SPECT Image Features for Early Detection of Parkinson’s Disease using Machine Learning Methods

Emmi Antikainen; Patrick Cella; Antti Tolonen; Mark van Gils

doi:10.1109/EMBC46164.2021.9630272

SPECT Image Features for Early Detection of Parkinson’s Disease using Machine Learning Methods

Emmi Antikainen (Corresponding author), Patrick Cella, Antti Tolonen, Mark van Gils

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

3 Citations (Scopus)

96 Downloads (Pure)

Abstract

Millions of people around the world suffer from Parkinson’s disease, a neurodegenerative disorder with no remedy. Currently, the best response to interventions is achieved when the disease is diagnosed at an early stage. Supervised machine learning models are a common approach to assist early diagnosis from clinical data, but their performance is highly dependent on available example data and selected input features. In this study, we explore 23 single photon emission computed tomography (SPECT) image features for the early diagnosis of Parkinson’s disease on 646 subjects. We achieve 94 % balanced classification accuracy in independent test data using the full feature space and show that matching accuracy can be achieved with only eight features, including original features introduced in this study. All the presented features can be generated using a routinely available clinical software and are therefore straightforward to extract and apply.

Original language	English
Title of host publication	43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Publisher	IEEE Institute of Electrical and Electronic Engineers
Number of pages	5
ISBN (Electronic)	978-1-7281-1179-7
DOIs	https://doi.org/10.1109/EMBC46164.2021.9630272
Publication status	Published - Nov 2021
MoE publication type	A4 Article in a conference publication
Event	43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Duration: 30 Oct 2021 → 5 Nov 2021 Conference number: 43 http://embc.embs.orf/2021

Conference

Conference	43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Abbreviated title	EMBC
Period	30/10/21 → 5/11/21
Internet address	http://embc.embs.orf/2021

Access to Document

10.1109/EMBC46164.2021.9630272

ML_SPECT_submissionSubmitted manuscript, 242 KB

Cite this

@inproceedings{e7995fafbd6e4f53ad4fe31e2cde1cd6,

title = "SPECT Image Features for Early Detection of Parkinson{\textquoteright}s Disease using Machine Learning Methods",

abstract = "Millions of people around the world suffer from Parkinson{\textquoteright}s disease, a neurodegenerative disorder with no remedy. Currently, the best response to interventions is achieved when the disease is diagnosed at an early stage. Supervised machine learning models are a common approach to assist early diagnosis from clinical data, but their performance is highly dependent on available example data and selected input features. In this study, we explore 23 single photon emission computed tomography (SPECT) image features for the early diagnosis of Parkinson{\textquoteright}s disease on 646 subjects. We achieve 94 % balanced classification accuracy in independent test data using the full feature space and show that matching accuracy can be achieved with only eight features, including original features introduced in this study. All the presented features can be generated using a routinely available clinical software and are therefore straightforward to extract and apply.",

author = "Emmi Antikainen and Patrick Cella and Antti Tolonen and {van Gils}, Mark",

note = "Funding Information: This work was supported by GE Healthcare UK ; 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC ; Conference date: 30-10-2021 Through 05-11-2021",

year = "2021",

month = nov,

doi = "10.1109/EMBC46164.2021.9630272",

language = "English",

booktitle = "43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society",

publisher = "IEEE Institute of Electrical and Electronic Engineers",

address = "United States",

url = "http://embc.embs.orf/2021",

}

Antikainen, E, Cella, P, Tolonen, A & van Gils, M 2021, SPECT Image Features for Early Detection of Parkinson’s Disease using Machine Learning Methods. in 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Institute of Electrical and Electronic Engineers, 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 30/10/21. https://doi.org/10.1109/EMBC46164.2021.9630272

SPECT Image Features for Early Detection of Parkinson’s Disease using Machine Learning Methods. / Antikainen, Emmi (Corresponding author); Cella, Patrick; Tolonen, Antti et al.
43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Institute of Electrical and Electronic Engineers, 2021.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - SPECT Image Features for Early Detection of Parkinson’s Disease using Machine Learning Methods

AU - Antikainen, Emmi

AU - Cella, Patrick

AU - Tolonen, Antti

AU - van Gils, Mark

N1 - Conference code: 43

PY - 2021/11

Y1 - 2021/11

N2 - Millions of people around the world suffer from Parkinson’s disease, a neurodegenerative disorder with no remedy. Currently, the best response to interventions is achieved when the disease is diagnosed at an early stage. Supervised machine learning models are a common approach to assist early diagnosis from clinical data, but their performance is highly dependent on available example data and selected input features. In this study, we explore 23 single photon emission computed tomography (SPECT) image features for the early diagnosis of Parkinson’s disease on 646 subjects. We achieve 94 % balanced classification accuracy in independent test data using the full feature space and show that matching accuracy can be achieved with only eight features, including original features introduced in this study. All the presented features can be generated using a routinely available clinical software and are therefore straightforward to extract and apply.

AB - Millions of people around the world suffer from Parkinson’s disease, a neurodegenerative disorder with no remedy. Currently, the best response to interventions is achieved when the disease is diagnosed at an early stage. Supervised machine learning models are a common approach to assist early diagnosis from clinical data, but their performance is highly dependent on available example data and selected input features. In this study, we explore 23 single photon emission computed tomography (SPECT) image features for the early diagnosis of Parkinson’s disease on 646 subjects. We achieve 94 % balanced classification accuracy in independent test data using the full feature space and show that matching accuracy can be achieved with only eight features, including original features introduced in this study. All the presented features can be generated using a routinely available clinical software and are therefore straightforward to extract and apply.

UR - http://www.scopus.com/inward/record.url?scp=85122514009&partnerID=8YFLogxK

U2 - 10.1109/EMBC46164.2021.9630272

DO - 10.1109/EMBC46164.2021.9630272

M3 - Conference article in proceedings

BT - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

PB - IEEE Institute of Electrical and Electronic Engineers

T2 - 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society

Y2 - 30 October 2021 through 5 November 2021

ER -

SPECT Image Features for Early Detection of Parkinson’s Disease using Machine Learning Methods

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this