{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T19:02:13Z","timestamp":1790190133206,"version":"4.1.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Digit Imaging. Inform. med."],"DOI":"10.1007\/s10278-026-02313-3","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T18:28:29Z","timestamp":1790188109000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Calibration and Reliability of Deep Learning in Medical Imaging Classification: Impact of Image Resolution"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2238-1516","authenticated-orcid":false,"given":"Krishna","family":"Mridha","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Madhu","family":"Shukla","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"2313_CR1","doi-asserted-by":"crossref","unstructured":"Geert Litjens, Thijs Kooi, Babak Ehteshami Bejnordi, Arnaud Arindra Adiyoso Setio, Francesco Ciompi, Mohsen Ghafoorian, Jeroen AWM Van Der Laak, Bram Van Ginneken, and Clara I S\u00e1nchez. A survey on deep learning in medical image analysis. Medical Image Analysis, 42:60\u201388, 2017.","DOI":"10.1016\/j.media.2017.07.005"},{"key":"2313_CR2","doi-asserted-by":"crossref","unstructured":"Carl F Sabottke and Bradley M Spieler. The effect of image resolution on deep learning in radiography. Radiology: Artificial Intelligence, 2(1):e190015, 2020.","DOI":"10.1148\/ryai.2019190015"},{"key":"2313_CR3","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian Q Weinberger. On calibration of modern neural networks. In International Conference on Machine Learning (ICML), pages 1321\u20131330. PMLR, 2017."},{"key":"2313_CR4","unstructured":"Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, and Florian Buettner. Post-hoc uncertainty calibration for domain drift scenarios. arXiv preprint arXiv:2012.10988, 2020. arXiv:2012.10988."},{"key":"2313_CR5","doi-asserted-by":"crossref","unstructured":"Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, and Bingbing Ni. MedMNIST v2: A large-scale lightweight benchmark for 2D and 3D biomedical image classification. Scientific Data, 10(1):41, 2023. Originally published as arXiv:2110.14795 (2021).","DOI":"10.1038\/s41597-022-01721-8"},{"key":"2313_CR6","unstructured":"Esther Tiu, Eliana Talius, Piyush Patel, Curtis P Langlotz, Andrew Y Ng, and Pranav Rajpurkar. The effect of image resolution on the performance of a deep learning model for skin lesion classification. arXiv preprint arXiv:2011.11965, 2020."},{"key":"2313_CR7","unstructured":"Abhijit Guha Roy, Sailesh Conjeti, Nassir Navab, and Christian Wachinger. Resolution and uncertainty in medical image segmentation. Medical Image Analysis, 62:101657, 2020."},{"key":"2313_CR8","doi-asserted-by":"crossref","unstructured":"Xing Shen, Hengguan Huang, Brennan Nichyporuk, and Tal Arbel. Improving robustness and reliability in medical image classification with latent-guided diffusion and nested-ensembles. IEEE Transactions on Medical Imaging, 44(5):1843\u20131855, 2025. Preprint arXiv:2310.15952 (2023).","DOI":"10.1109\/TMI.2025.3583974"},{"key":"2313_CR9","first-page":"7510","volume":"34","author":"Junjiao Tian","year":"2021","unstructured":"Junjiao Tian, Dylan Yung, Yen-Chang Hsu, and Zsolt Kira. A geometric perspective towards neural calibration via sensitivity decomposition. In Advances in Neural Information Processing Systems (NeurIPS), volume 34, pages 7510\u20137521, 2021.","journal-title":"In Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"2313_CR10","doi-asserted-by":"crossref","unstructured":"Jiayi Huang, Sangwoo Park, and Osvaldo Simeone. Calibration-aware bayesian learning. In IEEE International Workshop on Machine Learning for Signal Processing (MLSP), pages 1\u20136. IEEE, 2023.","DOI":"10.1109\/MLSP55844.2023.10285894"},{"key":"2313_CR11","doi-asserted-by":"crossref","unstructured":"Allan H Murphy. The value of climatological, categorical and probabilistic forecasts in the cost-loss ratio situation. Monthly Weather Review, 105(7):803\u2013816, 1977.","DOI":"10.1175\/1520-0493(1977)105<0803:TVOCCA>2.0.CO;2"},{"key":"2313_CR12","unstructured":"Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Wilson Le\u00e3o, and Christian Gagn\u00e9. Unsupervised temperature scaling: An unsupervised post-processing calibration method of deep networks. arXiv preprint arXiv:1905.05562, 2019. arXiv:1905.05562."},{"key":"2313_CR13","unstructured":"Azadeh Sadat Mozafari, Hugo Siqueira Gomes, Wilson Le\u00e3o, Steeven Janny, and Christian Gagn\u00e9. Attended temperature scaling: A practical approach for calibrating deep neural networks. arXiv preprint arXiv:1810.11586, 2018. arXiv:1810.11586."},{"key":"2313_CR14","doi-asserted-by":"crossref","unstructured":"Gongbo Liang, Yu Zhang, Xiaoqin Wang, and Nathan Jacobs. Improved trainable calibration method for neural networks on medical imaging classification. arXiv preprint arXiv:2009.04057, 2020. arXiv:2009.04057.","DOI":"10.5244\/C.34.16"},{"key":"2313_CR15","doi-asserted-by":"crossref","unstructured":"Jacob Carse, Andres Alvarez Olmo, and Stephen J McKenna. Calibration of deep medical image classifiers: An empirical comparison using dermatology and histopathology datasets. In International Workshop on Interpretability of Machine Intelligence in Medical Image Computing, pages 91\u2013101. Springer, 2022.","DOI":"10.1007\/978-3-031-16749-2_9"},{"key":"2313_CR16","unstructured":"Ximei Wang, Mingsheng Long, Jianmin Wang, and Michael I Jordan. Transferable calibration with lower bias and variance in domain adaptation. arXiv preprint arXiv:2007.08259, 2020. arXiv:2007.08259."},{"key":"2313_CR17","unstructured":"Jian Liang and Chuan-Sheng Foo. Pseudocal: A source-free approach to unsupervised uncertainty calibration in domain adaptation. arXiv preprint arXiv:2307.07623, 2023. arXiv:2307.07623."},{"key":"2313_CR18","unstructured":"Christian Tomani, Sebastian Gruber, Muhammed Ebrar Erdem, Daniel Cremers, and Florian Buettner. Beyond in-domain scenarios: Robust density-aware calibration. arXiv preprint arXiv:2302.05118, 2023. arXiv:2302.05118."},{"key":"2313_CR19","unstructured":"Jian Liang, Chuan-Sheng Foo, Kien Do, et al. Test-time adaptation with calibration of medical image classification nets for label distribution shift. arXiv preprint arXiv:2207.00769, 2022. arXiv:2207.00769."},{"key":"2313_CR20","unstructured":"Junjian Tian et al. Hidden heterogeneity: When to choose similarity-based calibration. arXiv preprint arXiv:2202.01840, 2022. arXiv:2202.01840."},{"key":"2313_CR21","unstructured":"Kunal Kumar et al. Estimating model performance under domain shifts with class-specific confidence scores. arXiv preprint arXiv:2207.09957, 2022. arXiv:2207.09957."},{"key":"2313_CR22","unstructured":"Riqiang Gao, Yucheng Tang, Zhoubing Xu, Michael N Kammer, and Sanja L Antic. A comparative study of confidence calibration in deep learning: From computer vision to medical imaging. arXiv preprint arXiv:2206.08833, 2022. arXiv:2206.08833."},{"key":"2313_CR23","doi-asserted-by":"crossref","unstructured":"Tareen Dawood, Emily Chan, Reza Razavi, Andrew P King, and Esther Puyol-Ant\u00f3n. Addressing deep learning model calibration using evidential neural networks and uncertainty-aware training. In IEEE International Symposium on Biomedical Imaging (ISBI), pages 1\u20135. IEEE, 2023.","DOI":"10.1109\/ISBI53787.2023.10230515"},{"key":"2313_CR24","unstructured":"Hongshan Liu, A Bamba, and Yu Gan. Uncertainty measurement and confidence calibration for calcium detection in optical coherence images. In Proc. SPIE 12466, Medical Imaging 2023: Image Processing, volume 12466, page 124662U, 2023."},{"key":"2313_CR25","unstructured":"Cheng Jun et al. Improved post-hoc probability calibration for out-of-domain mri segmentation. arXiv preprint arXiv:2208.02870, 2022. arXiv:2208.02870."},{"key":"2313_CR26","unstructured":"Yao Chen et al. Calibrating ensembles for scalable uncertainty quantification in deep learning-based medical segmentation. arXiv preprint arXiv:2209.09563, 2022. arXiv:2209.09563."},{"key":"2313_CR27","doi-asserted-by":"crossref","unstructured":"Zeinab Abboud, Herv\u00e9 Lombaert, and Samuel Kadoury. Sparse bayesian networks: Efficient uncertainty quantification in medical image analysis. arXiv preprint arXiv:2406.06946, 2024. arXiv:2406.06946.","DOI":"10.1007\/978-3-031-72117-5_63"},{"key":"2313_CR28","doi-asserted-by":"crossref","unstructured":"F. X. Erick et al. Uncertainty-aware vision transformers for medical image analysis. In Lecture Notes in Computer Science, volume 14533, pages 171\u2013180. Springer, 2024.","DOI":"10.1007\/978-3-031-73158-7_16"},{"key":"2313_CR29","unstructured":"Francesco Di Salvo, Sebastian Doerrich, and Christian Ledig. Medmnist-c: Comprehensive benchmark and improved classifier robustness by simulating realistic image corruptions. arXiv preprint arXiv:2406.17536, 2024. arXiv:2406.17536."},{"key":"2313_CR30","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, 30, 2017."},{"key":"2313_CR31","unstructured":"Yarin Gal and Zoubin Ghahramani. Dropout as a bayesian approximation: Representing model uncertainty in deep learning. In International Conference on Machine Learning (ICML), pages 1050\u20131059. PMLR, 2016."},{"key":"2313_CR32","unstructured":"Dan Hendrycks and Kevin Gimpel. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In International Conference on Learning Representations, 2017."},{"issue":"1","key":"2313_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-022-00624-0","volume":"9","author":"Hayat Shahir Thalji Al-Dmour","year":"2022","unstructured":"Hayat Shahir Thalji Al-Dmour. Ramifications of incorrect image segmentations: emphasizing on the potential effects on deep learning methods failure. Journal of Big Data, 9(1):1\u201319, 2022.","journal-title":"Journal of Big Data"},{"key":"2313_CR34","unstructured":"Aikaterini Chatzipapadopoulou. Ensemble learning in uncertainty quantification for multi-label prediction: From theoretical foundations to medical image understanding. Master\u2019s thesis, Athens University of Economics and Business, 2023. Available at: https:\/\/www2.aueb.gr\/users\/ion\/docs\/a_chatzipapadopoulou_msc_thesis.pdf. Accessed 7 May 2026."},{"key":"2313_CR35","unstructured":"Angelos Filos, Sebastian Farquhar, Aidan N Gomez, Tim GJ Rudner, Zachary Kenton, Lewis Smith, Milad Alizadeh, Arnoud de Kroon, and Yarin Gal. A systematic comparison of bayesian deep learning robustness in diabetic retinopathy tasks. In Medical Imaging with Deep Learning, 2019."},{"key":"2313_CR36","doi-asserted-by":"crossref","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770\u2013778, 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2313_CR37","unstructured":"Daniel S Kermany et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 2018."},{"key":"2313_CR38","unstructured":"Daniel S Kermany, Kang Zhang, and Michael Goldbaum. Large dataset of labeled optical coherence tomography (oct) and chest x-ray images, 2018."},{"key":"2313_CR39","doi-asserted-by":"crossref","unstructured":"W. Al-Dhabyani, M. Gomaa, H. Khaled, and A. Fahmy. Dataset of breast ultrasound images. Data in Brief, 2020.","DOI":"10.1016\/j.dib.2019.104863"},{"key":"2313_CR40","doi-asserted-by":"crossref","unstructured":"A. Acevedo, A. Merino, S. Alf\u00e9rez, A. Molina, L. Bold\u00fa, and J. Rodellar. A dataset for microscopic peripheral blood cell images for development of automatic recognition systems, 2020.","DOI":"10.1016\/j.dib.2020.105474"},{"key":"2313_CR41","doi-asserted-by":"publisher","first-page":"105474","DOI":"10.1016\/j.dib.2020.105474","volume":"30","author":"A Acevedo","year":"2020","unstructured":"A. Acevedo, A. Merino, S. Alf\u00e9rez, A. Molina, L. Bold\u00fa, and J. Rodellar. A dataset of microscopic peripheral blood cell images for development of automatic recognition systems. Data in Brief, 30:105474, 2020.","journal-title":"Data in Brief"}],"container-title":["Journal of Imaging Informatics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02313-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10278-026-02313-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10278-026-02313-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T18:28:37Z","timestamp":1790188117000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10278-026-02313-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":41,"alternative-id":["2313"],"URL":"https:\/\/doi.org\/10.1007\/s10278-026-02313-3","relation":{},"ISSN":["2948-2933"],"issn-type":[{"value":"2948-2933","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"assertion":[{"value":"31 July 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All datasets used in this study are publicly available and consist of anonymized or de-identified medical images that were originally collected with appropriate ethical oversight. As this work involves secondary analysis of publicly available de-identified data, no additional institutional ethical approval was required.","order":1,"name":"Ethics","label":"Ethics Approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. This study involved secondary analysis of publicly available, de-identified imaging datasets (MedMNIST); no new human participants were recruited and no new data were collected from individuals by the authors.","order":2,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. This manuscript does not contain any individual person's identifiable data, images, or other personal information requiring consent to publish.","order":3,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships that could have appeared to influence the work reported in this paper.","order":4,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"During the preparation of this manuscript, the authors used ChatGPT (OpenAI) to assist with improving the English language, including grammar, spelling, and phrasing, and for minor formatting support in documenting experimental code. All scientific content, analysis, and conclusions were developed by the authors.","order":5,"name":"Ethics","label":"Generative AI Statement","group":{"name":"EthicsHeading","label":"Declarations"}}]}}