Abstract
Gastrointestinal stromal tumour (GIST) is the type of tumour that develops in the gastrointestinal tract and disrupts the digestive system. The two most crucial factors for GIST detection and monitoring are structural and functional information, either one of which can be determined by a single imaging modality. Computed tomography (CT) and positron emission tomography (PET) are the two non-invasive imaging techniques that are frequently employed for this purpose. Effective clinical management dependent on precise diagnosis, which centres on accurate tumour detection and segmentation, is the major concern with manual processes. To over this problem, we proposed a deep learning framework in two stages: in the first stage, we use Dense Net and VGG model for CT and PET image fusion, and in the second stage, for effective tumour segmentation we use feature pyramid network (FPN) for automatic and accurate tumour detection. The advantage of using Dense Net and VGG Net for medical image fusion is their ability to extract features at different scales and resolutions. This allows for a more comprehensive representation of the input images, which can be beneficial from medical image fusion. The fused image is segmented using FPN semantic segmentation model with Efficient Net-B0 as encoder; finally the proposed model performance was evaluated through qualitative and quantitative metrics. The average mean squared error value is 63.27, the average peak signal-to-noise ratio value is 30.154 and the average Structural Similarity Index Measure value is 0.9647. The proposed FPN with Efficient Net-B0 segmentation produced an intersection over union of 0.8521 and pixel accuracy 96.09, which are comparatively higher than the other existing models. The proposed deep learning framework outperformed well in automatically and accurately segmenting GIST, assisting doctors in effective clinical management.
Similar content being viewed by others
Availability of data and materials
References
Bai X, Zhou W, Li Y, Lin G (2021) Transanal endoscopic microsurgery with alternative neoadjuvant imatinib for localized rectal gastrointestinal stromal tumor: a single center experience with long-term surveillance. Surg Endosc 35:3607–3617
Ballati A, Essaidi Z, El Attar L, Errguibi D, Hajri A, Boufettal R, Jai SRE, Chehab F (2021) A gastrointestinal stromal tumor of stomach presenting with an intratumoral abscess: a case report. Ann Med Surg 63:102143
Chen T, Liu S, Li Y, Feng X, Xiong W, Zhao X, Yang Y et al (2019) Developed and validated a prognostic nomogram for recurrence-free survival after complete surgical resection of local primary gastrointestinal stromal tumors based on deep learning. EBioMedicine 39:272–279
Domingues I, Pereira G, Martins P, Duarte H, Santos J, Abreu PH (2020) Using deep learning techniques in medical imaging: a systematic review of applications on CT and PET. Artif Intell Rev 53:4093–4160
Saito H, Aoki T, Aoyama K, Kato Y, Tsuboi A, Yamada A, Fujishiro M et al (2020) Automatic detection and classification of protruding lesions in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointest Endosc 92(1):144–151
Garg H, Gupta N, Agrawal R, Shivani S, Sharma B (2022) A real time cloud-based framework for glaucoma screening using EfficientNet. Multimed Tools Appl. https://doi.org/10.1007/s11042-021-11559-8
Griffith AM, Olpin JD (2022) Imaging of gastrointestinal stromal tumors. Curr Radiol Rep 10(11):129–139
Gupta SK, Rateria N (2020) Gastrointestinal stromal tumors (GIST): an overview. Indian J Surg. https://doi.org/10.1007/s12262-019-02052-6
Haskins G, Kruger U, Yan P (2020) Deep learning in medical image registration: a survey. Mach vis Appl 31:1–18
Huang M-L, Yi-Zhen Wu (2022) Semantic segmentation of pancreatic medical images by using convolutional neural network. Biomed Signal Process Control 73:103458
Inoue A, Ota S, Yamasaki M, Batsaikhan B, Furukawa A, Watanabe Y (2022) Gastrointestinal stromal tumors: a comprehensive radiological review. Jpn J Radiol 40(11):1105–1120
Jia X, Wan L, Chen X, Ji W, Huang S, Qi Y, Cui J et al (2022) Risk stratification for 1-to 2 cm gastric gastrointestinal stromal tumors: visual assessment of CT and EUS high-risk features versus CT radiomics analysis. Eur Radiol. https://doi.org/10.1007/s00330-022-09228-x
Li L, Zhao X, Wei Lu, Tan S (2020) Deep learning for variational multimodality tumor segmentation in PET/CT. Neurocomputing 392:277–295
Li Yi, Zhao J, Lv Z, Li J (2021a) Medical image fusion method by deep learning. Int J Cognit Comput Eng 2:21–29
Li G, Lin Y, Xingda Qu (2021b) An infrared and visible image fusion method based on multi-scale transformation and norm optimization. Inform Fusion 71:109–129
Menon N, Mandelkern M (2022) Utility of PET scans in the diagnosis and management of gastrointestinal tumors. Dig Dis Sci 67(10):4633–4653
Minoda Y, Ihara E, Komori K, Ogino H, Otsuka Y, Chinen T, Tsuda Y, Ando K, Yamamoto H, Ogawa Y (2020) Efficacy of endoscopic ultrasound with artificial intelligence for the diagnosis of gastrointestinal stromal tumors. J Gastroenterol 55:1119–1126
Pu B, Yuhuan Lu, Chen J, Li S, Zhu N, Wei W, Li K (2022) Mobileunet-fpn: a semantic segmentation model for fetal ultrasound four-chamber segmentation in edge computing environments. IEEE J Biomed Health Inform 26(11):5540–5550
Saeidi N, AlAli Y, Boushehry R, Safi SA (2022) An unusual and life-threatening presentation of a large GIST. Int J Surg Case Rep 99:107666. https://doi.org/10.1016/j.ijscr.2022.107666
Sharma N, Gupta S, Koundal D, Alyami S, Alshahrani H, Asiri Y, Shaikh A (2023) U-Net model with transfer learning model as a backbone for segmentation of gastrointestinal tract. Bioengineering 10(1):119
Tuladhar S, Abeer Alsadoon PWC, Prasad AE, Ali, and Ahmad Alrubaie, (2022) A novel solution of deep learning for endoscopic ultrasound image segmentation: enhanced computer aided diagnosis of gastrointestinal stromal tumor. Multimed Tools Appl 81(17):23845–23865
Varnyú D, Szirmay-Kalos L (2022) A comparative study of deep neural networks for real-time semantic segmentation during the transurethral resection of bladder tumors. Diagnostics 12(11):2849
Virarkar Mayur K, Sai Swarupa R Vulasala, Anjali Verma Gupta, DheerajReddy Gopireddy, Sindhu Kumar, Mauricio Hernandez, Chandana Lall, Priya Bhosale (2022) Virtual non-contrast imaging in The Abdomen and The Pelvis: an overview. In: Seminars in Ultrasound, CT and MRI. 43(4): 293-310, WB Saunders
Yang C-H, Ren J-H, Huang H-C, Chuang L-Y, Chang P-Y (2021) Deep hybrid convolutional neural network for segmentation of melanoma skin lesion. Comput Intell Neurosci 2021:1–15
Zhang H, Han Xu, Tian X, Jiang J, Ma J (2021) Image fusion meets deep learning: a survey and perspective. Inform Fusion 76:323–336
Zhang B, Zhu F, Li P, Zhu J (2022) Artificial intelligence-assisted endoscopic ultrasound in the diagnosis of gastrointestinal stromal tumors: a meta-analysis. Surg Endosc. https://doi.org/10.1007/s00464-022-09597-w
Funding
There is no funding for the research.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
There are no competing interests.
Ethical approval
Ethical approval is not applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Allapakam, V., Karuna, Y. A hybrid feature pyramid network and Efficient Net-B0-based GIST detection and segmentation from fused CT-PET image. Soft Comput 27, 11877–11893 (2023). https://doi.org/10.1007/s00500-023-08614-x
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-023-08614-x