Share：
Share this content in WeChat
X
[Chinese][PDF]181
• Review •
Research progress of artificial intelligence in automatic segmentation and visualization of gastrointestinal tumor images
JIANG Changqin  ZHANG Youjun  MA Wenshan  FENG Qiang 

Cite this article as: JIANG C Q, ZHANG Y J, MA W S, et al. Research progress of artificial intelligence in automatic segmentation and visualization of gastrointestinal tumor images[J]. Chin J Magn Reson Imaging, 2025, 16(6): 214-219. DOI:10.12015/issn.1674-8034.2025.06.033.


[Abstract] The rapid development of medical imaging technology has significantly enhanced the diagnosis and treatment of gastrointestinal tumors (GIT). However, due to the complex morphology of tumors, variations in imaging modalities, and the need for high-precision depiction, accurate segmentation and visualization of GIT remain challenging in clinical practice. Artificial intelligence (AI), particularly deep learning (DL) models, has emerged as a transformative approach in medical imaging, demonstrating great potential in automating tumor segmentation tasks. Nevertheless, issues such as limited generalization ability of models persist. The high heterogeneity of GIT imposes greater demands on segmentation models, and the current lack of standardized evaluation criteria and clinical validation mechanisms further limits the reliability and interpretability of AI tools in real-world diagnostic and therapeutic settings. This article provides a comprehensive review of recent advancements in AI-based automatic segmentation of GIT images. It focuses on the key achievements in AI frameworks, including DL architectures and multimodal imaging models, applied across various imaging modalities. The article also summarizes the limitations of existing research and outlines future directions. By systematically reviewing the progress in GIT segmentation and visualization, this work aims to explore future research trajectories and offer both theoretical support and practical guidance for the application of AI-driven segmentation tools in research and clinical translation.
[Keywords] artificial intelligence；gastrointestinal tumors；deep learning；diagnosis；multimodal imaging

JIANG Changqin   ZHANG Youjun   MA Wenshan   FENG Qiang*  

Medical Imaging Department of Yidu Central Hospital Affiliated to Shandong Second Medical University, Weifang 262500, China

Corresponding author: FENG Q, E-mail: fengqiang220812@163.com

Conflicts of interest   None.

Received  2025-02-06
Accepted  2025-06-05
DOI: 10.12015/issn.1674-8034.2025.06.033
Cite this article as: JIANG C Q, ZHANG Y J, MA W S, et al. Research progress of artificial intelligence in automatic segmentation and visualization of gastrointestinal tumor images[J]. Chin J Magn Reson Imaging, 2025, 16(6): 214-219. DOI:10.12015/issn.1674-8034.2025.06.033.

[1]
BRAY F, LAVERSANNE M, SUNG H, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2024, 74(3): 229-263. DOI: 10.3322/caac.21834.
[2]
FERLAY J, COLOMBET M, SOERJOMATARAM I, et al. Cancer statistics for the year 2020: An overview[J/OL]. Int J Cancer, 2021 [2025-04-18]. https://onlinelibrary.wiley.com/doi/10.1002/ijc.33588. DOI: 10.1002/ijc.33588.
[3]
Early Diagnosis and Treatment Group Chinese Society of Oncology of Chinese Medical Association, MIAO Z F, XU Z F, et al. Chinese expert consensus on early diagnosis and treatment of gastric cancer(2023 edition)[J]. Chin J Dig Surg, 2024(1): 23-36. DOI: 10.3760/cma.j.cn115610-20231207-00239.
[4]
National Health Commission of the People′s Republic of China, Chinese Society of Oncology of Chinese Medical Association, GU J, et al. Chinese protocol of diagnosis and treatment of colorectal cancer(2023 edition)[J]. Chin J Surg, 2023, 61(8): 617-644. DOI: 10.3760/cma.j.cn112139-20230603-00222.
[5]
LITJENS G, KOOI T, BEJNORDI B E, et al. A survey on deep learning in medical image analysis[J]. Med Image Anal, 2017, 42: 60-88. DOI: 10.1016/j.media.2017.07.005.
[6]
ESTEVA A, CHOU K, YEUNG S, et al. Deep learning-enabled medical computer vision[J/OL]. NPJ Digit Med, 2021, 4(1): 5 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC7794558/. DOI: 10.1038/s41746-020-00376-2.
[7]
BOHLENDER S, OKSUZ I, MUKHOPADHYAY A. A survey on shape-constraint deep learning for medical image segmentation[J]. IEEE Rev Biomed Eng, 2023, 16: 225-240. DOI: 10.1109/RBME.2021.3136343.
[8]
XUE H Z, YAO Y D, TENG Y Y. Multi-modal tumor segmentation methods based on deep learning: a narrative review[J]. Quant Imaging Med Surg, 2024, 14(1): 1122-1140. DOI: 10.21037/qims-23-818.
[9]
LEWIS J, CHA Y J, KIM J. Dual encoder-decoder-based deep polyp segmentation network for colonoscopy images[J/OL]. Sci Rep, 2023, 13(1): 1183 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9867760/. DOI: 10.1038/s41598-023-28530-2.
[10]
YANG P, WU J M, LIU M Q, et al. Preoperative CT-based radiomics and deep learning model for predicting risk stratification of gastric gastrointestinal stromal tumors[J]. Med Phys, 2024, 51(10): 7257-7268. DOI: 10.1002/mp.17276.
[11]
TSANG B, GUPTA A, TAKAHASHI M S, et al. Applications of artificial intelligence in magnetic resonance imaging of primary pediatric cancers: a scoping review and CLAIM score assessment[J]. Jpn J Radiol, 2023, 41(10): 1127-1147. DOI: 10.1007/s11604-023-01437-8.
[12]
SOOMRO M H, COPPOTELLI M, CONFORTO S, et al. Automated segmentation of colorectal tumor in 3D MRI using 3D multiscale densely connected convolutional neural network[J/OL]. J Healthc Eng, 2019, 2019: 1075434 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/30838121. DOI: 10.1155/2019/1075434.
[13]
DEVI K G, RADHAKRISHNAN R. Automatic segmentation of colon in 3D CT images and removal of opacified fluid using cascade feed forward neural network[J/OL]. Comput Math Methods Med, 2015, 2015: 670739 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/25838838. DOI: 10.1155/2015/670739.
[14]
TAO J, LIU D, HU F B, et al. Development and validation of a computed tomography-based model for noninvasive prediction of the T stage in gastric cancer: multicenter retrospective study[J/OL]. J Med Internet Res, 2024, 26: e56851 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/39382960. DOI: 10.2196/56851.
[15]
GUO Z, LI X, HUANG H, et al. Deep learning-based image segmentation on multimodal medical imaging[J]. IEEE Trans Radiat Plasma Med Sci, 2019, 3(2): 162-169. DOI: 10.1109/trpms.2018.2890359.
[16]
YOUSEFIRIZI F, DECAZES P, AMYAR A, et al. AI-based detection, classification and prediction/prognosis in medical imaging: : towards radiophenomics[J]. PET Clin, 2022, 17(1): 183-212. DOI: 10.1016/j.cpet.2021.09.010.
[17]
CALVARESE M, CORBETTA E, CONTRERAS J, et al. Endomicroscopic AI-driven morphochemical imaging and fs-laser ablation for selective tumor identification and selective tissue removal[J/OL]. Sci Adv, 2024, 10(50): eado9721 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC11633757/. DOI: 10.1126/sciadv.ado9721.
[18]
XU J C, JING M J, WANG S M, et al. A review of medical image detection for cancers in digestive system based on artificial intelligence[J]. Expert Rev Med Devices, 2019, 16(10): 877-889. DOI: 10.1080/17434440.2019.1669447.
[19]
VAN DER VELDEN B H M, KUIJF H J, GILHUIJS K G A, et al. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis[J/OL]. Med Image Anal, 2022, 79: 102470 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/35576821/. DOI: 10.1016/j.media.2022.102470.
[20]
ZUNAIR H, HAMZA A BEN. Sharp U-Net: Depthwise convolutional network for biomedical image segmentation[J/OL]. Comput Biol Med, 2021, 136: 104699 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/34348214/. DOI: 10.1016/j.compbiomed.2021.104699.
[21]
VALANARASU J M J, SINDAGI V A, HACIHALILOGLU I, et al. KiU-Net: overcomplete convolutional architectures for biomedical image and volumetric segmentation[J]. IEEE Trans Med Imag, 2022, 41(4): 965-976. DOI: 10.1109/TMI.2021.3130469.
[22]
LIU Z S, LV Q J, YANG Z D, et al. Recent progress in transformer-based medical image analysis[J/OL]. Comput Biol Med, 2023, 164: 107268 [2025-02-05]. https://pubmed.ncbi.nlm.nih.gov/37494821/. DOI: 10.1016/j.compbiomed.2023.107268.
[23]
LI W X, QU C Y, CHEN X X, et al. AbdomenAtlas: A large-scale, detailed-annotated, & multi-center dataset for efficient transfer learning and open algorithmic benchmarking[J/OL]. Med Image Anal, 2024, 97: 103285 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/37494821/. DOI: 10.1016/j.media.2024.103285.
[24]
PIRABAHARAN R, KHAN N. Interactive segmentation using U-Net with weight map and dynamic user interactions[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 4754-4757. DOI: 10.1109/EMBC48229.2022.9871361.
[25]
WANG Y L. Transfer learning based ROI region extraction in stomach CT image sequences[D]. Xi'an: Xidian University, 2013. DOI: 10.7666/d.D363549.
[26]
ZHENG K Y, WU H, YUAN W J, et al. Feasibility study of three-dimensional nnU-Net deep learning network for automatic segmentation of colorectal cancer based on abdominal CT images[J]. Chin J Radiol, 2024, 58(8): 829-835. DOI: 10.3760/cma.j.cn112149-20231231-00505.
[27]
LI H M, LIU B, ZHANG Y T, et al. 3D IFPN: improved feature pyramid network for automatic segmentation of gastric tumor[J/OL]. Front Oncol, 2021, 11: 618496 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC8173118/. DOI: 10.3389/fonc.2021.618496.
[28]
LI Z S. Research on automatic segmentation of rectal cancer based on semi-supervised deep learning[D]. Tianjin: Tianjin University, 2021. DOI: 10.27356/d.cnki.gtjdu.2021.005043.
[29]
HE J J, ZHANG M D, LI W C, et al. SaB-Net: Self-attention backward network for gastric tumor segmentation in CT images[J/OL]. Comput Biol Med, 2024, 169: 107866 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/38134751/. DOI: 10.1016/j.compbiomed.2023.107866.
[30]
HE D Z, ZHANG Y Y, HUANG H, et al. Dual-branch hybrid network for lesion segmentation in gastric cancer images[J/OL]. Sci Rep, 2023, 13(1): 6377 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10115814/. DOI: 10.1038/s41598-023-33462-y.
[31]
LU D W, WU Y F, ACAR A, et al. ASSIST-U: a system for segmentation and image style transfer for ureteroscopy[J]. Healthc Technol Lett, 2023, 11(2/3): 40-47. DOI: 10.1049/htl2.12065.
[32]
RAN Z, JIAN J M, WANG M M, et al. Automatic segmentation method based on full convolution neural network for rectal cancer tumors in magnetic resonance image[J]. Beijing Biomed Eng, 2019, 38(5): 465-471. DOI: 10.3969/j.issn.1002-3208.2019.05.004.
[33]
MA Y L. Tumor region segmentation and KRAS gene status prediction in colorectal cancer patients based on deep learning[D]. Taiyuan: Taiyuan University of Technology, 2022. DOI: 10.27352/d.cnki.gylgu.2022.001557.
[34]
XUE Z L, LI P, ZHANG L, et al. Multi-modal co-learning for liver lesion segmentation on PET-CT images[J]. IEEE Trans Med Imaging, 2021, 40(12): 3531-3542. DOI: 10.1109/TMI.2021.3089702.
[35]
KANG S, XI Z H, HUANG C, et al. Rectal tumor segmentation and T staging based on DPU-net[J]. Chin J Med Phys, 2023, 40(10): 1189-1197. DOI: 10.3969/j.issn.1005-202X.2023.10.001.
[36]
LIU Y J, WANG J, WU C P, et al. Fovea-UNet: detection and segmentation of lymph node metastases in colorectal cancer with deep learning[J/OL]. Biomed Eng Online, 2023, 22(1): 74 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC10362618/. DOI: 10.1186/s12938-023-01137-4.
[37]
NAGARAJU G P, SANDHYA T, SRILATHA M, et al. Artificial intelligence in gastrointestinal cancers: diagnostic, prognostic, and surgical strategies[J/OL]. Cancer Lett, 2025, 612: 217461 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/39809357/. DOI: 10.1016/j.canlet.2025.217461.
[38]
MATTA S, LAMARD M, ZHANG P, et al. A systematic review of generalization research in medical image classification[J/OL]. Comput Biol Med, 2024, 183: 109256 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/39427426/. DOI: 10.1016/j.compbiomed.2024.109256.
[39]
ALI S, ZHOU F, BAILEY A, et al. A deep learning framework for quality assessment and restoration in video endoscopy[J/OL]. Med Image Anal, 2021, 68: 101900 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/33246229/. DOI: 10.1016/j.media.2020.101900.
[40]
JIANG Y, CHEN J, GONG C, et al. Deep-learning-based real-time and automatic target-to-background ratio calculation in fluorescence endoscopy for cancer detection and localization[J/OL]. Diagnostics (Basel), 2022, 12(9): 2031 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9497969/. DOI: 10.3390/diagnostics12092031.
[41]
LIU X Q. The study of automatic recognition and segmentaion methods of gastric lesion on ME-NBI endoscopic images[D]. Chongqing: Chongqing University, 2019. DOI: 10.27670/d.cnki.gcqdu.2019.001488.
[42]
CHEN K C, QIN T X, LEE V H, et al. Learning robust shape regularization for generalizable medical image segmentation[J]. IEEE Trans Med Imag, 2024, 43(7): 2693-2706. DOI: 10.1109/TMI.2024.3371987.
[43]
LI L Q, ZHAO X M, LU W, et al. Deep learning for variational multimodality tumor segmentation in PET/CT[J]. Neurocomputing (Amst), 2020, 392: 277-295. DOI: 10.1016/j.neucom.2018.10.099.
[44]
KLIMONT M, ORONOWICZ-JAŚKOWIAK A, FLIEGER M, et al. Deep learning-based segmentation and volume calculation of pediatric lymphoma on contrast-enhanced computed tomographies[J/OL]. J Pers Med, 2023, 13(2): 184 [2025-04-18]. https://pubmed.ncbi.nlm.nih.gov/36836418. DOI: 10.3390/jpm13020184.
[45]
CONSTANTINO C S, LEOCÁDIO S, OLIVEIRA F P M, et al. Evaluation of semiautomatic and deep learning-based fully automatic segmentation methods on [18F] FDG PET/CT images from patients with lymphoma: influence on tumor characterization[J]. J Digit Imaging, 2023, 36(4): 1864-1876. DOI: 10.1007/s10278-023-00823-y.
[46]
YUE Y T, LI N, XING W Y, et al. Condition control training-based ConVMLP-ResU-Net for semantic segmentation of esophageal cancer in 18F-FDG PET/CT images[J]. Phys Eng Sci Med, 2023, 46(4): 1643-1658. DOI: 10.1007/s13246-023-01327-3.
[47]
SHELLER M J, EDWARDS B, REINA G A, et al. Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data[J/OL]. Sci Rep, 2020, 10(1): 12598 [2025-04-18]. https://pmc.ncbi.nlm.nih.gov/articles/PMC7387485/. DOI: 10.1038/s41598-020-69250-1.

PREV Research progress in predicting gastric cancer neoadjuvant chemotherapy based on CT, MRI, and related technologies
NEXT Progress of multimodal MRI in evaluating biomarkers related to treatment and prognosis of cervical cancer
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn