{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T14:32:13Z","timestamp":1784039533772,"version":"3.55.0"},"reference-count":47,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T00:00:00Z","timestamp":1713484800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Gastrointestinal (GI) diseases are prevalent medical conditions that require accurate and timely diagnosis for effective treatment. To address this, we developed the Multi-Fusion Convolutional Neural Network (MF-CNN), a deep learning framework that strategically integrates and adapts elements from six deep learning models, enhancing feature extraction and classification of GI diseases from endoscopic images. The MF-CNN architecture leverages truncated and partially frozen layers from existing models, augmented with novel components such as Auxiliary Fusing Layers (AuxFL), Fusion Residual Block (FuRB), and Alpha Dropouts (\u03b1DO) to improve precision and robustness. This design facilitates the precise identification of conditions such as ulcerative colitis, polyps, esophagitis, and healthy colons. Our methodology involved preprocessing endoscopic images sourced from open databases, including KVASIR and ETIS-Larib Polyp DB, using adaptive histogram equalization (AHE) to enhance their quality. The MF-CNN framework supports detailed feature mapping for improved interpretability of the model\u2019s internal workings. An ablation study was conducted to validate the contribution of each component, demonstrating that the integration of AuxFL, \u03b1DO, and FuRB played a crucial part in reducing overfitting and efficiency saturation and enhancing overall model performance. The MF-CNN demonstrated outstanding performance in terms of efficacy, achieving an accuracy rate of 99.25%. It also excelled in other key performance metrics with a precision of 99.27%, a recall of 99.25%, and an F1-score of 99.25%. These metrics confirmed the model\u2019s proficiency in accurate classification and its capability to minimize false positives and negatives across all tested GI disease categories. Furthermore, the AUC values were exceptional, averaging 1.00 for both test and validation sets, indicating perfect discriminative ability. The findings of the P-R curve analysis and confusion matrix further confirmed the robust classification performance of the MF-CNN. This research introduces a technique for medical imaging that can potentially transform diagnostics in gastrointestinal healthcare facilities worldwide.<\/jats:p>","DOI":"10.7717\/peerj-cs.1950","type":"journal-article","created":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T07:44:42Z","timestamp":1713512682000},"page":"e1950","source":"Crossref","is-referenced-by-count":10,"title":["Development of a multi-fusion convolutional neural network (MF-CNN) for enhanced gastrointestinal disease diagnosis in endoscopy image analysis"],"prefix":"10.7717","volume":"10","author":[{"given":"Tanzim","family":"Hossain","sequence":"first","affiliation":[{"name":"Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9176-3537","authenticated-orcid":true,"given":"F M Javed Mehedi","family":"Shamrat","sequence":"additional","affiliation":[{"name":"Department of Computer System and Technology, University of Malaya, Kuala Lumpur, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xujuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Business, University of Southern Queensland, Springfield, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imran","family":"Mahmud","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md. Sakib Ali","family":"Mazumder","sequence":"additional","affiliation":[{"name":"Department of Software Engineering, Daffodil International University, Dhaka, Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sharmin","family":"Sharmin","sequence":"additional","affiliation":[{"name":"Department of Computer System and Technology, University of Malaya, Kuala Lumpur, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5919-0174","authenticated-orcid":true,"given":"Raj","family":"Gururajan","sequence":"additional","affiliation":[{"name":"School of Business, University of Southern Queensland, Springfield, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2024,4,19]]},"reference":[{"issue":"11","key":"10.7717\/peerj-cs.1950\/ref-1","doi-asserted-by":"publisher","first-page":"1174","DOI":"10.3390\/biology10111174","article-title":"COVID-19 detection using deep learning algorithm on chest X-ray images","volume":"10","author":"Akter","year":"2021","journal-title":"Biology"},{"issue":"5","key":"10.7717\/peerj-cs.1950\/ref-2","doi-asserted-by":"publisher","first-page":"595","DOI":"10.3390\/pr8050595","article-title":"MobileNetV2 ensemble for cervical precancerous lesions classification","volume":"8","author":"Buiu","year":"2020","journal-title":"Processes"},{"key":"10.7717\/peerj-cs.1950\/ref-3","article-title":"Keras","author":"Chollet","year":"2015"},{"key":"10.7717\/peerj-cs.1950\/ref-4","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1610.02357","article-title":"Xception: deep learning with depthwise separable convolutions (Version 3). ArXiv","author":"Chollet","year":"2016"},{"issue":"3","key":"10.7717\/peerj-cs.1950\/ref-5","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1007\/s13246-020-00888-x","article-title":"Truncated inception net: COVID-19 outbreak screening using chest X-rays","volume":"43","author":"Das","year":"2020","journal-title":"Physical and Engineering Sciences in Medicine"},{"issue":"4","key":"10.7717\/peerj-cs.1950\/ref-6","doi-asserted-by":"publisher","first-page":"5343","DOI":"10.1007\/s11042-022-12178-7","article-title":"Multi-modal active learning with deep reinforcement learning for target feature extraction in multi-media image processing applications","volume":"82","author":"Dhiman","year":"2023","journal-title":"Multimedia Tools and Applications"},{"issue":"16","key":"10.7717\/peerj-cs.1950\/ref-7","doi-asserted-by":"publisher","first-page":"165001","DOI":"10.1088\/1361-6560\/aad51c","article-title":"Computer-aided detection of small intestinal ulcer and erosion in wireless capsule endoscopy images","volume":"63","author":"Fan","year":"2018","journal-title":"Physics in Medicine and Biology"},{"key":"10.7717\/peerj-cs.1950\/ref-8","article-title":"Loss Functions\u2014ML Glossary documentation\u201d, Ml-cheatsheet.readthedocs.io","author":"GitHub","year":"2020"},{"key":"10.7717\/peerj-cs.1950\/ref-9","article-title":"Everything you need to know about VGG16","author":"Great Learning","year":"2022"},{"issue":"7","key":"10.7717\/peerj-cs.1950\/ref-10","doi-asserted-by":"publisher","first-page":"809","DOI":"10.3390\/bioengineering10070809","article-title":"GIT-Net: an ensemble deep learning-based GI tract classification of endoscopic images","volume":"10","author":"Gunasekaran","year":"2023","journal-title":"Bioengineering"},{"issue":"1","key":"10.7717\/peerj-cs.1950\/ref-11","doi-asserted-by":"publisher","first-page":"2084878","DOI":"10.1080\/23311916.2022.2084878","article-title":"Detection and classification of gastrointestinal disease using convolutional neural network and SVM","volume":"9","author":"Haile","year":"2022","journal-title":"Cogent Engineering"},{"key":"10.7717\/peerj-cs.1950\/ref-12","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","article-title":"Identity mappings in deep residual networks","volume":"9908","author":"He","year":"2016","journal-title":"ECCV"},{"issue":"2","key":"10.7717\/peerj-cs.1950\/ref-13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/6170416","article-title":"Deep learning algorithms for detection and classification of gastrointestinal diseases","volume":"2021","author":"Hmoud Al-Adhaileh","year":"2021","journal-title":"Complexity"},{"key":"10.7717\/peerj-cs.1950\/ref-14","doi-asserted-by":"publisher","DOI":"10.1109\/icosec54921.2022.9951879","article-title":"COVID-19 detection through deep learning algorithms using chest x-ray images","author":"Hossain","year":"2022"},{"key":"10.7717\/peerj-cs.1950\/ref-15","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1109\/ACII.2013.47","article-title":"Facing imbalanced data-recommendations for the use of performance metrics","author":"Jeni","year":"2013"},{"key":"10.7717\/peerj-cs.1950\/ref-16","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3010448","article-title":"Computer-aided gastrointestinal diseases analysis from wireless capsule endoscopy: a framework of best features selection","volume":"8","author":"Khan","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.1950\/ref-17","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1109\/JBHI.2016.2635663","article-title":"An ensemble of fine-tuned convolutional neural networks for medical image classification","volume":"21","author":"Kumar","year":"2017","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"5","key":"10.7717\/peerj-cs.1950\/ref-18","doi-asserted-by":"publisher","first-page":"e0232127","DOI":"10.1371\/journal.pone.0232127","article-title":"Classification of breast cancer histopathological images using interleaved DenseNet with SENet (IDSNet)","volume":"15","author":"Li","year":"2020","journal-title":"PLOS ONE"},{"issue":"11","key":"10.7717\/peerj-cs.1950\/ref-19","doi-asserted-by":"publisher","first-page":"102416","DOI":"10.1016\/j.displa.2023.102416","article-title":"MFID-Net: multi-scaled feature-fused image dehazing via dynamic weights","volume":"78","author":"Liu","year":"2023","journal-title":"Displays"},{"issue":"5","key":"10.7717\/peerj-cs.1950\/ref-20","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1002\/jemt.23447","article-title":"Classification of stomach infections: a paradigm of convolutional neural network along with classical features fusion and selection","volume":"83","author":"Majid","year":"2020","journal-title":"Microscopy Research and Technique"},{"issue":"12","key":"10.7717\/peerj-cs.1950\/ref-21","doi-asserted-by":"publisher","first-page":"101794","DOI":"10.1016\/j.media.2020.101794","article-title":"Deep-COVID: predicting COVID-19 from chest X-ray images using deep transfer learning","volume":"65","author":"Minaee","year":"2020","journal-title":"Medical Image Analysis"},{"issue":"6","key":"10.7717\/peerj-cs.1950\/ref-22","doi-asserted-by":"publisher","first-page":"103683","DOI":"10.1016\/j.bspc.2022.103683","article-title":"Diagnosing gastrointestinal diseases from endoscopy images through a multi-fused CNN with auxiliary layers, alpha dropouts, and a fusion residual block","volume":"76","author":"Montalbo","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"issue":"4","key":"10.7717\/peerj-cs.1950\/ref-23","doi-asserted-by":"publisher","first-page":"101925","DOI":"10.1016\/j.mex.2022.101925","article-title":"Fusing compressed deep ConvNets with a self-normalizing residual block and alpha dropout for a cost-efficient classification and diagnosis of gastrointestinal tract diseases","volume":"9","author":"Montalbo","year":"2022","journal-title":"MethodsX"},{"issue":"9","key":"10.7717\/peerj-cs.1950\/ref-24","doi-asserted-by":"publisher","first-page":"102072","DOI":"10.1016\/j.mex.2023.102072","article-title":"Automating mosquito taxonomy by compressing and enhancing a feature fused EfficientNet with knowledge distillation and a novel residual skip block","volume":"10","author":"Montalbo","year":"2023","journal-title":"MethodsX"},{"issue":"3","key":"10.7717\/peerj-cs.1950\/ref-25","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1002\/ima.22850","article-title":"An automatic gastric polyp detection technique using deep learning","volume":"33","author":"Mushtaq","year":"2023","journal-title":"International Journal of Imaging Systems and Technology"},{"issue":"4","key":"10.7717\/peerj-cs.1950\/ref-26","doi-asserted-by":"publisher","first-page":"479","DOI":"10.2174\/1573405616666200928144626","article-title":"Detection and classification of gastrointestinal diseases using machine learning","volume":"17","author":"Naz","year":"2021","journal-title":"Current Medical Imaging"},{"key":"10.7717\/peerj-cs.1950\/ref-27","doi-asserted-by":"publisher","first-page":"114883","DOI":"10.1016\/j.eswa.2021.114883","article-title":"COVID-19: automatic detection from X-ray images by utilizing deep learning methods","volume":"176","author":"Nigam","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.1950\/ref-28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/2742781","article-title":"Automatic classification of hypertension types based on personal features by machine learning algorithms","author":"Nour","year":"2020"},{"key":"10.7717\/peerj-cs.1950\/ref-29","first-page":"31","article-title":"Modern neural networks generalize on small data sets","author":"Olson","year":"2018"},{"key":"10.7717\/peerj-cs.1950\/ref-30","first-page":"12607","article-title":"In defense of pre-trained imagenet architectures for real-time semantic segmentation of road-driving images","author":"Orsic","year":"2019"},{"issue":"7","key":"10.7717\/peerj-cs.1950\/ref-31","doi-asserted-by":"publisher","first-page":"103638","DOI":"10.1016\/j.jbi.2020.103638","article-title":"Residual LSTM layered CNN for classification of gastrointestinal tract diseases","volume":"113","author":"\u00d6zt\u00fcrk","year":"2021","journal-title":"Journal of Biomedical Informatics"},{"key":"10.7717\/peerj-cs.1950\/ref-32","volume-title":"The burden of digestive diseases in the Region of the Americas, 2000\u20132019","author":"PAHO","year":"2021"},{"issue":"2","key":"10.7717\/peerj-cs.1950\/ref-33","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3329\/jemc.v4i2.19458","article-title":"Upper gastrointestinal symptoms in general population of a district in Bangladesh","volume":"4","author":"Perveen","year":"2014","journal-title":"Journal of Enam Medical College"},{"issue":"3","key":"10.7717\/peerj-cs.1950\/ref-34","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/S0734-189X(87)80186-X","article-title":"Adaptive histogram equalization and its variations","volume":"39","author":"Pizer","year":"1987","journal-title":"Computer Vision, Graphics, and Image Processing"},{"key":"10.7717\/peerj-cs.1950\/ref-35","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1145\/3083187.3083212","article-title":"Kvasir: a multi-class image dataset for computer aided gastrointestinal disease detection","author":"Pogorelov","year":"2017"},{"key":"10.7717\/peerj-cs.1950\/ref-36","doi-asserted-by":"publisher","first-page":"99227","DOI":"10.1109\/ACCESS.2020.2996770","article-title":"Colorectal disease classification using efficiently scaled dilation in convolutional neural network","volume":"8","author":"Poudel","year":"2020","journal-title":"IEEE Access"},{"issue":"1","key":"10.7717\/peerj-cs.1950\/ref-37","doi-asserted-by":"publisher","first-page":"20804","DOI":"10.1038\/s41598-022-25089-2","article-title":"ResNet-32 and FastAI for diagnoses of ductal carcinoma from 2D tissue slides","volume":"12","author":"Praveen","year":"2022","journal-title":"Scientific Reports"},{"key":"10.7717\/peerj-cs.1950\/ref-38","first-page":"158","article-title":"Feature extraction: a survey of the types, techniques, applications","author":"Salau","year":"2019"},{"key":"10.7717\/peerj-cs.1950\/ref-39","doi-asserted-by":"publisher","first-page":"4510","DOI":"10.1109\/CVPR.2018.00474","article-title":"MobileNetV2: inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"issue":"3","key":"10.7717\/peerj-cs.1950\/ref-40","doi-asserted-by":"publisher","first-page":"101214","DOI":"10.1016\/j.jestch.2022.101214","article-title":"Towards automated eye cancer classification via VGG and ResNet networks using transfer learning","volume":"35","author":"Santos-Bustos","year":"2022","journal-title":"Engineering Science and Technology, an International Journal"},{"issue":"1","key":"10.7717\/peerj-cs.1950\/ref-41","doi-asserted-by":"publisher","first-page":"119","DOI":"10.3390\/bioengineering10010119","article-title":"U-Net model with transfer learning model as a backbone for segmentation of gastrointestinal tract","volume":"10","author":"Sharma","year":"2023","journal-title":"Bioengineering"},{"issue":"2","key":"10.7717\/peerj-cs.1950\/ref-42","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s11548-013-0926-3","article-title":"Toward embedded detection of polyps in WCE images for early diagnosis of colorectal cancer","volume":"9","author":"Silva","year":"2014","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"10.7717\/peerj-cs.1950\/ref-43","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.compmedimag.2019.05.001","article-title":"Brain tumor classification for MR images using transfer learning and fine-tuning","volume":"75","author":"Swati","year":"2019","journal-title":"Computerized Medical Imaging and Graphics"},{"issue":"2","key":"10.7717\/peerj-cs.1950\/ref-44","doi-asserted-by":"publisher","first-page":"379","DOI":"10.3390\/sym15020379","article-title":"A deep-learning approach for identifying and classifying digestive diseases","volume":"15","author":"Thomas Abraham","year":"2023","journal-title":"Symmetry"},{"issue":"6","key":"10.7717\/peerj-cs.1950\/ref-45","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1016\/j.gie.2013.06.026","article-title":"Wireless capsule endoscopy","volume":"78","author":"Wang","year":"2013","journal-title":"Gastrointestinal Endoscopy"},{"issue":"9","key":"10.7717\/peerj-cs.1950\/ref-46","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.21037\/atm.2020.04.39","article-title":"A deep learning, image based approach for automated diagnosis for inflammatory skin diseases","volume":"8","author":"Wu","year":"2020","journal-title":"Annals of Translational Medicine"},{"issue":"8","key":"10.7717\/peerj-cs.1950\/ref-47","doi-asserted-by":"publisher","first-page":"100394","DOI":"10.1016\/j.smhl.2023.100394","article-title":"Deep learning for gastric location classification: An analysis of location boundaries and improvements through attention and contrastive learning","volume":"28","author":"Zhang","year":"2023","journal-title":"Smart Health"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-1950.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1950.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1950.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1950.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T07:44:55Z","timestamp":1713512695000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-1950"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,19]]},"references-count":47,"alternative-id":["10.7717\/peerj-cs.1950"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.1950","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,19]]},"article-number":"e1950"}}