, X. (2026) · The Visual Computer · doi:10.1007/s00371-026-04435-9
AutoPrompt-SAM3D: integrated generation and selection for SAM2-based 3D medical segmentation
Cheng, W., Tang, J., Wang, T., Li, S., & Deng, T. (2026) · BMC Bioinformatics · doi:10.1186/s12859-026-06390-7
PromptReg: Interactive Registration by “Corresponding Prompts” for Segment Anything Model (SAM)
Huang, S., Xu, T., Li, J., Saeed, S. U., Shen, Z., Barratt, D. C., & Hu, Y. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3683270
Self-citationLiu, F., Yang, J., Zhang, Y., Xing, H., Yang, J., Lü, T., Wu, F., & Deng, L. (2026) · Scientific Reports · doi:10.1038/s41598-026-51220-8
A Next-Generation Multi-Disease Biomedical Diagnostic Platform Using Green AI, Edge Cloud Computing
Sowmya, M., Sundhari, R. P. M., Suriya, S. S. R., Varshini, R., Thangameena, R., & Preethi, V. (2026) · International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) · doi:10.1109/aimla67915.2026.11522520
iMedSTAM: Interactive Segmentation and Tracking Anything in 3D Medical Images and Videos
Friedetzki, T., Haberzettl, L., Buttmann, R., Puppe, F., & Krenzer, A. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-23496-4_10
3D Segment Anything Model With Visual Mamba for Diagnosing Placenta Accreta Spectrum
Zhang, Y., He, F., Peng, L., Yan, T., Zhang, P., Song, T., Du, L., & Chen, D. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3694185
SAM-3D-MSF: Parameter-Efficient Adaptation of Segment Anything Model for 3D Tooth CBCT Segmentation
Zhang, Y., Shen, C., & Li, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-1462-4_42
Self-citationA Remote Sensing Image Object Detection Method Based on Improved YOLOv11
Zhang, X., Feng, S., & He, H. (2026) · International Conference on Image, Signal Processing and Pattern Recognition (ISPP) · doi:10.1109/ispp69262.2026.11542836
Guo, Y., Xiao, W., Zhao, F., Feng, A., & Wang, K. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133343
Wang, Z., Li, B., Ma, J., Liu, J., & Yao, X. (2026) · Physica Scripta · doi:10.1088/1402-4896/ae8abe
Self-citationYao, Y., Sun, H., Chen, C., Liu, T., Zhang, W., Wang, Q., Liu, Y., Zhao, L., & Huang, D. J. (2026) · Physics in Medicine and Biology · doi:10.1088/1361-6560/ae9688
ROI-Focused Geometry-Aware Adaptation for Accurate Small-Structure Segmentation in Medical SAM
Wang, T., Li, J., Yang, C., Xu, J., Zhou, M., Dang, K., & Zhang, L. (2026) · Proceedings - International Conference on Image Processing · doi:10.1109/icip61757.2026.11629916
Self-citationKidney Tumour Segmentation Using Deep Learning: Progress, Challenges, and Future Trends
Tyagi, P., Sharma, A., & Gupta, G. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-35173-9_5
3D CSFM: Cross-domain adaptation of visual foundation models for 3D seismic fault segmentation
Zhou, G., Li, K., Hao, S., Yin, R., & Chu, S. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105170
CPNet: Channel partitioning with completion for medical image segmentation
Wang, Q., Wang, X., Wang, Y., Mai, Z., Liu, W., Shi, C., & Zhang, C. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111351
Chen, X., Yi, M., Deng, Y., & Shen, Q. (2026) · Precision Radiation Oncology · doi:10.1002/pro6.70090
Generative large language models in medicine: a scoping review of recent methodological advances
LI, F., Li, J., Cao, W., Li, H., Li, Y., Sun, Z., Chen, D., Duan, T., Li, P., Tizhoosh, H., et al. (2026) · npj Health Systems · doi:10.1038/s44401-026-00137-5
Self-citationGong, J., Liu, J., & Wang, Q. (2026) · Electronics · doi:10.3390/electronics15184227
FST-SAM3: Taming SAM 3 with Frequency-Spatio-Temporal Refinement for Video Polyp Segmentation
Wu, G., Chen, G., Wu, H., & Qin, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37032-7_13
Lin, H., Huang, B., Wang, M., Ren, Y., Liu, Z., & Huang, B. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38470-6_58
DentalPSAM: Lifting SAM to Dental Plaque Segmentation with Hybrid 2D-3D Knowledge Fusion
Jiang, H., Fok, M. R., Zhang, X., Sun, R., Yeung, J. H. K., Deng, K., & Qu, L. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-38082-1_9
PDSVF: Prompt-driven SAM-Med2D with parallel ViT and state-space fusion for skin lesion segmentation
Hu, S., Liu, J., Wang, Z., Ye, Z., Wu, W., Hou, Q., & Huo, T. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.111557
Self-citationAnatomy-informed multi-task framework for visceral artery aneurysm screening on non-contrast CT
Xu, Z., Liu, T., Bai, L., Wang, H., Zhang, J., Wang, Z., Li, H., Hu, Y., Zhou, M., Ning, J., et al. (2026) · Medical Image Analysis · doi:10.1016/j.media.2026.104269
Self-citationAbadian‐Zadeh, F., Mohammadi, M. R., & Soryani, M. (2026) · Journal of Imaging Informatics in Medicine · doi:10.1007/s10278-026-02359-3
Wu, X., Wei, X., Zhu, Y., Duan, S., Zhang, X., Qian, Q., Song, J., & Dai, J. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.135293
Fault-SAM: An interactive cross-domain foundation model for 3D seismic fault segmentation
Guangyue, Z., & Zhou, G. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117185
Xia, Q., Sun, X., Jiang, B., Yun, Z., Chen, D., & Zhai, S. (2026) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2026.102835
MSA-SAM: A Decoder Enhancement Framework for 3D Tumor Segmentation Based on Segment Anything
Yang, Y., Li, N., & Huang, W. (2026) · Applied Sciences · doi:10.3390/app162010395
Zheng, S., Li, J., Li, W., & Yu, L. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.134890
Self-citation
Metadata
- Authors
- Gong, S., Zhong, Y., Ma, W., Li, J., Wang, Z., Zhang, J., Heng, P.-A., & Dou, Q.
- Affiliations
- Chinese University of Hong Kong (HK)
- Corresponding author
- Dou, Qi
- Venue
- Medical Image Analysis
- Publisher
- Elsevier BV
- Published
- 2024-12
- Volume
- 98
- Pages
- 103324
- ISSN
- 1361-8415 (ISSN-L)
- OpenAlex
- W4401852105
- Cited by
- 156
- References
- 72
- Citations by year
- 2026: 51 · 2025: 61 · 2024: 41
- FWCI
- 21.42
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Medical Image Analysis (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- National Natural Science Foundation of China
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- Segment Anything Model, 3D medical image segmentation, tumor segmentation, prompt-based segmentation, parameter-efficient fine-tuning, volumetric medical data, interactive segmentation, domain adaptation
- MeSH terms
- Algorithms, Humans, Neoplasms, Imaging, Three-Dimensional
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
