{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:00:01Z","timestamp":1787497201735,"version":"build-2736575974"},"posted":{"date-parts":[[2025,5,16]]},"group-title":"Neurology","reference-count":77,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T00:00:00Z","timestamp":1747353600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,6,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>The study aims to develop a method for differentiating between healthy, post-infectious hydrocephalus (PIH), and non-post-infectious hydrocephalus (NPIH) in infants using low-field MRI, which is a safer, low-cost alternative to CT scans. The study develops a custom approach that captures hydrocephalic etiology while simultaneously addressing quality issues encountered in low-field MRI.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Specifically, we propose GLAPAL-H, a Global, Local, And Parts Aware Learner, which develops a multi-task architecture with global, local, and parts segmentation branches. The architecture segments images into brain tissue and CSF while using a shallow CNN for local feature extraction and develops a parallel deep CNN branch for global feature extraction. Three regularized training loss functions are developed \u2014 one for each of global, local, and parts components. The global regularizer captures holistic features, the local focuses on fine details, and the parts regularizer learns soft segmentation masks that enable local features to capture hydrocephalic etiology.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The study\u2019s results show that GLAPAL-H outperforms state-of-the-art alternatives, including CT-based approaches, for both Two-Class (PIH vs. NPIH) and Three-Class (PIH vs. NPIH vs. Healthy) classification tasks in accuracy, interpretability, and generalizability.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion\/Significance<\/jats:title>\n                  <jats:p>\n                    GLAPAL-H highlights the potential of low-field MRI as a safer, low-cost alternative to CT imaging for pediatric hydrocephalus infection diagnosis and management. Practically, GLAPAL-H demonstrates robustness against quantity and quality of training imagery, enhancing its deployability. The code for this work is available here:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/github.com\/mukherjeesrijit\/glapalh\">https:\/\/github.com\/mukherjeesrijit\/glapalh<\/jats:ext-link>\n                    .\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.05.14.25327461","type":"posted-content","created":{"date-parts":[[2025,5,16]],"date-time":"2025-05-16T15:00:21Z","timestamp":1747407621000},"source":"Crossref","is-referenced-by-count":2,"title":["GLAPAL-H: Global, Local, And Parts Aware Learner for Hydrocephalus Infection Diagnosis in Low-Field MRI"],"prefix":"10.64898","author":[{"given":"Srijit","family":"Mukherjee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelsey","family":"Templeton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Starlin","family":"Tindimwebwa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivy","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Sutin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingzhao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mallory","family":"Peterson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chip","family":"Truwit","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2623-3614","authenticated-orcid":false,"given":"Steven J.","family":"Schiff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vishal","family":"Monga","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025060904201401000_2025.05.14.25327461v2.1","doi-asserted-by":"crossref","unstructured":"B. C. Warf . \u201cComparison of endoscopic third ventriculostomy alone and combined with choroid plexus cauterization in infants younger than 1 year of age: a prospective study in 550 African children\u201d. J. Neurosurg.: Pediatr. 2005.","DOI":"10.3171\/ped.2005.103.6.0475"},{"key":"2025060904201401000_2025.05.14.25327461v2.2","doi-asserted-by":"crossref","unstructured":"A. V. Kulkarni et al. \u201cEndoscopic treatment versus shunting for infant hydrocephalus in Uganda\u201d. New England Journal of Medicine. 2017.","DOI":"10.1056\/NEJMoa1707568"},{"key":"2025060904201401000_2025.05.14.25327461v2.3","unstructured":"M. C. Dewan et al. \u201cGlobal hydrocephalus epidemiology and incidence: systematic review and meta-analysis\u201d. Journal of neurosurgery. 2018."},{"key":"2025060904201401000_2025.05.14.25327461v2.4","doi-asserted-by":"crossref","unstructured":"K. T. Kahle et al. \u201cPaediatric hydrocephalus\u201d. Nature Reviews Disease Primers. 2024.","DOI":"10.1038\/s41572-024-00519-9"},{"key":"2025060904201401000_2025.05.14.25327461v2.5","doi-asserted-by":"crossref","unstructured":"J. N. Paulson et al. \u201cPaenibacillus infection with frequent viral coinfection contributes to postinfectious hydrocephalus in Ugandan infants\u201d. Science translational medicine. 2020.","DOI":"10.1126\/scitranslmed.aba0565"},{"key":"2025060904201401000_2025.05.14.25327461v2.6","doi-asserted-by":"crossref","unstructured":"M. R. Peterson et al. \u201cNormal childhood brain growth and a universal sex and anthropomorphic relationship to cere-brospinal fluid\u201d. Journal of Neurosurgery: Pediatrics. 2021.","DOI":"10.3171\/2021.2.PEDS201006"},{"key":"2025060904201401000_2025.05.14.25327461v2.7","doi-asserted-by":"crossref","unstructured":"M. Punchak et al. \u201cThe incidence of postoperative seizures following treatment of postinfectious hydrocephalus in Ugan-dan infants: a post hoc comparison of endoscopic treatment vs shunt placement in a randomized controlled trial\u201d. Neuro-surgery. 2019.","DOI":"10.1093\/neuros\/nyz122"},{"key":"2025060904201401000_2025.05.14.25327461v2.8","doi-asserted-by":"crossref","unstructured":"S. J. Schiff et al. \u201cBrain growth after surgical treatment for infant postinfectious hydrocephalus in Sub-Saharan Africa: 2-year results of a randomized trial\u201d. Journal of Neurosurgery: Pediatrics. 2021.","DOI":"10.3171\/2021.2.PEDS20949"},{"key":"2025060904201401000_2025.05.14.25327461v2.9","doi-asserted-by":"crossref","unstructured":"C. D. Robson et al. \u201cNeuroimaging of children with surgi-cally treated hydrocephalus: a practical approach\u201d. American Journal of Roentgenology. 2017.","DOI":"10.2214\/AJR.16.16870"},{"key":"2025060904201401000_2025.05.14.25327461v2.10","doi-asserted-by":"crossref","unstructured":"J. P. Sheppard et al. \u201cRisk of brain tumor induction from pediatric head CT procedures: a systematic literature review\u201d. Brain tumor research and treatment. 2018.","DOI":"10.14791\/btrt.2018.6.e4"},{"key":"2025060904201401000_2025.05.14.25327461v2.11","doi-asserted-by":"crossref","unstructured":"D. J. Brenner and E. J. Hall . \u201cComputed tomography\u2014an increasing source of radiation exposure\u201d. New England journal of medicine. 2007.","DOI":"10.1056\/NEJMra072149"},{"key":"2025060904201401000_2025.05.14.25327461v2.12","doi-asserted-by":"crossref","unstructured":"J. R. Harper et al. \u201cAssessing the utility of low resolution brain imaging: treatment of infant hydrocephalus\u201d. NeuroImage: Clinical. 2021.","DOI":"10.1101\/2021.07.21.21260949"},{"key":"2025060904201401000_2025.05.14.25327461v2.13","doi-asserted-by":"crossref","unstructured":"W. T. Kimberly et al. \u201cBrain imaging with portable low-field MRI\u201d. Nature reviews bioengineering. 2023.","DOI":"10.1038\/s44222-023-00086-w"},{"key":"2025060904201401000_2025.05.14.25327461v2.14","unstructured":"M. H. Mazurek et al. \u201cPortable, bedside, low-field magnetic resonance imaging for evaluation of intracerebral hemorrhage\u201d. Nature communications. 2021."},{"key":"2025060904201401000_2025.05.14.25327461v2.15","doi-asserted-by":"crossref","unstructured":"S. C. Deoni et al. \u201cDevelopment of a mobile low-field MRI scanner\u201d. Scientific reports. 2022.","DOI":"10.1038\/s41598-022-09760-2"},{"key":"2025060904201401000_2025.05.14.25327461v2.16","doi-asserted-by":"crossref","unstructured":"A. Iqbal et al. \u201cShared and subject-specific dictionary learning (ShSSDL) algorithm for multisubject fMRI data analysis\u201d. IEEE Trans. Biomed. Eng. 2018.","DOI":"10.1109\/TBME.2018.2806958"},{"key":"2025060904201401000_2025.05.14.25327461v2.17","doi-asserted-by":"crossref","unstructured":"S. R. Barnes et al. \u201cSemiautomated detection of cerebral microbleeds in magnetic resonance images\u201d. MRI. 2011.","DOI":"10.1016\/j.mri.2011.02.028"},{"key":"2025060904201401000_2025.05.14.25327461v2.18","doi-asserted-by":"crossref","unstructured":"M. Heidari et al. \u201cApplying a random projection algorithm to optimize machine learning model for breast lesion classification\u201d. IEEE Transactions on Biomedical Engineering. 2021.","DOI":"10.1109\/TBME.2021.3054248"},{"key":"2025060904201401000_2025.05.14.25327461v2.19","doi-asserted-by":"crossref","unstructured":"S. T. J\u00fcnger et al. \u201cFully automated MR detection and segmentation of brain metastases in non-small cell lung cancer using deep learning\u201d. J. Magn. Reson. Imaging. 2021.","DOI":"10.1002\/jmri.27741"},{"key":"2025060904201401000_2025.05.14.25327461v2.20","doi-asserted-by":"crossref","unstructured":"M. Masud et al. \u201cA Machine Learning Approach to Diagnosing Lung and Colon Cancer Using a Deep Learning-Based Classification Framework\u201d. Sensors (Basel, Switzerland). 2021.","DOI":"10.3390\/s21030748"},{"key":"2025060904201401000_2025.05.14.25327461v2.21","doi-asserted-by":"crossref","unstructured":"J. Chen et al. \u201cLung cancer diagnosis using deep attention-based multiple instance learning and radiomics\u201d. Med. Phys. 2022.","DOI":"10.1002\/mp.15539"},{"key":"2025060904201401000_2025.05.14.25327461v2.22","doi-asserted-by":"crossref","unstructured":"S. Kumar et al. \u201cBrain tumor classification using deep neural network and transfer learning\u201d. Brain topography. 2023.","DOI":"10.1007\/s10548-023-00953-0"},{"key":"2025060904201401000_2025.05.14.25327461v2.23","doi-asserted-by":"crossref","unstructured":"S. Solanki et al. \u201cBrain tumor detection and classification using intelligence techniques: an overview\u201d. IEEE Access. 2023.","DOI":"10.1109\/ACCESS.2023.3242666"},{"key":"2025060904201401000_2025.05.14.25327461v2.24","doi-asserted-by":"crossref","unstructured":"M. A. Talukder et al. \u201cAn efficient deep learning model to categorize brain tumor using reconstruction and fine-tuning\u201d. Expert systems with applications. 2023.","DOI":"10.31224\/3012"},{"key":"2025060904201401000_2025.05.14.25327461v2.25","doi-asserted-by":"crossref","unstructured":"F. Demir et al. \u201cImproving brain tumor classification performance with an effective approach based on new deep learning model named 3ACL from 3D MRI data\u201d. Biomedical Signal Processing and Control. 2023.","DOI":"10.1016\/j.bspc.2022.104424"},{"key":"2025060904201401000_2025.05.14.25327461v2.26","doi-asserted-by":"crossref","unstructured":"C. Li et al. \u201cTransfer learning for establishment of recognition of COVID-19 on CT imaging using small-sized training datasets\u201d. Knowledge-Based Systems. 2021.","DOI":"10.1016\/j.knosys.2021.106849"},{"key":"2025060904201401000_2025.05.14.25327461v2.27","doi-asserted-by":"crossref","unstructured":"X.-J. Liu et al. \u201cFew-shot learning for skin lesion image classification\u201d. Multimedia Tools and Appls. 2022.","DOI":"10.1007\/s11042-021-11472-0"},{"key":"2025060904201401000_2025.05.14.25327461v2.28","doi-asserted-by":"crossref","unstructured":"Y. Ma et al. \u201cUnsupervised deformable image registration network for 3D medical images\u201d. Applied Intelligence. 2022.","DOI":"10.1007\/s10489-021-02196-7"},{"key":"2025060904201401000_2025.05.14.25327461v2.29","doi-asserted-by":"crossref","unstructured":"R. Mahmoudi et al. \u201cA deep learning-based diagnosis system for COVID-19 detection and pneumonia screening using CT imaging\u201d. Applied Sciences. 2022.","DOI":"10.3390\/app12104825"},{"key":"2025060904201401000_2025.05.14.25327461v2.30","doi-asserted-by":"crossref","unstructured":"M. Mamalakis et al. \u201cDenResCov-19: A deep transfer learning network for robust automatic classification of COVID-19, pneumonia, and tuberculosis from X-rays\u201d. Computerized Medical Imaging and Graphics. 2021.","DOI":"10.1016\/j.compmedimag.2021.102008"},{"key":"2025060904201401000_2025.05.14.25327461v2.31","doi-asserted-by":"crossref","unstructured":"S. Masoudi et al. \u201cDeep learning based staging of bone lesions from computed tomography scans\u201d. IEEE access. 2021.","DOI":"10.1109\/ACCESS.2021.3074051"},{"key":"2025060904201401000_2025.05.14.25327461v2.32","doi-asserted-by":"crossref","unstructured":"S. Mehmood et al. \u201cMalignancy detection in lung and colon histopathology images using transfer learning with class selective image processing\u201d. IEEE Access. 2022.","DOI":"10.1109\/ACCESS.2022.3150924"},{"key":"2025060904201401000_2025.05.14.25327461v2.33","doi-asserted-by":"crossref","unstructured":"M.-A. Mercioni and L. L. Stavarache . \u201cDisease diagnosis with medical imaging using deep learning\u201d. In: Future of Information and Communication Conference. Springer. 2022.","DOI":"10.1007\/978-3-030-98015-3_13"},{"key":"2025060904201401000_2025.05.14.25327461v2.34","doi-asserted-by":"crossref","unstructured":"M. M. Mijwil . \u201cSkin cancer disease images classification using deep learning solutions\u201d. Mult. Tools and Applications. 2021.","DOI":"10.1007\/s11042-021-10952-7"},{"key":"2025060904201401000_2025.05.14.25327461v2.35","doi-asserted-by":"crossref","unstructured":"Z. Mousavi et al. \u201cCOVID-19 detection using chest X-ray images based on a developed deep neural network\u201d. SLAS technology. 2022.","DOI":"10.1016\/j.slast.2021.10.011"},{"key":"2025060904201401000_2025.05.14.25327461v2.36","doi-asserted-by":"crossref","unstructured":"A. Chinkamol et al. \u201cOCTAve: 2D en face optical coherence tomography angiography vessel segmentation in weakly-supervised learning with locality augmentation\u201d. IEEE Transactions on Biomedical Engineering. 2022.","DOI":"10.1109\/TBME.2022.3232102"},{"key":"2025060904201401000_2025.05.14.25327461v2.37","doi-asserted-by":"crossref","unstructured":"L. Rettenberger et al. \u201cSelf-supervised learning for annotation efficient biomedical image segmentation\u201d. IEEE Transactions on Biomedical Engineering. 2023.","DOI":"10.1109\/TBME.2023.3252889"},{"key":"2025060904201401000_2025.05.14.25327461v2.38","unstructured":"H. Guan and M. Liu . \u201cDomain adaptation for medical image analysis: a survey\u201d. IEEE Transactions on Biomedical Engineering. 2021."},{"key":"2025060904201401000_2025.05.14.25327461v2.39","doi-asserted-by":"crossref","unstructured":"M. Yu et al. \u201cInfection diagnosis in hydrocephalus CT images: a domain enriched attention learning approach\u201d. Journal of neural engineering. 2023.","DOI":"10.1088\/1741-2552\/acd9ee"},{"key":"2025060904201401000_2025.05.14.25327461v2.40","unstructured":"M. M. Jimeno et al. \u201cArtifactID: Identifying artifacts in low-field MRI of the brain using deep learning\u201d. Magnetic resonance imaging. 2022."},{"key":"2025060904201401000_2025.05.14.25327461v2.41","unstructured":"D. Tu et al. \u201cAutomated analysis of low-field brain MRI in cerebral malaria\u201d. Biometrics. 2023."},{"key":"2025060904201401000_2025.05.14.25327461v2.42","doi-asserted-by":"crossref","unstructured":"R. Ayde et al. \u201cDeep learning for fast low-field MRI acquisitions\u201d. Scientific reports. 2022.","DOI":"10.1038\/s41598-022-14039-7"},{"key":"2025060904201401000_2025.05.14.25327461v2.43","doi-asserted-by":"crossref","unstructured":"N. Koonjoo et al. \u201cBoosting the signal-to-noise of low-field MRI with deep learning image reconstruction\u201d. Scientific reports. 2021.","DOI":"10.21203\/rs.3.rs-126917\/v1"},{"key":"2025060904201401000_2025.05.14.25327461v2.44","doi-asserted-by":"crossref","unstructured":"D. Schote et al. \u201cJoint B0 and Image Reconstruction in Low-Field MRI by Physics-Informed Deep-Learning\u201d. IEEE Transactions on Biomedical Engineering. 2024.","DOI":"10.1109\/TBME.2024.3396223"},{"key":"2025060904201401000_2025.05.14.25327461v2.45","doi-asserted-by":"crossref","unstructured":"A. G. Hernandez et al. \u201cImproving image quality in low-field MRI with deep learning\u201d. In: International Conference on Image Processing (ICIP). IEEE. 2021.","DOI":"10.1109\/ICIP42928.2021.9506659"},{"key":"2025060904201401000_2025.05.14.25327461v2.46","doi-asserted-by":"crossref","unstructured":"V. Lau et al. \u201cPushing the limits of low-cost ultra-low-field MRI by dual-acquisition deep learning 3D uperresolution\u201d. Magnetic Resonance in Medicine. 2023.","DOI":"10.1002\/mrm.29642"},{"key":"2025060904201401000_2025.05.14.25327461v2.47","unstructured":"M. e. a. Zijta . \u201cAutomatic Segmentation of Low-Field MRI Brain Scans by Integrating Analytic and Deep Learning Techniques\u201d. https:\/\/repository.tudelft.nl\/record\/uuid:fff93273-f840-44c7-88ad-55ddccff9356. 2021."},{"key":"2025060904201401000_2025.05.14.25327461v2.48","doi-asserted-by":"crossref","unstructured":"X. Lin et al. \u201cImproving tumor classification by reusing self-predicted segmentation of medical images as guiding knowledge\u201d. IEEE Jour. of Biomed. and Health Inform. 2023.","DOI":"10.1109\/JBHI.2023.3293009"},{"key":"2025060904201401000_2025.05.14.25327461v2.49","doi-asserted-by":"crossref","unstructured":"P. Tang et al. \u201cGP-CNN-DTEL: Global-part CNN model with data-transformed ensemble learning for skin lesion classification\u201d. IEEE journal of biomed and health inform. 2020.","DOI":"10.1109\/JBHI.2020.2977013"},{"key":"2025060904201401000_2025.05.14.25327461v2.50","doi-asserted-by":"crossref","unstructured":"S.-X. Zhao et al. \u201cA local and global feature disentangled network: toward classification of benign-malignant thyroid nodules from ultrasound image\u201d. IEEE Trans. on Med. Imag. 2022.","DOI":"10.1109\/TMI.2022.3140797"},{"key":"2025060904201401000_2025.05.14.25327461v2.51","doi-asserted-by":"crossref","unstructured":"G. Li et al. \u201cMulti-Task Cascaded Attention Network for Brain Tumor Segmentation and Classification\u201d. In: IEEE Int. Conference on Acoustics, Speech and Signal Processing. 2024.","DOI":"10.1109\/ICASSP48485.2024.10447772"},{"key":"2025060904201401000_2025.05.14.25327461v2.52","doi-asserted-by":"crossref","unstructured":"X. Liu et al. \u201cSRTRP-Net: A multi-task learning network for segmentation and prediction of stereotactic radiosurgery treatment response in brain metastases\u201d. Computers in Biology and Medicine. 2024.","DOI":"10.1016\/j.compbiomed.2024.108503"},{"key":"2025060904201401000_2025.05.14.25327461v2.53","doi-asserted-by":"crossref","unstructured":"Y. Zhao et al. \u201cMulti-task deep learning for medical image computing and analysis: A review\u201d. Computers in Biology and Medicine. 2023.","DOI":"10.1016\/j.compbiomed.2022.106496"},{"key":"2025060904201401000_2025.05.14.25327461v2.54","doi-asserted-by":"crossref","unstructured":"S. Graham et al. \u201cOne model is all you need: multi-task learning enables simultaneous histology image segmentation and classification\u201d. Medical Image Analysis. 2023.","DOI":"10.1016\/j.media.2022.102685"},{"key":"2025060904201401000_2025.05.14.25327461v2.55","doi-asserted-by":"crossref","unstructured":"F. Gao et al. \u201cA feature transfer enabled multi-task deep learning model on medical imaging\u201d. Expert Systems with Applications. 2020.","DOI":"10.1016\/j.eswa.2019.112957"},{"key":"2025060904201401000_2025.05.14.25327461v2.56","doi-asserted-by":"crossref","unstructured":"Y. Zhang et al. \u201c3D multi-attention guided multi-task learning network for automatic gastric tumor segmentation and lymph node classification\u201d. IEEE Trans. Med. Imaging. 2021.","DOI":"10.1109\/TMI.2021.3062902"},{"key":"2025060904201401000_2025.05.14.25327461v2.57","doi-asserted-by":"crossref","unstructured":"A. Harouni et al. \u201cUniversal multi-modal deep network for classification and segmentation of medical images\u201d. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). IEEE. 2018.","DOI":"10.1109\/ISBI.2018.8363710"},{"key":"2025060904201401000_2025.05.14.25327461v2.58","doi-asserted-by":"crossref","unstructured":"A. Amyar et al. \u201cMulti-task deep learning based CT imaging analysis for COVID-19 pneumonia: Classification and segmentation\u201d. Computers in biology and medicine. 2020.","DOI":"10.1101\/2020.04.16.20064709"},{"key":"2025060904201401000_2025.05.14.25327461v2.59","unstructured":"B. Huang et al. \u201cDeep semantic segmentation feature-based radiomics for the classification tasks in medical image analysis\u201d. IEEE J. Biomed. Health Inform. 2020."},{"key":"2025060904201401000_2025.05.14.25327461v2.60","doi-asserted-by":"crossref","unstructured":"H. Huang et al. \u201cA deep multi-task learning framework for brain tumor segmentation\u201d. Frontiers in oncology. 2021.","DOI":"10.3389\/fonc.2021.690244"},{"key":"2025060904201401000_2025.05.14.25327461v2.61","doi-asserted-by":"crossref","unstructured":"P. Sunthornwetchapong et al. \u201cReal-Time Multi-Task Deep Learning Model for Polyp Detection, Characterization, and Size Estimation\u201d. IEEE Access. 2025.","DOI":"10.1109\/ACCESS.2025.3527720"},{"key":"2025060904201401000_2025.05.14.25327461v2.62","doi-asserted-by":"crossref","unstructured":"Q. Yu et al. \u201cMulti-task learning for calcaneus fracture diagnosis of X-ray images\u201d. Biomedical Signal Processing and Control. 2025.","DOI":"10.1016\/j.bspc.2024.106843"},{"key":"2025060904201401000_2025.05.14.25327461v2.63","doi-asserted-by":"crossref","unstructured":"S. Kordnoori et al. \u201cLungXpertAI: A deep multi-task learning model for chest CT scan analysis and COVID-19 detection\u201d. Biomedical Signal Processing and Control. 2025.","DOI":"10.1016\/j.bspc.2024.106866"},{"key":"2025060904201401000_2025.05.14.25327461v2.64","doi-asserted-by":"crossref","unstructured":"A. Lucas et al. \u201cMulti-contrast high-field quality image synthesis for portable low-field MRI using generative adversarial networks and paired data\u201d. medRxiv. 2023.","DOI":"10.1101\/2023.12.28.23300409"},{"key":"2025060904201401000_2025.05.14.25327461v2.65","unstructured":"O. Ronneberger et al. \u201cU-net: Convolutional networks for biomedical image segmentation\u201d. In: Medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18. Springer. 2015."},{"key":"2025060904201401000_2025.05.14.25327461v2.66","doi-asserted-by":"crossref","unstructured":"K. He et al. \u201cDeep residual learning for image recognition\u201d. In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"2025060904201401000_2025.05.14.25327461v2.67","doi-asserted-by":"crossref","unstructured":"V. V. Estrela et al. \u201cTotal variation applications in computer vision\u201d. In: Handbook of Research on Emerging Perspectives in Intelligent Pattern Recognition, Analysis, and Image Processing. 2016.","DOI":"10.4018\/978-1-4666-8654-0.ch002"},{"key":"2025060904201401000_2025.05.14.25327461v2.68","doi-asserted-by":"crossref","unstructured":"P. A. Yushkevich et al. \u201cUser-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability\u201d. Neuroimage. 2006.","DOI":"10.1016\/j.neuroimage.2006.01.015"},{"key":"2025060904201401000_2025.05.14.25327461v2.69","doi-asserted-by":"crossref","unstructured":"S. Roy et al. \u201cMednext: transformer-driven scaling of convnets for medical image segmentation\u201d. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer. 2023.","DOI":"10.1007\/978-3-031-43901-8_39"},{"key":"2025060904201401000_2025.05.14.25327461v2.70","doi-asserted-by":"crossref","unstructured":"O. N. Manzari et al. \u201cMedViT: a robust vision transformer for generalized medical image classification\u201d. Computers in Biology and Medicine. 2023.","DOI":"10.1016\/j.compbiomed.2023.106791"},{"key":"2025060904201401000_2025.05.14.25327461v2.71","article-title":"Adam: A method for stochastic optimization","year":"2014","journal-title":"arXiv preprint"},{"key":"2025060904201401000_2025.05.14.25327461v2.72","article-title":"Model evaluation, model selection, and algorithm selection in machine learning","year":"2018","journal-title":"arXiv preprint"},{"key":"2025060904201401000_2025.05.14.25327461v2.73","unstructured":"A. Paszke et al. \u201cPytorch: An imperative style, high-performance deep learning library\u201d. Advances in neural information processing systems. 2019."},{"key":"2025060904201401000_2025.05.14.25327461v2.74","doi-asserted-by":"crossref","unstructured":"B. J. Erickson and F. Kitamura . Magician\u2019s corner: 9. Performance metrics for machine learning models. 2021.","DOI":"10.1148\/ryai.2021200126"},{"key":"2025060904201401000_2025.05.14.25327461v2.75","unstructured":"J. H. McDonald . \u201cHandbook of biological statistics\u201d. 2014."},{"key":"2025060904201401000_2025.05.14.25327461v2.76","unstructured":"B. Zhou et al. \u201cLearning deep features for scene recognition using places database\u201d. Advances in neural information processing systems. 2014."},{"key":"2025060904201401000_2025.05.14.25327461v2.77","doi-asserted-by":"crossref","unstructured":"J. K. Karimy et al. \u201cInflammation in acquired hydrocephalus: pathogenic mechanisms and therapeutic targets\u201d. Nature Reviews Neurology. 2020.","DOI":"10.1038\/s41582-020-0321-y"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.05.14.25327461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:36:07Z","timestamp":1768509367000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.05.14.25327461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,16]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1101\/2025.05.14.25327461","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1109\/TBME.2025.3578541","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2025,5,16]]},"subtype":"preprint"}}