{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T05:47:46Z","timestamp":1761198466334,"version":"build-2065373602"},"reference-count":26,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T00:00:00Z","timestamp":1747785600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Wright foundation","award":["R25CA225513"],"award-info":[{"award-number":["R25CA225513"]}]},{"name":"National Cancer Institute","award":["R25CA225513"],"award-info":[{"award-number":["R25CA225513"]}]},{"name":"Norris Comprehensive Cancer Center in Los Angeles","award":["R25CA225513"],"award-info":[{"award-number":["R25CA225513"]}]},{"name":"Department of Pediatrics at Children\u2019s Hospital Los Angeles, Concern Foundation for Cancer Research","award":["R25CA225513"],"award-info":[{"award-number":["R25CA225513"]}]},{"name":"Curing Kids Cancer","award":["R25CA225513"],"award-info":[{"award-number":["R25CA225513"]}]},{"name":"Tri Delta","award":["R25CA225513"],"award-info":[{"award-number":["R25CA225513"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MTI"],"abstract":"<jats:p>Radiomics involves extracting quantitative features from medical images, resulting in high-dimensional data. Unsupervised clustering has been used to discover patterns in radiomic features, potentially yielding hidden biological insights. However, its effectiveness depends on the selection of dimensionality reduction techniques, clustering methods, and hyperparameter optimization, an area with limited exploration in the literature. We present a novel bootstrapping-based hyperparameter search approach to optimize clustering efficacy, treating dimensionality reduction and clustering as a connected process chain. The hyperparameter search was guided by the Adjusted Rand Index (ARI) and Davies\u2013Bouldin Index (DBI) within a bootstrapping framework of 100 iterations. The cluster assignments were generated through 10-fold cross-validation, and a grid search strategy was used to explore hyperparameter combinations. We evaluated ten unsupervised learning pipelines using both simulation studies and real-world radiomics data derived from multiphase CT images of renal cell carcinoma. In simulations, we found that Non-negative Matrix Factorization (NMF) and Spectral Clustering outperformed the traditional Principal Component Analysis (PCA)-based approach. The best-performing pipeline (NMF followed by K-means clustering) successfully identified all three simulated clusters, achieving a Cram\u00e9r\u2019s V of 0.9. The simulation also established a reference framework for understanding the concordance patterns among different pipelines under varying strengths of clustering effects. High concordance reflects strong clustering. In the real-world data application, we observed a moderate clustering effect, which aligned with the weak associations to clinical outcomes, as indicated by the highest AUROC of 0.63.<\/jats:p>","DOI":"10.3390\/mti9050049","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T06:31:27Z","timestamp":1747809087000},"page":"49","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Integrated Hyperparameter Optimization with Dimensionality Reduction and Clustering for Radiomics: A Bootstrapped Approach"],"prefix":"10.3390","volume":"9","author":[{"given":"S. J.","family":"Pawan","sequence":"first","affiliation":[{"name":"Radiomics Lab, University of Southern California, Los Angeles, CA 90033, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4281-813X","authenticated-orcid":false,"given":"Matthew","family":"Muellner","sequence":"additional","affiliation":[{"name":"Radiomics Lab, University of Southern California, Los Angeles, CA 90033, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8899-5177","authenticated-orcid":false,"given":"Xiaomeng","family":"Lei","sequence":"additional","affiliation":[{"name":"Radiomics Lab, University of Southern California, Los Angeles, CA 90033, USA"},{"name":"Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA 90033, USA"}]},{"given":"Mihir","family":"Desai","sequence":"additional","affiliation":[{"name":"Institute of Urology, University of Southern California, Los Angeles, CA 90033, USA"}]},{"given":"Bino","family":"Varghese","sequence":"additional","affiliation":[{"name":"Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA 90033, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4808-5715","authenticated-orcid":false,"given":"Vinay","family":"Duddalwar","sequence":"additional","affiliation":[{"name":"Radiomics Lab, University of Southern California, Los Angeles, CA 90033, USA"},{"name":"Institute of Urology, University of Southern California, Los Angeles, CA 90033, USA"},{"name":"Department of Radiology, Los Angeles General Medical Center, Los Angeles, CA 90033, USA"},{"name":"Alfred E Mann Department of Biomedical Engineering, USC Viterbi School of Engineering, Los Angeles, CA 90089, USA"}]},{"given":"Steven Y.","family":"Cen","sequence":"additional","affiliation":[{"name":"Radiomics Lab, University of Southern California, Los Angeles, CA 90033, USA"},{"name":"Department of Radiology, Keck School of Medicine, University of Southern California, Los Angeles, CA 90033, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,5,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images Are More than Pictures, They Are Data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1717","DOI":"10.1148\/rg.2021210037","article-title":"Radiomics in Oncology: A Practical Guide","volume":"41","author":"Shur","year":"2021","journal-title":"Radiographics"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"520","DOI":"10.2214\/AJR.18.20624","article-title":"Texture analysis of imaging: What radiologists need to know","volume":"212","author":"Varghese","year":"2019","journal-title":"Am. J. Roentgenol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1186\/s13244-021-01107-1","article-title":"Machine learning-based CT radiomics approach for predicting WHO\/ISUP nuclear grade of clear cell renal cell carcinoma: An exploratory and comparative study","volume":"12","author":"Xv","year":"2021","journal-title":"Insights Into Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: The process and the challenges","volume":"30","author":"Kumar","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.7150\/thno.30309","article-title":"The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges","volume":"9","author":"Liu","year":"2019","journal-title":"Theranostics"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"100869","DOI":"10.1016\/j.neo.2022.100869","article-title":"Unsupervised machine learning using K-means identifies radiomic subgroups of pediatric low-grade gliomas that correlate with key molecular markers","volume":"36","author":"Haldar","year":"2023","journal-title":"Neoplasia"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s41747-018-0068-z","article-title":"Radiomics: The facts and the challenges of image analysis","volume":"2","author":"Rizzo","year":"2018","journal-title":"Eur. Radiol. Exp."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Bhattacharjee, S., Hwang, Y.-B., Sumon, R.I., Rahman, H., Hyeon, D.-W., Moon, D., Carole, K.S., Kim, H.-C., and Choi, H.-K. (2022, January 5\u20137). Cluster Analysis: Unsupervised Classification for Identifying Benign and Malignant Tumors on Whole Slide Image of Prostate Cancer. Proceedings of the 2022 IEEE 5th International Conference on Image Processing Applications and Systems (IPAS), Genova, Italy.","DOI":"10.1109\/IPAS55744.2022.10052952"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"031904","DOI":"10.1117\/1.JMI.8.3.031904","article-title":"Reproducibility of radiomic features using network analysis and its application in Wasserstein k-means clustering","volume":"8","author":"Oh","year":"2021","journal-title":"J. Med. Imaging"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"e1444","DOI":"10.1002\/widm.1444","article-title":"Validation of cluster analysis results on validation data: A systematic framework","volume":"12","author":"Ullmann","year":"2022","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Lee, C., Abdool, A., and Huang, C.-H. (2009). PCA-based population structure inference with generic clustering algorithms. BMC Bioinform., 10.","DOI":"10.1186\/1471-2105-10-S1-S73"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"17009","DOI":"10.1038\/nrdp.2017.9","article-title":"Renal cell carcinoma","volume":"3","author":"Hsieh","year":"2017","journal-title":"Nat. Rev. Dis. Primers"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1038\/s41585-022-00651-9","article-title":"The shifting treatment paradigm of metastatic renal cell carcinoma","volume":"19","author":"Ged","year":"2022","journal-title":"Nat. Rev. Urol."},{"key":"ref_15","unstructured":"American Cancer Society (2024, March 01). Key Statistics About Kidney Cancer-2024. Available online: https:\/\/www.cancer.org\/cancer\/types\/kidney-cancer\/about\/key-statistics.html."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s43588-022-00380-4","article-title":"Dynamic visualization of high-dimensional data","volume":"3","author":"Sun","year":"2023","journal-title":"Nat. Comput. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"2552","DOI":"10.1007\/s00330-021-08344-4","article-title":"CT-based radiomics stratification of tumor grade and TNM stage of clear cell renal cell carcinoma","volume":"32","author":"Demirjian","year":"2022","journal-title":"Eur. Radiol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Friston, K.J. (2003). Statistical parametric mapping. Neuroscience Databases: A Practical Guide, Springer.","DOI":"10.1007\/978-1-4615-1079-6_16"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Fedorov","year":"2017","journal-title":"Cancer Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"104877","DOI":"10.1016\/j.oraloncology.2020.104877","article-title":"Radiomic analysis identifies tumor subtypes associated with distinct molecular and microenvironmental factors in head and neck squamous cell carcinoma","volume":"110","author":"Katsoulakis","year":"2020","journal-title":"Oral Oncol."},{"key":"ref_21","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e31816","DOI":"10.1016\/j.heliyon.2024.e31816","article-title":"Identification of clear cell renal cell carcinoma subtypes by integrating radiomics and transcriptomics","volume":"10","author":"Gao","year":"2024","journal-title":"Heliyon"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1016\/j.radonc.2019.08.008","article-title":"Sensitivity of radiomic features to inter-observer variability and image pre-processing in Apparent Diffusion Coefficient (ADC) maps of cervix cancer patients","volume":"143","author":"Traverso","year":"2020","journal-title":"Radiother. Oncol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"12822","DOI":"10.1038\/s41598-022-16520-9","article-title":"The impact of inter-observer variation in delineation on robustness of radiomics features in non-small cell lung cancer","volume":"12","author":"Kothari","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hershman, M., Yousefi, B., Serletti, L., Galperin-Aizenberg, M., Roshkovan, L., Luna, J.M., Thompson, J.C., Aggarwal, C., Carpenter, E.L., and Kontos, D. (2021). Impact of Interobserver Variability in Manual Segmentation of Non-Small Cell Lung Cancer (NSCLC) Applying Low-Rank Radiomic Representation on Computed Tomography. Cancers, 13, (In English).","DOI":"10.3390\/cancers13235985"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Cross, J.L., Choma, M.A., and Onofrey, J.A. (2024). Bias in medical AI: Implications for clinical decision-making. PLOS Digit. Health, 3.","DOI":"10.1371\/journal.pdig.0000651"}],"container-title":["Multimodal Technologies and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2414-4088\/9\/5\/49\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:36:25Z","timestamp":1760031385000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2414-4088\/9\/5\/49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,21]]},"references-count":26,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["mti9050049"],"URL":"https:\/\/doi.org\/10.3390\/mti9050049","relation":{},"ISSN":["2414-4088"],"issn-type":[{"type":"electronic","value":"2414-4088"}],"subject":[],"published":{"date-parts":[[2025,5,21]]}}}