{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:26:58Z","timestamp":1775064418700,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T00:00:00Z","timestamp":1622764800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Early detection of thyroid nodules can greatly contribute to the prediction of cancer burdening and the steering of personalized management. We propose a novel multimodal MRI-based computer-aided diagnosis (CAD) system that differentiates malignant from benign thyroid nodules. The proposed CAD is based on a novel convolutional neural network (CNN)-based texture learning architecture. The main contribution of our system is three-fold. Firstly, our system is the first of its kind to combine T2-weighted MRI and apparent diffusion coefficient (ADC) maps using a CNN to model thyroid cancer. Secondly, it learns independent texture features for each input, giving it more advanced capabilities to simultaneously extract complex texture patterns from both modalities. Finally, the proposed system uses multiple channels for each input to combine multiple scans collected into the deep learning process using different values of the configurable diffusion gradient coefficient. Accordingly, the proposed system would enable the learning of more advanced radiomics with an additional advantage of visualizing the texture patterns after learning. We evaluated the proposed system using data collected from a cohort of 49 patients with pathologically proven thyroid nodules. The accuracy of the proposed system has also been compared against recent CNN models as well as multiple machine learning (ML) frameworks that use hand-crafted features. Our system achieved the highest performance among all compared methods with a diagnostic accuracy of 0.87, specificity of 0.97, and sensitivity of 0.69. The results suggest that texture features extracted using deep learning can contribute to the protocols of cancer diagnosis and treatment and can lead to the advancement of precision medicine.<\/jats:p>","DOI":"10.3390\/s21113878","type":"journal-article","created":{"date-parts":[[2021,6,7]],"date-time":"2021-06-07T01:56:40Z","timestamp":1623031000000},"page":"3878","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":39,"title":["Novel MRI-Based CAD System for Early Detection of Thyroid Cancer Using Multi-Input CNN"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1590-2766","authenticated-orcid":false,"given":"Ahmed","family":"Naglah","sequence":"first","affiliation":[{"name":"Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3318-2851","authenticated-orcid":false,"given":"Fahmi","family":"Khalifa","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reem","family":"Khaled","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Mansoura University, Mansoura 35516, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9613-5932","authenticated-orcid":false,"given":"Ahmed Abdel Khalek","family":"Abdel Razek","sequence":"additional","affiliation":[{"name":"Faculty of Medicine, Mansoura University, Mansoura 35516, Egypt"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9045-6698","authenticated-orcid":false,"given":"Mohammad","family":"Ghazal","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering Department, Abu Dhabi University, Abu Dhabi 59911, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guruprasad","family":"Giridharan","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7264-1323","authenticated-orcid":false,"given":"Ayman","family":"El-Baz","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Louisville, Louisville, KY 40292, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,4]]},"reference":[{"key":"ref_1","unstructured":"Society, A.C. (2020). Cancer Facts and Figures 2020, American Cancer Society."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1089\/thy.2015.0020","article-title":"2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer: The American Thyroid Association guidelines task force on thyroid nodules and differentiated thyroid cancer","volume":"26","author":"Haugen","year":"2016","journal-title":"Thyroid"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.cireng.2018.07.013","article-title":"Current Use of Molecular Profiling for Indeterminate Thyroid Nodules","volume":"96","author":"Rojo","year":"2018","journal-title":"Cirug\u00eda Espa\u00f1ola (Engl. Ed.)"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"111","DOI":"10.21037\/gs.2018.01.03","article-title":"Which needle in the treatment of thyroid nodules?","volume":"7","author":"Pescatori","year":"2018","journal-title":"Gland. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1016\/j.rcl.2020.07.003","article-title":"Thyroid Ultrasound: Diffuse and Nodular Disease","volume":"58","author":"Alexander","year":"2020","journal-title":"Radiol. Clin."},{"key":"ref_6","first-page":"e7239","article-title":"Ultrasound Classification of Thyroid Nodules: A Systematic Review","volume":"12","author":"Mistry","year":"2020","journal-title":"Cureus"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1983","DOI":"10.7863\/ultra.14.09057","article-title":"Classification of benign and malignant thyroid nodules using wavelet texture analysis of sonograms","volume":"34","author":"Ardakani","year":"2015","journal-title":"J. Ultrasound Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1038\/s41574-019-0204-8","article-title":"Sonographic diagnosis of thyroid cancer with support of AI","volume":"15","author":"Verburg","year":"2019","journal-title":"Nat. Rev. Endocrinol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.ejrad.2019.02.029","article-title":"Comparison between linear and nonlinear machine-learning algorithms for the classification of thyroid nodules","volume":"113","author":"Ouyang","year":"2019","journal-title":"Eur. J. Radiol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Zhang, R., Liu, Q., Cui, H., Wang, X., Song, S., Huang, G., and Feng, D. (2018, January 4\u20137). Thyroid classification via new multi-channel feature association and learning from multi-modality MRI images. Proceedings of the 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018), Washington, DC, USA.","DOI":"10.1109\/ISBI.2018.8363573"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1002\/jmri.23998","article-title":"Comparison of dixon and T1-weighted MR methods to assess the degree of fat infiltration in duchenne muscular dystrophy patients","volume":"38","author":"Wokke","year":"2013","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"021010","DOI":"10.1115\/1.3005171","article-title":"Three-dimensional computational modeling of subject-specific cerebrospinal fluid flow in the subarachnoid space","volume":"131","author":"Gupta","year":"2009","journal-title":"J. Biomech. Eng."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"6289","DOI":"10.1088\/0031-9155\/59\/20\/6289","article-title":"Isotropic diffusion weighting for measurement of a high-resolution apparent diffusion coefficient map using a single radial scan in MRI","volume":"59","author":"Seo","year":"2014","journal-title":"Phys. Med. Biol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1622","DOI":"10.2214\/AJR.06.1403","article-title":"Diffusion-weighted MRI in the body: Applications and challenges in oncology","volume":"188","author":"Koh","year":"2007","journal-title":"Am. J. Roentgenol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1002\/jmri.25290","article-title":"Differentiation between malignant and benign thyroid nodules and stratification of papillary thyroid cancer with aggressive histological features: Whole-lesion diffusion-weighted imaging histogram analysis","volume":"44","author":"Hao","year":"2016","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1708","DOI":"10.1002\/mrm.25743","article-title":"Multi-institutional validation of a novel textural analysis tool for preoperative stratification of suspected thyroid tumors on diffusion-weighted MRI","volume":"75","author":"Brown","year":"2016","journal-title":"Magn. Reson. Med."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Schob, S., Meyer, H.J., Dieckow, J., Pervinder, B., Pazaitis, N., H\u00f6hn, A.K., Garnov, N., Horvath-Rizea, D., Hoffmann, K.T., and Surov, A. (2017). Histogram analysis of diffusion weighted imaging at 3T is useful for prediction of lymphatic metastatic spread, proliferative activity, and cellularity in thyroid cancer. Int. J. Mol. Sci., 18.","DOI":"10.3390\/ijms18040821"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Naglah, A., Khalifa, F., Khaled, R., El-Baz, A., and Abdel Khalek Abdel Razek, A. (2021, January 13\u201316). Thyroid cancer computer-aided diagnosis system using MRI-based multi-input CNN model. Proceedings of the 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI 2021), Nice, France.","DOI":"10.1109\/ISBI48211.2021.9433841"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"828","DOI":"10.1016\/j.tranon.2017.08.001","article-title":"Proving of a mathematical model of cell calculation based on apparent diffusion coefficient","volume":"10","author":"Surov","year":"2017","journal-title":"Transl. Oncol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108755","DOI":"10.1016\/j.ejrad.2019.108755","article-title":"Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma","volume":"122","author":"Wang","year":"2020","journal-title":"Eur. J. Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"288","DOI":"10.1063\/1.1695690","article-title":"Spin diffusion measurements: Spin echoes in the presence of a time-dependent field gradient","volume":"42","author":"Stejskal","year":"1965","journal-title":"J. Chem. Phys."},{"key":"ref_22","unstructured":"Agarap, A.F. (2018). Deep learning using rectified linear units (relu). arXiv."},{"key":"ref_23","unstructured":"Finney, D.J. (1952). Probit Analysis: A Statistical Treatment of the Sigmoid Response Curve, Cambridge University Press."},{"key":"ref_24","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_25","unstructured":"M\u00fcller, C. (2006). Spherical Harmonics, Springer."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1016\/S0034-4257(97)00049-7","article-title":"Decision tree classification of land cover from remotely sensed data","volume":"61","author":"Friedl","year":"1997","journal-title":"Remote Sens. Environ."},{"key":"ref_27","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"ref_28","first-page":"41","article-title":"A comparison of event models for naive bayes text classification","volume":"Volume 752","author":"McCallum","year":"1998","journal-title":"AAAI-98 Workshop on Learning for Text Categorization"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1023\/A:1018628609742","article-title":"Least squares support vector machine classifiers","volume":"9","author":"Suykens","year":"1999","journal-title":"Neural Process. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Dodge, S., and Karam, L. (August, January 31). A study and comparison of human and deep learning recognition performance under visual distortions. Proceedings of the 2017 26th International Conference on Computer Communication and Networks (ICCCN), Vancouver, BC, Canada.","DOI":"10.1109\/ICCCN.2017.8038465"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Negi, S.S., and Bhandari, Y.S. (2014, January 9\u201311). A hybrid approach to image enhancement using contrast stretching on image sharpening and the analysis of various cases arising using histogram. Proceedings of the International Conference on Recent Advances and Innovations in Engineering (ICRAIE-2014), Jaipur, India.","DOI":"10.1109\/ICRAIE.2014.6909232"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1007\/s00357-014-9161-z","article-title":"Ward\u2019s hierarchical agglomerative clustering method: Which algorithms implement Ward\u2019s criterion?","volume":"31","author":"Murtagh","year":"2014","journal-title":"J. Classif."},{"key":"ref_36","first-page":"274","article-title":"The clustering validity with silhouette and sum of squared errors?","volume":"3","author":"Murtagh","year":"2015","journal-title":"Learning"},{"key":"ref_37","unstructured":"Thinsungnoena, T., Kaoungkub, N., Durongdumronchaib, P., Kerdprasopb, K., and Kerdprasopb, N. (2015, January 28\u201331). The clustering validity with silhouette and sum of squared errors. Proceedings of the 3rd International Conference on Industrial Application Engineering 2015, Kitakyushu, Japan. Available online: https:\/\/pdfs.semanticscholar.org\/8785\/b45c92622ebbbffee055aec198190c621b00.pdf."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/11\/3878\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:10:49Z","timestamp":1760163049000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/11\/3878"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,4]]},"references-count":37,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21113878"],"URL":"https:\/\/doi.org\/10.3390\/s21113878","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,4]]}}}