1
|
van Veen R, Tamboli NRB, Lövdal S, Meles SK, Renken RJ, de Vries GJ, Arnaldi D, Morbelli S, Clavero P, Obeso JA, Oroz MCR, Leenders KL, Villmann T, Biehl M. Subspace corrected relevance learning with application in neuroimaging. Artif Intell Med 2024; 149:102786. [PMID: 38462286 DOI: 10.1016/j.artmed.2024.102786] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/10/2023] [Revised: 01/12/2024] [Accepted: 01/21/2024] [Indexed: 03/12/2024]
Abstract
In machine learning, data often comes from different sources, but combining them can introduce extraneous variation that affects both generalization and interpretability. For example, we investigate the classification of neurodegenerative diseases using FDG-PET data collected from multiple neuroimaging centers. However, data collected at different centers introduces unwanted variation due to differences in scanners, scanning protocols, and processing methods. To address this issue, we propose a two-step approach to limit the influence of center-dependent variation on the classification of healthy controls and early vs. late-stage Parkinson's disease patients. First, we train a Generalized Matrix Learning Vector Quantization (GMLVQ) model on healthy control data to identify a "relevance space" that distinguishes between centers. Second, we use this space to construct a correction matrix that restricts a second GMLVQ system's training on the diagnostic problem. We evaluate the effectiveness of this approach on the real-world multi-center datasets and simulated artificial dataset. Our results demonstrate that the approach produces machine learning systems with reduced bias - being more specific due to eliminating information related to center differences during the training process - and more informative relevance profiles that can be interpreted by medical experts. This method can be adapted to similar problems outside the neuroimaging domain, as long as an appropriate "relevance space" can be identified to construct the correction matrix.
Collapse
Affiliation(s)
- Rick van Veen
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands.
| | - Neha Rajendra Bari Tamboli
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands.
| | - Sofie Lövdal
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands; Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, The Netherlands.
| | - Sanne K Meles
- Department of Neurology, University Medical Center Groningen, The Netherlands.
| | - Remco J Renken
- Department of Biomedical Sciences of Cells & Systems, Cognitive Neuroscience Center, University Medical Center Groningen, The Netherlands.
| | | | - Dario Arnaldi
- Department of Neuroscience, University of Genoa, Italy; IRCCS Ospedale Policlinico San Martino, Genoa, Italy.
| | - Silvia Morbelli
- IRCCS Ospedale Policlinico San Martino, Genoa, Italy; Department of Health Sciences, University of Genoa, Italy.
| | - Pedro Clavero
- Servicio de Neurología, Complejo Hospitalario de Navarra, Pamplona, Spain.
| | - José A Obeso
- Académico de Número Real Academia Nacional de Medicina de España, Spain.
| | - Maria C Rodriguez Oroz
- Neurology Department, Clínica Universidad de Navarra, Spain; Neuroscience Program, Center for Applied Medical Research, Universidad de Navarra, Pamplona, Spain; Navarra Institute for Health Research, Pamplona, Spain
| | - Klaus L Leenders
- Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, The Netherlands.
| | - Thomas Villmann
- Saxon Institute for Computational Intelligence and Machine Learning, University of Applied Sciences Mittweida, Germany.
| | - Michael Biehl
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, The Netherlands; SMQB, Inst. of Metabolism and Systems Research, College of Medical and Dental Sciences, Birmingham, United Kingdom.
| |
Collapse
|
2
|
Prete A, Lang K, Pavlov D, Rhayem Y, Sitch AJ, Franke AS, Gilligan LC, Shackleton CHL, Hahner S, Quinkler M, Dekkers T, Deinum J, Reincke M, Beuschlein F, Biehl M, Arlt W. Urine steroid metabolomics as a diagnostic tool in primary aldosteronism. J Steroid Biochem Mol Biol 2024; 237:106445. [PMID: 38104729 DOI: 10.1016/j.jsbmb.2023.106445] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Revised: 11/03/2023] [Accepted: 12/13/2023] [Indexed: 12/19/2023]
Abstract
Primary aldosteronism (PA) causes 5-10% of hypertension cases, but only a minority of patients are currently diagnosed and treated because of a complex, stepwise, and partly invasive workup. We tested the performance of urine steroid metabolomics, the computational analysis of 24-hour urine steroid metabolome data by machine learning, for the identification and subtyping of PA. Mass spectrometry-based multi-steroid profiling was used to quantify the excretion of 34 steroid metabolites in 24-hour urine samples from 158 adults with PA (88 with unilateral PA [UPA] due to aldosterone-producing adenomas [APAs]; 70 with bilateral PA [BPA]) and 65 sex- and age-matched healthy controls. All APAs were resected and underwent targeted gene sequencing to detect somatic mutations associated with UPA. Patients with PA had increased urinary metabolite excretion of mineralocorticoids, glucocorticoids, and glucocorticoid precursors. Urine steroid metabolomics identified patients with PA with high accuracy, both when applied to all 34 or only the three most discriminative steroid metabolites (average areas under the receiver-operating characteristics curve [AUCs-ROC] 0.95-0.97). Whilst machine learning was suboptimal in differentiating UPA from BPA (average AUCs-ROC 0.65-0.73), it readily identified APA cases harbouring somatic KCNJ5 mutations (average AUCs-ROC 0.79-85). These patients showed a distinctly increased urine excretion of the hybrid steroid 18-hydroxycortisol and its metabolite 18-oxo-tetrahydrocortisol, the latter identified by machine learning as by far the most discriminative steroid. In conclusion, urine steroid metabolomics is a non-invasive candidate test for the accurate identification of PA cases and KCNJ5-mutated APAs.
Collapse
Affiliation(s)
- Alessandro Prete
- Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK; Centre for Endocrinology, Diabetes and Metabolism, Birmingham Health Partners, Birmingham, UK; Department of Endocrinology, Queen Elizabeth Hospital, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK; NIHR Birmingham Biomedical Research Centre, University of Birmingham and University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK.
| | - Katharina Lang
- Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK; Centre for Endocrinology, Diabetes and Metabolism, Birmingham Health Partners, Birmingham, UK; Department of Endocrinology, Queen Elizabeth Hospital, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK
| | - David Pavlov
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, the Netherlands
| | - Yara Rhayem
- Medizinische Klinik and Poliklinik IV, Klinikum der Universität, Ludwig-Maximilians-Universität München, Munich, Germany; Service de Biologie Clinique, Hôpital Foch, Suresnes, France
| | - Alice J Sitch
- NIHR Birmingham Biomedical Research Centre, University of Birmingham and University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK; Institute of Applied Health Research, University of Birmingham, Birmingham, UK
| | - Anna S Franke
- Medizinische Klinik and Poliklinik IV, Klinikum der Universität, Ludwig-Maximilians-Universität München, Munich, Germany
| | - Lorna C Gilligan
- Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK
| | - Cedric H L Shackleton
- Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK; UCSF Benioff Children's Hospital Oakland Research Institute, Oakland, CA, USA
| | - Stefanie Hahner
- Department of Internal Medicine I, Division of Endocrinology and Diabetes, University Hospital, University of Würzburg, Würzburg, Germany
| | | | - Tanja Dekkers
- Department of Internal Medicine, Radboud University Medical Center, Nijmegen, the Netherlands
| | - Jaap Deinum
- Department of Internal Medicine, Radboud University Medical Center, Nijmegen, the Netherlands
| | - Martin Reincke
- Medizinische Klinik and Poliklinik IV, Klinikum der Universität, Ludwig-Maximilians-Universität München, Munich, Germany
| | - Felix Beuschlein
- Medizinische Klinik and Poliklinik IV, Klinikum der Universität, Ludwig-Maximilians-Universität München, Munich, Germany; Klinik für Endokrinologie, Diabetologie und Klinische Ernährung, Universitäts-Spital Zürich (USZ) und Universität Zürich (UZH), Zurich, Switzerland
| | - Michael Biehl
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, the Netherlands; Centre for Systems Modelling and Quantitative Biomedicine, University of Birmingham, Birmingham, UK
| | - Wiebke Arlt
- Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, University of Birmingham, Birmingham, UK; Centre for Endocrinology, Diabetes and Metabolism, Birmingham Health Partners, Birmingham, UK; Department of Endocrinology, Queen Elizabeth Hospital, University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK; Medical Research Council Laboratory of Medical Sciences, London, UK; Institute of Clinical Sciences, Faculty of Medicine, Imperial College, London, UK
| |
Collapse
|
3
|
Li R, Harshfield EL, Bell S, Burkhart M, Tuladhar AM, Hilal S, Tozer DJ, Chappell FM, Makin SD, Lo JW, Wardlaw JM, de Leeuw FE, Chen C, Kourtzi Z, Markus HS. Predicting incident dementia in cerebral small vessel disease: comparison of machine learning and traditional statistical models. CEREBRAL CIRCULATION - COGNITION AND BEHAVIOR 2023; 5:100179. [PMID: 37593075 PMCID: PMC10428032 DOI: 10.1016/j.cccb.2023.100179] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/21/2023] [Revised: 07/07/2023] [Accepted: 08/08/2023] [Indexed: 08/19/2023]
Abstract
Background Cerebral small vessel disease (SVD) contributes to 45% of dementia cases worldwide, yet we lack a reliable model for predicting dementia in SVD. Past attempts largely relied on traditional statistical approaches. Here, we investigated whether machine learning (ML) methods improved prediction of incident dementia in SVD from baseline SVD-related features over traditional statistical methods. Methods We included three cohorts with varying SVD severity (RUN DMC, n = 503; SCANS, n = 121; HARMONISATION, n = 265). Baseline demographics, vascular risk factors, cognitive scores, and magnetic resonance imaging (MRI) features of SVD were used for prediction. We conducted both survival analysis and classification analysis predicting 3-year dementia risk. For each analysis, several ML methods were evaluated against standard Cox or logistic regression. Finally, we compared the feature importance ranked by different models. Results We included 789 participants without missing data in the survival analysis, amongst whom 108 (13.7%) developed dementia during a median follow-up of 5.4 years. Excluding those censored before three years, we included 750 participants in the classification analysis, amongst whom 48 (6.4%) developed dementia by year 3. Comparing statistical and ML models, only regularised Cox/logistic regression outperformed their statistical counterparts overall, but not significantly so in survival analysis. Baseline cognition was highly predictive, and global cognition was the most important feature. Conclusions When using baseline SVD-related features to predict dementia in SVD, the ML survival or classification models we evaluated brought little improvement over traditional statistical approaches. The benefits of ML should be evaluated with caution, especially given limited sample size and features.
Collapse
Affiliation(s)
- Rui Li
- Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
| | - Eric L. Harshfield
- Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
- Heart and Lung Research Institute, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
| | - Steven Bell
- Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
- Heart and Lung Research Institute, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
- Precision Breast Cancer Institute, Department of Oncology, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
| | - Michael Burkhart
- Adaptive Brain Lab, Department of Psychology, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
| | - Anil M. Tuladhar
- Department of Neurology, Donders Centre for Medical Neuroscience, Radboud University Medical Centre, Nijmegen, Netherlands
| | - Saima Hilal
- Memory Aging and Cognition Centre, Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
- Saw Swee Hock School of Public Health, National University of Singapore and National University Health System, Singapore
| | - Daniel J. Tozer
- Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
| | - Francesca M. Chappell
- Centre for Clinical Brain Sciences, University of Edinburgh, United Kingdom of Great Britain and Northern Ireland
| | - Stephen D.J. Makin
- Centre for Rural Health, Institute of Applied Health Sciences, University of Aberdeen, United Kingdom of Great Britain and Northern Ireland
| | - Jessica W. Lo
- Centre for Healthy Brain Ageing, University of New South Wales, Sydney, Australia
| | - Joanna M. Wardlaw
- Centre for Clinical Brain Sciences, University of Edinburgh, United Kingdom of Great Britain and Northern Ireland
| | - Frank-Erik de Leeuw
- Department of Neurology, Donders Centre for Medical Neuroscience, Radboud University Medical Centre, Nijmegen, Netherlands
| | - Christopher Chen
- Memory Aging and Cognition Centre, Department of Pharmacology, Yong Loo Lin School of Medicine, National University of Singapore, Singapore
| | - Zoe Kourtzi
- Adaptive Brain Lab, Department of Psychology, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
| | - Hugh S. Markus
- Stroke Research Group, Department of Clinical Neurosciences, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
- Heart and Lung Research Institute, University of Cambridge, United Kingdom of Great Britain and Northern Ireland
| |
Collapse
|
4
|
Pauli R, Kohls G, Tino P, Rogers JC, Baumann S, Ackermann K, Bernhard A, Martinelli A, Jansen L, Oldenhof H, Gonzalez-Madruga K, Smaragdi A, Gonzalez-Torres MA, Kerexeta-Lizeaga I, Boonmann C, Kersten L, Bigorra A, Hervas A, Stadler C, Fernandez-Rivas A, Popma A, Konrad K, Herpertz-Dahlmann B, Fairchild G, Freitag CM, Rotshtein P, De Brito SA. Machine learning classification of conduct disorder with high versus low levels of callous-unemotional traits based on facial emotion recognition abilities. Eur Child Adolesc Psychiatry 2023; 32:589-600. [PMID: 34661765 PMCID: PMC10115711 DOI: 10.1007/s00787-021-01893-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/25/2021] [Accepted: 07/14/2021] [Indexed: 11/30/2022]
Abstract
Conduct disorder (CD) with high levels of callous-unemotional traits (CD/HCU) has been theoretically linked to specific difficulties with fear and sadness recognition, in contrast to CD with low levels of callous-unemotional traits (CD/LCU). However, experimental evidence for this distinction is mixed, and it is unclear whether these difficulties are a reliable marker of CD/HCU compared to CD/LCU. In a large sample (N = 1263, 9-18 years), we combined univariate analyses and machine learning classifiers to investigate whether CD/HCU is associated with disproportionate difficulties with fear and sadness recognition over other emotions, and whether such difficulties are a reliable individual-level marker of CD/HCU. We observed similar emotion recognition abilities in CD/HCU and CD/LCU. The CD/HCU group underperformed relative to typically developing (TD) youths, but difficulties were not specific to fear or sadness. Classifiers did not distinguish between youths with CD/HCU versus CD/LCU (52% accuracy), although youths with CD/HCU and CD/LCU were reliably distinguished from TD youths (64% and 60%, respectively). In the subset of classifiers that performed well for youths with CD/HCU, fear and sadness were the most relevant emotions for distinguishing them from youths with CD/LCU and TD youths, respectively. We conclude that non-specific emotion recognition difficulties are common in CD/HCU, but are not reliable individual-level markers of CD/HCU versus CD/LCU. These findings highlight that a reduced ability to recognise facial expressions of distress should not be assumed to be a core feature of CD/HCU.
Collapse
Affiliation(s)
- Ruth Pauli
- Centre for Human Brain Health, School of Psychology, University of Birmingham, Birmingham, B15 2TT, UK.
| | - Gregor Kohls
- Child Neuropsychology Section, Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, RWTH Aachen University, Aachen, Germany
- Department of Child and Adolescent Psychiatry, Faculty of Medicine, TU, Dresden, Germany
| | - Peter Tino
- School of Computer Science, University of Birmingham, Birmingham, UK
| | - Jack C Rogers
- Centre for Human Brain Health, School of Psychology, University of Birmingham, Birmingham, B15 2TT, UK
- Institute for Mental Health, School of Psychology, University of Birmingham, Birmingham, UK
| | - Sarah Baumann
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, University Hospital RWTH Aachen, Aachen, Germany
| | - Katharina Ackermann
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Goethe University, University Hospital Frankfurt, Frankfurt am Main, Germany
- Faculty of Education, Hamburg University, Hamburg, Germany
| | - Anka Bernhard
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Goethe University, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Anne Martinelli
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Goethe University, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Lucres Jansen
- Department of Child and Adolescent Psychiatry, VU University Medical Center, Amsterdam, the Netherlands
| | - Helena Oldenhof
- Department of Child and Adolescent Psychiatry, VU University Medical Center, Amsterdam, the Netherlands
| | - Karen Gonzalez-Madruga
- Department of Child and Adolescent Psychiatry, Institute of Psychiatry, Psychology and Neuroscience, Kings College London, London, UK
| | | | | | | | - Cyril Boonmann
- Department of Child and Adolescent Psychiatry, University Psychiatric Hospitals, University of Basel, Basel, Switzerland
| | - Linda Kersten
- Department of Child and Adolescent Psychiatry, University Psychiatric Hospitals, University of Basel, Basel, Switzerland
| | | | - Amaia Hervas
- University Hospital Mutua Terrassa, Barcelona, Spain
| | - Christina Stadler
- Department of Child and Adolescent Psychiatry, University Psychiatric Hospitals, University of Basel, Basel, Switzerland
| | | | - Arne Popma
- Department of Child and Adolescent Psychiatry, VU University Medical Center, Amsterdam, the Netherlands
| | - Kerstin Konrad
- Child Neuropsychology Section, Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, RWTH Aachen University, Aachen, Germany
- JARA-Brain Institute II, Molecular Neuroscience and Neuroimaging, RWTH Aachen and Research Centre Juelich, Juelich, Germany
| | - Beate Herpertz-Dahlmann
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, University Hospital RWTH Aachen, Aachen, Germany
| | | | - Christine M Freitag
- Department of Child and Adolescent Psychiatry, Psychosomatics and Psychotherapy, Goethe University, University Hospital Frankfurt, Frankfurt am Main, Germany
| | - Pia Rotshtein
- Centre for Human Brain Health, School of Psychology, University of Birmingham, Birmingham, B15 2TT, UK
| | - Stephane A De Brito
- Centre for Human Brain Health, School of Psychology, University of Birmingham, Birmingham, B15 2TT, UK.
| |
Collapse
|
5
|
Engelsberger A, Villmann T. Quantum Computing Approaches for Vector Quantization-Current Perspectives and Developments. ENTROPY (BASEL, SWITZERLAND) 2023; 25:540. [PMID: 36981428 PMCID: PMC10048050 DOI: 10.3390/e25030540] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/11/2023] [Revised: 03/15/2023] [Accepted: 03/20/2023] [Indexed: 06/18/2023]
Abstract
In the field of machine learning, vector quantization is a category of low-complexity approaches that are nonetheless powerful for data representation and clustering or classification tasks. Vector quantization is based on the idea of representing a data or a class distribution using a small set of prototypes, and hence, it belongs to interpretable models in machine learning. Further, the low complexity of vector quantizers makes them interesting for the application of quantum concepts for their implementation. This is especially true for current and upcoming generations of quantum devices, which only allow the execution of simple and restricted algorithms. Motivated by different adaptation and optimization paradigms for vector quantizers, we provide an overview of respective existing quantum algorithms and routines to realize vector quantization concepts, maybe only partially, on quantum devices. Thus, the reader can infer the current state-of-the-art when considering quantum computing approaches for vector quantization.
Collapse
|
6
|
Lisboa P, Saralajew S, Vellido A, Fernández-Domenech R, Villmann T. The Coming of Age of Interpretable and Explainable Machine Learning Models. Neurocomputing 2023. [DOI: 10.1016/j.neucom.2023.02.040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/05/2023]
|
7
|
Awotunde JB, Imoize AL, Ayoade OB, Abiodun MK, Do DT, Silva A, Sur SN. An Enhanced Hyper-Parameter Optimization of a Convolutional Neural Network Model for Leukemia Cancer Diagnosis in a Smart Healthcare System. SENSORS (BASEL, SWITZERLAND) 2022; 22:9689. [PMID: 36560057 PMCID: PMC9785310 DOI: 10.3390/s22249689] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/14/2022] [Revised: 12/07/2022] [Accepted: 12/08/2022] [Indexed: 06/17/2023]
Abstract
Healthcare systems in recent times have witnessed timely diagnoses with a high level of accuracy. Internet of Medical Things (IoMT)-enabled deep learning (DL) models have been used to support medical diagnostics in real time, thus resolving the issue of late-stage diagnosis of various diseases and increasing performance accuracy. The current approach for the diagnosis of leukemia uses traditional procedures, and in most cases, fails in the initial period. Hence, several patients suffering from cancer have died prematurely due to the late discovery of cancerous cells in blood tissue. Therefore, this study proposes an IoMT-enabled convolutional neural network (CNN) model to detect malignant and benign cancer cells in the patient's blood tissue. In particular, the hyper-parameter optimization through radial basis function and dynamic coordinate search (HORD) optimization algorithm was used to search for optimal values of CNN hyper-parameters. Utilizing the HORD algorithm significantly increased the effectiveness of finding the best solution for the CNN model by searching multidimensional hyper-parameters. This implies that the HORD method successfully found the values of hyper-parameters for precise leukemia features. Additionally, the HORD method increased the performance of the model by optimizing and searching for the best set of hyper-parameters for the CNN model. Leukemia datasets were used to evaluate the performance of the proposed model using standard performance indicators. The proposed model revealed significant classification accuracy compared to other state-of-the-art models.
Collapse
Affiliation(s)
- Joseph Bamidele Awotunde
- Department of Computer Science, Faculty of Information and Communication Sciences, University of Ilorin, Ilorin 240003, Nigeria
| | - Agbotiname Lucky Imoize
- Department of Electrical and Electronics Engineering, Faculty of Engineering, University of Lagos, Akoka, Lagos 100213, Nigeria
- Department of Electrical Engineering and Information Technology, Institute of Digital Communication, Ruhr University, 44801 Bochum, Germany
| | - Oluwafisayo Babatope Ayoade
- Department of Computing and Information Science, School of Pure & Applied Sciences, College of Science, Bamidele Olumilua University of Education, Science & Technology, Ikere-Ekiti 361264, Nigeria
| | | | - Dinh-Thuan Do
- Department of Computer Science and Information Engineering, College of Information and Electrical Engineering, Asia University, Taichung 41354, Taiwan
| | - Adão Silva
- Instituto de Telecomunicações (IT) and Departamento de Eletrónica, Telecomunicações e Informática (DETI), University of Aveiro, 3810-193 Aveiro, Portugal
| | - Samarendra Nath Sur
- Department of Electronics and Communication Engineering, Sikkim Manipal Institute of Technology, Sikkim Manipal University, Majitar, Rangpo 737136, Sikkim, India
| |
Collapse
|
8
|
van Veen R, Meles SK, Renken RJ, Reesink FE, Oertel WH, Janzen A, de Vries GJ, Leenders KL, Biehl M. FDG-PET combined with learning vector quantization allows classification of neurodegenerative diseases and reveals the trajectory of idiopathic REM sleep behavior disorder. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 225:107042. [PMID: 35970056 DOI: 10.1016/j.cmpb.2022.107042] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/01/2022] [Revised: 07/11/2022] [Accepted: 07/27/2022] [Indexed: 06/15/2023]
Abstract
BACKGROUND AND OBJECTIVES 18F-fluorodeoxyglucose (FDG) positron emission tomography (PET) combined with principal component analysis (PCA) has been applied to identify disease-related brain patterns in neurodegenerative disorders such as Parkinson's disease (PD), Dementia with Lewy Bodies (DLB) and Alzheimer's disease (AD). These patterns are used to quantify functional brain changes at the single subject level. This is especially relevant in determining disease progression in idiopathic REM sleep behavior disorder (iRBD), a prodromal stage of PD and DLB. However, the PCA method is limited in discriminating between neurodegenerative conditions. More advanced machine learning algorithms may provide a solution. In this study, we apply Generalized Matrix Learning Vector Quantization (GMLVQ) to FDG-PET scans of healthy controls, and patients with AD, PD and DLB. Scans of iRBD patients, scanned twice with an approximate 4 year interval, were projected into GMLVQ space to visualize their trajectory. METHODS We applied a combination of SSM/PCA and GMLVQ as a classifier on FDG-PET data of healthy controls, AD, DLB, and PD patients. We determined the diagnostic performance by performing a ten times repeated ten fold cross validation. We analyzed the validity of the classification system by inspecting the GMLVQ space. First by the projection of the patients into this space. Second by representing the axis, that span this decision space, into a voxel map. Furthermore, we projected a cohort of RBD patients, whom have been scanned twice (approximately 4 years apart), into the same decision space and visualized their trajectories. RESULTS The GMLVQ prototypes, relevance diagonal, and decision space voxel maps showed metabolic patterns that agree with previously identified disease-related brain patterns. The GMLVQ decision space showed a plausible quantification of FDG-PET data. Distance traveled by iRBD subjects through GMLVQ space per year (i.e. velocity) was correlated with the change in motor symptoms per year (Spearman's rho =0.62, P=0.004). CONCLUSION In this proof-of-concept study, we show that GMLVQ provides a classification of patients with neurodegenerative disorders, and may be useful in future studies investigating speed of progression in prodromal disease stages.
Collapse
Affiliation(s)
- Rick van Veen
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, the Netherlands; Data Science Department, Software Competence Center Hagenberg, Hagenberg, Austria.
| | - Sanne K Meles
- Department of Neurology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands
| | - Remco J Renken
- Department of Biomedical Sciences of Cells & Systems, University of Groningen, University Medical Center Groningen, Cognitive Neuroscience Center, Groningen, the Netherlands
| | - Fransje E Reesink
- Department of Neurology, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands
| | - Wolfgang H Oertel
- Department of Neurology, Philipps-Universität Marburg, Marburg, Germany; Institute for Neurogenomics, Helmholtz Center for Health and Environment, Munich, Germany
| | - Annette Janzen
- Department of Neurology, Philipps-Universität Marburg, Marburg, Germany
| | | | - Klaus L Leenders
- Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Groningen, the Netherlands
| | - Michael Biehl
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, the Netherlands; SMQB, Institute of Metabolism and Systems Research, College of Medical and Dental Sciences, Birmingham, United Kingdom
| |
Collapse
|
9
|
Ravichandran J, Kaden M, Villmann T. Variants of recurrent learning vector quantization. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2022.06.035] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
10
|
Ren Q, Yuan C, Zhao Y, Yang L. A multi-birth metric learning framework based on binary constraints. Neural Netw 2022; 154:165-178. [PMID: 35882084 DOI: 10.1016/j.neunet.2022.07.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2021] [Revised: 05/11/2022] [Accepted: 07/07/2022] [Indexed: 11/28/2022]
Abstract
Multi-metric learning plays a significant role in improving the generalization of algorithms related to distance metrics since using a single metric is sometimes insufficient to handle complex data. Metric learning can adjust automatically the distance between samples to make the intra-class samples compact while making the inter-class distance as far as possible. To implement this intention better,in this work, we propose a novel multi-metric learning framework based on the pair constraints instead of triple constraints to reduce computational burden. To solve effectively the problem, we first propose a multi-birth metric learning model (termed MBML), where for each class sample, the global metric and a local metric are jointly trained. Both global and local structural information are adapted to better depict sample information. Then two alternating iterative algorithms are developed to optimize the MBML. The convergence of the proposed algorithm and complexity are analyzed theoretically. Moreover, a fast diagonal multi-metric learning method is proposed based on binary constraints, and problem can be reformulated a linear programming, with fast training speed, low the computational burden and the global optimal solutions. Numerical experiments are carried out on different scales and different types of datasets including an artificial data, benchmark datasets and an image database from binary class and multi-class problems. Experiment results confirm the feasibility and effectiveness of the proposed methods.
Collapse
Affiliation(s)
- QiangQiang Ren
- College of Information and Electrical Engineering, China Agricultural University, 100083, Beijing, China
| | - Chao Yuan
- College of Information and Electrical Engineering, China Agricultural University, 100083, Beijing, China
| | - Yifeng Zhao
- College of Information and Electrical Engineering, China Agricultural University, 100083, Beijing, China
| | - Liming Yang
- College of Science, China Agricultural University, 100083, Beijing, China.
| |
Collapse
|
11
|
Giorgio J, Jagust WJ, Baker S, Landau SM, Tino P, Kourtzi Z. A robust and interpretable machine learning approach using multimodal biological data to predict future pathological tau accumulation. Nat Commun 2022; 13:1887. [PMID: 35393421 PMCID: PMC8989879 DOI: 10.1038/s41467-022-28795-7] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2020] [Accepted: 02/11/2022] [Indexed: 01/21/2023] Open
Abstract
The early stages of Alzheimer’s disease (AD) involve interactions between multiple pathophysiological processes. Although these processes are well studied, we still lack robust tools to predict individualised trajectories of disease progression. Here, we employ a robust and interpretable machine learning approach to combine multimodal biological data and predict future pathological tau accumulation. In particular, we use machine learning to quantify interactions between key pathological markers (β-amyloid, medial temporal lobe atrophy, tau and APOE 4) at mildly impaired and asymptomatic stages of AD. Using baseline non-tau markers we derive a prognostic index that: (a) stratifies patients based on future pathological tau accumulation, (b) predicts individualised regional future rate of tau accumulation, and (c) translates predictions from deep phenotyping patient cohorts to cognitively normal individuals. Our results propose a robust approach for fine scale stratification and prognostication with translation impact for clinical trial design targeting the earliest stages of AD. The authors present a machine learning approach that combines baseline multimodal data to accurately predict individualised trajectories of future pathological tau accumulation at asymptomatic and mildly impaired stages of Alzheimer’s disease.
Collapse
Affiliation(s)
- Joseph Giorgio
- Department of Psychology, University of Cambridge, Cambridge, UK
| | - William J Jagust
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA.,Molecular Biophysics & Integrated Bioimaging, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Suzanne Baker
- Molecular Biophysics & Integrated Bioimaging, Lawrence Berkeley National Laboratory, Berkeley, CA, USA
| | - Susan M Landau
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA, USA
| | - Peter Tino
- School of Computer Science, University of Birmingham, Birmingham, UK
| | - Zoe Kourtzi
- Department of Psychology, University of Cambridge, Cambridge, UK.
| | | |
Collapse
|
12
|
|
13
|
Artelt A, Hammer B. Efficient computation of counterfactual explanations and counterfactual metrics of prototype-based classifiers. Neurocomputing 2022. [DOI: 10.1016/j.neucom.2021.04.129] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
14
|
Abstract
AbstractPrototype-based models like the Generalized Learning Vector Quantization (GLVQ) belong to the class of interpretable classifiers. Moreover, quantum-inspired methods get more and more into focus in machine learning due to its potential efficient computing. Further, its interesting mathematical perspectives offer new ideas for alternative learning scenarios. This paper proposes a quantum computing-inspired variant of the prototype-based GLVQ for classification learning. We start considering kernelized GLVQ with real- and complex-valued kernels and their respective feature mapping. Thereafter, we explain how quantum space ideas could be integrated into a GLVQ using quantum bit vector space in the quantum state space $${\mathcal {H}}^{n}$$
H
n
and show the relations to kernelized GLVQ. In particular, we explain the related feature mapping of data into the quantum state space $${\mathcal {H}}^{n}$$
H
n
. A key feature for this approach is that $${\mathcal {H}}^{n}$$
H
n
is an Hilbert space with particular inner product properties, which finally restrict the prototype adaptations to be unitary transformations. The resulting approach is denoted as Qu-GLVQ. We provide the mathematical framework and give exemplary numerical results.
Collapse
|
15
|
Bohnsack KS, Kaden M, Abel J, Saralajew S, Villmann T. The Resolved Mutual Information Function as a Structural Fingerprint of Biomolecular Sequences for Interpretable Machine Learning Classifiers. ENTROPY (BASEL, SWITZERLAND) 2021; 23:1357. [PMID: 34682081 PMCID: PMC8534762 DOI: 10.3390/e23101357] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 09/19/2021] [Revised: 10/11/2021] [Accepted: 10/14/2021] [Indexed: 11/16/2022]
Abstract
In the present article we propose the application of variants of the mutual information function as characteristic fingerprints of biomolecular sequences for classification analysis. In particular, we consider the resolved mutual information functions based on Shannon-, Rényi-, and Tsallis-entropy. In combination with interpretable machine learning classifier models based on generalized learning vector quantization, a powerful methodology for sequence classification is achieved which allows substantial knowledge extraction in addition to the high classification ability due to the model-inherent robustness. Any potential (slightly) inferior performance of the used classifier is compensated by the additional knowledge provided by interpretable models. This knowledge may assist the user in the analysis and understanding of the used data and considered task. After theoretical justification of the concepts, we demonstrate the approach for various example data sets covering different areas in biomolecular sequence analysis.
Collapse
Affiliation(s)
- Katrin Sophie Bohnsack
- Saxon Institute for Computational Intelligence and Machine Learning, University of Applied Sciences Mittweida, 09648 Mittweida, Germany; (M.K.); (J.A.)
| | - Marika Kaden
- Saxon Institute for Computational Intelligence and Machine Learning, University of Applied Sciences Mittweida, 09648 Mittweida, Germany; (M.K.); (J.A.)
| | - Julia Abel
- Saxon Institute for Computational Intelligence and Machine Learning, University of Applied Sciences Mittweida, 09648 Mittweida, Germany; (M.K.); (J.A.)
| | - Sascha Saralajew
- Bosch Center for Artificial Intelligence, 71272 Renningen, Germany;
| | - Thomas Villmann
- Saxon Institute for Computational Intelligence and Machine Learning, University of Applied Sciences Mittweida, 09648 Mittweida, Germany; (M.K.); (J.A.)
| |
Collapse
|
16
|
van der Stouwe AMM, Tuitert I, Giotis I, Calon J, Gannamani R, Dalenberg JR, van der Veen S, Klamer MR, Telea AC, Tijssen MAJ. Next move in movement disorders (NEMO): developing a computer-aided classification tool for hyperkinetic movement disorders. BMJ Open 2021; 11:e055068. [PMID: 34635535 PMCID: PMC8506849 DOI: 10.1136/bmjopen-2021-055068] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/06/2021] [Accepted: 09/28/2021] [Indexed: 11/05/2022] Open
Abstract
INTRODUCTION Our aim is to develop a novel approach to hyperkinetic movement disorder classification, that combines clinical information, electromyography, accelerometry and video in a computer-aided classification tool. We see this as the next step towards rapid and accurate phenotype classification, the cornerstone of both the diagnostic and treatment process. METHODS AND ANALYSIS The Next Move in Movement Disorders (NEMO) study is a cross-sectional study at Expertise Centre Movement Disorders Groningen, University Medical Centre Groningen. It comprises patients with single and mixed phenotype movement disorders. Single phenotype groups will first include dystonia, myoclonus and tremor, and then chorea, tics, ataxia and spasticity. Mixed phenotypes are myoclonus-dystonia, dystonic tremor, myoclonus ataxia and jerky/tremulous functional movement disorders. Groups will contain 20 patients, or 40 healthy participants. The gold standard for inclusion consists of interobserver agreement on the phenotype among three independent clinical experts. Electromyography, accelerometry and three-dimensional video data will be recorded during performance of a set of movement tasks, chosen by a team of specialists to elicit movement disorders. These data will serve as input for the machine learning algorithm. Labels for supervised learning are provided by the expert-based classification, allowing the algorithm to learn to predict what the output label should be when given new input data. Methods using manually engineered features based on existing clinical knowledge will be used, as well as deep learning methods which can detect relevant and possibly new features. Finally, we will employ visual analytics to visualise how the classification algorithm arrives at its decision. ETHICS AND DISSEMINATION Ethical approval has been obtained from the relevant local ethics committee. The NEMO study is designed to pioneer the application of machine learning of movement disorders. We expect to publish articles in multiple related fields of research and patients will be informed of important results via patient associations and press releases.
Collapse
Affiliation(s)
- A M Madelein van der Stouwe
- Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, The Netherlands
- Expertise Centre Movement Disorders Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Inge Tuitert
- Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, The Netherlands
- Expertise Centre Movement Disorders Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Ioannis Giotis
- ZiuZ Visual Intelligence BV, Gorredijk, Groningen, The Netherlands
| | - Joost Calon
- ZiuZ Visual Intelligence BV, Gorredijk, Groningen, The Netherlands
| | - Rahul Gannamani
- Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, The Netherlands
- Expertise Centre Movement Disorders Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Jelle R Dalenberg
- Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, The Netherlands
- Expertise Centre Movement Disorders Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Sterre van der Veen
- Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, The Netherlands
- Expertise Centre Movement Disorders Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Marrit R Klamer
- Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, The Netherlands
- Expertise Centre Movement Disorders Groningen, University Medical Center Groningen, Groningen, The Netherlands
- ZiuZ Visual Intelligence BV, Gorredijk, Groningen, The Netherlands
| | - Alex C Telea
- Department of Information and Computing Sciences, University of Utrecht, Utrecht, The Netherlands
| | - Marina A J Tijssen
- Department of Neurology, University Medical Centre Groningen, University of Groningen, Groningen, The Netherlands
- Expertise Centre Movement Disorders Groningen, University Medical Center Groningen, Groningen, The Netherlands
| |
Collapse
|
17
|
Zoghlami F, Kaden M, Villmann T, Schneider G, Heinrich H. AI-Based Multi Sensor Fusion for Smart Decision Making: A Bi-Functional System for Single Sensor Evaluation in a Classification Task. SENSORS 2021; 21:s21134405. [PMID: 34199090 PMCID: PMC8271452 DOI: 10.3390/s21134405] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/21/2021] [Revised: 06/18/2021] [Accepted: 06/23/2021] [Indexed: 11/16/2022]
Abstract
Sensor fusion has gained a great deal of attention in recent years. It is used as an application tool in many different fields, especially the semiconductor, automotive, and medical industries. However, this field of research, regardless of the field of application, still presents different challenges concerning the choice of the sensors to be combined and the fusion architecture to be developed. To decrease application costs and engineering efforts, it is very important to analyze the sensors' data beforehand once the application target is defined. This pre-analysis is a basic step to establish a working environment with fewer misclassification cases and high safety. One promising approach to do so is to analyze the system using deep neural networks. The disadvantages of this approach are mainly the required huge storage capacity, the big training effort, and that these networks are difficult to interpret. In this paper, we focus on developing a smart and interpretable bi-functional artificial intelligence (AI) system, which has to discriminate the combined data regarding predefined classes. Furthermore, the system can evaluate the single source signals used in the classification task. The evaluation here covers each sensor contribution and robustness. More precisely, we train a smart and interpretable prototype-based neural network, which learns automatically to weight the influence of the sensors for the classification decision. Moreover, the prototype-based classifier is equipped with a reject option to measure classification certainty. To validate our approach's efficiency, we refer to different industrial sensor fusion applications.
Collapse
Affiliation(s)
- Feryel Zoghlami
- Automation, Maintenance and Factory Integration, Infineon Technologies Dresden GmbH & Co. KG, 01099 Dresden, Germany; (G.S.); (H.H.)
- Correspondence:
| | - Marika Kaden
- Computational Intelligence, University of Applied Sciences Mittweida, 09648 Mittweda, Germany; (M.K.); (T.V.)
| | - Thomas Villmann
- Computational Intelligence, University of Applied Sciences Mittweida, 09648 Mittweda, Germany; (M.K.); (T.V.)
| | - Germar Schneider
- Automation, Maintenance and Factory Integration, Infineon Technologies Dresden GmbH & Co. KG, 01099 Dresden, Germany; (G.S.); (H.H.)
| | - Harald Heinrich
- Automation, Maintenance and Factory Integration, Infineon Technologies Dresden GmbH & Co. KG, 01099 Dresden, Germany; (G.S.); (H.H.)
| |
Collapse
|
18
|
Tang F, Feng H, Tino P, Si B, Ji D. Probabilistic learning vector quantization on manifold of symmetric positive definite matrices. Neural Netw 2021; 142:105-118. [PMID: 33984734 DOI: 10.1016/j.neunet.2021.04.024] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2020] [Revised: 04/07/2021] [Accepted: 04/20/2021] [Indexed: 10/21/2022]
Abstract
In this paper, we develop a new classification method for manifold-valued data in the framework of probabilistic learning vector quantization. In many classification scenarios, the data can be naturally represented by symmetric positive definite matrices, which are inherently points that live on a curved Riemannian manifold. Due to the non-Euclidean geometry of Riemannian manifolds, traditional Euclidean machine learning algorithms yield poor results on such data. In this paper, we generalize the probabilistic learning vector quantization algorithm for data points living on the manifold of symmetric positive definite matrices equipped with Riemannian natural metric (affine-invariant metric). By exploiting the induced Riemannian distance, we derive the probabilistic learning Riemannian space quantization algorithm, obtaining the learning rule through Riemannian gradient descent. Empirical investigations on synthetic data, image data , and motor imagery electroencephalogram (EEG) data demonstrate the superior performance of the proposed method.
Collapse
Affiliation(s)
- Fengzhen Tang
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China; Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China.
| | - Haifeng Feng
- State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, 110016, China; Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, 110169, China; University of Chinese Academy of Sciences, Beijing, 100049, China.
| | - Peter Tino
- School of computer Science, University of Birmingham, Birmingham, B15 2TT, UK.
| | - Bailu Si
- School of Systems Science, Beijing Normal University, Beijing, 100875, China.
| | - Daxiong Ji
- Institute of Marine Electronics and Intelligent Systems, Ocean College, Zhejiang University, The Key Laboratory of Ocean Observation-Imaging Testbed of Zhejiang Province, The Engineering Research Center of Oceanic Sensing Technology and Equipment, Ministry of Education, Zhoushan, 316021, China.
| |
Collapse
|
19
|
Kaden M, Bohnsack KS, Weber M, Kudła M, Gutowska K, Blazewicz J, Villmann T. Learning vector quantization as an interpretable classifier for the detection of SARS-CoV-2 types based on their RNA sequences. Neural Comput Appl 2021; 34:67-78. [PMID: 33935376 PMCID: PMC8076884 DOI: 10.1007/s00521-021-06018-2] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/13/2020] [Accepted: 04/07/2021] [Indexed: 02/06/2023]
Abstract
We present an approach to discriminate SARS-CoV-2 virus types based on their RNA sequence descriptions avoiding a sequence alignment. For that purpose, sequences are preprocessed by feature extraction and the resulting feature vectors are analyzed by prototype-based classification to remain interpretable. In particular, we propose to use variants of learning vector quantization (LVQ) based on dissimilarity measures for RNA sequence data. The respective matrix LVQ provides additional knowledge about the classification decisions like discriminant feature correlations and, additionally, can be equipped with easy to realize reject options for uncertain data. Those options provide self-controlled evidence, i.e., the model refuses to make a classification decision if the model evidence for the presented data is not sufficient. This model is first trained using a GISAID dataset with given virus types detected according to the molecular differences in coronavirus populations by phylogenetic tree clustering. In a second step, we apply the trained model to another but unlabeled SARS-CoV-2 virus dataset. For these data, we can either assign a virus type to the sequences or reject atypical samples. Those rejected sequences allow to speculate about new virus types with respect to nucleotide base mutations in the viral sequences. Moreover, this rejection analysis improves model robustness. Last but not least, the presented approach has lower computational complexity compared to methods based on (multiple) sequence alignment. SUPPLEMENTARY INFORMATION The online version contains supplementary material available at 10.1007/s00521-021-06018-2.
Collapse
Affiliation(s)
- Marika Kaden
- University of Applied Sciences Mittweida, Technikumplatz 17, 09648 Mittweida, Germany
- Saxon Institute for Computational Intelligence and Machine Learning, Technikumplatz 17, 09648 Mittweida, Germany
| | - Katrin Sophie Bohnsack
- University of Applied Sciences Mittweida, Technikumplatz 17, 09648 Mittweida, Germany
- Saxon Institute for Computational Intelligence and Machine Learning, Technikumplatz 17, 09648 Mittweida, Germany
| | - Mirko Weber
- University of Applied Sciences Mittweida, Technikumplatz 17, 09648 Mittweida, Germany
- Saxon Institute for Computational Intelligence and Machine Learning, Technikumplatz 17, 09648 Mittweida, Germany
| | - Mateusz Kudła
- University of Applied Sciences Mittweida, Technikumplatz 17, 09648 Mittweida, Germany
- Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland
| | - Kaja Gutowska
- Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland
- Institute of Bioorganic Chemistry, Polish Academy of Sciences, Noskowskiego 12/14, 61-704 Poznan, Poland
- European Centre for Bioinformatics and Genomics, Piotrowo 2, 60-965 Poznan, Poland
| | - Jacek Blazewicz
- Institute of Computing Science, Poznan University of Technology, Piotrowo 2, 60-965 Poznan, Poland
- Institute of Bioorganic Chemistry, Polish Academy of Sciences, Noskowskiego 12/14, 61-704 Poznan, Poland
- European Centre for Bioinformatics and Genomics, Piotrowo 2, 60-965 Poznan, Poland
| | - Thomas Villmann
- University of Applied Sciences Mittweida, Technikumplatz 17, 09648 Mittweida, Germany
- Saxon Institute for Computational Intelligence and Machine Learning, Technikumplatz 17, 09648 Mittweida, Germany
| |
Collapse
|
20
|
Tang F, Fan M, Tino P. Generalized Learning Riemannian Space Quantization: A Case Study on Riemannian Manifold of SPD Matrices. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2021; 32:281-292. [PMID: 32203035 DOI: 10.1109/tnnls.2020.2978514] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Learning vector quantization (LVQ) is a simple and efficient classification method, enjoying great popularity. However, in many classification scenarios, such as electroencephalogram (EEG) classification, the input features are represented by symmetric positive-definite (SPD) matrices that live in a curved manifold rather than vectors that live in the flat Euclidean space. In this article, we propose a new classification method for data points that live in the curved Riemannian manifolds in the framework of LVQ. The proposed method alters generalized LVQ (GLVQ) with the Euclidean distance to the one operating under the appropriate Riemannian metric. We instantiate the proposed method for the Riemannian manifold of SPD matrices equipped with the Riemannian natural metric. Empirical investigations on synthetic data and real-world motor imagery EEG data demonstrate that the performance of the proposed generalized learning Riemannian space quantization can significantly outperform the Euclidean GLVQ, generalized relevance LVQ (GRLVQ), and generalized matrix LVQ (GMLVQ). The proposed method also shows competitive performance to the state-of-the-art methods on the EEG classification of motor imagery tasks.
Collapse
|
21
|
Abstract
AbstractIn this contribution, we consider the classification of time series and similar functional data which can be represented in complex Fourier and wavelet coefficient space. We apply versions of learning vector quantization (LVQ) which are suitable for complex-valued data, based on the so-called Wirtinger calculus. It allows for the formulation of gradient-based update rules in the framework of cost-function-based generalized matrix relevance LVQ (GMLVQ). Alternatively, we consider the concatenation of real and imaginary parts of Fourier coefficients in a real-valued feature vector and the classification of time-domain representations by means of conventional GMLVQ. In addition, we consider the application of the method in combination with wavelet-space features to heartbeat classification.
Collapse
|
22
|
van Veen R, Gurvits V, Kogan RV, Meles SK, de Vries GJ, Renken RJ, Rodriguez-Oroz MC, Rodriguez-Rojas R, Arnaldi D, Raffa S, de Jong BM, Leenders KL, Biehl M. An application of generalized matrix learning vector quantization in neuroimaging. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2020; 197:105708. [PMID: 32977181 DOI: 10.1016/j.cmpb.2020.105708] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/27/2020] [Accepted: 08/08/2020] [Indexed: 06/11/2023]
Abstract
BACKGROUND AND OBJECTIVE Neurodegenerative diseases like Parkinson's disease often take several years before they can be diagnosed reliably based on clinical grounds. Imaging techniques such as MRI are used to detect anatomical (structural) pathological changes. However, these kinds of changes are usually seen only late in the development. The measurement of functional brain activity by means of [18F]fluorodeoxyglucose positron emission tomography (FDG-PET) can provide useful information, but its interpretation is more difficult. The scaled sub-profile model principal component analysis (SSM/PCA) was shown to provide more useful information than other statistical techniques. Our objective is to improve the performance further by combining SSM/PCA and prototype-based generalized matrix learning vector quantization (GMLVQ). METHODS We apply a combination of SSM/PCA and GMLVQ as a classifier. In order to demonstrate the combination's validity, we analyze FDG-PET data of Parkinson's disease (PD) patients collected at three different neuroimaging centers in Europe. We determine the diagnostic performance by performing a ten times repeated ten fold cross validation. Additionally, discriminant visualizations of the data are included. The prototypes and relevance of GMLVQ are transformed back to the original voxel space by exploiting the linearity of SSM/PCA. The resulting prototypes and relevance profiles have then been assessed by three neurologists. RESULTS One important finding is that discriminative visualization can help to identify disease-related properties as well as differences which are due to center-specific factors. Secondly, the neurologist assessed the interpretability of the method and confirmed that prototypes are similar to known activity profiles of PD patients. CONCLUSION We have shown that the presented combination of SSM/PCA and GMLVQ can provide useful means to assess and better understand characteristic differences in FDG-PET data from PD patients and HCs. Based on the assessments by medical experts and the results of our computational analysis we conclude that the first steps towards a diagnostic support system have been taken successfully.
Collapse
Affiliation(s)
- Rick van Veen
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, the Netherlands.
| | - Vita Gurvits
- Department of Nuclear Medicine & Molecular Imaging, University Medical Center Groningen, the Netherlands
| | - Rosalie V Kogan
- Department of Nuclear Medicine & Molecular Imaging, University Medical Center Groningen, the Netherlands
| | - Sanne K Meles
- Department of Neurology, University Medical Centre Groningen, the Netherlands
| | | | - Remco J Renken
- Department of Biomedical Sciences of Cells & Systems, Cognitive Neuroscience Center, University Medical Center Groningen, the Netherlands
| | | | | | - Dario Arnaldi
- Department of Neuroscience, University of Genoa, Italy; Neurology Clinic, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Stefano Raffa
- Department of Health Sciences, University of Genoa, Italy; Nuclear Medicine Unit, IRCCS Ospedale Policlinico San Martino, Genoa, Italy
| | - Bauke M de Jong
- Department of Neurology, University Medical Centre Groningen, the Netherlands
| | - Klaus L Leenders
- Department of Nuclear Medicine & Molecular Imaging, University Medical Center Groningen, the Netherlands
| | - Michael Biehl
- Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, the Netherlands
| |
Collapse
|
23
|
Brinkrolf J, Hammer B. Time integration and reject options for probabilistic output of pairwise LVQ. Neural Comput Appl 2020. [DOI: 10.1007/s00521-018-03966-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
24
|
Ravichandran J, Kaden M, Saralajew S, Villmann T. Variants of DropConnect in Learning vector quantization networks for evaluation of classification stability. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2019.12.131] [Citation(s) in RCA: 8] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
25
|
Shen YY, Zhang YM, Zhang XY, Liu CL. Online semi-supervised learning with learning vector quantization. Neurocomputing 2020. [DOI: 10.1016/j.neucom.2020.03.025] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
|
26
|
Moolla A, de Boer J, Pavlov D, Amin A, Taylor A, Gilligan L, Hughes B, Ryan J, Barnes E, Hassan‐Smith Z, Grove J, Aithal GP, Verrijken A, Francque S, Van Gaal L, Armstrong MJ, Newsome PN, Cobbold JF, Arlt W, Biehl M, Tomlinson JW. Accurate non-invasive diagnosis and staging of non-alcoholic fatty liver disease using the urinary steroid metabolome. Aliment Pharmacol Ther 2020; 51:1188-1197. [PMID: 32298002 PMCID: PMC8150165 DOI: 10.1111/apt.15710] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/26/2019] [Revised: 12/17/2019] [Accepted: 03/15/2020] [Indexed: 12/22/2022]
Abstract
BACKGROUND The development of accurate, non-invasive markers to diagnose and stage non-alcoholic fatty liver disease (NAFLD) is critical to reduce the need for an invasive liver biopsy and to identify patients who are at the highest risk of hepatic and cardio-metabolic complications. Disruption of steroid hormone metabolic pathways has been described in patients with NAFLD. AIM(S) To assess the hypothesis that assessment of the urinary steroid metabolome may provide a novel, non-invasive biomarker strategy to stage NAFLD. METHODS We analysed the urinary steroid metabolome in 275 subjects (121 with biopsy-proven NAFLD, 48 with alcohol-related cirrhosis and 106 controls), using gas chromatography-mass spectrometry (GC-MS) coupled with machine learning-based Generalised Matrix Learning Vector Quantisation (GMLVQ) analysis. RESULTS Generalised Matrix Learning Vector Quantisation analysis achieved excellent separation of early (F0-F2) from advanced (F3-F4) fibrosis (AUC receiver operating characteristics [ROC]: 0.92 [0.91-0.94]). Furthermore, there was near perfect separation of controls from patients with advanced fibrotic NAFLD (AUC ROC = 0.99 [0.98-0.99]) and from those with NAFLD cirrhosis (AUC ROC = 1.0 [1.0-1.0]). This approach was also able to distinguish patients with NAFLD cirrhosis from those with alcohol-related cirrhosis (AUC ROC = 0.83 [0.81-0.85]). CONCLUSIONS Unbiased GMLVQ analysis of the urinary steroid metabolome offers excellent potential as a non-invasive biomarker approach to stage NAFLD fibrosis as well as to screen for NAFLD. A highly sensitive and specific urinary biomarker is likely to have clinical utility both in secondary care and in the broader general population within primary care and could significantly decrease the need for liver biopsy.
Collapse
|
27
|
Large-scale predictive modeling and analytics through regression queries in data management systems. INTERNATIONAL JOURNAL OF DATA SCIENCE AND ANALYTICS 2020. [DOI: 10.1007/s41060-018-0163-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/27/2022]
|
28
|
Giorgio J, Landau SM, Jagust WJ, Tino P, Kourtzi Z. Modelling prognostic trajectories of cognitive decline due to Alzheimer's disease. Neuroimage Clin 2020; 26:102199. [PMID: 32106025 PMCID: PMC7044529 DOI: 10.1016/j.nicl.2020.102199] [Citation(s) in RCA: 37] [Impact Index Per Article: 9.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2019] [Revised: 01/24/2020] [Accepted: 01/25/2020] [Indexed: 01/13/2023]
Abstract
Alzheimer's disease (AD) is characterised by a dynamic process of neurocognitive changes from normal cognition to mild cognitive impairment (MCI) and progression to dementia. However, not all individuals with MCI develop dementia. Predicting whether individuals with MCI will decline (i.e. progressive MCI) or remain stable (i.e. stable MCI) is impeded by patient heterogeneity due to comorbidities that may lead to MCI diagnosis without progression to AD. Despite the importance of early diagnosis of AD for prognosis and personalised interventions, we still lack robust tools for predicting individual progression to dementia. Here, we propose a novel trajectory modelling approach based on metric learning (Generalised Metric Learning Vector Quantization) that mines multimodal data from MCI patients in the Alzheimer's disease Neuroimaging Initiative (ADNI) cohort to derive individualised prognostic scores of cognitive decline due to AD. We develop an integrated biomarker generation- using partial least squares regression- and classification methodology that extends beyond binary patient classification into discrete subgroups (i.e. stable vs. progressive MCI), determines individual profiles from baseline (i.e. cognitive or biological) data and predicts individual cognitive trajectories (i.e. change in memory scores from baseline). We demonstrate that a metric learning model trained on baseline cognitive data (memory, executive function, affective measurements) discriminates stable vs. progressive MCI individuals with high accuracy (81.4%), revealing an interaction between cognitive (memory, executive functions) and affective scores that may relate to MCI comorbidity (e.g. affective disturbance). Training the model to perform the same binary classification on biological data (mean cortical β-amyloid burden, grey matter density, APOE 4) results in similar prediction accuracy (81.9%). Extending beyond binary classifications, we develop and implement a trajectory modelling approach that shows significantly better performance in predicting individualised rate of future cognitive decline (i.e. change in memory scores from baseline), when the metric learning model is trained with biological (r = -0.68) compared to cognitive (r = -0.4) data. Our trajectory modelling approach reveals interpretable and interoperable markers of progression to AD and has strong potential to guide effective stratification of individuals based on prognostic disease trajectories, reducing MCI patient misclassification, that is critical for clinical practice and discovery of personalised interventions.
Collapse
Affiliation(s)
- Joseph Giorgio
- Department of Psychology, University of Cambridge, Cambridge, United Kingdom
| | - Susan M Landau
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA USA
| | - William J Jagust
- Helen Wills Neuroscience Institute, University of California, Berkeley, CA USA
| | - Peter Tino
- School of Computer Science, University of Birmingham, Birmingham, United Kingdom
| | - Zoe Kourtzi
- Department of Psychology, University of Cambridge, Cambridge, United Kingdom.
| |
Collapse
|
29
|
Duan Y, Lu J, Zheng W, Zhou J. Deep Adversarial Metric Learning. IEEE TRANSACTIONS ON IMAGE PROCESSING : A PUBLICATION OF THE IEEE SIGNAL PROCESSING SOCIETY 2019; 29:2037-2051. [PMID: 31670672 DOI: 10.1109/tip.2019.2948472] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/10/2023]
Abstract
Learning an effective distance measurement between sample pairs plays an important role in visual analysis, where the training procedure largely relies on hard negative samples. However, hard negative samples usually account for the tiny minority in the training set, which may fail to fully describe the data distribution close to the decision boundary. In this paper, we present a deep adversarial metric learning (DAML) framework to generate synthetic hard negatives from the original negative samples, which is widely applicable to existing supervised deep metric learning algorithms. Different from existing sampling strategies which simply ignore numerous easy negatives, our DAML aim to exploit them by generating synthetic hard negatives adversarial to the learned metric as complements. We simultaneously train the feature embedding and hard negative generator in an adversarial manner, so that adequate and targeted synthetic hard negatives are created to learn more precise distance metrics. As a single transformation may not be powerful enough to describe the global input space under the attack of the hard negative generator, we further propose a deep adversarial multi-metric learning (DAMML) method by learning multiple local transformations for more complete description. We simultaneously exploit the collaborative and competitive relationships among multiple metrics, where the metrics display unity against the generator for effective distance measurement as well as compete for more training data through a metric discriminator to avoid overlapping. Extensive experimental results on five benchmark datasets show that our DAML and DAMML effectively boost the performance of existing deep metric learning approaches through adversarial learning.
Collapse
|
30
|
Melchert F, Bani G, Seiffert U, Biehl M. Adaptive basis functions for prototype-based classification of functional data. Neural Comput Appl 2019. [DOI: 10.1007/s00521-019-04299-2] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
Abstract
AbstractWe present a framework for distance-based classification of functional data. We consider the analysis of labeled spectral data and time series by means of generalized matrix relevance learning vector quantization (GMLVQ) as an example. To take advantage of the functional nature, a functional expansion of the input data is considered. Instead of using a predefined set of basis functions for the expansion, a more flexible scheme of an adaptive functional basis is employed. GMLVQ is applied on the resulting functional parameters to solve the classification task. For comparison of the classification, a GMLVQ system is also applied to the raw input data, as well as on data expanded by a different predefined functional basis. Computer experiments show that the methods offer potential to improve classification performance significantly. Furthermore, the analysis of the adapted set of basis functions give further insights into the data structure and yields an option for a drastic reduction of dimensionality.
Collapse
|
31
|
|
32
|
|
33
|
Prahm C, Schulz A, Paaben B, Schoisswohl J, Kaniusas E, Dorffner G, Hammer B, Aszmann O. Counteracting Electrode Shifts in Upper-Limb Prosthesis Control via Transfer Learning. IEEE Trans Neural Syst Rehabil Eng 2019; 27:956-962. [PMID: 30908234 DOI: 10.1109/tnsre.2019.2907200] [Citation(s) in RCA: 21] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022]
Abstract
Research on machine learning approaches for upper-limb prosthesis control has shown impressive progress. However, translating these results from the lab to patient's everyday lives remains a challenge because advanced control schemes tend to break down under everyday disturbances, such as electrode shifts. Recently, it has been suggested to apply adaptive transfer learning to counteract electrode shifts using as little newly recorded training data as possible. In this paper, we present a novel, simple version of transfer learning and provide the first user study demonstrating the effectiveness of transfer learning to counteract electrode shifts. For this purpose, we introduce the novel Box and Beans test to evaluate prosthesis proficiency and compare user performance with an initial simple pattern recognition system, the system under electrode shifts, and the system after transfer learning. Our results show that transfer learning could significantly alleviate the impact of electrode shifts on user performance in the Box and Beans test.
Collapse
|
34
|
Mohamed Shakeel P, Baskar S, Sarma Dhulipala VR, Mishra S, Jaber MM. Maintaining Security and Privacy in Health Care System Using Learning Based Deep-Q-Networks. J Med Syst 2018; 42:186. [PMID: 30171378 DOI: 10.1007/s10916-018-1045-z] [Citation(s) in RCA: 131] [Impact Index Per Article: 21.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/18/2018] [Accepted: 08/23/2018] [Indexed: 11/28/2022]
Abstract
In the recent past, Internet of Things (IoT) plays a significant role in different applications such as health care, industrial sector, defense and research etc.… It provides effective framework in maintaining the security, privacy and reliability of the information in internet environment. Among various applications as mentioned health care place a major role, because security, privacy and reliability of the medical information is maintained in an effective way. Even though, IoT provides the effective protocols for maintaining the information, several intermediate attacks and intruders trying to access the health information which in turn reduce the privacy, security and reliability of the entire health care system in internet environment. As a result and to solve the issues, in this research Learning based Deep-Q-Networks has been introduced for reducing the malware attacks while managing the health information. This method examines the medical information in different layers according to the Q-learning concept which helps to minimize the intermediate attacks with less complexity. The efficiency of the system has been evaluated with the help of experimental results and discussions.
Collapse
Affiliation(s)
- P Mohamed Shakeel
- Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka, Durian Tunggal, Malaysia.
| | - S Baskar
- Department of Electronics and Communication Engineering, Karpagam Academy of Higher Education, Coimbatore, India
| | | | - Sukumar Mishra
- Department of Electrical Engineering, Indian Institute of Technology, New Delhi, India
| | | |
Collapse
|
35
|
Paaßen B, Schulz A, Hahne J, Hammer B. Expectation maximization transfer learning and its application for bionic hand prostheses. Neurocomputing 2018. [DOI: 10.1016/j.neucom.2017.11.072] [Citation(s) in RCA: 10] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
36
|
|
37
|
|
38
|
Ural B. A Computer-Based Brain Tumor Detection Approach with Advanced Image Processing and Probabilistic Neural Network Methods. J Med Biol Eng 2017. [DOI: 10.1007/s40846-017-0353-y] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
39
|
What you see is what you can change: Human-centered machine learning by interactive visualization. Neurocomputing 2017. [DOI: 10.1016/j.neucom.2017.01.105] [Citation(s) in RCA: 83] [Impact Index Per Article: 11.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/24/2022]
|
40
|
DSouza AM, Abidin AZ, Leistritz L, Wismüller A. Identifying HIV Associated Neurocognitive Disorder Using Large-Scale Granger Causality Analysis on Resting-State Functional MRI. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2017; 10133. [PMID: 29167591 DOI: 10.1117/12.2254690] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
We investigate the applicability of large-scale Granger Causality (lsGC) for extracting a measure of multivariate information flow between pairs of regional brain activities from resting-state functional MRI (fMRI) and test the effectiveness of these measures for predicting a disease state. Such pairwise multivariate measures of interaction provide high-dimensional representations of connectivity profiles for each subject and are used in a machine learning task to distinguish between healthy controls and individuals presenting with symptoms of HIV Associated Neurocognitive Disorder (HAND). Cognitive impairment in several domains can occur as a result of HIV infection of the central nervous system. The current paradigm for assessing such impairment is through neuropsychological testing. With fMRI data analysis, we aim at non-invasively capturing differences in brain connectivity patterns between healthy subjects and subjects presenting with symptoms of HAND. To classify the extracted interaction patterns among brain regions, we use a prototype-based learning algorithm called Generalized Matrix Learning Vector Quantization (GMLVQ). Our approach to characterize connectivity using lsGC followed by GMLVQ for subsequent classification yields good prediction results with an accuracy of 87% and an area under the ROC curve (AUC) of up to 0.90. We obtain a statistically significant improvement (p<0.01) over a conventional Granger causality approach (accuracy = 0.76, AUC = 0.74). High accuracy and AUC values using our multivariate method to connectivity analysis suggests that our approach is able to better capture changes in interaction patterns between different brain regions when compared to conventional Granger causality analysis known from the literature.
Collapse
Affiliation(s)
- Adora M DSouza
- Department of Electrical Engineering, University of Rochester, NY, USA
| | - Anas Z Abidin
- Department of Biomedical Engineering, University of Rochester, NY, USA
| | - Lutz Leistritz
- Bernstein Group for Computational Neuroscience Jena, Institute of Medical Statistics, Computer Science, and Documentation, Jena University Hospital, Friedrich Schiller University Jena, Germany
| | - Axel Wismüller
- Department of Electrical Engineering, University of Rochester, NY, USA.,Department of Biomedical Engineering, University of Rochester, NY, USA.,Department of Imaging Sciences, University of Rochester, NY, USA.,Faculty of Medicine and Institute of Clinical Radiology, Ludwig Maximilian University, Germany
| |
Collapse
|
41
|
Tang F, Tiňo P. Ordinal regression based on learning vector quantization. Neural Netw 2017; 93:76-88. [PMID: 28552507 DOI: 10.1016/j.neunet.2017.05.006] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2015] [Revised: 04/27/2017] [Accepted: 05/04/2017] [Indexed: 11/16/2022]
Abstract
Recently, ordinal regression, which predicts categories of ordinal scale, has received considerable attention. In this paper, we propose a new approach to solve ordinal regression problems within the learning vector quantization framework. It extends the previous approach termed ordinal generalized matrix learning vector quantization with a more suitable and natural cost function, leading to more intuitive parameter update rules. Moreover, in our approach the bandwidth of the prototype weights is automatically adapted. Empirical investigation on a number of datasets reveals that overall the proposed approach tends to have superior out-of-sample performance, when compared to alternative ordinal regression methods.
Collapse
Affiliation(s)
- Fengzhen Tang
- Shenyang Institute of Automation, Chinese Academy of Sciences, No.114, Nanta Street, Shenyang, Liaoning Province, 110016, China; School of Computer Science, The University of Birmingham, Edgbaston, Birmingham B15 2TT, UK.
| | - Peter Tiňo
- School of Computer Science, The University of Birmingham, Edgbaston, Birmingham B15 2TT, UK.
| |
Collapse
|
42
|
DSouza AM, Abidin AZ, Wismüller A. Investigating Changes in Resting-State Connectivity from Functional MRI Data in Patients with HIV Associated Neurocognitive Disorder Using MCA and Machine Learning. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2017; 10137. [PMID: 29170578 DOI: 10.1117/12.2254189] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
Infection of the brain by the Human Immunodeficiency Virus (HIV) causes irreversible damage to the synaptic connections resulting in cognitive impairment. Patients with HIV infection, showing signs of impairment in multiple cognitive domains, as assessed by neuropsychological testing, are said to exhibit symptoms of HIV Associated Neurocognitive Disorder (HAND). In this study, we use resting-state functional MRI (fMRI) data to distinguish between healthy subjects and subjects with symptoms of HAND. To this end, we first establish a measure of interaction between pairs of regional time-series by quantifying their non-linear functional connectivity using Mutual Connectivity Analysis (MCA). Subsequently, we use a classifier to distinguish patterns of interaction between healthy and diseased individuals. Our results, quantified as the mean Area under the ROC curve (AUC) over 75 iterations, indicate that, using fMRI data, we can discriminate between the two cohorts well (AUC > 0.8). Specifically, we find that MCA (mean AUC = 0.89) based connectivity features perform significantly better (p < 0.05) when compared to cross-correlation (mean AUC = 0.82) at the classification task. A higher AUC using our approach suggests that such a nonlinear approach is better able to capture connectivity changes between brain regions and has potential for the development of novel neuro-imaging biomarkers.
Collapse
Affiliation(s)
- Adora M DSouza
- Department of Electrical Engineering, University of Rochester, NY, USA
| | - Anas Z Abidin
- Department of Biomedical Engineering, University of Rochester, NY, USA
| | - Axel Wismüller
- Department of Electrical Engineering, University of Rochester, NY, USA.,Department of Biomedical Engineering, University of Rochester, NY, USA.,Department of Imaging Sciences, University of Rochester, NY, USA.,Faculty of Medicine and Institute of Clinical Radiology, Ludwig Maximilian University, Munich, Germany
| |
Collapse
|
43
|
Can Learning Vector Quantization be an Alternative to SVM and Deep Learning? - Recent Trends and Advanced Variants of Learning Vector Quantization for Classification Learning. JOURNAL OF ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING RESEARCH 2016. [DOI: 10.1515/jaiscr-2017-0005] [Citation(s) in RCA: 37] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
Abstract
Learning vector quantization (LVQ) is one of the most powerful approaches for prototype based classification of vector data, intuitively introduced by Kohonen. The prototype adaptation scheme relies on its attraction and repulsion during the learning providing an easy geometric interpretability of the learning as well as of the classification decision scheme. Although deep learning architectures and support vector classifiers frequently achieve comparable or even better results, LVQ models are smart alternatives with low complexity and computational costs making them attractive for many industrial applications like intelligent sensor systems or advanced driver assistance systems.
Nowadays, the mathematical theory developed for LVQ delivers sufficient justification of the algorithm making it an appealing alternative to other approaches like support vector machines and deep learning techniques.
This review article reports current developments and extensions of LVQ starting from the generalized LVQ (GLVQ), which is known as the most powerful cost function based realization of the original LVQ. The cost function minimized in GLVQ is an soft-approximation of the standard classification error allowing gradient descent learning techniques. The GLVQ variants considered in this contribution, cover many aspects like bordersensitive learning, application of non-Euclidean metrics like kernel distances or divergences, relevance learning as well as optimization of advanced statistical classification quality measures beyond the accuracy including sensitivity and specificity or area under the ROC-curve.
According to these topics, the paper highlights the basic motivation for these variants and extensions together with the mathematical prerequisites and treatments for integration into the standard GLVQ scheme and compares them to other machine learning approaches. For detailed description and mathematical theory behind all, the reader is referred to the respective original articles.
Thus, the intention of the paper is to provide a comprehensive overview of the stateof- the-art serving as a starting point to search for an appropriate LVQ variant in case of a given specific classification problem as well as a reference to recently developed variants and improvements of the basic GLVQ scheme.
Collapse
|
44
|
Alahmadi HH, Shen Y, Fouad S, Luft CDB, Bentham P, Kourtzi Z, Tino P. Classifying Cognitive Profiles Using Machine Learning with Privileged Information in Mild Cognitive Impairment. Front Comput Neurosci 2016; 10:117. [PMID: 27909405 PMCID: PMC5112260 DOI: 10.3389/fncom.2016.00117] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2016] [Accepted: 10/31/2016] [Indexed: 11/28/2022] Open
Abstract
Early diagnosis of dementia is critical for assessing disease progression and potential treatment. State-or-the-art machine learning techniques have been increasingly employed to take on this diagnostic task. In this study, we employed Generalized Matrix Learning Vector Quantization (GMLVQ) classifiers to discriminate patients with Mild Cognitive Impairment (MCI) from healthy controls based on their cognitive skills. Further, we adopted a “Learning with privileged information” approach to combine cognitive and fMRI data for the classification task. The resulting classifier operates solely on the cognitive data while it incorporates the fMRI data as privileged information (PI) during training. This novel classifier is of practical use as the collection of brain imaging data is not always possible with patients and older participants. MCI patients and healthy age-matched controls were trained to extract structure from temporal sequences. We ask whether machine learning classifiers can be used to discriminate patients from controls and whether differences between these groups relate to individual cognitive profiles. To this end, we tested participants in four cognitive tasks: working memory, cognitive inhibition, divided attention, and selective attention. We also collected fMRI data before and after training on a probabilistic sequence learning task and extracted fMRI responses and connectivity as features for machine learning classifiers. Our results show that the PI guided GMLVQ classifiers outperform the baseline classifier that only used the cognitive data. In addition, we found that for the baseline classifier, divided attention is the only relevant cognitive feature. When PI was incorporated, divided attention remained the most relevant feature while cognitive inhibition became also relevant for the task. Interestingly, this analysis for the fMRI GMLVQ classifier suggests that (1) when overall fMRI signal is used as inputs to the classifier, the post-training session is most relevant; and (2) when the graph feature reflecting underlying spatiotemporal fMRI pattern is used, the pre-training session is most relevant. Taken together these results suggest that brain connectivity before training and overall fMRI signal after training are both diagnostic of cognitive skills in MCI.
Collapse
Affiliation(s)
- Hanin H Alahmadi
- School of Computer Science, The University of Birmingham Birmingham, UK
| | - Yuan Shen
- School of Computer Science, The University of Birmingham Birmingham, UK
| | - Shereen Fouad
- School of Dentistry, The University of Birmingham Birmingham, UK
| | - Caroline Di B Luft
- School of Biological and Chemical Sciences, Queen Mary University of London London, UK
| | - Peter Bentham
- School of Clinical and Experimental Medicine, The University of Birmingham Birmingham, UK
| | - Zoe Kourtzi
- Department of Psychology, The University of Cambridge Cambridge, UK
| | - Peter Tino
- School of Computer Science, The University of Birmingham Birmingham, UK
| |
Collapse
|
45
|
|
46
|
|
47
|
Liu T, Tao D, Xu D. Dimensionality-Dependent Generalization Bounds for k-Dimensional Coding Schemes. Neural Comput 2016; 28:2213-49. [PMID: 27391679 DOI: 10.1162/neco_a_00872] [Citation(s) in RCA: 41] [Impact Index Per Article: 5.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
The k-dimensional coding schemes refer to a collection of methods that attempt to represent data using a set of representative k-dimensional vectors and include nonnegative matrix factorization, dictionary learning, sparse coding, k-means clustering, and vector quantization as special cases. Previous generalization bounds for the reconstruction error of the k-dimensional coding schemes are mainly dimensionality-independent. A major advantage of these bounds is that they can be used to analyze the generalization error when data are mapped into an infinite- or high-dimensional feature space. However, many applications use finite-dimensional data features. Can we obtain dimensionality-dependent generalization bounds for k-dimensional coding schemes that are tighter than dimensionality-independent bounds when data are in a finite-dimensional feature space? Yes. In this letter, we address this problem and derive a dimensionality-dependent generalization bound for k-dimensional coding schemes by bounding the covering number of the loss function class induced by the reconstruction error. The bound is of order [Formula: see text], where m is the dimension of features, k is the number of the columns in the linear implementation of coding schemes, and n is the size of sample, [Formula: see text] when n is finite and [Formula: see text] when n is infinite. We show that our bound can be tighter than previous results because it avoids inducing the worst-case upper bound on k of the loss function. The proposed generalization bound is also applied to some specific coding schemes to demonstrate that the dimensionality-dependent bound is an indispensable complement to the dimensionality-independent generalization bounds.
Collapse
Affiliation(s)
- Tongliang Liu
- Centre for Quantum Computation and Intelligent Systems, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia
| | - Dacheng Tao
- Centre for Quantum Computation and Intelligent Systems, Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW 2007, Australia
| | - Dong Xu
- School of Electrical and Information Engineering, University of Sydney, Sydney, NSW 2007, Australia
| |
Collapse
|
48
|
Paassen B, Mokbel B, Hammer B. Adaptive structure metrics for automated feedback provision in intelligent tutoring systems. Neurocomputing 2016. [DOI: 10.1016/j.neucom.2015.12.108] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
|
49
|
Bohnsack A, Domaschke K, Kaden M, Lange M, Villmann T. Learning matrix quantization and relevance learning based on Schatten-p-norms. Neurocomputing 2016. [DOI: 10.1016/j.neucom.2015.12.109] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
50
|
Biehl M, Hammer B, Villmann T. Prototype-based models in machine learning. WILEY INTERDISCIPLINARY REVIEWS. COGNITIVE SCIENCE 2016; 7:92-111. [PMID: 26800334 DOI: 10.1002/wcs.1378] [Citation(s) in RCA: 24] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/20/2015] [Revised: 10/07/2015] [Accepted: 12/09/2015] [Indexed: 11/08/2022]
Abstract
An overview is given of prototype-based models in machine learning. In this framework, observations, i.e., data, are stored in terms of typical representatives. Together with a suitable measure of similarity, the systems can be employed in the context of unsupervised and supervised analysis of potentially high-dimensional, complex datasets. We discuss basic schemes of competitive vector quantization as well as the so-called neural gas approach and Kohonen's topology-preserving self-organizing map. Supervised learning in prototype systems is exemplified in terms of learning vector quantization. Most frequently, the familiar Euclidean distance serves as a dissimilarity measure. We present extensions of the framework to nonstandard measures and give an introduction to the use of adaptive distances in relevance learning.
Collapse
Affiliation(s)
- Michael Biehl
- Johann Bernoulli Institute for Mathematics and Computer Science, Faculty of Mathematics and Natural Sciences, University of Groningen, Groningen, The Netherlands
| | - Barbara Hammer
- CITEC Centre of Excellence, Faculty of Technology, Bielefeld University, Bielefeld, Germany
| | - Thomas Villmann
- Department of Mathematics, University of Applied Sciences Mittweida, Mittweida, Germany
| |
Collapse
|