{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T18:25:20Z","timestamp":1787077520415,"version":"build-2736575974"},"reference-count":55,"publisher":"Public Library of Science (PLoS)","issue":"8","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004595","name":"Universiti Sains Malaysia","doi-asserted-by":"publisher","award":["Grant Number: R502-KR-RUT002-0000000244-K134"],"award-info":[{"award-number":["Grant Number: R502-KR-RUT002-0000000244-K134"]}],"id":[{"id":"10.13039\/501100004595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Primary malignant bone tumours of the skeleton have a great diversity in their biological behaviour, and the most common in adolescence is osteosarcoma for which the diagnosis and therapeutic management are both a challenge. The use of machine and deep learning in image analysis for MRI, diffusion-weighted imaging (DWI) and dynamic contrast-enhanced MRI (DCE-MRI) to diagnose osteosarcoma has shown major improvements recently. This systematic review is performed according to PRISMA 2020 guidelines, and it comprises a critical analysis of 38 peer-reviewed articles from 2020 to 2025, which address the various aspects of tumour segmentation, classification, and prognosis. The methodological mapping revealed seven main categories that included numerous examples of radiomics (n\u2009=\u20098) and convolutional neural networks (CNNs, n\u2009=\u20096), as well as vision transformers and multimodal architectures for emerging technologies (n\u2009=\u20095 each). A quantitative evaluation of the segmentation performance showed that Multimodal achieved the best spatial overlap with an average Dice Similarity Coefficient (DSC) of 94.7% (range: 94.5\u201394.9%), while CNN of standard size was comparable, Lightweight networks had a DSC between 91.4 and 99.4% with an average of 91.9% and Vision Transformers a range of 90.5\u201394.9% with an average of 92.1%. By contrast, the performance gap among the Attention Mechanisms was greatest with a mean of 87.67% (64.6\u201398.5%), while the lowest was the mean 85.7% (81.6\u201389.8%) for Unsupervised Clustering. In addition to segmentation, the clinical nomograms based on radiomics also showed excellent prognostic potential:The AUC values for predicting pathological necrosis after chemotherapy varied from 0.807 to 0.848. More importantly it was found that there were significant translational gaps because all 38 models were limited to retrospective, single centre cohorts, with evaluation of risk of bias. Advanced algorithms perform well with localized precision but face a number of challenges with robust multicenter testing and a public repository.<\/jats:p>","DOI":"10.1371\/journal.pone.0354896","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T17:33:37Z","timestamp":1787074417000},"page":"e0354896","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning applications in osteosarcoma MRI: A systematic review of recent advances in AI-based osteosarcoma diagnosis"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2257-6751","authenticated-orcid":true,"given":"Galib Muhammad Shahriar","family":"Himel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2015-2269","authenticated-orcid":true,"given":"Anusha","family":"Achuthan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusuf Abas","family":"Mohamed","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3492-2551","authenticated-orcid":true,"given":"Bee Ee","family":"Khoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohd Ezane","family":"Bin Aziz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"issue":"10","key":"pone.0354896.ref001","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.3390\/cells10102684","article-title":"Osteosarcoma in adolescents and young adults","volume":"10","author":"JA Lee","year":"2021","journal-title":"Cells"},{"issue":"1","key":"pone.0354896.ref002","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1038\/s41572-022-00409-y","article-title":"Osteosarcoma","volume":"8","author":"HC Beird","year":"2022","journal-title":"Nat Rev Dis Primers"},{"issue":"4","key":"pone.0354896.ref003","doi-asserted-by":"crossref","first-page":"599","DOI":"10.3390\/cancers17040599","article-title":"Multimodal Imaging of osteosarcoma: from first diagnosis to radiomics","volume":"17","author":"M C\u00e8","year":"2025","journal-title":"Cancers (Basel)"},{"key":"pone.0354896.ref004","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.mri.2021.07.003","article-title":"Prognostic and therapeutic evaluation of nasopharyngeal carcinoma by dynamic contrast-enhanced (DCE), diffusion-weighted (DW) magnetic resonance imaging (MRI) and magnetic resonance spectroscopy (MRS)","volume":"83","author":"AWL Mui","year":"2021","journal-title":"Magn Reson Imaging"},{"issue":"4","key":"pone.0354896.ref005","doi-asserted-by":"crossref","first-page":"330","DOI":"10.1007\/s13224-021-01488-9","article-title":"Added-Value of Diffusion-Weighted Imaging (DWI) and Dynamic Contrast-Enhanced (DCE-MRI) magnetic resonance imaging in the preoperative assessment of cervical cancer","volume":"72","author":"R Bhardwaj","year":"2022","journal-title":"J Obstet Gynaecol India"},{"issue":"15","key":"pone.0354896.ref006","doi-asserted-by":"crossref","first-page":"3648","DOI":"10.3390\/cancers14153648","article-title":"Comparative multicentric evaluation of inter-observer variability in neuroblastic tumor segmentation","volume":"14","author":"D Veiga-Canuto","year":"2022","journal-title":"Cancers"},{"key":"pone.0354896.ref007","doi-asserted-by":"crossref","first-page":"242","DOI":"10.1016\/j.ejmp.2021.04.016","article-title":"Artificial intelligence and machine learning for medical imaging: a technology review","volume":"83","author":"A Barrag\u00e1n-Montero","year":"2021","journal-title":"Phys Med"},{"key":"pone.0354896.ref008","doi-asserted-by":"crossref","first-page":"26731","DOI":"10.1007\/s11042-022-14305-w","article-title":"Machine learning and deep learning approach for medical image analysis: diagnosis to detection","volume":"82","author":"M Rana","year":"2023","journal-title":"Multimed Tools Appl"},{"issue":"3","key":"pone.0354896.ref009","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.job.2022.03.003","article-title":"Deep learning models in medical image analysis","volume":"64","author":"M Tsuneki","year":"2022","journal-title":"J Oral Biosci"},{"issue":"2","key":"pone.0354896.ref010","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1007\/s40846-024-00863-x","article-title":"Role of artificial intelligence in medical image analysis: a review of current trends and future directions","volume":"44","author":"X Li","year":"2024","journal-title":"J Med Biol Eng"},{"key":"pone.0354896.ref011","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3389\/fncom.2020.00025","article-title":"Brain tumor segmentation using an ensemble of 3d u-nets and overall survival prediction using radiomic features","volume":"14","author":"X Feng","year":"2020","journal-title":"Front Comput Neurosci"},{"issue":"4","key":"pone.0354896.ref012","first-page":"599","article-title":"Multimodal imaging of osteosarcoma: a narrative review","volume":"17","author":"M C\u00e8","year":"2025","journal-title":"Cancers"},{"issue":"8","key":"pone.0354896.ref013","doi-asserted-by":"crossref","DOI":"10.1111\/exsy.13018","article-title":"Analysis of breast cancer classification robustness with radiomics feature extraction and deep learning techniques","volume":"39","author":"HU Rashid","year":"2022","journal-title":"Expert Systems"},{"key":"pone.0354896.ref014","doi-asserted-by":"crossref","first-page":"104304","DOI":"10.1016\/j.compbiomed.2021.104304","article-title":"Machine learning-based prognostic modeling using clinical data and quantitative radiomic features from chest CT images in COVID-19 patients","volume":"132","author":"I Shiri","year":"2021","journal-title":"Comput Biol Med"},{"issue":"1","key":"pone.0354896.ref015","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s13244-022-01277-6","article-title":"An updated systematic review of radiomics in osteosarcoma: utilizing CLAIM to adapt the increasing trend of deep learning application in radiomics","volume":"13","author":"J Zhong","year":"2022","journal-title":"Insights Imaging"},{"issue":"2","key":"pone.0354896.ref016","doi-asserted-by":"crossref","DOI":"10.2307\/4132319","article-title":"Analyzing the past to prepare for the future: writing a literature review","volume":"26","author":"J Webster","year":"2002","journal-title":"MIS Q"},{"key":"pone.0354896.ref017","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.jclinepi.2021.02.003","article-title":"Updating guidance for reporting systematic reviews: development of the PRISMA 2020 statement","volume":"134","author":"MJ Page","year":"2021","journal-title":"J Clin Epidemiol"},{"issue":"5","key":"pone.0354896.ref018","doi-asserted-by":"crossref","first-page":"6031","DOI":"10.1007\/s40747-024-01479-z","article-title":"An intelligent MRI assisted diagnosis and treatment system for osteosarcoma based on super-resolution","volume":"10","author":"X Zhong","year":"2024","journal-title":"Complex Intell Syst"},{"key":"pone.0354896.ref019","doi-asserted-by":"crossref","first-page":"108308","DOI":"10.1016\/j.compbiomed.2024.108308","article-title":"DECIDE: a decoupled semantic and boundary learning network for precise osteosarcoma segmentation by integrating multi-modality MRI","volume":"174","author":"Y Wu","year":"2024","journal-title":"Comput Biol Med"},{"issue":"10","key":"pone.0354896.ref020","doi-asserted-by":"crossref","first-page":"3040","DOI":"10.1049\/ipr2.12854","article-title":"Image segmentation technology based on transformer in medical decision\u2010making system","volume":"17","author":"K He","year":"2023","journal-title":"IET Image Processing"},{"issue":"10","key":"pone.0354896.ref021","doi-asserted-by":"crossref","first-page":"1665","DOI":"10.3390\/math10101665","article-title":"An attention-preserving network-based method for assisted segmentation of osteosarcoma MRI images","volume":"10","author":"F Liu","year":"2022","journal-title":"Mathematics"},{"key":"pone.0354896.ref022","doi-asserted-by":"crossref","first-page":"107974","DOI":"10.1016\/j.cmpb.2023.107974","article-title":"Self-supervised tumor segmentation and prognosis prediction in osteosarcoma using multiparametric MRI and clinical characteristics","volume":"244","author":"Z Zhou","year":"2024","journal-title":"Comput Methods Programs Biomed"},{"issue":"2","key":"pone.0354896.ref023","doi-asserted-by":"crossref","first-page":"1","DOI":"10.37934\/araset.49.2.114","article-title":"MRI T1-weighted fat segmentation based on active contour for osteosarcoma patients","volume":"49","author":"MS Muhammad Shukor","year":"2024","journal-title":"J Adv Res Appl Sci Eng Tech"},{"key":"pone.0354896.ref024","doi-asserted-by":"crossref","first-page":"109359","DOI":"10.1016\/j.ejrad.2020.109359","article-title":"Automatic segmentation and RECIST score evaluation in osteosarcoma using diffusion MRI: a computer aided system process","volume":"133","author":"E Baidya Kayal","year":"2020","journal-title":"Eur J Radiol"},{"issue":"6","key":"pone.0354896.ref025","doi-asserted-by":"crossref","first-page":"1310","DOI":"10.1049\/ipr2.12106","article-title":"Segmentation of osteosarcoma in MRI images by K\u2010means clustering, Chan\u2010Vese segmentation, and iterative Gaussian filtering","volume":"15","author":"M Nasor","year":"2020","journal-title":"IET Image Processing"},{"key":"pone.0354896.ref026","doi-asserted-by":"crossref","unstructured":"Othman MH, Chiew Meng BC, Damanhuri NS, Aziz ME, Othman NA. MRI Thigh Sequences in Determining the Tumor Size Using Fuzzy C-Means for Patients with Osteosarcoma. In: 2022 IEEE 12th International Conference on Control System, Computing and Engineering (ICCSCE). 2022. pp. 125\u201330.","DOI":"10.1109\/ICCSCE54767.2022.9935630"},{"issue":"4","key":"pone.0354896.ref027","doi-asserted-by":"crossref","first-page":"727","DOI":"10.1007\/s11760-019-01599-x","article-title":"Segmentation of osteosarcoma tumor using diffusion weighted MRI: a comparative study using nine segmentation algorithms","volume":"14","author":"E Baidya Kayal","year":"2019","journal-title":"SIViP"},{"issue":"5","key":"pone.0354896.ref028","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.3390\/math11051187","article-title":"A tumor MRI image segmentation framework based on class-correlation pattern aggregation in medical decision-making system","volume":"11","author":"H Wei","year":"2023","journal-title":"Mathematics"},{"issue":"11","key":"pone.0354896.ref029","doi-asserted-by":"crossref","first-page":"8436","DOI":"10.1002\/int.22949","article-title":"A medical assistant segmentation method for MRI images of osteosarcoma based on DecoupleSegNet","volume":"37","author":"J Wu","year":"2022","journal-title":"Int J Intelligent Sys"},{"issue":"8","key":"pone.0354896.ref030","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.3390\/healthcare10081468","article-title":"Auxiliary segmentation method of osteosarcoma in MRI images based on denoising and local enhancement","volume":"10","author":"L Wang","year":"2022","journal-title":"Healthcare"},{"issue":"9","key":"pone.0354896.ref031","doi-asserted-by":"crossref","first-page":"4656","DOI":"10.1109\/JBHI.2022.3184930","article-title":"An Artificial Intelligence Multiprocessing Scheme for the Diagnosis of Osteosarcoma MRI Images","volume":"26","author":"J Wu","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0354896.ref032","first-page":"3881833","article-title":"BA-GCA Net: boundary-aware grid contextual attention net in osteosarcoma MRI image segmentation","volume":"2022","author":"J Wu","year":"2022","journal-title":"Comput Intell Neurosci"},{"issue":"1","key":"pone.0354896.ref033","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.imed.2021.04.001","article-title":"Artificial intelligence-based medical image segmentation for 3D printing and naked eye 3D visualization","volume":"2","author":"G Jia","year":"2022","journal-title":"Intell Med"},{"key":"pone.0354896.ref034","first-page":"7703583","article-title":"Intelligent segmentation medical assistance system for mri images of osteosarcoma in developing countries","volume":"2022","author":"J Wu","year":"2022","journal-title":"Comput Math Methods Med"},{"key":"pone.0354896.ref035","first-page":"7285600","article-title":"A residual fusion network for osteosarcoma MRI image segmentation in developing countries","volume":"2022","author":"J Wu","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"pone.0354896.ref036","doi-asserted-by":"crossref","unstructured":"Gou F, Wu J. An Attention-based AI-assisted Segmentation System for Osteosarcoma MRI Images. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2022. pp. 1539\u20131543.","DOI":"10.1109\/BIBM55620.2022.9995391"},{"issue":"11","key":"pone.0354896.ref037","doi-asserted-by":"crossref","first-page":"2313","DOI":"10.3390\/healthcare10112313","article-title":"AI-assisted diagnosis and decision-making method in developing countries for osteosarcoma","volume":"10","author":"H Tang","year":"2022","journal-title":"Healthcare"},{"issue":"7","key":"pone.0354896.ref038","doi-asserted-by":"crossref","first-page":"1090","DOI":"10.3390\/math10071090","article-title":"Osteosarcoma MRI image-assisted segmentation system base on guided aggregated bilateral network","volume":"10","author":"Y Shen","year":"2022","journal-title":"Mathematics"},{"issue":"12","key":"pone.0354896.ref039","doi-asserted-by":"crossref","first-page":"2099","DOI":"10.3390\/math10122099","article-title":"Multi-scale tumor localization based on priori guidance-based segmentation method for osteosarcoma MRI images","volume":"10","author":"B Lv","year":"2022","journal-title":"Mathematics"},{"issue":"6","key":"pone.0354896.ref040","doi-asserted-by":"crossref","first-page":"1063","DOI":"10.3390\/diagnostics13061063","article-title":"Artificial intelligence-aided diagnosis solution by enhancing the edge features of medical images","volume":"13","author":"B Lv","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"pone.0354896.ref041","doi-asserted-by":"crossref","first-page":"908873","DOI":"10.3389\/fonc.2022.908873","article-title":"Emerging applications of deep learning in bone tumors: current advances and challenges","volume":"12","author":"X Zhou","year":"2022","journal-title":"Front Oncol"},{"key":"pone.0354896.ref042","doi-asserted-by":"crossref","first-page":"802234","DOI":"10.3389\/fonc.2022.802234","article-title":"Radiomics analysis of multiparametric MRI for prediction of synchronous lung metastases in osteosarcoma","volume":"12","author":"Z Luo","year":"2022","journal-title":"Front Oncol"},{"issue":"1","key":"pone.0354896.ref043","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1186\/s12885-020-06825-1","article-title":"Feasibility of multi-parametric magnetic resonance imaging combined with machine learning in the assessment of necrosis of osteosarcoma after neoadjuvant chemotherapy: a preliminary study","volume":"20","author":"B Huang","year":"2020","journal-title":"BMC Cancer"},{"key":"pone.0354896.ref044","doi-asserted-by":"crossref","first-page":"758921","DOI":"10.3389\/fonc.2021.758921","article-title":"Machine learning-based radiomics nomogram with dynamic contrast-enhanced MRI of the osteosarcoma for evaluation of efficacy of neoadjuvant chemotherapy","volume":"11","author":"L Zhang","year":"2021","journal-title":"Front Oncol"},{"issue":"10","key":"pone.0354896.ref045","doi-asserted-by":"crossref","first-page":"7913","DOI":"10.1007\/s00330-021-07748-6","article-title":"MRI-based radiomics signature for pretreatment prediction of pathological response to neoadjuvant chemotherapy in osteosarcoma: a multicenter study","volume":"31","author":"H Chen","year":"2021","journal-title":"Eur Radiol"},{"issue":"3","key":"pone.0354896.ref046","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1016\/j.radi.2022.04.008","article-title":"MRI for evaluation of preoperative chemotherapy in osteosarcoma","volume":"28","author":"O Yildirim","year":"2022","journal-title":"Radiography (Lond)"},{"issue":"2","key":"pone.0354896.ref047","doi-asserted-by":"crossref","first-page":"163","DOI":"10.7150\/ijms.77906","article-title":"Characteristic of apparent diffusion coefficient and time intensity curve analysis of dynamic contrast enhanced MRI in osteosarcoma histopathologic subtypes","volume":"20","author":"R Setiawati","year":"2023","journal-title":"Int J Med Sci"},{"issue":"3","key":"pone.0354896.ref048","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1007\/s00256-022-04098-2","article-title":"T2-weighted MRI radiomics in high-grade intramedullary osteosarcoma: predictive accuracy in assessing histologic response to chemotherapy, overall survival, and disease-free survival","volume":"52","author":"LM White","year":"2023","journal-title":"Skeletal Radiol"},{"key":"pone.0354896.ref049","doi-asserted-by":"crossref","first-page":"1345576","DOI":"10.3389\/fonc.2024.1345576","article-title":"Evaluation of the neoadjuvant chemotherapy response in osteosarcoma using the MRI DWI-based machine learning radiomics nomogram","volume":"14","author":"L Zhang","year":"2024","journal-title":"Front Oncol"},{"issue":"2","key":"pone.0354896.ref050","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s00256-023-04402-8","article-title":"Evaluation of response to neoadjuvant chemotherapy in osteosarcoma using dynamic contrast-enhanced MRI: development and external validation of a model","volume":"53","author":"GM Kalisvaart","year":"2024","journal-title":"Skeletal Radiol"},{"key":"pone.0354896.ref051","first-page":"9990092","article-title":"Auxiliary segmentation method of osteosarcoma MRI image based on transformer and U-net","volume":"2022","author":"F Liu","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"pone.0354896.ref052","doi-asserted-by":"crossref","first-page":"7973404","DOI":"10.1155\/2022\/7973404","article-title":"Rethinking U-net from an attention perspective with transformers for osteosarcoma MRI image segmentation","volume":"2022","author":"T Ouyang","year":"2022","journal-title":"Comput Intell Neurosci"},{"issue":"11","key":"pone.0354896.ref053","doi-asserted-by":"crossref","first-page":"5563","DOI":"10.1109\/JBHI.2022.3196043","article-title":"Intelligent assistant diagnosis system of osteosarcoma MRI image based on transformer and convolution in developing countries","volume":"26","author":"Z Ling","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0354896.ref054","doi-asserted-by":"crossref","unstructured":"Zou B, Chen Y, Chen Z, Sun Y, Huang Y, Qin F, et al. RTUNet++: Assessment of Osteosarcoma MRI Image Segmentation leveraging Hybrid CNN-Transformer Approach with Dense Skip Connection. In: 2023 8th International Conference on Signal and Image Processing (ICSIP). 2023. pp. 217\u2013223.","DOI":"10.1109\/ICSIP57908.2023.10270849"},{"issue":"9","key":"pone.0354896.ref055","doi-asserted-by":"crossref","first-page":"2116","DOI":"10.3390\/math11092116","article-title":"A novel medical decision-making system based on multi-scale feature enhancement for small samples","volume":"11","author":"K He","year":"2023","journal-title":"Mathematics"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354896","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T17:33:45Z","timestamp":1787074425000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0354896"}},"subtitle":[],"editor":[{"given":"Mario","family":"Tortora","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":55,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0354896","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]}}}