{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T04:30:22Z","timestamp":1786336222342,"version":"build-2736575974"},"reference-count":53,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Terry Fox New Frontiers Program Project Grants"},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"crossref","award":["NSERC\u2212RGPIN:2019:06846"],"award-info":[{"award-number":["NSERC\u2212RGPIN:2019:06846"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]},{"award":["NSERC\u2212RGPIN:2019:06846"],"award-info":[{"award-number":["NSERC\u2212RGPIN:2019:06846"]}],"id":[{"id":"https:\/\/ror.org\/01h531d29","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: We aimed to evaluate the generalizability of QUS spectral parametric imaging radiomics for breast tumor characterization in a large cohort through methodological optimization and rigorous validation, including comprehensive feature extraction and evaluation of multiple classifiers, addressing limitations of previous studies potentially affected by data leakage. Methods: This study included 277 participants (185 malignant cases (median age, 51 years [IQR: 44\u201363 years]) and 92 benign cases (median age, 46 years [IQR: 38\u201351 years]) with breast masses, acquired between September 2014 and October 2021. QUS spectroscopic analysis resulted in five maps, from which first-order statistical, various textural, and morphological features were extracted from both the tumor core and a surrounding 5 mm margin. The ground truth label was determined from histopathological analysis. Predictive models were developed to distinguish malignant from benign lesions. Their generalization performance was assessed using hold-out validation. Beyond assessing models\u2019 performance, SHapley Additive exPlanations (SHAP) analysis identified the most influential features to the predictions. Results: 329 radiomics features demonstrated statistically significant differences (p-values &lt; 0.00005). Averaged across 50 partitions, SVM-Linear models produced test performance of 82 \u00b1 8% (CI: 59\u201397) recall, 79 \u00b1 9% (CI: 50\u2013100) specificity, and 0.87 \u00b1 0.05 (CI: 0.71\u20130.98) area under the receiver operating characteristic curve (AUROC). The best single partition performance with an SVM-Linear model was 92% recall, 89% specificity, and 0.97 AUROC. Conclusions: This work establishes a performance benchmark for handcrafted radiomic features derived from QUS spectral parametric images in breast lesion characterization, demonstrating its strong generalization and servicing as a reference for future model development.<\/jats:p>","DOI":"10.3390\/cancers18162548","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T01:20:03Z","timestamp":1786324803000},"page":"2548","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Comprehensive Radiomics Analysis to Enhance Breast Lesion Characterization Using QUS Spectral Parametric Imaging"],"prefix":"10.3390","volume":"18","author":[{"given":"Laurentius Oscar","family":"Osapoetra","sequence":"first","affiliation":[{"name":"Physical Sciences, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lakshmanan","family":"Sannachi","sequence":"additional","affiliation":[{"name":"Physical Sciences, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Schontal","family":"Halstead","sequence":"additional","affiliation":[{"name":"Physical Sciences, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9727-1227","authenticated-orcid":false,"given":"David","family":"Alberico","sequence":"additional","affiliation":[{"name":"Physical Sciences, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Moore-Palhares","sequence":"additional","affiliation":[{"name":"Physical Sciences, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"},{"name":"Department of Radiation Oncology, Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregory J.","family":"Czarnota","sequence":"additional","affiliation":[{"name":"Physical Sciences, Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"},{"name":"Department of Radiation Oncology, Odette Cancer Centre, Sunnybrook Health Sciences Centre, Toronto, ON M4N 3M5, Canada"},{"name":"Department of Radiation Oncology, University of Toronto, Toronto, ON M5T 1P5, Canada"},{"name":"Department of Medical Biophysics, University of Toronto, Toronto, ON M5G 1L7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"ref_1","first-page":"17","article-title":"Cancer Statistics, 2023","volume":"73","author":"Siegel","year":"2023","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","unstructured":"(2026, January 01). United States Cancer Cases and Death Statistics at a Glance, Available online: https:\/\/gis.cdc.gov\/cancer\/uscs\/dataviz.html."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.jacr.2009.09.022","article-title":"Breast Cancer Screening with Imaging: Recommendations from the Society of Breast Imaging and the ACR on the Use of Mammography, Breast MRI, Breast Ultrasound, and Other Technologies for the Detection of Clinically Occult Breast Cancer","volume":"7","author":"Lee","year":"2010","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_4","first-page":"199","article-title":"Advantages and Disadvantages of Mammography Screening","volume":"6","author":"Hacker","year":"2011","journal-title":"Breast Care"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1148\/radiol.2016161174","article-title":"National Performance Benchmarks for Modern Screening Digital Mammography: Update from the Breast Cancer Surveillance Consortium","volume":"283","author":"Lehman","year":"2017","journal-title":"Radiology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1148\/radiol.09090838","article-title":"Cancerous Breast Lesions on Dynamic Contrast-Enhanced MR Images: Computerized Characterization for Image-Based Prognostic Markers","volume":"254","author":"Bhooshan","year":"2010","journal-title":"Radiology"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1148\/radiology.196.1.7784555","article-title":"Solid Breast Nodules: Use of Sonography to Distinguish between Benign and Malignant Lesions","volume":"196","author":"Stavros","year":"1995","journal-title":"Radiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1292","DOI":"10.1109\/TMI.2004.834617","article-title":"Computer-Aided Diagnosis of Solid Breast Nodules: Use of an Artificial Neural Network Based on Multiple Sonographic Features","volume":"23","author":"Joo","year":"2004","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1148\/radiol.2262011843","article-title":"Breast Lesions on Sonograms: Computer-Aided Diagnosis with Nearly Setting-Independent Features and Artificial Neural Networks","volume":"226","author":"Chen","year":"2003","journal-title":"Radiology"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"13638","DOI":"10.1038\/s41598-017-13977-x","article-title":"Breast-Lesion Characterization Using Textural Features of Quantitative Ultrasound Parametric Maps","volume":"7","author":"Suraweera","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100827","DOI":"10.1016\/j.tranon.2020.100827","article-title":"Breast Lesion Characterization Using Quantitative Ultrasound (QUS) and Derivative Texture Methods","volume":"13","author":"Osapoetra","year":"2020","journal-title":"Transl. Oncol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Osapoetra, L.O., Chan, W., Tran, W., Kolios, M.C., and Czarnota, G.J. (2020). Comparison of Methods for Texture Analysis of QUS Parametric Images in the Characterization of Breast Lesions. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0244965"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.ultrasmedbio.2019.10.024","article-title":"Added Value of Quantitative Ultrasound and Machine Learning in BI-RADS 4\u20135 Assessment of Solid Breast Lesions","volume":"46","author":"Destrempes","year":"2020","journal-title":"Ultrasound Med. Biol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1341","DOI":"10.1016\/j.ultrasmedbio.2018.02.014","article-title":"High-Frequency Quantitative Ultrasound for Imaging Prostate Cancer Using a Novel Micro-Ultrasound Scanner","volume":"44","author":"Rohrbach","year":"2018","journal-title":"Ultrasound Med. Biol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1142","DOI":"10.1016\/j.ultrasmedbio.2020.01.022","article-title":"Quantitative Ultrasound Monitoring of Breast Tumour Response to Neoadjuvant Chemotherapy: Comparison of Results among Clinical Scanners","volume":"46","author":"Sannachi","year":"2020","journal-title":"Ultrasound Med. Biol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Safakish, A., Sannachi, L., DiCenzo, D., Kolios, C., Pejovi\u0107-Mili\u0107, A., and Czarnota, G.J. (2023). Predicting Head and Neck Cancer Treatment Outcomes with Pre-Treatment Quantitative Ultrasound Texture Features and Optimising Machine Learning Classifiers with Texture-of-Texture Features. Front. Oncol., 13.","DOI":"10.3389\/fonc.2023.1258970"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"22687","DOI":"10.1038\/s41598-023-49478-3","article-title":"A Priori Prediction of Breast Cancer Response to Neoadjuvant Chemotherapy Using Quantitative Ultrasound, Texture Derivative and Molecular Subtype","volume":"13","author":"Sannachi","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e230029","DOI":"10.1148\/rycan.230029","article-title":"Quantitative US Delta Radiomics to Predict Radiation Response in Individuals with Head and Neck Squamous Cell Carcinoma","volume":"6","author":"Osapoetra","year":"2024","journal-title":"Radiol. Imaging Cancer"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1016\/j.ultrasmedbio.2009.10.007","article-title":"Three-Dimensional High-Frequency Characterization of Cancerous Lymph Nodes","volume":"36","author":"Mamou","year":"2010","journal-title":"Ultrasound Med. Biol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2198","DOI":"10.1118\/1.3566064","article-title":"Classification of Scattering Media within Benign and Malignant Breast Tumours Based on Ultrasound Texture-Feature-Based and Nakagami-Parameter Images","volume":"38","author":"Liao","year":"2011","journal-title":"Med. Phys."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"106744","DOI":"10.1016\/j.ultras.2022.106744","article-title":"Ultrasound Classification of Breast Masses Using a Comprehensive Nakagami Imaging and Machine Learning Framework","volume":"124","author":"Chowdhury","year":"2022","journal-title":"Ultrasonics"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3786","DOI":"10.1172\/JCI60534","article-title":"Heterogeneity in Breast Cancer","volume":"121","author":"Polyak","year":"2011","journal-title":"J. Clin. Investig."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1007\/s13244-012-0196-6","article-title":"Assessment of Tumour Heterogeneity: An Emerging Imaging Tool for Clinical Practice?","volume":"3","author":"Davnall","year":"2012","journal-title":"Insights Imaging"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1038\/labinvest.2014.155","article-title":"Mapping Spatial Heterogeneity in the Tumour Microenvironment: A New Era for Digital Pathology","volume":"95","author":"Heindl","year":"2015","journal-title":"Lab. Investig."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1158\/1078-0432.CCR-14-0990","article-title":"Imaging Intratumour Heterogeneity: Role in Therapy Response, Resistance, and Clinical Outcome","volume":"21","author":"Rose","year":"2015","journal-title":"Clin. Cancer Res."},{"key":"ref_26","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_27","first-page":"1","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"D\u2019Orsi, C., Bassett, L., and Feig, S. (2018). Breast Imaging Reporting and Data System (BI-RADS). Breast Imaging Atlas, American College of Radiology. [4th ed.].","DOI":"10.1093\/med\/9780190270261.003.0005"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Mamou, J., and Oelze, M. (2023). Quantitative Ultrasound in Soft Tissues, Springer Nature.","DOI":"10.1007\/978-3-031-21987-0"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.ultras.2010.05.005","article-title":"Estimate of the Attenuation Coefficient Using a Clinical Array Transducer for the Detection of Cervical Ripening in Human Pregnancy","volume":"51","author":"Labyed","year":"2011","journal-title":"Ultrasonics"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"610","DOI":"10.1109\/TSMC.1973.4309314","article-title":"Textural Features for Image Classification","volume":"6","author":"Haralick","year":"1973","journal-title":"IEEE Trans. Syst. Man. Cybern."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/S0146-664X(75)80008-6","article-title":"Texture Analysis Using Gray Level Run Lengths","volume":"4","author":"Galloway","year":"1975","journal-title":"Comput. Graph. Image Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/0167-8655(91)80014-2","article-title":"Image Characterizations Based on Joint Gray Level Run-Length Distributions","volume":"12","author":"Dasarathy","year":"1991","journal-title":"Pattern Recognit. Lett."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1016\/0167-8655(90)90112-F","article-title":"Use of Gray Value Distribution of Run Lengths for Texture Analysis","volume":"11","author":"Chu","year":"1990","journal-title":"Pattern Recognit. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1602","DOI":"10.1109\/83.725367","article-title":"Texture Information in Run-Length Matrices","volume":"7","author":"Tang","year":"1998","journal-title":"IEEE Trans. Image Process."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/TBME.2013.2284600","article-title":"Advanced Statistical Matrices for Texture Characterization: Application to Cell Classification","volume":"61","author":"Thibault","year":"2014","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1109\/21.44046","article-title":"Textural Features Corresponding to Textural Properties","volume":"19","author":"Amadasun","year":"1989","journal-title":"IEEE Trans. Syst. Man. Cybern."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1016\/0734-189X(83)90032-4","article-title":"Neighboring Gray Level Dependence Matrix for Texture Classification","volume":"23","author":"Sun","year":"1983","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Liu, F.T., Ting, K.M., and Zhou, Z.H. (2008). Isolation Forest. Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, Pisa, Italy, 15\u201319 December 2008, IEEE.","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1226","DOI":"10.1109\/TPAMI.2005.159","article-title":"Feature Selection Based on Mutual Information Criteria of Max-Dependency, Max-Relevance, and Min-Redundancy","volume":"27","author":"Peng","year":"2005","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority over-Sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-Vector Networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A Decision-Theoretic Generalization of on-Line Learning and an Application to Boosting","volume":"55","author":"Freund","year":"1997","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy Function Approximation: A Gradient Boosting Machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_45","unstructured":"Bishop, C.M., and Nasrabadi, N.M. (2006). Pattern Recognition and Machine Learning, Springer."},{"key":"ref_46","unstructured":"Glantz, S.A. (2012). Primer of Biostatistics, The McGraw-Hill Companies. [7th ed.]."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Skiena, S.S. (2017). The Data Science Design Manual, Springer.","DOI":"10.1007\/978-3-319-55444-0"},{"key":"ref_48","unstructured":"Alpaydin, E. (2014). Introduction to Machine Learning, MIT Press."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27\u201330 June 2016, IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_50","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2020). An Image Is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"32805","DOI":"10.1038\/s41598-025-15772-5","article-title":"End-to-End CNN-Based Deep Learning Enhances Breast Lesion Characterization Using Quantitative Ultrasound (QUS) Spectral Parametric Images","volume":"15","author":"Osapoetra","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"104966","DOI":"10.1016\/j.compbiomed.2021.104966","article-title":"Comparing Deep Learning-Based Automatic Segmentation of Breast Masses to Expert Interobserver Variability in Ultrasound Imaging","volume":"139","author":"Webb","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"14163","DOI":"10.1038\/s41598-020-70940-z","article-title":"MRI-Based Radiomics in Breast Cancer: Feature Robustness with Respect to Inter-Observer Segmentation Variability","volume":"10","author":"Granzier","year":"2020","journal-title":"Sci. Rep."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/16\/2548\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T04:14:05Z","timestamp":1786335245000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/18\/16\/2548"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":53,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["cancers18162548"],"URL":"https:\/\/doi.org\/10.3390\/cancers18162548","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,8]]}}}