{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T03:28:01Z","timestamp":1790393281766,"version":"4.1.0"},"reference-count":68,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:00:00Z","timestamp":1755820800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH","award":["R01CA259008"],"award-info":[{"award-number":["R01CA259008"]}]},{"name":"NIH","award":["R44CA183390"],"award-info":[{"award-number":["R44CA183390"]}]},{"name":"NIH","award":["R01EB031577"],"award-info":[{"award-number":["R01EB031577"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Objectives<\/jats:title>\n<jats:p>Computed tomography (CT) provides high spatial-resolution visualization of 3D structures for various applications. Traditional analytical\/iterative CT reconstruction algorithms require hundreds of angular samplings, a condition may not be met practically for physical and mechanical limitations. Sparse view CT reconstruction has been proposed using constrained optimization and machine learning methods with varying success, less so for ultra-sparse view reconstruction. Neural radiance field (NeRF) is a powerful tool for reconstructing and rendering 3D natural scenes from sparse views, but its direct application to 3D medical image reconstruction has been minimally successful due to the differences in photon transportation and available prior information between optic and X-ray.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We develop TomoGRAF to reconstruct high-quality 3D CT volumes using ultra-sparse projections. TomoGRAF has two main novelties pertinent to X-ray physics and CT imaging. First, TomoGRAF\u2019s volume rendering module accumulates x-ray material attenuation passing through an object with CT geometry rather than visible light material color and opacity from surface interaction in NeRF. Second, TomoGRAF penalizes the difference between the simulated and ground truth volume during training besides the 2D views, thus significantly improving the prior fidelity.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>TomoGRAF is trained on LIDC-IDRI dataset (1011 scans) and evaluated on an unseen in-house dataset (100 scans) of distinct imaging characteristics from training and demonstrates a vast leap in performance compared with state-of-the-art deep learning and NeRF methods.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>TomoGRAF provides the first generalizable solution for image-guided radiotherapy and interventional radiology applications, where only one\/a few X-ray views are available, but 3D volumetric information is desired.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0330463","type":"journal-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:46:23Z","timestamp":1755884783000},"page":"e0330463","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":2,"title":["TomoGRAF: An X-ray physics-driven generative radiance field framework for extremely sparse view CT reconstruction"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5587-5275","authenticated-orcid":true,"given":"Di","family":"Xu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengjie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihui","family":"Lyu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martina","family":"Descovich","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Ruan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6696-5409","authenticated-orcid":true,"given":"Ke","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"issue":"3","key":"pone.0330463.ref001","doi-asserted-by":"crossref","first-page":"546","DOI":"10.1137\/0143035","article-title":"An inversion formula for cone-beam reconstruction","volume":"43","author":"HK Tuy","year":"1983","journal-title":"SIAM J Appl Math"},{"issue":"1","key":"pone.0330463.ref002","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.meddos.2005.12.010","article-title":"In-room CT techniques for image-guided radiation therapy","volume":"31","author":"C-MC Ma","year":"2006","journal-title":"Med Dosim"},{"key":"pone.0330463.ref003","first-page":"173","article-title":"CT-Guided Interventions: Current Practice and Future Directions.","volume-title":"Intraoperative Imaging and Image-Guided Therapy [Internet]","author":"R Gupta","year":"2014"},{"issue":"18","key":"pone.0330463.ref004","doi-asserted-by":"crossref","first-page":"5134","DOI":"10.1158\/1078-0432.CCR-12-0891","article-title":"Validation of a radiosensitivity molecular signature in breast cancer","volume":"18","author":"SA Eschrich","year":"2012","journal-title":"Clin Cancer Res"},{"issue":"3","key":"pone.0330463.ref005","doi-asserted-by":"crossref","first-page":"663","DOI":"10.1148\/radiol.2015141303","article-title":"Digital Breast Tomosynthesis: State of the Art","volume":"277","author":"S Vedantham","year":"2015","journal-title":"Radiology"},{"issue":"1","key":"pone.0330463.ref006","doi-asserted-by":"crossref","first-page":"014302","DOI":"10.1118\/1.4770281","article-title":"A review of breast tomosynthesis. Part II. Image reconstruction, processing and analysis, and advanced applications","volume":"40","author":"I Sechopoulos","year":"2013","journal-title":"Med Phys"},{"issue":"3","key":"pone.0330463.ref007","doi-asserted-by":"crossref","first-page":"748","DOI":"10.1109\/TMI.2014.2380993","article-title":"Sparse-view spectral CT reconstruction using spectral patch-based low-rank penalty","volume":"34","author":"K Kim","year":"2015","journal-title":"IEEE Trans Med Imaging"},{"issue":"19","key":"pone.0330463.ref008","doi-asserted-by":"crossref","first-page":"7437","DOI":"10.1088\/0031-9155\/60\/19\/7437","article-title":"Ultra-low dose CT attenuation correction for PET\/CT: analysis of sparse view data acquisition and reconstruction algorithms","volume":"60","author":"X Rui","year":"2015","journal-title":"Phys Med Biol"},{"issue":"11","key":"pone.0330463.ref009","doi-asserted-by":"crossref","first-page":"3254","DOI":"10.1016\/j.ejrad.2012.03.006","article-title":"Time-resolved CT angiography in aortic dissection","volume":"81","author":"FG Meinel","year":"2012","journal-title":"Eur J Radiol"},{"issue":"4","key":"pone.0330463.ref010","doi-asserted-by":"crossref","first-page":"041912","DOI":"10.1118\/1.4868510","article-title":"Image quality in thoracic 4D cone-beam CT: a sensitivity analysis of respiratory signal, binning method, reconstruction algorithm, and projection angular spacing","volume":"41","author":"C-C Shieh","year":"2014","journal-title":"Med Phys"},{"issue":"6","key":"pone.0330463.ref011","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1364\/JOSAA.1.000612","article-title":"Practical cone-beam algorithm","volume":"1","author":"LA Feldkamp","year":"1984","journal-title":"J Opt Soc Am A"},{"issue":"3","key":"pone.0330463.ref012","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1016\/0022-5193(70)90109-8","article-title":"Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography","volume":"29","author":"R Gordon","year":"1970","journal-title":"J Theor Biol"},{"issue":"1","key":"pone.0330463.ref013","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1177\/016173468400600107","article-title":"Simultaneous algebraic reconstruction technique (SART): a superior implementation of the art algorithm","volume":"6","author":"AH Andersen","year":"1984","journal-title":"Ultrason Imaging"},{"issue":"4","key":"pone.0330463.ref014","doi-asserted-by":"crossref","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","article-title":"Compressed sensing","volume":"52","author":"DL Donoho","year":"2006","journal-title":"IEEE Trans Inform Theory"},{"issue":"17","key":"pone.0330463.ref015","doi-asserted-by":"crossref","first-page":"4777","DOI":"10.1088\/0031-9155\/53\/17\/021","article-title":"Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization","volume":"53","author":"EY Sidky","year":"2008","journal-title":"Phys Med Biol"},{"issue":"23","key":"pone.0330463.ref016","doi-asserted-by":"crossref","first-page":"7923","DOI":"10.1088\/0031-9155\/57\/23\/7923","article-title":"Adaptive-weighted total variation minimization for sparse data toward low-dose x-ray computed tomography image reconstruction","volume":"57","author":"Y Liu","year":"2012","journal-title":"Phys Med Biol"},{"issue":"3","key":"pone.0330463.ref017","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1109\/TMI.2013.2295738","article-title":"Total variation-stokes strategy for sparse-view X-ray CT image reconstruction","volume":"33","author":"Y Liu","year":"2014","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0330463.ref018","first-page":"685618","volume-title":"Prior image constrained compressed sensing (PICCS)","author":"GH Chen","year":"2008"},{"key":"pone.0330463.ref019","first-page":"438617","article-title":"Nonlocal means-based denoising for medical images","volume":"2012","author":"K Lu","year":"2012","journal-title":"Comput Math Methods Med"},{"issue":"12","key":"pone.0330463.ref020","doi-asserted-by":"crossref","first-page":"2271","DOI":"10.1109\/TMI.2014.2336860","article-title":"Artifact suppressed dictionary learning for low-dose CT image processing","volume":"33","author":"Y Chen","year":"2014","journal-title":"IEEE Trans Med Imaging"},{"issue":"9","key":"pone.0330463.ref021","doi-asserted-by":"crossref","first-page":"2667","DOI":"10.1088\/0031-9155\/57\/9\/2667","article-title":"Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means","volume":"57","author":"Y Chen","year":"2012","journal-title":"Phys Med Biol"},{"key":"pone.0330463.ref022","doi-asserted-by":"crossref","first-page":"2392","DOI":"10.1109\/CVPR.2012.6247952","article-title":"Image denoising: Can plain neural networks compete with BM3D?","volume-title":"2012 IEEE Conference on Computer Vision and Pattern Recognition [Internet]","author":"HC Burger","year":"2012"},{"key":"pone.0330463.ref023","article-title":"Image denoising with multi-layer perceptrons, part 1: comparison with existing algorithms and with bounds [Internet]","author":"HC Burger","year":"2012","journal-title":"arXiv"},{"issue":"4","key":"pone.0330463.ref024","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1097\/RLI.ob013e3181dzfeec","article-title":"Reducing Abdominal CT Radiation Dose With Adaptive Statistical Iterative Reconstruction Technique","volume":"45","author":"P Prakash","year":"2010","journal-title":"Investig Radiol"},{"issue":"10","key":"pone.0330463.ref025","doi-asserted-by":"crossref","DOI":"10.1002\/mp.12344","article-title":"A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction","volume":"44","author":"E Kang","year":"2017","journal-title":"Med Phys"},{"issue":"9","key":"pone.0330463.ref026","doi-asserted-by":"crossref","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","article-title":"Deep Convolutional Neural Network for Inverse Problems in Imaging","volume":"26","author":"KH Jin","year":"2017","journal-title":"IEEE Trans Image Process"},{"issue":"11","key":"pone.0330463.ref027","doi-asserted-by":"crossref","first-page":"4750","DOI":"10.1109\/TIP.2014.2341971","article-title":"Improving filtered backprojection reconstruction by data-dependent filtering","volume":"23","author":"DM Pelt","year":"2014","journal-title":"IEEE Trans Image Process"},{"key":"pone.0330463.ref028","first-page":"432","article-title":"Deep Learning Computed Tomography.","volume-title":"Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016 [Internet]. Lecture Notes in Computer Science","author":"T W\u00fcrfl","year":"2016"},{"key":"pone.0330463.ref029","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1016\/S0168-9002(99)01453-9","article-title":"Neural network CT image reconstruction method for small amount of projection data","volume":"449","author":"XF Ma","year":"2000","journal-title":"Nucl Instrum Methods Phys Res Section A: Accelerators, Spectrometers Detectors Associated Equipment"},{"issue":"12","key":"pone.0330463.ref030","doi-asserted-by":"crossref","first-page":"2862","DOI":"10.1016\/j.ijleo.2014.01.003","article-title":"Dictionary learning based sinogram inpainting for CT sparse reconstruction","volume":"125","author":"S Li","year":"2014","journal-title":"Optik"},{"issue":"2","key":"pone.0330463.ref031","doi-asserted-by":"crossref","first-page":"414","DOI":"10.1109\/TCSVT.2016.2615444","article-title":"Structure-Adaptive Fuzzy Estimation for Random-Valued Impulse Noise Suppression","volume":"28","author":"Y Chen","year":"2018","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"12","key":"pone.0330463.ref032","doi-asserted-by":"crossref","first-page":"2499","DOI":"10.1109\/TMI.2017.2739841","article-title":"Discriminative Feature Representation to Improve Projection Data Inconsistency for Low Dose CT Imaging","volume":"36","author":"J Liu","year":"2017","journal-title":"IEEE Trans Med Imaging"},{"key":"pone.0330463.ref033","first-page":"1013328","volume-title":"View-interpolation of sparsely sampled sinogram using convolutional neural network","author":"H Lee","year":"2017"},{"issue":"2","key":"pone.0330463.ref034","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1002\/mp.14504","article-title":"CT artifact correction for sparse and truncated projection data using generative adversarial networks","volume":"48","author":"AR Podgorsak","year":"2021","journal-title":"Med Phys"},{"key":"pone.0330463.ref035","article-title":"Deep ADMM-Net for compressive sensing MRI","volume":"29","author":"J Sun","year":"2016","journal-title":"Adv Neu Inf Process Syst"},{"issue":"5","key":"pone.0330463.ref036","doi-asserted-by":"crossref","first-page":"2498","DOI":"10.1118\/1.4918577","article-title":"A method for volumetric imaging in radiotherapy using single x-ray projection","volume":"42","author":"Y Xu","year":"2015","journal-title":"Med Phys"},{"issue":"11","key":"pone.0330463.ref037","doi-asserted-by":"crossref","first-page":"6840","DOI":"10.1002\/mp.15877","article-title":"Effect of subject motion and gantry rotation speed on image quality and dose delivery in CT-guided radiotherapy","volume":"49","author":"WT Hrinivich","year":"2022","journal-title":"Med Phys"},{"key":"pone.0330463.ref038","doi-asserted-by":"crossref","first-page":"110179","DOI":"10.1016\/j.radonc.2024.110179","article-title":"Deep match: A zero-shot framework for improved fiducial-free respiratory motion tracking","volume":"194","author":"D Xu","year":"2024","journal-title":"Radiother Oncol"},{"key":"pone.0330463.ref039","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1016\/B978-0-12-816176-0.00031-4","article-title":"Technology and applications in interventional imaging: 2D X-ray radiography\/fluoroscopy and 3D cone-beam CT","volume-title":"Handbook of Medical Image Computing and Computer Assisted Intervention","author":"S Schafer","year":"2020"},{"issue":"11","key":"pone.0330463.ref040","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1038\/s41551-019-0466-4","article-title":"Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning","volume":"3","author":"L Shen","year":"2019","journal-title":"Nat Biomed Eng"},{"key":"pone.0330463.ref041","article-title":"X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks","author":"X Ying","year":"2019","journal-title":"arXiv"},{"key":"pone.0330463.ref042","article-title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","author":"K Schwarz","year":"2021","journal-title":"arXiv"},{"key":"pone.0330463.ref043","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","article-title":"Deep Learning in Medical Image Analysis","volume":"19","author":"D Shen","year":"2017","journal-title":"Annu Rev Biomed Eng"},{"key":"pone.0330463.ref044","article-title":"NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis","author":"B Mildenhall","year":"2020","journal-title":"arXiv"},{"key":"pone.0330463.ref045","author":"P Isola","year":"2016"},{"key":"pone.0330463.ref046","first-page":"3843","article-title":"MedNeRF: Medical Neural Radiance Fields for Reconstructing 3D-aware CT-Projections from a Single X-ray.","volume-title":"2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) [Internet]","author":"A Corona-Figueroa","year":"2022"},{"issue":"1","key":"pone.0330463.ref047","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1118\/1.595739","article-title":"Calculation of the radiological depth: Technical Reports: Calculation of the radiological depth","volume":"12","author":"RL Siddon","year":"1985","journal-title":"Med Phys"},{"key":"pone.0330463.ref048","article-title":"Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis [Internet]","author":"B Liu","year":"2021","journal-title":"arXiv"},{"key":"pone.0330463.ref049","article-title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric [Internet]","author":"R Zhang","year":"2018","journal-title":"arXiv"},{"key":"pone.0330463.ref050","article-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","author":"K Simonyan","year":"2015","journal-title":"arXiv"},{"key":"pone.0330463.ref051","doi-asserted-by":"crossref","first-page":"1882","DOI":"10.1109\/TIP.2021.3049346","article-title":"On Data Augmentation for GAN Training","volume":"30","author":"N-T Tran","year":"2021","journal-title":"IEEE Trans Image Process"},{"key":"pone.0330463.ref052","article-title":"Auto-Encoding Variational Bayes [Internet]","author":"DP Kingma","year":"2022","journal-title":"arXiv"},{"issue":"2","key":"pone.0330463.ref053","doi-asserted-by":"crossref","first-page":"915","DOI":"10.1118\/1.3528204","article-title":"The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans","volume":"38","author":"SG 3rd Armato","year":"2011","journal-title":"Med Phys"},{"issue":"5","key":"pone.0330463.ref054","article-title":"Intrafraction verification of gated RapidArc by using beam-level kilovoltage X-ray images","volume":"83","author":"R Li","year":"2012","journal-title":"Int J Radiat Oncol Biol Phys"},{"issue":"12","key":"pone.0330463.ref055","doi-asserted-by":"crossref","first-page":"2421","DOI":"10.1016\/j.ejrad.2015.06.014","article-title":"From 3D to 4D: Integration of temporal information into CT angiography studies","volume":"84","author":"H Haubenreisser","year":"2015","journal-title":"Eur J Radiol"},{"issue":"1","key":"pone.0330463.ref056","doi-asserted-by":"crossref","first-page":"102","DOI":"10.3174\/ajnr.A7382","article-title":"4D Flat Panel Conebeam CTA for Analysis of the Angioarchitecture of Cerebral AVMs with a Novel Software Prototype","volume":"43","author":"F Keil","year":"2022","journal-title":"AJNR Am J Neuroradiol"},{"issue":"3","key":"pone.0330463.ref057","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1002\/acm2.12279","article-title":"Monitoring frequency of intra-fraction patient motion using the ExacTrac system for LINAC-based SRS treatments","volume":"19","author":"BC Lewis","year":"2018","journal-title":"J Appl Clin Med Phys"},{"issue":"5","key":"pone.0330463.ref058","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1177\/153303461000900502","article-title":"The CyberKnife Robotic Radiosurgery System in 2010","volume":"9","author":"W Kilby","year":"2010","journal-title":"Technol Cancer Res Treat"},{"issue":"5","key":"pone.0330463.ref059","doi-asserted-by":"crossref","DOI":"10.1002\/mp.14625","article-title":"AAPM Task Group 264: The safe clinical implementation of MLC tracking in radiotherapy","volume":"48","author":"PJ Keall","year":"2021","journal-title":"Med Phys"},{"key":"pone.0330463.ref060","article-title":"Learning both Weights and Connections for Efficient Neural Networks [Internet]","author":"S Han","year":"2015","journal-title":"arXiv"},{"key":"pone.0330463.ref061","article-title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference [Internet]","author":"B Jacob","year":"2017","journal-title":"arXiv"},{"key":"pone.0330463.ref062","first-page":"226","volume-title":"Demystifying TensorRT: Characterizing Neural Network Inference Engine on Nvidia Edge Devices. In: 2021 IEEE International Symposium on Workload Characterization (IISWC) [Internet]","author":"O Shafi","year":"2021"},{"key":"pone.0330463.ref063","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/3020078.3021740","article-title":"Can FPGAs Beat GPUs in Accelerating Next-Generation Deep Neural Networks?","author":"E Nurvitadhi","year":"2017","journal-title":"Proceedings of the 2017 ACM\/SIGDA International Symposium on Field-Programmable Gate Arrays. Monterey California USA: ACM"},{"key":"pone.0330463.ref064","first-page":"1","article-title":"In-Datacenter Performance Analysis of a Tensor Processing Unit.","author":"NP Jouppi","year":"2017","journal-title":"Proceedings of the 44th Annual International Symposium on Computer Architecture. Toronto ON Canada: ACM"},{"key":"pone.0330463.ref065","article-title":"Implicit Neural Representations with Periodic Activation Functions","author":"V Sitzmann","year":"2020","journal-title":"arXiv"},{"issue":"4","key":"pone.0330463.ref066","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3528223.3530127","article-title":"Instant neural graphics primitives with a multiresolution hash encoding","volume":"41","author":"T M\u00fcller","year":"2022","journal-title":"ACM Trans Graph"},{"key":"pone.0330463.ref067","author":"P Hedman","year":"2021"},{"issue":"4","key":"pone.0330463.ref068","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3625287","article-title":"Explainable deep learning methods in medical image classification: a survey","volume":"56","author":"C Patr\u00edcio","year":"2024","journal-title":"ACM Comput Surv"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330463","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T17:46:35Z","timestamp":1755884795000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0330463"}},"subtitle":[],"editor":[{"given":"Zhentian","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,8,22]]},"references-count":68,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0330463","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,22]]}}}