{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T03:49:04Z","timestamp":1792036144879,"version":"4.4.0"},"reference-count":71,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T00:00:00Z","timestamp":1675814400000},"content-version":"vor","delay-in-days":38,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2016-04175"],"award-info":[{"award-number":["RGPIN-2016-04175"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2023,1]]},"abstract":"<jats:p>Biomarkers based on resting\u2010state electroencephalography (EEG) signals have emerged as a promising tool in the study of Alzheimer\u2019s disease (AD). Recently, a state\u2010of\u2010the\u2010art biomarker was found based on visual inspection of power modulation spectrograms where three \u201cpatches\u201d or regions from the modulation spectrogram were proposed and used for AD diagnostics. Here, we propose the use of deep neural networks, in particular convolutional neural networks (CNNs) combined with saliency maps, trained on power modulation spectrogram inputs to find optimal patches in a data\u2010driven manner. Experiments are conducted on EEG data collected from fifty\u2010four participants, including 20 healthy controls, 19 patients with mild AD, and 15 moderate\u2010to\u2010severe AD patients. Five classification tasks are explored, including the three\u2010class problem, early\u2010stage detection (control vs. mild\u2010AD), and severity level detection (mild vs. moderate\u2010to\u2010severe). Experimental results show the proposed biomarkers outperform the state\u2010of\u2010the\u2010art benchmark across all five tasks, as well as finding complementary modulation spectrogram regions not previously seen via visual inspection. Lastly, experiments are conducted on the proposed biomarkers to test their sensitivity to age, as this is a known confound in AD characterization. Across all five tasks, none of the proposed biomarkers showed a significant relationship with age, thus further highlighting their usefulness for automated AD diagnostics.<\/jats:p>","DOI":"10.1155\/2023\/3198066","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T00:05:08Z","timestamp":1675901108000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Using CNN Saliency Maps and EEG Modulation Spectra for Improved and More Interpretable Machine Learning\u2010Based Alzheimer\u2019s Disease Diagnosis"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2354-7781","authenticated-orcid":false,"given":"Marilia","family":"Lopes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3509-5543","authenticated-orcid":false,"given":"Raymundo","family":"Cassani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5739-2514","authenticated-orcid":false,"given":"Tiago H.","family":"Falk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,2,8]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1037\/a0029857"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1097\/00002093-200210000-00001"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2011.03.003"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2014.10.038"},{"key":"e_1_2_9_5_2","volume-title":"World Alzheimer Report 2011: The Benefits of Early Diagnosis and Intervention","author":"Prince M.","year":"2018"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.17352\/ojc.000012"},{"key":"e_1_2_9_7_2","doi-asserted-by":"publisher","DOI":"10.4103\/1673-5374.253509"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1177\/1179573520907397"},{"key":"e_1_2_9_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2008.04.014"},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.43.11.2412-a"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/s1053-8119(02)00026-5"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrneurol.2009.215"},{"key":"e_1_2_9_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2011.09.004"},{"key":"e_1_2_9_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2010.04.024"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1038\/gim.2015.117"},{"key":"e_1_2_9_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinph.2020.03.003"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2019.00017"},{"key":"e_1_2_9_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-7020-5307-8.00015-6"},{"key":"e_1_2_9_19_2","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/5174815"},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.3390\/s22103696"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3198988"},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.3390\/app12115413"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-192"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0072240"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2014.00055"},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195050387.001.0001"},{"key":"e_1_2_9_27_2","doi-asserted-by":"crossref","unstructured":"ElgendiM. VialatteF. CichockiA. LatchoumaneC. JeongJ. andDauwelsJ. Optimization of EEG frequency bands for improved diagnosis of Alzheimer disease Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society August 2011 Boston MA USA IEEE 6087\u20136091.","DOI":"10.1109\/IEMBS.2011.6091504"},{"key":"e_1_2_9_28_2","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/12\/1\/016018"},{"key":"e_1_2_9_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2019.2953475"},{"key":"e_1_2_9_30_2","unstructured":"SimonyanK. VedaldiA. andZissermanA. Deep inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps 2013 https:\/\/arxiv.org\/abs\/1312.6034."},{"key":"e_1_2_9_31_2","doi-asserted-by":"publisher","DOI":"10.1117\/12.2007092"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"Ben-AhmedO. LecellierF. PaccalinM. andFernandez-MaloigneC. Multi-view visual saliency-based MRI classification for Alzheimer\u2019s disease diagnosis Proceedings of the 2017 Seventh International Conference on Image Processing Theory Tools and Applications (IPTA) November 2017 Montreal QC Canada IEEE 1\u20136.","DOI":"10.1109\/IPTA.2017.8310118"},{"key":"e_1_2_9_33_2","doi-asserted-by":"publisher","DOI":"10.1212\/wnl.34.7.939"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1590\/s0004-282x2003000500014"},{"key":"e_1_2_9_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2006.05.033"},{"key":"e_1_2_9_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2011.08.005"},{"key":"e_1_2_9_37_2","doi-asserted-by":"crossref","unstructured":"TrambaiolliL. R. FalkT. H. FragaF. J. AnghinahR. andLorenaA. C. EEG spectro-temporal modulation energy: a new feature for automated diagnosis of Alzheimer\u2019s disease Proceedings of the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society August 2011 Boston MA USA IEEE 3828\u20133831.","DOI":"10.1109\/IEMBS.2011.6090951"},{"key":"e_1_2_9_38_2","doi-asserted-by":"publisher","DOI":"10.1155\/s1110865703305013"},{"key":"e_1_2_9_39_2","volume-title":"Spectrotemporal Modeling of Biomedical Signals: Theoretical Foundation and Applications, Reference Module In Biomedical Sciences","author":"Cassani R.","year":"2018"},{"key":"e_1_2_9_40_2","volume-title":"Deep Learning: A Practitioner\u2019s Approach","author":"Patterson J.","year":"2017"},{"key":"e_1_2_9_41_2","doi-asserted-by":"crossref","unstructured":"LeCunY. KavukcuogluK. andFarabetC. Convolutional networks and applications in vision Proceedings of the 2010 IEEE International Symposium on Circuits and Systems May 2010 Paris France IEEE 253\u2013256.","DOI":"10.1109\/ISCAS.2010.5537907"},{"key":"e_1_2_9_42_2","unstructured":"O\u2019SheaK.andNashR. An Introduction to Convolutional Neural Networks 2015 https:\/\/arxiv.org\/abs\/1511.08458."},{"key":"e_1_2_9_43_2","unstructured":"KoushikJ. Understanding Convolutional Neural Networks 2016 https:\/\/arxiv.org\/abs\/1605.09081."},{"key":"e_1_2_9_44_2","doi-asserted-by":"crossref","unstructured":"PlathottamS. J. SalehfarH. andRanganathanP. Convolutional Neural Networks (CNNs) for power system big data analysis Proceedings of the 2017 North American Power Symposium (NAPS) September 2017 Morgantown WV USA IEEE 1\u20136.","DOI":"10.1109\/NAPS.2017.8107202"},{"key":"e_1_2_9_45_2","volume-title":"Deep Learning","author":"Goodfellow I.","year":"2016"},{"key":"e_1_2_9_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_9_47_2","doi-asserted-by":"crossref","unstructured":"BrockiL.andChungN. C. Concept saliency maps to visualize relevant features in deep generative models Proceedings of the 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA) December 2019 Boca Raton FL USA IEEE 1771\u20131778.","DOI":"10.1109\/ICMLA.2019.00287"},{"key":"e_1_2_9_48_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0146388"},{"key":"e_1_2_9_49_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0187209"},{"key":"e_1_2_9_50_2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364909346069"},{"key":"e_1_2_9_51_2","doi-asserted-by":"publisher","DOI":"10.3390\/ai1040030"},{"key":"e_1_2_9_52_2","doi-asserted-by":"crossref","unstructured":"RamenahalliS. MendatD. R. Dura-BernalS. CulurcielloE. NieburE. andAndreouA. Audio-visual saliency map: overview basic models and hardware implementation Proceedings of the 2013 47th Annual Conference on Information Sciences and Systems (CISS) March 2013 Baltimore MD USA IEEE 1\u20136.","DOI":"10.1109\/CISS.2013.6552285"},{"key":"e_1_2_9_53_2","doi-asserted-by":"crossref","unstructured":"HendersonR.andRotheR. Picasso: A Modular Framework for Visualizing the Learning Process of Neural Network Image Classifiers 2017 https:\/\/arxiv.org\/abs\/1705.05627.","DOI":"10.5334\/jors.178"},{"key":"e_1_2_9_54_2","doi-asserted-by":"crossref","unstructured":"CassaniR.andFalkT. H. Automated alzheimer\u2019s disease diagnosis using a low-density EEG layout and new features based on the power of modulation spectral \u201cpatches\u201d Proceedings of the 2019 IEEE International Conference on Systems Man and Cybernetics (SMC) October 2019 Bari Italy IEEE 1259\u20131263.","DOI":"10.1109\/SMC.2019.8914540"},{"key":"e_1_2_9_55_2","doi-asserted-by":"publisher","DOI":"10.1023\/b:stco.0000035301.49549.88"},{"key":"e_1_2_9_56_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13073-015-0232-5"},{"key":"e_1_2_9_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.celrep.2019.03.099"},{"key":"e_1_2_9_58_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0168-5597(97)96139-6"},{"key":"e_1_2_9_59_2","doi-asserted-by":"publisher","DOI":"10.1016\/s0167-8760(97)00772-1"},{"key":"e_1_2_9_60_2","doi-asserted-by":"publisher","DOI":"10.1002\/ana.410270502"},{"key":"e_1_2_9_61_2","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhn113"},{"key":"e_1_2_9_62_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2017.03.057"},{"key":"e_1_2_9_63_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurobiolaging.2008.07.019"},{"key":"e_1_2_9_64_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00702-008-0083-y"},{"key":"e_1_2_9_65_2","doi-asserted-by":"crossref","unstructured":"TrambaiolliL. R. CassaniR. andFalkT. H. Eeg spectro-temporal amplitude modulation as a measurement of cortical hemodynamics: an eeg-fnirs study Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) July 2020 Montreal QC Canada IEEE 3481\u20133484.","DOI":"10.1109\/EMBC44109.2020.9175409"},{"key":"e_1_2_9_66_2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn.2017.48"},{"key":"e_1_2_9_67_2","doi-asserted-by":"publisher","DOI":"10.3233\/jad-2012-120793"},{"key":"e_1_2_9_68_2","doi-asserted-by":"publisher","DOI":"10.1016\/0013-4694(85)90942-3"},{"key":"e_1_2_9_69_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2016.12.009"},{"key":"e_1_2_9_70_2","article-title":"Multimodal prediction of alzheimer\u2019s disease severity level based on resting-state EEG and structural MRI","volume":"495","author":"De Jesus Junior B.","year":"2020","journal-title":"Frontiers in Human Neuroscience"},{"key":"e_1_2_9_71_2","unstructured":"Soares LopesM. K. On the use of saliency maps for improved modulation spectral patch features for alzheimer\u2019s disease diagnosis 2021 Ma\u00eetrise en t\u00e9l\u00e9communications New York City Ph.D. dissertation."}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2023\/3198066.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2023\/3198066.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2023\/3198066","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T13:01:39Z","timestamp":1722949299000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2023\/3198066"}},"subtitle":[],"editor":[{"given":"Guangming","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,1]]},"references-count":71,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1155\/2023\/3198066"],"URL":"https:\/\/doi.org\/10.1155\/2023\/3198066","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1]]},"assertion":[{"value":"2022-05-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-11","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-02-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"3198066"}}