{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T01:08:30Z","timestamp":1769044110805,"version":"3.49.0"},"reference-count":40,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2017,12,14]],"date-time":"2017-12-14T00:00:00Z","timestamp":1513209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Indonesia Endowment Fund for Education (LPDP)"},{"name":"Row Fogo Charitable Trust (MCVH)"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>In the wake of the use of deep learning algorithms in medical image analysis, we compared performance of deep learning algorithms, namely the deep Boltzmann machine (DBM), convolutional encoder network (CEN) and patch-wise convolutional neural network (patch-CNN), with two conventional machine learning schemes: Support vector machine (SVM) and random forest (RF), for white matter hyperintensities (WMH) segmentation on brain MRI with mild or no vascular pathology. We also compared all these approaches with a method in the Lesion Segmentation Tool public toolbox named lesion growth algorithm (LGA). We used a dataset comprised of 60 MRI data from 20 subjects in the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) database, each scanned once every year during three consecutive years. Spatial agreement score, receiver operating characteristic and precision-recall performance curves, volume disagreement score, agreement with intra-\/inter-observer reliability measurements and visual evaluation were used to find the best configuration of each learning algorithm for WMH segmentation. By using optimum threshold values for the probabilistic output from each algorithm to produce binary masks of WMH, we found that SVM and RF produced good results for medium to very large WMH burden but deep learning algorithms performed generally better than conventional ones in most evaluations.<\/jats:p>","DOI":"10.3390\/jimaging3040066","type":"journal-article","created":{"date-parts":[[2017,12,14]],"date-time":"2017-12-14T12:35:45Z","timestamp":1513254945000},"page":"66","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Deep Learning vs. Conventional Machine Learning: Pilot Study of WMH Segmentation in Brain MRI with Absence or Mild Vascular Pathology"],"prefix":"10.3390","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1672-9149","authenticated-orcid":false,"given":"Muhammad","family":"Rachmadi","sequence":"first","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, UK"},{"name":"Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh EH16 4SB, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2771-6546","authenticated-orcid":false,"given":"Maria","family":"Vald\u00e9s-Hern\u00e1ndez","sequence":"additional","affiliation":[{"name":"Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh EH16 4SB, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6910-9635","authenticated-orcid":false,"given":"Maria","family":"Agan","sequence":"additional","affiliation":[{"name":"Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh EH16 4SB, UK"}]},{"given":"Taku","family":"Komura","sequence":"additional","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, UK"}]}],"member":"1968","published-online":{"date-parts":[[2017,12,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"822","DOI":"10.1016\/S1474-4422(13)70124-8","article-title":"Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration","volume":"12","author":"Wardlaw","year":"2013","journal-title":"Lancet Neurol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1016\/j.neurobiolaging.2013.10.072","article-title":"Regional white matter hyperintensities: Aging, Alzheimer\u2019s disease risk, and cognitive function","volume":"35","author":"Birdsill","year":"2014","journal-title":"Neurobiol. Aging"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1016\/j.neuroimage.2011.04.053","article-title":"A comparison of different automated methods for the detection of white matter lesions in MRI data","volume":"57","author":"Abdulkadir","year":"2011","journal-title":"NeuroImage"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"014002","DOI":"10.1117\/1.JMI.2.1.014002","article-title":"Etiology-based classification of brain white matter hyperintensity on magnetic resonance imaging","volume":"2","author":"Leite","year":"2015","journal-title":"J. Med. Imaging"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"4219","DOI":"10.1002\/hbm.22472","article-title":"Extracting and summarizing white matter hyperintensities using supervised segmentation methods in Alzheimer\u2019s disease risk and aging studies","volume":"35","author":"Ithapu","year":"2014","journal-title":"Hum. Brain Mapp."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1016\/j.neuroimage.2014.06.077","article-title":"Hierarchical feature representation and multimodal fusion with deep learning for AD\/MCI diagnosis","volume":"101","author":"Suk","year":"2014","journal-title":"NeuroImage"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.media.2016.10.004","article-title":"Efficient multi-scale 3D {CNN} with fully connected {CRF} for accurate brain lesion segmentation","volume":"36","author":"Kamnitsas","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1109\/TMI.2016.2528821","article-title":"Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation","volume":"35","author":"Brosch","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Brosch, T., Yoo, Y., Tang, L.Y., Li, D.K., Traboulsee, A., and Tam, R. (2015, January 5\u20139). Deep convolutional encoder networks for multiple sclerosis lesion segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_1"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Rachmadi, M., Komura, T., Valdes Hernandez, M., and Agan, M. (2017). Evaluation of Four Supervised Learning Schemes in White Matter Hyperintensities Segmentation in Absence or Mild Presence of Vascular Pathology. Medical Image Understanding and Analysis (MIUA 2017), Springer.","DOI":"10.1007\/978-3-319-60964-5_42"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"55","DOI":"10.3174\/ajnr.A3612","article-title":"Morphologic, distributional, volumetric, and intensity characterization of periventricular hyperintensities","volume":"35","author":"Piper","year":"2014","journal-title":"Am. J. Neuroradiol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3774","DOI":"10.1016\/j.neuroimage.2011.11.032","article-title":"An automated tool for detection of FLAIR-hyperintense white-matter lesions in multiple sclerosis","volume":"59","author":"Schmidt","year":"2012","journal-title":"NeuroImage"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1016\/j.nic.2005.09.008","article-title":"The Alzheimer\u2019s disease neuroimaging initiative","volume":"15","author":"Mueller","year":"2005","journal-title":"Neuroimaging Clin. N. Am."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"S1","DOI":"10.1016\/j.jalz.2011.09.172","article-title":"The Alzheimer\u2019s Disease Neuroimaging Initiative: A review of papers published since its inception","volume":"8","author":"Weiner","year":"2012","journal-title":"Alzheimers Dement."},{"key":"ref_15","unstructured":"Lancaster, J.L., and Martinez, M.J. (2016, August 17). Multi-Image Analysis GUI (Mango). Available online: http:\/\/ric.uthscsa.edu\/mango\/."},{"key":"ref_16","unstructured":"Vald\u00e9s Hern\u00e1ndez, M.d.C. (2017, December 13). Reference Segmentations of White Matter Hyperintensities from a Subset of 20 Subjects Scanned Three Consecutive Years, 2010\u20132014 [Dataset]. Available online: https:\/\/datashare.is.ed.ac.uk\/handle\/10283\/2214."},{"key":"ref_17","unstructured":"Agan, M.L.F., and Vald\u00e9s Hern\u00e1ndez, M.d.C. (2017, December 13). Manual Segmentations of White Matter Hyperintensities from A Subset of 7 ADNI Subjects Scanned Three Consecutive Years, for Inter-\/Intra-Observer Reliability Analyses, 2012\u20132017 [dataset]. Available online: https:\/\/datashare.is.ed.ac.uk\/handle\/10283\/2706."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1006\/nimg.2002.1132","article-title":"Improved optimization for the robust and accurate linear registration and motion correction of brain images","volume":"17","author":"Jenkinson","year":"2002","journal-title":"NeuroImage"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Lutkenhoff, E.S., Rosenberg, M., Chiang, J., Zhang, K., Pickard, J.D., Owen, A.M., and Monti, M.M. (2014). Optimized brain extraction for pathological brains (optiBET). PLoS ONE, 9.","DOI":"10.1371\/journal.pone.0115551"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/42.836373","article-title":"New variants of a method of MRI scale standardization","volume":"19","author":"Udupa","year":"2000","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_21","unstructured":"Kamnitsas, K., and Glocker, B. (2016, June 13). DeepMedic. Available online: https:\/\/biomedia.doc.ic.ac.uk\/software\/deepmedic\/."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"ref_23","unstructured":"Myers, J.L., Well, A., and Lorch, R.F. (2010). Research Design and Statistical Analysis, Routledge."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/0022-510X(93)90041-V","article-title":"A semiquantative rating scale for the assessment of signal hyperintensities on magnetic resonance imaging","volume":"114","author":"Scheltens","year":"1993","journal-title":"J. Neurol. Sci."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1159\/000341859","article-title":"Close correlation between quantitative and qualitative assessments of white matter lesions","volume":"40","author":"Morris","year":"2013","journal-title":"Neuroepidemiology"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"351","DOI":"10.2214\/ajr.149.2.351","article-title":"MR signal abnormalities at 1.5 T in Alzheimer\u2019s dementia and normal aging","volume":"149","author":"Fazekas","year":"1987","journal-title":"Am. J. Roentgenol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1161\/01.STR.27.8.1274","article-title":"Clinical correlates of white matter findings on cranial magnetic resonance imaging of 3301 elderly people","volume":"27","author":"Longstreth","year":"1996","journal-title":"Stroke"},{"key":"ref_28","unstructured":"Schmidt, P. (2016, May 01). LST\u2014A lEsion Segmentation Tool for SPM. Available online: http:\/\/www.applied-statistics.de\/lst.html."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-Vector Networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1613\/jair.614","article-title":"Popular ensemble methods: An empirical study","volume":"11","author":"Opitz","year":"1999","journal-title":"J. Artif. Intell. Res."},{"key":"ref_31","unstructured":"Ithapu, V., Singh, V., Lindner, C., Austin, B.P., Hinrichs, C., Carlsson, C.M., Bendlin, B.B., and Johnson, S.C. (2015, June 15). Wisconsin White Matter Hyperintensities Segmentation Toolbox (W2MHS). Available online: https:\/\/www.nitrc.org\/projects\/w2mhs\/."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Jolliffe, I.T. (1986). Principal Component Analysis and Factor Analysis. Principal Component Analysis, Springer.","DOI":"10.1007\/978-1-4757-1904-8"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1016\/S0925-2312(03)00433-8","article-title":"A comparison of PCA, KPCA and ICA for dimensionality reduction in support vector machine","volume":"55","author":"Cao","year":"2003","journal-title":"Neurocomputing"},{"key":"ref_34","unstructured":"Salakhutdinov, R., and Hinton, G.E. (2009, January 16\u201318). Deep boltzmann machines. Proceedings of the International Conference on Artificial Intelligence and Statistics, Clearwater Beach, FL, USA."},{"key":"ref_35","first-page":"926","article-title":"A practical guide to training restricted Boltzmann machines","volume":"9","author":"Hinton","year":"2010","journal-title":"Momentum"},{"key":"ref_36","unstructured":"Salakhutdinov, R. (2016, May 29). Learning Deep Boltzmann Machines. Available online: http:\/\/www.cs.toronto.edu\/~rsalakhu\/DBM.html."},{"key":"ref_37","unstructured":"Nair, V., and Hinton, G.E. (2010, January 21\u201325). Rectified linear units improve restricted boltzmann machines. Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel."},{"key":"ref_38","unstructured":"Chollet, F. (2016, June 21). Keras. Available online: https:\/\/github.com\/fchollet\/keras."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 11\u201318). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"e00415","DOI":"10.1002\/brb3.415","article-title":"Rationale, design and methodology of the image analysis protocol for studies of patients with cerebral small vessel disease and mild stroke","volume":"5","author":"Armitage","year":"2015","journal-title":"Brain Behav."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/3\/4\/66\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:54:01Z","timestamp":1760208841000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/3\/4\/66"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,12,14]]},"references-count":40,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2017,12]]}},"alternative-id":["jimaging3040066"],"URL":"https:\/\/doi.org\/10.3390\/jimaging3040066","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,12,14]]}}}