{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T17:10:21Z","timestamp":1785431421242,"version":"3.56.0"},"reference-count":31,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"RESILIENT competence center"},{"DOI":"10.13039\/501100004527","name":"Swedish Energy Agency","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004527","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/0359z7n90","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011914","name":"M\u00e4lardalen University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100011914","id-type":"DOI","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/033vfbz75","id-type":"ROR","asserted-by":"publisher"}]},{"name":"XPRES"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Nutrients"],"abstract":"<jats:p>Background\/Objectives: Accurate estimation of meal composition from food images can support safer and more reliable insulin bolus decision-making for individuals with Type 1 diabetes. Existing food recognition and nutrition estimation systems are often designed for general dietary logging and do not directly integrate food analysis with personalized insulin therapy parameters. Methods: This study presents an image-based nutrition estimation and insulin decision-support module developed within the AI-assisted Diabetes Care (AIDCARE) platform. The proposed system uses a convolutional neural network (CNN) to classify food items from a single meal image, and retrieves reference nutritional values from a food composition database. A separate multimodal large language model (MLLM)-based estimation component is then used to estimate portion size, allowing carbohydrate and nutrient values to be scaled according to the observed serving. Results: A curated food image dataset containing 40 food categories was used to evaluate three CNN architectures: ResNet50, Inception V3, and EfficientNet-B0. EfficientNet-B0 achieved the best classification performance, with 94.91% validation accuracy, 95.55% precision, 94.87% recall, and 94.90% F1-score. The portion-estimation component achieved an MAE of 12.27 g and an RMSE of 15.11 g. The estimated carbohydrate value is combined with user-specific clinical parameters, including the insulin-to-carbohydrate ratio and insulin sensitivity factor, to generate advisory bolus guidance. To support safety, the system requires user confirmation or correction of the recognized food category and estimated portion before insulin guidance is displayed. Conclusions: The proposed system is intended for advisory decision support only and is not designed to replace clinical judgment or autonomous insulin delivery systems.<\/jats:p>","DOI":"10.3390\/nu18132205","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T09:53:46Z","timestamp":1783418026000},"page":"2205","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid CNN\u2013MLLM Architecture for Image-Based Nutrition Estimation and Advisory Insulin Decision Support in Type 1 Diabetes"],"prefix":"10.3390","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5546-8299","authenticated-orcid":false,"given":"Jean Chrinot","family":"Velombe","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Kocaeli University, 41001 \u0130zmit, T\u00fcrkiye"},{"name":"Wireless Information and Intelligent Systems (WINS) Research Center, Kocaeli University, 41001 Kocaeli, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6063-0213","authenticated-orcid":false,"given":"Sema","family":"Bayraktar","sequence":"additional","affiliation":[{"name":"Wireless Information and Intelligent Systems (WINS) Research Center, Kocaeli University, 41001 Kocaeli, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5694-8042","authenticated-orcid":false,"given":"Adnan","family":"Kavak","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kocaeli University, 41001 \u0130zmit, T\u00fcrkiye"},{"name":"Wireless Information and Intelligent Systems (WINS) Research Center, Kocaeli University, 41001 Kocaeli, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0934-1069","authenticated-orcid":false,"given":"Muhammad","family":"Jamil","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kocaeli University, 41001 \u0130zmit, T\u00fcrkiye"},{"name":"Wireless Information and Intelligent Systems (WINS) Research Center, Kocaeli University, 41001 Kocaeli, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0933-654X","authenticated-orcid":false,"given":"Alpaslan Burak","family":"\u0130nner","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Kocaeli University, 41001 \u0130zmit, T\u00fcrkiye"},{"name":"Wireless Information and Intelligent Systems (WINS) Research Center, Kocaeli University, 41001 Kocaeli, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9851-4103","authenticated-orcid":false,"given":"Gautam","family":"Srivastava","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sogang University, Seoul 04107, Republic of Korea"},{"name":"Research Center for Interneural Computing, China Medical University, Taichung 40402, Taiwan"},{"name":"Centre for Research Impact & Outcome, Chitkara University Institute of Engineering and Technology, Chitkara University, Rajpura 140401, Punjab, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5590-0784","authenticated-orcid":false,"given":"Hossein","family":"Fotouhi","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Computer Engineering, M\u00e4lardalen University (MDU), 72123 V\u00e4ster\u00e5s, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"110230","DOI":"10.1016\/j.diabres.2022.110230","article-title":"The impact of flash glucose monitoring on adults with type 1 diabetes\u2019 eating habits and relationship with food","volume":"196","author":"Wallace","year":"2023","journal-title":"Diabetes Res. Clin. Pract."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1080\/17446651.2025.2454396","article-title":"Is there anything left to eat? A lived experience insight of following a restrictive type 1 diabetes and dialysis diet","volume":"21","author":"Schneider","year":"2025","journal-title":"Expert Rev. Endocrinol. Metab."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2536","DOI":"10.1109\/JBHI.2023.3249571","article-title":"A personalized and adaptive insulin bolus calculator based on double deep q-learning to improve type 1 diabetes management","volume":"27","author":"Noaro","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1109\/JBHI.2023.3348334","article-title":"Exploring nutritional influence on blood glucose forecasting for type 1 diabetes using explainable AI","volume":"28","author":"Annuzzi","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1481","DOI":"10.1109\/TBME.2022.3219370","article-title":"Safe and personalized meal bolus calculator for type-1 diabetes using bayesian optimization","volume":"70","author":"Krishnamoorthy","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/s12393-024-09386-2","article-title":"Application of artificial intelligence in food processing: Current status and future prospects","volume":"17","author":"Bidyalakshmi","year":"2025","journal-title":"Food Eng. Rev."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Quan, W., Zhou, J., Wang, J., Huang, J., and Du, L. (2025). Machine Learning-Driven Precision Nutrition: A Paradigm Evolution in Dietary Assessment and Intervention. Nutrients, 18.","DOI":"10.3390\/nu18010045"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"144908","DOI":"10.1016\/j.foodchem.2025.144908","article-title":"Structure from motion-convolutional neural network model (SfM-CNN) achieved accurate portable Chinese dietary chemical composition estimation for dietary recall","volume":"489","author":"Ma","year":"2025","journal-title":"Food Chem."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e101619","DOI":"10.1136\/bmjopen-2025-101619","article-title":"Diet and diet-related challenges with specific focus on carbohydrates and carbohydrate counting in adults with type 1 diabetes: A cross-sectional study","volume":"15","author":"Hellman","year":"2025","journal-title":"BMJ Open"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Dymi\u0144ska, M., Kowalczyk-Korcz, E., Piechowiak, K., and Szypowska, A. (2025). The Impact of Two Different Insulin Dose Calculation Methods on Postprandial Glycemia After a Mixed Meal in Children with Type 1 Diabetes: A Randomized Study. Nutrients, 17.","DOI":"10.3390\/nu17203287"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Khawate, S., Gaikwad, S., Davda, Y., Shirbhate, R., Gham, P., and Borate, V. (2025). Dietary Monitoring with Deep Learning and Computer Vision. Proceedings of the 2025 International Conference on Computing Technologies & Data Communication (ICCTDC), IEEE.","DOI":"10.1109\/ICCTDC64446.2025.11158839"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"100978","DOI":"10.1016\/j.focha.2025.100978","article-title":"Diet engine: A real-time food nutrition assistant system for personalized dietary guidance","volume":"7","author":"Saad","year":"2025","journal-title":"Food Chem. Adv."},{"key":"ref_13","first-page":"58","article-title":"Transfer learning approach with EfficientNet to enhance food recognition systems for health monitoring","volume":"2025","author":"Alam","year":"2025","journal-title":"Commun. Math. Biol. Neurosci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Motghare, M., Joshi, V.K., Jamal, M., Shanmugam, M., Patil, R.V., and Rawool, N.J. (2025). Leveraging Deep Learning for Nutritional Profiling: A Comparative Analysis of EfficientNetB0, MobileNetV2, and ResNet50 for Healthy and Unhealthy Food Classification. Proceedings of the 2025 IEEE International Conference on Recent Advances in Computing and Systems (REACS), IEEE.","DOI":"10.1109\/REACS67479.2025.11413325"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Raju, V.B., and Sazonov, E. (2022). FOODCAM: A novel structured light-stereo imaging system for food portion size estimation. Sensors, 22.","DOI":"10.3390\/s22093300"},{"key":"ref_16","unstructured":"Li, B. (2025). Food Portion Analysis for Nutritional Monitoring and Dietary Assessment. [Ph.D. Thesis, University of Pittsburgh]."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s11042-026-21209-6","article-title":"A synergistic hybrid approach for calorie estimation using multi-view food images and deep learning-based segmentation and classification","volume":"85","author":"Chopra","year":"2026","journal-title":"Multimed. Tools Appl."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Qi, H., Zhu, B., Ngo, C.W., Chen, J., and Lim, E.P. (July, January 30). Advancing food nutrition estimation via visual-ingredient feature fusion. Proceedings of the 2025 International Conference on Multimedia Retrieval, Chicago, IL, USA.","DOI":"10.1145\/3731715.3733269"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jung, J.H., Kim, E.T., Kim, S., Lee, J.H., Kim, B., and Chang, B. (2025). Is \u2018right\u2019 right? enhancing object orientation understanding in multimodal large language models through egocentric instruction tuning. Proceedings of the 2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR52734.2025.01330"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Phalle, A., and Gokhale, D. (2025). Navigating next-gen nutrition care using artificial intelligence-assisted dietary assessment tools\u2014A scoping review of potential applications. Front. Nutr., 12.","DOI":"10.3389\/fnut.2025.1518466"},{"key":"ref_21","unstructured":"Zhao, M. (2025). Enabling Better Healthy Food Recommendation by Incorporating Contextual Knowledge. [Ph.D. Thesis, University of Sheffield]."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Strydom, H., Muchiri, J., Delport, E., and White, Z. (2025). Adherence to personalised nutrition education based on glycemic and food insulin index principles and their association with blood glucose control in individuals with type 2 diabetes mellitus. Int. J. Environ. Res. Public Health, 22.","DOI":"10.3390\/ijerph22060925"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e22074","DOI":"10.2196\/22074","article-title":"Carbohydrate counting app using image recognition for youth with type 1 diabetes: Pilot randomized control trial","volume":"8","author":"Alfonsi","year":"2020","journal-title":"JMIR MHealth UHealth"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Chotwanvirat, P., Hnoohom, N., Rojroongwasinkul, N., and Kriengsinyos, W. (2021). Feasibility study of an automated carbohydrate estimation system using Thai food images in comparison with estimation by dietitians. Front. Nutr., 8.","DOI":"10.3389\/fnut.2021.732449"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"e70116","DOI":"10.1111\/1750-3841.70116","article-title":"Image-based food groups and portion prediction by using deep learning","volume":"90","author":"Nogay","year":"2025","journal-title":"J. Food Sci."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1177\/15209156251376012","article-title":"Carbohydrate Counting\/Bolus Calculator Mobile Application Improves Time in Range in Adults with Type 1 Diabetes Subjects","volume":"28","author":"AlBabtain","year":"2026","journal-title":"Diabetes Technol. Ther."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., and Fei-Fei, L. (2009). ImageNet: A large-scale hierarchical image database. Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Senapati, B., Talburt, J.R., Naeem, A.B., and Batthula, V.J.R. (2023). Transfer learning based models for food detection using ResNet-50. Proceedings of the 2023 IEEE International Conference on Electro Information Technology (eIT), IEEE.","DOI":"10.1109\/eIT57321.2023.10187288"},{"key":"ref_29","unstructured":"Tan, M., and Le, Q.V. (2019, January 9\u201315). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (2015). Rethinking the Inception architecture for computer vision. arXiv.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1109\/TIP.2020.3045639","article-title":"A Study of Multi-Task and Region-Wise Deep Learning for Food Ingredient Recognition","volume":"30","author":"Chen","year":"2021","journal-title":"IEEE Trans. Image Process."}],"container-title":["Nutrients"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6643\/18\/13\/2205\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:24:58Z","timestamp":1783571098000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6643\/18\/13\/2205"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":31,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["nu18132205"],"URL":"https:\/\/doi.org\/10.3390\/nu18132205","relation":{},"ISSN":["2072-6643"],"issn-type":[{"value":"2072-6643","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]}}}