{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T15:41:01Z","timestamp":1770824461499,"version":"3.50.1"},"reference-count":52,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T00:00:00Z","timestamp":1612310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ultragen","award":["Ultragen"],"award-info":[{"award-number":["Ultragen"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The quality of magnetic resonance images may influence the diagnosis and subsequent treatment. Therefore, in this paper, a novel no-reference (NR) magnetic resonance image quality assessment (MRIQA) method is proposed. In the approach, deep convolutional neural network architectures are fused and jointly trained to better capture the characteristics of MR images. Then, to improve the quality prediction performance, the support vector machine regression (SVR) technique is employed on the features generated by fused networks. In the paper, several promising network architectures are introduced, investigated, and experimentally compared with state-of-the-art NR-IQA methods on two representative MRIQA benchmark datasets. One of the datasets is introduced in this work. As the experimental validation reveals, the proposed fusion of networks outperforms related approaches in terms of correlation with subjective opinions of a large number of experienced radiologists.<\/jats:p>","DOI":"10.3390\/s21041043","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T20:31:51Z","timestamp":1612384311000},"page":"1043","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Fusion of Deep Convolutional Neural Networks for No-Reference Magnetic Resonance Image Quality Assessment"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6614-1218","authenticated-orcid":false,"given":"Igor","family":"St\u0119pie\u0144","sequence":"first","affiliation":[{"name":"Doctoral School of Engineering and Technical Sciences at the Rzeszow University of Technology, al. Powstancow Warszawy 12, 35-959 Rzeszow, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5883-5551","authenticated-orcid":false,"given":"Rafa\u0142","family":"Obuchowicz","sequence":"additional","affiliation":[{"name":"Department of Diagnostic Imaging, Jagiellonian University Medical College, 19 Kopernika Street, 31-501 Cracow, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4773-5322","authenticated-orcid":false,"given":"Adam","family":"Pi\u00f3rkowski","sequence":"additional","affiliation":[{"name":"Department of Biocybernetics and Biomedical Engineering, AGH University of Science and Technology, al. Mickiewicza 30, 30-059 Cracow, Poland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5482-6313","authenticated-orcid":false,"given":"Mariusz","family":"Oszust","sequence":"additional","affiliation":[{"name":"Department of Computer and Control Engineering, Rzeszow University of Technology, W. Pola 2, 35-959 Rzeszow, Poland"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Welvaert, M., and Rosseel, Y. (2013). On the Definition of Signal-To-Noise Ratio and Contrast-To-Noise Ratio for fMRI Data. PLoS ONE, 8.","DOI":"10.1371\/journal.pone.0077089"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Yu, S., Dai, G., Wang, Z., Li, L., Wei, X., and Xie, Y. (2018). A consistency evaluation of signal-to-noise ratio in the quality assessment of human brain magnetic resonance images. BMC Med. Imaging, 18.","DOI":"10.1186\/s12880-018-0256-6"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2182","DOI":"10.3390\/s140202182","article-title":"Optimal configuration for relaxation times estimation in complex spin echo imaging","volume":"14","author":"Baselice","year":"2014","journal-title":"Sensors"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.bspc.2016.02.006","article-title":"Review of medical image quality assessment","volume":"27","author":"Chow","year":"2016","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.mri.2017.07.016","article-title":"Modified-BRISQUE as no reference image quality assessment for structural MR images","volume":"43","author":"Chow","year":"2017","journal-title":"Magn. Reson. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1002\/mrm.27084","article-title":"Quality evaluation of no-reference MR images using multidirectional filters and image statistics","volume":"80","author":"Jang","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Obuchowicz, R., Oszust, M., Bielecka, M., Bielecki, A., and Pi\u00f3rkowski, A. (2020). Magnetic Resonance Image Quality Assessment by Using Non-Maximum Suppression and Entropy Analysis. Entropy, 22.","DOI":"10.3390\/e22020220"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1648","DOI":"10.1002\/mrm.28201","article-title":"No-reference image quality assessment of magnetic resonance images with high-boost filtering and local features","volume":"84","author":"Oszust","year":"2020","journal-title":"Magn. Reson. Med."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Esteban, O., Birman, D., Schaer, M., Koyejo, O.O., Poldrack, R.A., and Gorgolewski, K.J. (2017). MRIQC: Advancing the automatic prediction of image quality in MRI from unseen sites. PLoS ONE, 12.","DOI":"10.1101\/111294"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"52","DOI":"10.3389\/fninf.2016.00052","article-title":"Automated Quality Assessment of Structural Magnetic Resonance Brain Images Based on a Supervised Machine Learning Algorithm","volume":"10","author":"Pizarro","year":"2016","journal-title":"Front. Neuroinform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s10334-017-0650-z","article-title":"Automated reference-free detection of motion artifacts in magnetic resonance images","volume":"31","author":"Kustner","year":"2018","journal-title":"Magn. Reson. Mater. Phys. Biol. Med."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sujit, S.J., Gabr, R.E., Coronado, I., Robinson, M., Datta, S., and Narayana, P.A. (2018, January 20\u201322). Automated Image Quality Evaluation of Structural Brain Magnetic Resonance Images using Deep Convolutional Neural Networks. Proceedings of the 9th Cairo International Biomedical Engineering Conference (CIBEC), Cairo, Egypt.","DOI":"10.1109\/CIBEC.2018.8641830"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3350","DOI":"10.1109\/TIP.2011.2147325","article-title":"Blind Image Quality Assessment: From Natural Scene Statistics to Perceptual Quality","volume":"20","author":"Moorthy","year":"2011","journal-title":"IEEE Trans. Image Process."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1109\/TIP.2012.2191563","article-title":"Blind Image Quality Assessment: A Natural Scene Statistics Approach in the DCT Domain","volume":"21","author":"Saad","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"4695","DOI":"10.1109\/TIP.2012.2214050","article-title":"No-Reference Image Quality Assessment in the Spatial Domain","volume":"21","author":"Mittal","year":"2012","journal-title":"IEEE Trans. Image Process."},{"key":"ref_16","unstructured":"Ye, P., Kumar, J., Kang, L., and Doermann, D. (2012, January 16\u201321). Unsupervised feature learning framework for no-reference image quality assessment. Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"4444","DOI":"10.1109\/TIP.2016.2585880","article-title":"Blind Image Quality Assessment Based on High Order Statistics Aggregation","volume":"25","author":"Xu","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4850","DOI":"10.1109\/TIP.2014.2355716","article-title":"Blind Image Quality Assessment Using Joint Statistics of Gradient Magnitude and Laplacian Features","volume":"23","author":"Xue","year":"2014","journal-title":"IEEE Trans. Image Process."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.image.2015.10.005","article-title":"Blind image quality assessment by relative gradient statistics and adaboosting neural network","volume":"40","author":"Liu","year":"2016","journal-title":"Signal Process. Image"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Oszust, M. (2019). No-Reference Image Quality Assessment with Local Gradient Orientations. Symmetry, 11.","DOI":"10.3390\/sym11010095"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1109\/LSP.2016.2537321","article-title":"No-Reference Quality Assessment for Multiply-Distorted Images in Gradient Domain","volume":"23","author":"Li","year":"2016","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.1109\/LSP.2017.2754539","article-title":"No-Reference Image Quality Assessment Using Image Statistics and Robust Feature Descriptors","volume":"24","author":"Oszust","year":"2017","journal-title":"IEEE Signal Process. Lett."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2579","DOI":"10.1109\/TIP.2015.2426416","article-title":"A Feature-Enriched Completely Blind Image Quality Evaluator","volume":"24","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Image Process."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2049","DOI":"10.1109\/TMM.2017.2788206","article-title":"Blind Quality Assessment Based on Pseudo-Reference Image","volume":"20","author":"Min","year":"2018","journal-title":"IEEE Trans. Multimed."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Bosse, S., Maniry, D., Wiegand, T., and Samek, W. (2016, January 25\u201328). A deep neural network for image quality assessment. Proceedings of the IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA.","DOI":"10.1109\/ICIP.2016.7533065"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1109\/JSTSP.2016.2639328","article-title":"Fully Deep Blind Image Quality Predictor","volume":"11","author":"Kim","year":"2017","journal-title":"IEEE J. Sel. Top. Signal"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3951","DOI":"10.1109\/TIP.2017.2708503","article-title":"dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs","volume":"26","author":"Ma","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_28","unstructured":"Zeng, H., Zhang, L., and Bovik, A.C. (2017). A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction. arxiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A Comprehensive Survey on Transfer Learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_30","unstructured":"Simonyan, K., and Zisserman, A. (2015). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S.E., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7\u201312). Going Deeper with Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., and Wojna, Z. (July, January 26). Rethinking the Inception Architecture for Computer Vision. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.C. (2019). MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., van der Maaten, L., and Weinberger, K.Q. (2018). Densely Connected Convolutional Networks. arXiv.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"125324","DOI":"10.1063\/1.5010804","article-title":"Image quality assessment using deep convolutional networks","volume":"7","author":"Li","year":"2017","journal-title":"AIP Adv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"He, Q., Li, D., Jiang, T., and Jiang, M. (2018, January 23\u201327). Quality Assessment for Tone-Mapped HDR Images Using Multi-Scale and Multi-Layer Information. Proceedings of the 2018 IEEE International Conference on Multimedia Expo Workshops (ICMEW), San Diego, CA, USA.","DOI":"10.1109\/ICMEW.2018.8551502"},{"key":"ref_38","unstructured":"Lin, H., Hosu, V., and Saupe, D. (2020). DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning. arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Ieremeiev, O., Lukin, V., Okarma, K., and Egiazarian, K. (2020). Full-Reference Quality Metric Based on Neural Network to Assess the Visual Quality of Remote Sensing Images. Remote Sens., 12.","DOI":"10.3390\/rs12152349"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Maqsood, M., Nazir, F., Khan, U., Aadil, F., Jamal, H., Mehmood, I., and Song, O. (2019). Transfer Learning Assisted Classification and Detection of Alzheimer\u2019s Disease Stages Using 3D MRI Scans. Sensors, 19.","DOI":"10.3390\/s19112645"},{"key":"ref_41","unstructured":"Griswold, M., Heidemann, R., and Jakob, P. (2003, January 10\u201316). Direct parallel imaging reconstruction of radially sampled data using GRAPPA with relative shifts. Proceedings of the 11th Annual Meeting of the ISMRM, Toronto, ON, Canada."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1002\/mrm.20430","article-title":"Dynamic autocalibrated parallel imaging using temporal GRAPPA (TGRAPPA)","volume":"53","author":"Breuer","year":"2005","journal-title":"Off. J. Int. Soc. Magn. Reson. Med."},{"key":"ref_43","unstructured":"Reykowski, A., and Blasche, M. (2004, January 15\u201321). Mode Matrix\u2014A Generalized Signal Combiner For Parallel Imaging Arrays. Proceedings of the 12th Annual Meeting of the International Society for Magnetic Resonance in Medicine, Kyoto, Japan."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1002\/jmri.23639","article-title":"Parallel MR imaging","volume":"36","author":"Deshmane","year":"2012","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"3440","DOI":"10.1109\/TIP.2006.881959","article-title":"A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms","volume":"15","author":"Sheikh","year":"2006","journal-title":"IEEE Trans. Image Process."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1109\/TIP.2017.2774045","article-title":"End-to-End Blind Image Quality Assessment Using Deep Neural Networks","volume":"27","author":"Ma","year":"2018","journal-title":"IEEE Trans. Image Process."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/TMM.2014.2373812","article-title":"Using Free Energy Principle For Blind Image Quality Assessment","volume":"17","author":"Gu","year":"2015","journal-title":"IEEE Trans. Multimed."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"11534","DOI":"10.1109\/ACCESS.2018.2796632","article-title":"Can Signal-to-Noise Ratio Perform as a Baseline Indicator for Medical Image Quality Assessment","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"555","DOI":"10.1109\/TBC.2014.2344471","article-title":"Hybrid No-Reference Quality Metric for Singly and Multiply Distorted Images","volume":"60","author":"Gu","year":"2014","journal-title":"IEEE Trans. Broadcast."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"3116","DOI":"10.1109\/TIP.2010.2052820","article-title":"Automatic Parameter Selection for Denoising Algorithms Using a No-Reference Measure of Image Content","volume":"19","author":"Zhu","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1007\/s10851-015-0560-5","article-title":"No-Reference Image Quality Assessment and Blind Deblurring with Sharpness Metrics Exploiting Fourier Phase Information","volume":"52","year":"2015","journal-title":"J. Math. Imaging Vis."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A Library for Support Vector Machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/4\/1043\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:19:39Z","timestamp":1760159979000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/4\/1043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,3]]},"references-count":52,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["s21041043"],"URL":"https:\/\/doi.org\/10.3390\/s21041043","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,3]]}}}