{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:41:55Z","timestamp":1778251315416,"version":"3.51.4"},"reference-count":22,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T00:00:00Z","timestamp":1677110400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Purpose: The detection of where an organ starts and where it ends is achievable and, since this information can be delivered in real time, it could be quite important for several reasons. For one, by having the practical knowledge of the Wireless Endoscopic Capsule (WEC) transition through an organ\u2019s domain, we are able to align and control the endoscopic operation with any other possible protocol, i.e., delivering some form of treatment on the spot. Another is having greater anatomical topography information per session, therefore treating the individual in detail (not \u201cin general\u201d). Even the fact that by gathering more accurate information for a patient by merely implementing clever software procedures is a task worth exploiting, since the problems we have to overcome in real-time processing of the capsule findings (i.e., wireless transfer of images to another unit that will apply the necessary real time computations) are still challenging. This study proposes a computer-aided detection (CAD) tool, a CNN algorithm deployed to run on field programmable gate array (FPGA), able to automatically track the capsule transitions through the entrance (gate) of esophagus, stomach, small intestine and colon, in real time. The input data are the wireless transmitted image shots of the capsule\u2019s camera (while the endoscopy capsule is operating). Methods: We developed and evaluated three distinct multiclass classification CNNs, trained on the same dataset of total 5520 images extracted by 99 capsule videos (total 1380 frames from each organ of interest). The proposed CNNs differ in size and number of convolution filters. The confusion matrix is obtained by training each classifier and evaluating the trained model on an independent test dataset comprising 496 images extracted by 39 capsule videos, 124 from each GI organ. The test dataset was further evaluated by one endoscopist, and his findings were compared with CNN-based results. The statistically significant of predictions between the four classes of each model and the comparison between the three distinct models is evaluated by calculating the p-values and chi-square test for multi class. The comparison between the three models is carried out by calculating the macro average F1 score and Mattheus correlation coefficient (MCC). The quality of the best CNN model is estimated by calculations of sensitivity and specificity. Results: Our experimental results of independent validation demonstrate that the best of our developed models addressed this topological problem by exhibiting an overall sensitivity (96.55%) and specificity of (94.73%) in the esophagus, (81.08% sensitivity and 96.55% specificity) in the stomach, (89.65% sensitivity and 97.89% specificity) in the small intestine and (100% sensitivity and 98.94% specificity) in the colon. The average macro accuracy is 95.56%, the average macro sensitivity is 91.82%.<\/jats:p>","DOI":"10.3390\/diagnostics13050865","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T03:01:01Z","timestamp":1677207661000},"page":"865","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Revealing the Boundaries of Selected Gastro-Intestinal (GI) Organs by Implementing CNNs in Endoscopic Capsule Images"],"prefix":"10.3390","volume":"13","author":[{"given":"Sofia A.","family":"Athanasiou","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Technical University of Crete, 73100 Chania, Greece"},{"name":"Department of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eleftheria S.","family":"Sergaki","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Technical University of Crete, 73100 Chania, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6165-3492","authenticated-orcid":false,"given":"Andreas A.","family":"Polydorou","sequence":"additional","affiliation":[{"name":"Aretaeio Hospital, 2nd University Department of Surgery, Medical School, National and Kapodistrian University of Athens, 11528 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9348-7481","authenticated-orcid":false,"given":"Alexios A.","family":"Polydorou","sequence":"additional","affiliation":[{"name":"Medical School, National and Kapodistrian University of Athens, 11528 Athens, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George S.","family":"Stavrakakis","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Technical University of Crete, 73100 Chania, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolaos M.","family":"Afentakis","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ioannis O.","family":"Vardiambasis","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Hellenic Mediterranean University, 73133 Chania, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michail E.","family":"Zervakis","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Technical University of Crete, 73100 Chania, Greece"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,23]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Vulpoi, R.-A., Luca, M., Ciobanu, A., Olteanu, A., Barboi, O.-B., and Drug, V.L. (2022). Artificial intelligence in digestive endoscopy\u2014Where are we and where are we going?. Diagnostics, 12.","DOI":"10.3390\/diagnostics12040927"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Kim, S.H., and Lim, Y.J. (2021). Artificial intelligence in capsule endoscopy: A practical guide to its past and future challenges. Diagnostics, 11.","DOI":"10.3390\/diagnostics11091722"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"328","DOI":"10.5946\/ce.2018.172","article-title":"Recent development of computer vision technology to improve capsule endoscopy","volume":"52","author":"Park","year":"2019","journal-title":"Clin. Endosc."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Song, Z., Zhang, W., Zhang, W., and Paolo, D. (2022). A novel biopsy capsule robot based on high-speed cutting tissue. Cyborg Bionic Syst., 9783517.","DOI":"10.34133\/2022\/9783517"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1467","DOI":"10.1136\/gut.2009.177774","article-title":"The feasibility of wireless capsule endoscopy in detecting small intestinal pathology in children under the age of 8 years: A multicentre European study","volume":"58","author":"Scherbakov","year":"2009","journal-title":"Gut"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1177\/2050640618789853","article-title":"Enteroscopy in children","volume":"6","author":"Calabrese","year":"2018","journal-title":"United Eur. Gastroenterol. J."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1138","DOI":"10.3109\/00365521.2011.584900","article-title":"Capsule endoscopy in pediatric patients: Technique and results in our first 100 consecutive children","volume":"46","author":"Nuutinen","year":"2011","journal-title":"Scand. J. Gastroenterol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"8103","DOI":"10.3748\/wjg.v27.i47.8103","article-title":"Artificial intelligence-assisted colonoscopy: A review of current state of practice and research","volume":"27","author":"Taghiakbari","year":"2021","journal-title":"World J. Gastroenterol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"402","DOI":"10.4236\/jbise.2021.1412034","article-title":"Detection of angioectasias and haemorrhages incorporated into a multi-class classification tool for the GI tract anomalies by using binary CNNs","volume":"14","author":"Barbagiannis","year":"2021","journal-title":"J. Biomed. Sci. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"103","DOI":"10.4236\/jbise.2021.143011","article-title":"Improving CAD hemorrhage detection in capsule endoscopy","volume":"14","author":"Polydorou","year":"2021","journal-title":"J. Biomed. Sci. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"21941","DOI":"10.1007\/s11042-020-08905-7","article-title":"Deep learning based image classification for intestinal hemorrhage","volume":"79","author":"Pannu","year":"2020","journal-title":"Multimed Tools"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Yu, J., Chen, L., Xiang, Z.Q., and Zou, Y. (2015, January 6\u20139). A hybrid convolutional neural networks with extreme learning machine for WCE image classification. Proceedings of the 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO), Zhuhai, China.","DOI":"10.1109\/ROBIO.2015.7419037"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Oleksy, P., and Januszkiewicz, L. (2022). Wireless capsule endoscope localization with phase detection algorithm and adaptive body model. Sensors, 22.","DOI":"10.3390\/s22062200"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"11204","DOI":"10.1038\/s41598-021-90523-w","article-title":"A localization method for wireless capsule endoscopy using side wall cameras and IMU sensor","volume":"11","author":"Vedaei","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zou, Y., Li, L., Wang, Y., Yu, J., Li, Y., and Deng, W.J. (2015, January 21\u201324). Classifying digestive organs in wireless capsule endoscopy images based on deep convolutional neural network. Proceedings of the 2015 International Conference on Digital Signal Processing (DSP), Singapore.","DOI":"10.1109\/ICDSP.2015.7252086"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Son, G., Eo, T., An, J., Oh, D.J., Shin, Y., Rha, H., Kim, Y.J., Lim, Y.J., and Hwang, D. (2022). Small bowel detection for wireless capsule endoscopy using convolutional neural networks with temporal filtering. Diagnostics, 12.","DOI":"10.3390\/diagnostics12081858"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Odagawa, M., Okamoto, T., Koide, T., Yoshida, S., Mieno, H., Tamaki, T., Raytchev, B., Kaneda, K., and Tanaka, S. (2020, January 16\u201319). Classification method with CNN features and SVM for computer-aided diagnosis system in colorectal magnified NBI endoscopy. Proceedings of the 2020 IEEE Region 10 Conference (TENCON), Osaka, Japan.","DOI":"10.1109\/TENCON50793.2020.9293709"},{"key":"ref_18","unstructured":"Tam, A. (2021). Training-validation-test split and cross-validation done right. Mach. Learn. Mastery, 23."},{"key":"ref_19","unstructured":"Alharbi, F., Alharbi, A., and Kamioka, E. (2018, January 10\u201312). Animal species classification using machine learning techniques. Proceedings of the 2018 International Joint Conference on Metallurgical and Materials Engineering (JCMME 2018), Wellington, New Zealand."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009, January 20\u201325). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chicco, D., and Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genom., 21.","DOI":"10.1186\/s12864-019-6413-7"},{"key":"ref_22","unstructured":"Grandini, M., Bagli, E., and Visani, G. (2022, January 10). Metrics for Multi-Class Classification: An Overview. Available online: https:\/\/arxiv.org\/abs\/2008.05756."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/13\/5\/865\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:41:01Z","timestamp":1760121661000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/13\/5\/865"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,23]]},"references-count":22,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,3]]}},"alternative-id":["diagnostics13050865"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics13050865","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,23]]}}}