Application of improved deep learning for detection of gastric cancer
DOI:
https://doi.org/10.65746/jbrha68Keywords:
Gastric Cancer, Early Detection, Mask-RCNN, Optimized CNN, AI-DFOAbstract
Gastric Cancer (GC) remains a major global health concern, with early-stage detection being critical for improving survival rates. However, identifying GC in its early stages is challenging due to subtle and diverse clinical manifestations. This research aims to develop an optimized deep learning framework to enhance the accuracy, efficiency, and robustness of GC detection, particularly in early-stage cases. A novel hybrid optimization technique, the Aquila Inherited Dragonfly Optimizer (AI-DFO), is proposed to fine-tune a Convolutional Neural Network (CNN) for GC classification. The approach incorporates advanced image pre-processing using median filtering and CLAHE, precise lesion segmentation with Mask R-CNN, and AI-DFO-based optimization to enhance feature learning and model generalization. The proposed AI-DFO+CNN model achieved state-of-the-art performance, with 99% accuracy for endoscopic images and 98% accuracy for histopathological images. Stage-wise analysis confirmed superior sensitivity in detecting both early and advanced GC. Furthermore, the model demonstrated strong robustness to noise and image deformation. Computational efficiency was improved with reduced training time and lower energy consumption compared to baseline models. The results validate the effectiveness of the proposed framework for reliable, early GC detection. The generalizable design of AI-DFO and the segmentation-classification pipeline make this approach scalable to other medical imaging tasks. Future research will focus on large-scale multi-center validation, integration with real-time clinical workflows, and the application of the AI-DFO framework to other complex medical image analysis tasks beyond gastric cancer.
References
1. Lee SA, Cho HC, Cho HC. A novel approach for increased convolutional neural network performance in gastric-cancer classification using endoscopic images. IEEE Access. 2021; 9: 51847–51854. doi: 10.1109/ACCESS.2021.3069747
2. Qiu W, Xie J, Shen Y, et al. Endoscopic image recognition method of gastric cancer based on deep learning model. Expert Systems. 2022; 39(3): e12758. doi: 10.1111/exsy.12758
3. Wang H, Ding Y, Chen Y, et al. A novel genomic classification system of gastric cancer via integrating multidimensional genomic characteristics. Gastric Cancer. 2021; 24(6): 1227–1241. doi: 10.1007/s10120-021-01201-9
4. Ooki A, Yamashita K, Kikuchi S, et al. Phosphatase of regenerating liver-3 as a prognostic biomarker in histologically node-negative gastric cancer. Oncology Reports. 2009; 21(6): 1467–1475. doi: 10.3892/or_00000376
5. 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. CA: A Cancer Journal for Clinicians. 2024; 74(3): 229–263. doi: 10.3322/caac.21834
6. Sun M, Zhang G, Dang H, et al. Accurate gastric cancer segmentation in digital pathology images using deformable convolution and multi-scale embedding networks. IEEE Access. 2019; 7: 75530–75541. doi: 10.1109/ACCESS.2019.2918800
7. Tang Z, Xu Y, Jin L, et al. Deep learning of imaging phenotype and genotype for predicting overall survival time of glioblastoma patients. IEEE Transactions on Medical Imaging. 2020; 39(6): 2100–2109. doi: 10.1109/TMI.2020.2964310
8. Zhang L, Dong D, Zhong, L et al. Multi-focus network to decode imaging phenotype for overall survival prediction of gastric cancer patients. IEEE Journal of Biomedical and Health Informatics. 2021; 25(10): 3933–3942. doi: 10.1109/JBHI.2021.3087634
9. Chisnariandini N, Aji AP, Mariyam PD, et al. Measurement on real-time diagnostic of gastric tumor model using wireless endoscopy system. 2018 5th International Conference on Information Technology, Computer, and Electrical Engineering (ICITACEE). IEEE; 2018. pp. 105–108. doi: 10.1109/ICITACEE.2018.8576964
10. Meng L, Dong D, Chen X, et al. 2D and 3D CT radiomic features performance comparison in characterization of gastric cancer: A multi-center study. IEEE Journal of Biomedical and Health Informatics. 2020; 25(3): 755–763. doi: 10.1109/JBHI.2020.3002805
11. Yazici O, Sendur MAN, Ozdemir N, et al. Targeted therapies in gastric cancer and future perspectives. World Journal of Gastroenterology. 2016; 22(2): 471. doi: 10.3748/wjg.v22.i2.471
12. Alberts SR, Cervantes A, Van de Velde C J H. Gastric cancer: Epidemiology, pathology and treatment. Annals of Oncology. 2003; 14: ii31–ii36. doi: 10.1093/annonc/mdg726
13. Cristian CR, Oliver S, Nicolae L, et al. Advanced image processing in support of thz imaging for early detection of gastric cancer. 2018 International Conference and Exposition on Electrical and Power Engineering (EPE). IEEE; 2018. pp. 0634–0637. doi: 10.1109/ICEPE.2018.8559831
14. Li X, Chai Y, Zhang K, et al. Early gastric cancer detection based on the combination of convolutional neural network and attention mechanism. 2021 China Automation Congress (CAC). IEEE; 2021. pp. 5731–5735. doi: 10.1109/cac53003.2021.9728413
15. Sakai Y, Takemoto S, Hori K, et al. Automatic detection of early gastric cancer in endoscopic images using a transferring convolutional neural network. 2018 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC). IEEE; 2018. pp. 4138–4141. doi: 10.1109/EMBC.2018.8513274
16. Pernot S, Terme M, Radosevic-Robin N, et al. Infiltrating and peripheral immune cell analysis in advanced gastric cancer according to the Lauren classification and its prognostic significance. Gastric Cancer. 2020; 23(1): 73–81. doi: 10.1007/s10120-019-00983-3
17. Dong D, Fang MJ, Tang L, et al. Deep learning radiomic nomogram can predict the number of lymph node metastasis in locally advanced gastric cancer: An international multicenter study. Annals of Oncology. 2020; 31(7): 912–920. doi: 10.1016/j.annonc.2020.04.003
18. Hatami S, Shamsaee R, Olyaei MH. Detection and classification of gastric precancerous diseases using deep learning. 2020 6th Iranian Conference on Signal Processing and Intelligent Systems (ICSPIS). IEEE; 2020. pp. 1–5. doi: 10.1109/ICSPIS51611.2020.9349603
19. Okamoto H, Cap QH, Nomura T, et al. Stochastic gastric image augmentation for cancer detection from X-ray Images. 2019 IEEE international conference on big data (big data). IEEE; 2019. pp. 4858–4863. doi: 10.1109/BigData47090.2019.9006079
20. Swamy ST, Thotakura SB, Puli A, et al. Design and Analysis of MEMS based GMI sensor for detection of gastric cancer cells. 2018 International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE; 2018 pp. 131–135. doi: 10.1109/ICSSIT.2018.8748635
21. Yao K. The endoscopic diagnosis of early gastric cancer. Annals of gastroenterology: quarterly publication of the Hellenic Society of Gastroenterology. 2013; 26(1): 11. doi: 10.1016/s0016-5107(79)73384-0
22. Turppa E, Polaka I, Vasiljevs E, et al. Repeatability study on a classifier for gastric cancer detection from breath sensor data. 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE). IEEE; 2019. pp. 450–453. doi: 10.1109/BIBE.2019.00087
23. Aslam MA, Xue C, Liu M, et al. Classification and prediction of gastric cancer from saliva diagnosis using Artificial neural network. Engineering Letters. 2021; 29(1).
24. Wang L, Shi B, Li P, et al. Short-term heart rate variability and blood biomarkers of gastric cancer prognosis. IEEE Access. 2020; 8: 15159–15165. doi: 10.1109/ACCESS.2020.2966378
25. Kinami S, Nakamura N, Miyashita T, et al. nPTD classification: An updated classification of gastric cancer location for function preserving gastrectomy based on physiological lymphatic flow. BMC Cancer. 2021; 21(1): 1231. doi: 10.1186/s12885-021-08936-9
26. Yoon HJ, Kim JH. Lesion-based convolutional neural network in diagnosis of early gastric cancer. Clinical Endoscopy. 2020; 53(2): 127–131. doi: 10.5946/ce.2020.046
27. Cao G, Song W, Zhao Z. Gastric cancer diagnosis with mask R-CNN. 2019 11th international conference on intelligent human-machine systems and cybernetics (IHMSC). IEEE. 2019; 1: 60–63. doi: 10.1109/IHMSC.2019.00022
28. Gao YL, Zhang YH. Gastric cancer prevention targeted on risk assessment: The Kyoto Classification of Gastritis. 2021 11th International Conference on Information Technology in Medicine and Education (ITME). IEEE; 2021. pp. 330–335. doi: 10.1109/itme53901.2021.00074
29. Polaka I, Padilla M, Mezmale L, et al. Class decomposition for gastric cancer detection from breath. 2021 62nd international scientific conference on Information Technology and Management Science of Riga Technical University (ITMS). IEEE; 2021. pp. 1–5. doi: 10.1109/itms52826.2021.9615341
30. Sharanyaa S, Vijayalakshmi S, Therasa M, et al. DCNET: A novel implementation of gastric cancer detection system through deep learning convolution networks. 2022 international conference on advanced computing technologies and applications (ICACTA). IEEE; 2022. pp. 1–5. doi: 10.1109/ICACTA54488.2022.9752960
31. Yenginer H, Demir Ö. Stomach cancer detection using CIELAB color space. 2019 Medical Technologies Congress (TIPTEKNO). IEEE; 2019. pp. 1–4. doi: 10.1109/tiptekno47231.2019.8972044
32. Abe K, Shirakawa K, Minami M, et al. Automated extraction of the essential region in computer-aided diagnosis of helicobacter pylori infection using gastric X-ray images. 2018 7th International Congress on Advanced Applied Informatics (IIAI-AAI). IEEE; 2018. pp. 626–629. doi: 10.1109/IIAI-AAI.2018.00131
33. Liu B, Yao K, Huang M, et al. Gastric pathology image recognition based on deep residual networks. 2018 IEEE 42nd annual computer software and applications conference (COMPSAC). IEEE. 2018; 2: 408–412. doi: 10.1109/COMPSAC.2018.10267
34. Minghao Y, Kangkang L, Jiachen Y, et al. Point-of-care chemiluminescence immunoassay centrifugal microfluidics for gastrin-17 detection. 2020 IEEE 5th Optoelectronics Global Conference (OGC). IEEE; 2020. pp. 204–206. doi: 10.1109/OGC50007.2020.9260468
35. Pan D, Zhang R, Wang Y, et al. Detection of early gastric cancer based on single shot detector with feature enhancement. 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). IEEE; 2020. pp. 1091–1095. doi: 10.1109/BIBM49941.2020.9313339
36. Alić B, Gurbeta L, Badnjević A, et al. Classification of metabolic syndrome patients using implemented expert system. CMBEBIH 2017: Proceedings of the International Conference on Medical and Biological Engineering 2017. Singapore: Springer Singapore; 2017. pp. 601–607. doi: 10.1007/978-981-10-4166-2_91
37. Badnjević A, Cifrek M, Koruga D. Integrated software suite for diagnosis of respiratory diseases. Eurocon 2013. IEEE; 2013. pp. 564–568. doi: 10.1109/eurocon.2013.6625037
38. Veljović E, Špirtović-Halilović S, Muratović S, et al. Artificial neural network and docking study in design and synthesis of xanthenes as antimicrobial agents. CMBEBIH 2017: Proceedings of the international conference on medical and biological engineering 2017. Singapore: Springer Singapore; 2017. pp. 617–626. doi: 10.1007/978-981-10-4166-2_93
39. Badnjevic A, Cifrek M, Koruga D. Classification of Chronic Obstructive Pulmonary Disease (COPD) using integrated software suite. XIII Mediterranean Conference on Medical and Biological Engineering and Computing 2013: MEDICON 2013, 25–28 September 2013, Seville, Spain. Cham: Springer International; 2014. pp. 911–914. doi: 10.1007/978-3-319-00846-2_225
40. Shibata T, Teramoto A, Yamada H, et al. Automated detection and segmentation of early gastric cancer from endoscopic images using mask R-CNN. Applied Sciences. 2020; 10(11): 3842. doi: 10.3390/app10113842
41. Abualigah L, Yousri D, Abd Elaziz M, et al. Aquila optimizer: A novel meta-heuristic optimization algorithm. Computers & Industrial Engineering. 2021; 157: 107250. doi: 10.1016/j.cie.2021.107250
42. Aghelpour P, Mohammadi B, Mehdizadeh S, et al. A novel hybrid dragonfly optimization algorithm for agricultural drought prediction. Stochastic Environmental Research and Risk Assessment. 2021; 35(12): 2459–2477. doi: 10.1007/s00477-021-02011-2
Downloads
Published
Data Availability Statement
The data used in this study are available from the corresponding author upon reasonable request.
Issue
Section
License
Copyright (c) 2026 Yamuna Bee Jafarullah Khan, Balaji Subramanian
This work is licensed under a Creative Commons Attribution 4.0 International License.
