Top

Published in:

Open Access 01-12-2024 | Gastrointestinal Stromal Tumor | Research

Convolutional neural network applied to preoperative venous-phase CT images predicts risk category in patients with gastric gastrointestinal stromal tumors

Authors: Jian Wang, Meihua Shao, Hongjie Hu, Wenbo Xiao, Guohua Cheng, Guangzhao Yang, Hongli Ji, Susu Yu, Jie Wan, Zongyu Xie, Maosheng Xu

Published in: BMC Cancer | Issue 1/2024

Abstract

Objective

The risk category of gastric gastrointestinal stromal tumors (GISTs) are closely related to the surgical method, the scope of resection, and the need for preoperative chemotherapy. We aimed to develop and validate convolutional neural network (CNN) models based on preoperative venous-phase CT images to predict the risk category of gastric GISTs.

Method

A total of 425 patients pathologically diagnosed with gastric GISTs at the authors’ medical centers between January 2012 and July 2021 were split into a training set (154, 84, and 59 with very low/low, intermediate, and high-risk, respectively) and a validation set (67, 35, and 26, respectively). Three CNN models were constructed by obtaining the upper and lower 1, 4, and 7 layers of the maximum tumour mask slice based on venous-phase CT Images and models of CNN_layer3, CNN_layer9, and CNN_layer15 established, respectively. The area under the receiver operating characteristics curve (AUROC) and the Obuchowski index were calculated to compare the diagnostic performance of the CNN models.

Results

In the validation set, CNN_layer3, CNN_layer9, and CNN_layer15 had AUROCs of 0.89, 0.90, and 0.90, respectively, for low-risk gastric GISTs; 0.82, 0.83, and 0.83 for intermediate-risk gastric GISTs; and 0.86, 0.86, and 0.85 for high-risk gastric GISTs. In the validation dataset, CNN_layer3 (Obuchowski index, 0.871) provided similar performance than CNN_layer9 and CNN_layer15 (Obuchowski index, 0.875 and 0.873, respectively) in prediction of the gastric GIST risk category (All P >.05).

Conclusions

The CNN based on preoperative venous-phase CT images showed good performance for predicting the risk category of gastric GISTs.

Seven G, Silahtaroglu G, Seven OO, et al. Differentiating gastrointestinal stromal tumors from leiomyomas using a neural network trained on endoscopic ultrasonography images. Dig Dis. 2022;40(4):427–35. https://doi.org/10.1159/000520032.CrossRefPubMed

Gronchi A, Bonvalot S, Poveda Velasco A, et al. Quality of surgery and outcome in localized gastrointestinal stromal tumors treated within an international intergroup randomized clinical trial of adjuvant imatinib. JAMA Surg. 2020;155(6):e200397–404. https://doi.org/10.1001/jamasurg.2020.0397.CrossRefPubMedPubMedCentral

Tu L, Hohenberger P, Allgayer H, et al. Standard approach to gastrointestinal stromal tumors - differences between China and Europe. Visc Med. 2018;34(5):353–8. https://doi.org/10.1159/000494347.CrossRefPubMedPubMedCentral

Klug LR, Khosroyani HM, Kent JD, et al. New treatment strategies for advanced-stage gastrointestinal stromal tumours. Nat Rev Clin Oncol. 2022;19(5):328–41. https://doi.org/10.1038/s41571-022-00606-4.CrossRefPubMed

Nishida T, Sakai Y, Takagi M, et al. Adherence to the guidelines and the pathological diagnosis of high-risk gastrointestinal stromal tumors in the real world. Gastric Cancer. 2020;23(1):118–25. https://doi.org/10.1007/s10120-019-00966-4.CrossRefPubMed

Casali PG, Blay JY, Abecassis N, et al. Gastrointestinal stromal tumours: ESMO-EURACAN-GENTURIS clinical practice guidelines for diagnosis, treatment and follow-up. Ann Oncol. 2022;33(1):20–33. https://doi.org/10.1016/j.annonc.2021.09.005.CrossRefPubMed

Wang JK. Predictive value and modeling analysis of MSCT signs in gastrointestinal stromal tumors (GISTs) to pathological risk degree. Eur Rev Med Pharmacol Sci. 2017;21(5):999–1005.PubMed

Xu D, Si GY, He QZ. Correlation analysis of multi-slice computed tomography (MSCT) findings, clinicopathological factors, and prognosis of gastric gastrointestinal stromal tumors. Transl Cancer Res. 2020;9(3):1787–94. https://doi.org/10.21037/tcr.2020.02.26.CrossRefPubMedPubMedCentral

Zheng J, Xia Y, Xu A, et al. Combined model based on enhanced CT texture features in liver metastasis prediction of high-risk gastrointestinal stromal tumors. Abdom Radiol (NY). 2022;47(1):85–93. https://doi.org/10.1007/s00261-021-03321-3.CrossRefPubMed

10.

Rajathi GM. Optimized radial basis neural network for classification of breast cancer images. Curr Med Imaging. 2021;17(1):97–108. https://doi.org/10.2174/1573405616666200516172.CrossRefPubMed

11.

Ueyama H, Kato Y, Akazawa Y, et al. Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow-band imaging. J Gastroenterol Hepatol. 2021;36(2):482–9. https://doi.org/10.1111/jgh.15190.CrossRefPubMed

12.

Mukherjee P, Zhou M, Lee E, et al. A shallow convolutional neural network predicts prognosis of lung cancer patients in multi-institutional CT-image data. Nat Mach Intell. 2020;2(5):274–82. https://doi.org/10.1038/s42256-020-0173-6.CrossRefPubMedPubMedCentral

13.

Kim H, Goo JM, Lee KH, et al. Preoperative CT-based deep learning model for predicting disease-free survival in patients with lung adenocarcinomas. Radiology. 2020;296(1):216–24. https://doi.org/10.1148/radiol.2020192764.CrossRefPubMed

14.

Kang B, Yuan X, Wang H, et al. Preoperative CT-based deep learning model for predicting risk stratification in patients with gastrointestinal stromal tumors. Front Oncol. 2021;11:750875. https://doi.org/10.3389/fonc.2021.750875.CrossRefPubMedPubMedCentral

15.

Hirai K, Kuwahara T, Furukawa K, et al. Artificial intelligence-based diagnosis of upper gastrointestinal subepithelial lesions on endoscopic ultrasonography images. Gastric Cancer. 2022;25(2):382–91. https://doi.org/10.1007/s10120-021-01261-x.CrossRefPubMed

16.

Liang CW, Fang PW, Huang HY, et al. Deep convolutional neural networks detect tumor genotype from pathological tissue images in gastrointestinal stromal tumors. Cancers (Basel). 2021;13(22):5758–67. https://doi.org/10.3390/cancers13225787.CrossRef

17.

Wang J, Liu Q, Xie H, et al. Boosted EfficientNet: detection of lymph node metastases in breast cancer using convolutional neural networks. Cancers (Basel). 2021;13(4):661–74. https://doi.org/10.3390/cancers13040661.

18.

Wang J, Zhang W, Zhou X, et al. Simple analysis of the computed tomography features of gastric schwannoma. Can Assoc Radiol J. 2019;70(3):246–53. /j.carj. 2018.09.002.CrossRefPubMed

19.

Blay J, Kang Y, Nishida T, et al. Gastrointestinal stromal tumours. Nat Rev Dis Primers. 2021;7(1):22–43. https://doi.org/10.1038/s41572-021-00254-5.CrossRefPubMed

20.

Joo MK, Park JJ, Lee YH, et al. Clinical efficacy and safety of endoscopic treatment of gastrointestinal stromal tumors in the stomach. Gut Liver. 2023 Feb;15. https://doi.org/10.5009/gnl210454. Epub ahead of print.

21.

Caturegli I, Raut CP. Gastrointestinal stromal tumors and the general surgeon. Surg Clin North Am. 2022;102(4):625–36. https://doi.org/10.1016/j.suc.2022.04.005.CrossRefPubMed

22.

Casali PG, Abecassis N, Aro HT, et al. Gastrointestinal stromal tumours: ESMO- EURACAN clinical practice guidelines for diagnosis, treatment and follow-up. Ann Oncol. 2018;29(Suppl 4):iv68–78. https://doi.org/10.1093/annonc/mdy320.CrossRefPubMed

23.

Akahoshi K, Oya M, Koga T, et al. Current clinical management of gastrointestinal stromal tumor. World J Gastroenterol. 2018;24(26):2806–17. https://doi.org/10.3748/wjg.CrossRefPubMedPubMedCentral

24.

Xu J, Zhou J, Wang X, et al. A multi-class scoring system based on CT features for preoperative prediction in gastric gastrointestinal stromal tumors. Am J Cancer Res. 2020;10(11):3867–81.PubMedPubMedCentral

25.

Chen XS, Yuan W, Xu ZH, et al. Prognostic value of preoperative CT features for disease-free survival in patients with primary gastric gastrointestinal stromal tumors after resection. Abdom Radiol (NY). 2023;8(2):494–501. https://doi.org/10.1007/s00261-022-03725-9.CrossRef

26.

Couture HD, Williams LA, Geradts J, et al. Image analysis with deep learning to predict breast cancer grade, ER status, histologic subtype, and intrinsic subtype. NPJ Breast Cancer. 2018;4:30. https://doi.org/10.1038/s41523-018-0079-1.CrossRefPubMedPubMedCentral

27.

Oh CK, Kim T, Cho YK, et al. Convolutional neural network-based object detection model to identify gastrointestinal stromal tumors in endoscopic ultrasound images. J Gastroenterol Hepatol. 2021;36(12):3387–94. https://doi.org/10.1111/jgh.15653.CrossRefPubMed

28.

Liu C, Guo Y, Jiang F, et al. Gastrointestinal stromal tumors diagnosis on multi-center endoscopic ultrasound images using multi-scale image normalization and transfer learning. Technol Health Care. 2022;30(S1):47–59. https://doi.org/10.3233/THC-228005.CrossRefPubMedPubMedCentral

29.

Cannella R, La Grutta L, Midiri M, et al. New advances in radiomics of gastrointestinal stromal tumors. World J Gastroenterol. 2020;26(32):4729–38. 10.3748/ wjg. v26.i32.4729.CrossRefPubMedPubMedCentral

30.

Ng F, Kozarski R, Ganeshan B, et al. Assessment of tumor heterogeneity by CT texture analysis: can the largest cross-sectional area be used as an alternative to whole tumor analysis? Eur J Radiol. 2013;82(3):342–8. https://doi.org/10.1016/j.ejrad.2012.10.023.CrossRefPubMed

31.

Gan W, Wang H, Gu H, et al. Automatic segmentation of lung tumors on CT images based on a 2D & 3D hybrid convolutional neural network. Br J Radiol. 2021;94(1126):20210038. https://doi.org/10.1259/bjr.20210038.CrossRefPubMed

32.

Gu H, Gan W, Zhang C, et al. A 2D-3D hybrid convolutional neural network for lung lobe auto-segmentation on standard slice thickness computed tomography of patients receiving radiotherapy. Biomed Eng Online. 2021;20(1):94–106. https://doi.org/10.1186/s12938-021-00932-1.CrossRefPubMedPubMedCentral

Title: Convolutional neural network applied to preoperative venous-phase CT images predicts risk category in patients with gastric gastrointestinal stromal tumors
Authors: Jian Wang
Meihua Shao
Hongjie Hu
Wenbo Xiao
Guohua Cheng
Guangzhao Yang
Hongli Ji
Susu Yu
Jie Wan
Zongyu Xie
Maosheng Xu
Publication date: 01-12-2024
Publisher: BioMed Central
Keywords: Gastrointestinal Stromal Tumor
Computed Tomography
Computed Tomography
Published in: BMC Cancer / Issue 1/2024
Electronic ISSN: 1471-2407
DOI: https://doi.org/10.1186/s12885-024-11962-y

Webinar | 19-02-2024 | 17:30 (CET)

Keynote webinar | Spotlight on antibody–drug conjugates in cancer

Watch now

Antibody–drug conjugates (ADCs) are novel agents that have shown promise across multiple tumor types. Explore the current landscape of ADCs in breast and lung cancer with our experts, and gain insights into the mechanism of action, key clinical trials data, existing challenges, and future directions.

Dr. Véronique Diéras

Prof. Fabrice Barlesi

Developed by: Springer Medicine

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Objective

Method

Results

Conclusions

Please log in to get access to this content

Other articles of this Issue 1/2024

Association of the Advanced Lung Cancer Inflammation Index (ALI) and Gustave Roussy Immune (GRIm) score with immune checkpoint inhibitor efficacy in patients with gastrointestinal and lung cancer

Deep learning for risk stratification of thymoma pathological subtypes based on preoperative CT images

Cellular senescence and metabolic reprogramming model based on bulk/single-cell RNA sequencing reveals PTGER4 as a therapeutic target for ccRCC

Correction: Clinical features and imaging examination assessment of cervical lymph nodes for thyroid carcinoma

Pancreatic cancer in Saudi Arabia (2005–2020): increasing trend

Exercise accelerates recruitment of CD8+ T cell to promotes anti-tumor immunity in lung cancer via epinephrine

Keynote webinar | Spotlight on antibody–drug conjugates in cancer