{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T10:46:24Z","timestamp":1761129984286,"version":"build-2065373602"},"reference-count":46,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T00:00:00Z","timestamp":1644883200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science and Technology Development Fund, Macau SAR","award":["0023\/2018\/AFJ"],"award-info":[{"award-number":["0023\/2018\/AFJ"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>It is challenging for endoscopists to accurately detect esophageal lesions during gastrointestinal endoscopic screening due to visual similarities among different lesions in terms of shape, size, and texture among patients. Additionally, endoscopists are busy fighting esophageal lesions every day, hence the need to develop a computer-aided diagnostic tool to classify and segment the lesions at endoscopic images to reduce their burden. Therefore, we propose a multi-task classification and segmentation (MTCS) model, including the Esophageal Lesions Classification Network (ELCNet) and Esophageal Lesions Segmentation Network (ELSNet). The ELCNet was used to classify types of esophageal lesions, and the ELSNet was used to identify lesion regions. We created a dataset by collecting 805 esophageal images from 255 patients and 198 images from 64 patients to train and evaluate the MTCS model. Compared with other methods, the proposed not only achieved a high accuracy (93.43%) in classification but achieved a dice similarity coefficient (77.84%) in segmentation. In conclusion, the MTCS model can boost the performance of endoscopists in the detection of esophageal lesions as it can accurately multi-classify and segment the lesions and is a potential assistant for endoscopists to reduce the risk of oversight.<\/jats:p>","DOI":"10.3390\/s22041492","type":"journal-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T22:44:47Z","timestamp":1644965087000},"page":"1492","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Diagnosis of Esophageal Lesions by Multi-Classification and Segmentation Using an Improved Multi-Task Deep Learning Model"],"prefix":"10.3390","volume":"22","author":[{"given":"Suigu","family":"Tang","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China"}]},{"given":"Xiaoyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7912-2913","authenticated-orcid":false,"given":"Chak-Fong","family":"Cheang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China"}]},{"given":"Zeming","family":"Hu","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China"}]},{"given":"Tong","family":"Fang","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Macau University of Science and Technology, Macau 999078, China"}]},{"given":"I-Cheong","family":"Choi","sequence":"additional","affiliation":[{"name":"Kiang Wu Hospital, Macau 999078, China"}]},{"given":"Hon-Ho","family":"Yu","sequence":"additional","affiliation":[{"name":"Kiang Wu Hospital, Macau 999078, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,2,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"209","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1111\/dote.12533","article-title":"Recommendations for pathologic staging (pTNM) of cancer of the esophagus and esophagogastric junction for the 8th edition AJCC\/UICC staging manuals","volume":"29","author":"Rice","year":"2016","journal-title":"Dis Esophagus"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2017","DOI":"10.1053\/j.gastro.2011.08.007","article-title":"Magnifying narrowband imaging is more accurate than conventional white-light imaging in diagnosis of gastric mucosal cancer","volume":"141","author":"Ezoe","year":"2011","journal-title":"Gastroenterology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1159\/000487470","article-title":"Narrow-band imaging: Clinical application in gastrointestinal endoscopy","volume":"26","author":"Barbeiro","year":"2018","journal-title":"GE-Port. J. Gastroenterol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.media.2016.04.007","article-title":"Identification of lesion images from gastrointestinal endoscope based on feature extraction of combinational methods with and without learning process","volume":"32","author":"Liu","year":"2016","journal-title":"Med. Image Anal."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"595","DOI":"10.1109\/42.932744","article-title":"Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique","volume":"20","author":"Lee","year":"2001","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.procs.2018.04.180","article-title":"Spleen segmentation in MRI sequence images using template matching and active contours","volume":"131","author":"Antonia","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"2967","DOI":"10.1109\/TBME.2013.2267212","article-title":"A likelihood and local constraint level set model for liver tumor segmentation from CT volumes","volume":"60","author":"Li","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ijaz, M.F., Alfian, G., Syafrudin, M., and Rhee, J. (2018). Hybrid prediction model for type 2 diabetes and hypertension using DBSCAN-based outlier detection, synthetic minority over sampling technique (SMOTE), and random forest. Appl. Sci., 8.","DOI":"10.3390\/app8081325"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Alfian, G., Syafrudin, M., Ijaz, M.F., Syaekhoni, M.A., Fitriyani, N.L., and Rhee, J. (2018). A personalized healthcare monitoring system for diabetic patients by utilizing BLE-based sensors and real-time data processing. Sensors, 18.","DOI":"10.3390\/s18072183"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ijaz, M.F., Attique, M., and Son, Y. (2020). Data-driven cervical cancer prediction model with outlier detection and over-sampling methods. Sensors, 50.","DOI":"10.3390\/s20102809"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Srinivasu, P.N., SivaSai, J.G., Ijaz, M.F., Bhoi, A.K., Kim, W., and Kang, J.J. (2021). Classification of skin disease using deep learning neural networks with MobileNet V2 and LSTM. Sensors, 21.","DOI":"10.3390\/s21082852"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.gie.2018.07.037","article-title":"Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks","volume":"89","author":"Horie","year":"2019","journal-title":"Gastrointest. Endosc."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1055\/a-0756-8754","article-title":"Computer-assisted diagnosis of early esophageal squamous cell carcinoma using narrow-band imaging magnifying endoscopy","volume":"51","author":"Zhao","year":"2019","journal-title":"Endoscopy"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.gie.2019.08.018","article-title":"Real-time automated diagnosis of precancerous lesions and early esophageal squamous cell carcinoma using a deep learning model (with videos)","volume":"91","author":"Guo","year":"2019","journal-title":"Gastrointest. Endosc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"486","DOI":"10.21037\/atm.2020.03.24","article-title":"Automatic classification of esophageal lesions in endoscopic images using a convolutional neural network","volume":"8","author":"Liu","year":"2020","journal-title":"Ann. Transl. Med."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"3066","DOI":"10.1364\/BOE.420935","article-title":"Automatic classification of esophageal disease in gas-troscopic images using an efficient channel attention deep dense convolutional neural network","volume":"12","author":"Du","year":"2021","journal-title":"Biomed. Opt. Express"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/JBHI.2020.2997760","article-title":"Multi-scale context-guided deep network for automated lesion segmentation with endoscopy images of gastrointestinal tract","volume":"25","author":"Wang","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.neucom.2018.10.100","article-title":"Fine-tuning pre-trained convolutional neural networks for gastric precancerous disease classification on magnification narrow-band imaging images","volume":"392","author":"Liu","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"103950","DOI":"10.1016\/j.compbiomed.2020.103950","article-title":"Anatomical classification of upper gastrointestinal organs under various image capture conditions using AlexNet","volume":"124","author":"Igarashi","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1007\/s10388-018-0651-7","article-title":"Diagnosis using deep-learning artificial intelligence based on the endocytoscopic observation of the esophagus","volume":"16","author":"Kumagai","year":"2019","journal-title":"Esophagus"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1016\/j.gie.2018.11.011","article-title":"Application of convolutional neural network in the diagnosis of the invasion depth of gastric cancer based on conventional endoscopy","volume":"89","author":"Zhu","year":"2019","journal-title":"Gastrointest. Endosc."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"122798","DOI":"10.1109\/ACCESS.2020.3007719","article-title":"Channel-attention U-net: Channel attention mechanism for semantic segmentation of esophagus and esophageal cancer","volume":"8","author":"Huang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"82867","DOI":"10.1109\/ACCESS.2019.2923760","article-title":"U-net plus: Deep semantic segmentation for esophagus and esophageal cancer in computed tomography images","volume":"7","author":"Chen","year":"2019","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"155548","DOI":"10.1109\/ACCESS.2020.3019518","article-title":"Eso-net: A novel 2.5D segmentation network with the multi-structure response filter for the cancerous esophagus","volume":"8","author":"Zhou","year":"2020","journal-title":"IEEE Access"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"99235","DOI":"10.1109\/ACCESS.2021.3096270","article-title":"Esophageal tumor segmentation in CT images using a dilated dense attention Unet (DDAUnet)","volume":"9","author":"Yousefi","year":"2021","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, X., and Chen, D. (2018, January 18\u201323). CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref_28","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: Semantic image segmentation with deep convo-lutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2020, January 13\u201319). ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net: Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_32","unstructured":"Oktay, O., Schlemper, J., Folgoc, L.L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention U-Net: Learning where to look for the pancreas. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"CE-Net: Context encoder network for 2D medical image segmentation","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","article-title":"Deep high-resolution representation learning for visual recognition","volume":"43","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"40496","DOI":"10.1109\/ACCESS.2021.3063716","article-title":"Real-time polyp detection, localization and segmentation in colonoscopy using deep learning","volume":"9","author":"Jha","year":"2021","journal-title":"IEEE Access"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2942","DOI":"10.1038\/ajg.2009.426","article-title":"Narrow-band imaging provides reliable screening for esophageal malignancy in patients with head and neck cancers","volume":"104","author":"Takenaka","year":"2009","journal-title":"Am. J. Gastroenterol."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1038\/ajg.2014.94","article-title":"Usefulness of non-magnifying narrow-band imaging in screening of early esophageal squamous cell carcinoma: A prospective comparative study using propensity score matching","volume":"109","author":"Nagami","year":"2014","journal-title":"Am. J. Gastroenterol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1585","DOI":"10.1016\/j.cgh.2017.11.031","article-title":"Lugol chromoendoscopy detects esophageal dysplasia with low levels of sensitivity in a high-risk region of China","volume":"16","author":"Li","year":"2018","journal-title":"Clin. Gastroenterol. Hepatol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"83","DOI":"10.4161\/jig.1.2.15048","article-title":"Quality endoscopists and quality endoscopy units","volume":"1","author":"Cotton","year":"2011","journal-title":"J. Interv. Gastroenterol."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1109\/TBME.2013.2295593","article-title":"Lung nodule classification with multi-level patch-based context analysis","volume":"61","author":"Zhang","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1016\/j.media.2014.04.002","article-title":"Digital facial dysmorphology for genetic screening: Hierarchical constrained local model using ICA","volume":"18","author":"Zhao","year":"2012","journal-title":"Med. Image Anal."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"ref_43","first-page":"2843","article-title":"Schmidhuber, J. Deep neural networks segment neuronal membranes in electron microscopy images","volume":"25","author":"Ciresan","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","article-title":"Fully convolutional networks for semantic segmentation","volume":"39","author":"Shelhamer","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/j.procs.2018.01.104","article-title":"Lung CT image segmentation using deep neural networks","volume":"127","author":"Skourt","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"202459","DOI":"10.1109\/ACCESS.2020.3035772","article-title":"Esophagus segmentation in computed tomography images using a U-Net neural network with a semiautomatic labeling method","volume":"8","author":"Lou","year":"2020","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/4\/1492\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:19:58Z","timestamp":1760134798000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/4\/1492"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,15]]},"references-count":46,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,2]]}},"alternative-id":["s22041492"],"URL":"https:\/\/doi.org\/10.3390\/s22041492","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2022,2,15]]}}}