Nicola Amoroso1, Domenico Diacono2, Annarita Fanizzi3, Marianna La Rocca4, Alfonso Monaco5, Angela Lombardi6, Cataldo Guaragnella7, Roberto Bellotti8, Sabina Tangaro9. 1. Dipartimento Interateneo di Fisica "M. Merlin", Università degli studi di Bari "A. Moro", Bari, Italy; Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy. Electronic address: nicola.amoroso@ba.infn.it. 2. Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy. Electronic address: domenico.diacono@ba.infn.it. 3. Istituto Tumori "Giovanni Paolo II" - I.R.C.C.S., Bari, Italy. Electronic address: annarita.fanizzi.af@gmail.com. 4. Dipartimento Interateneo di Fisica "M. Merlin", Università degli studi di Bari "A. Moro", Bari, Italy; Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy. Electronic address: marianna.larocca@ba.infn.it. 5. Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy. Electronic address: Alfonso.Monaco@ba.infn.it. 6. Dipartimento di Ingegneria Elettrica e dell'Informazione, Politecnico di Bari, Bari, Italy. Electronic address: angela.lombardi@poliba.it. 7. Dipartimento di Ingegneria Elettrica e dell'Informazione, Politecnico di Bari, Bari, Italy. Electronic address: cataldo.guaragnella@poliba.it. 8. Dipartimento Interateneo di Fisica "M. Merlin", Università degli studi di Bari "A. Moro", Bari, Italy; Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy. Electronic address: roberto.bellotti@uniba.it. 9. Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy. Electronic address: Sonia.Tangaro@ba.infn.it.
Abstract
BACKGROUND: Early diagnosis of Alzheimer's disease (AD) and its onset in subjects affected by mild cognitive impairment (MCI) based on structural MRI features is one of the most important open issues in neuroimaging. Accordingly, a scientific challenge has been promoted, on the international Kaggle platform, to assess the performance of different classification methods for prediction of MCI and its conversion to AD. NEW METHOD: This work presents a classification strategy based on Random Forest feature selection and Deep Neural Network classification using a mixed cohort including the four classes of classification problem, that is HC, AD, MCI and cMCI, to train the model. Moreover, we compare this approach with a novel classification strategy based on fuzzy logic learned on a mixed cohort including only HC and AD. EXPERIMENTS: A training set of 240 subjects and a test set including mixed cohort of 500 real and simulated subjects were used. The data included AD patients, MCI subjects converting to AD (cMCI), MCI subjects and healthy controls (HC). This work ranked third for overall accuracy (38.8%) over 19 participating teams. COMPARISON WITH EXISTING METHOD(S): The "International challenge for automated prediction of MCI from MRI data" hosted by the Kaggle platform has been promoted to validate different methodologies with a common set of data and evaluation procedures. CONCLUSION: DNNs reach a classification accuracy significantly higher than other machine learning strategies; on the other hand, fuzzy logic is particularly accurate with cMCI, suggesting a combination of these approaches could lead to interesting future perspectives.
BACKGROUND: Early diagnosis of Alzheimer's disease (AD) and its onset in subjects affected by mild cognitive impairment (MCI) based on structural MRI features is one of the most important open issues in neuroimaging. Accordingly, a scientific challenge has been promoted, on the international Kaggle platform, to assess the performance of different classification methods for prediction of MCI and its conversion to AD. NEW METHOD: This work presents a classification strategy based on Random Forest feature selection and Deep Neural Network classification using a mixed cohort including the four classes of classification problem, that is HC, AD, MCI and cMCI, to train the model. Moreover, we compare this approach with a novel classification strategy based on fuzzy logic learned on a mixed cohort including only HC and AD. EXPERIMENTS: A training set of 240 subjects and a test set including mixed cohort of 500 real and simulated subjects were used. The data included ADpatients, MCI subjects converting to AD (cMCI), MCI subjects and healthy controls (HC). This work ranked third for overall accuracy (38.8%) over 19 participating teams. COMPARISON WITH EXISTING METHOD(S): The "International challenge for automated prediction of MCI from MRI data" hosted by the Kaggle platform has been promoted to validate different methodologies with a common set of data and evaluation procedures. CONCLUSION: DNNs reach a classification accuracy significantly higher than other machine learning strategies; on the other hand, fuzzy logic is particularly accurate with cMCI, suggesting a combination of these approaches could lead to interesting future perspectives.
Authors: Solale Tabarestani; Mohammad Eslami; Mercedes Cabrerizo; Rosie E Curiel; Armando Barreto; Naphtali Rishe; David Vaillancourt; Steven T DeKosky; David A Loewenstein; Ranjan Duara; Malek Adjouadi Journal: Front Aging Neurosci Date: 2022-05-06 Impact factor: 5.702
Authors: Geneviève Richard; Knut Kolskår; Anne-Marthe Sanders; Tobias Kaufmann; Anders Petersen; Nhat Trung Doan; Jennifer Monereo Sánchez; Dag Alnæs; Kristine M Ulrichsen; Erlend S Dørum; Ole A Andreassen; Jan Egil Nordvik; Lars T Westlye Journal: PeerJ Date: 2018-11-30 Impact factor: 2.984
Authors: Telma Pereira; Francisco L Ferreira; Sandra Cardoso; Dina Silva; Alexandre de Mendonça; Manuela Guerreiro; Sara C Madeira Journal: BMC Med Inform Decis Mak Date: 2018-12-19 Impact factor: 2.796
Authors: Ahmed A Moustafa; Thierno M O Diallo; Nicola Amoroso; Nazar Zaki; Mubashir Hassan; Hany Alashwal Journal: Front Comput Neurosci Date: 2018-10-16 Impact factor: 2.380