Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN)

CALLUM ALTHAM; HUAIZHONG ZHANG; MARCELLO TROVATI; ELLA PEREIRA; Nicola Ray; Simon Keller; Antonella  Macerollo

Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN)

CALLUM ALTHAM^*, HUAIZHONG ZHANG, MARCELLO TROVATI, ELLA PEREIRA, Nicola Ray, Simon Keller, Antonella Macerollo

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding (ISBN) › peer-review

Abstract

Detecting the potential for Parkinson’s Disease Dementia
(PDD) as early as possible is crucial to ensure that quality of life can be
maintained. However, the full origins of this condition are unknown and
analysing potential causes such as the influence of the Cholinergic Basal
Forebrain (cBF) can be challenging due to variation in brain tissue as
well as low scan resolution. Additionally, the structure and function of
the cBF can span both brain hemispheres, and therefore prove difficult to
analyse using a singular deep learning method. In this paper, we propose
a multi-scale, dual-sided approach to analysis of regions with low surface
area such as the cBF. Initially, images are parsed using super-resolution
to increase resolution and contrast. Then, a dual sided multi-scale convolutional neural network (DSMS-CNN) model is proposed to classify
subjects as either normal cognition or PDD based on both hemispheres
of the cBF together. Ablation studies and comparison experiments with
state-of-the-art CNN models show that DSMS-CNN can achieve promising and superior performance

Original language	English
Title of host publication	Medical Imaging and Computer-Aided Diagnosis
Subtitle of host publication	Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022)
Editors	Ruidan Su, Yudong Zhang, Han Liu, Alejandro F Frang
Publisher	Springer
Pages	191-201
Number of pages	11
Volume	810
ISBN (Electronic)	9789811667756
Publication status	Published - 19 Dec 2023
Event	MICAD2022 - Leicester, United Kingdom Duration: 20 Nov 2022 → 21 Nov 2022

Publication series

Name	Lecture Notes in Electrical Engineering
ISSN (Electronic)	1876-1100

Conference

Conference	MICAD2022
Country/Territory	United Kingdom
City	Leicester
Period	20/11/22 → 21/11/22

Keywords

Parkinson’s Disease Dementia
Parkinson’s Disease
Magnetic Resonance Imaging
Convolutional Neural Network

Research Centres

Data and Complex Systems Research Centre
Centre for Intelligent Visual Computing Research

Cite this

ALTHAM, CALLUM., ZHANG, HUAIZHONG., TROVATI, MARCELLO., PEREIRA, ELLA., Ray, N., Keller, S., & Macerollo, A. (2023). Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN). In R. Su, Y. Zhang, H. Liu, & A. F Frang (Eds.), Medical Imaging and Computer-Aided Diagnosis: Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022) (Vol. 810, pp. 191-201). (Lecture Notes in Electrical Engineering). Springer.

ALTHAM, CALLUM ; ZHANG, HUAIZHONG ; TROVATI, MARCELLO et al. / Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN). Medical Imaging and Computer-Aided Diagnosis: Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022). editor / Ruidan Su ; Yudong Zhang ; Han Liu ; Alejandro F Frang. Vol. 810 Springer, 2023. pp. 191-201 (Lecture Notes in Electrical Engineering).

@inproceedings{3325af68df5341a09a8e0647dda16559,

title = "Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN)",

abstract = "Detecting the potential for Parkinson{\textquoteright}s Disease Dementia(PDD) as early as possible is crucial to ensure that quality of life can bemaintained. However, the full origins of this condition are unknown andanalysing potential causes such as the influence of the Cholinergic BasalForebrain (cBF) can be challenging due to variation in brain tissue aswell as low scan resolution. Additionally, the structure and function ofthe cBF can span both brain hemispheres, and therefore prove difficult toanalyse using a singular deep learning method. In this paper, we proposea multi-scale, dual-sided approach to analysis of regions with low surfacearea such as the cBF. Initially, images are parsed using super-resolutionto increase resolution and contrast. Then, a dual sided multi-scale convolutional neural network (DSMS-CNN) model is proposed to classifysubjects as either normal cognition or PDD based on both hemispheresof the cBF together. Ablation studies and comparison experiments withstate-of-the-art CNN models show that DSMS-CNN can achieve promising and superior performance",

keywords = "Parkinson{\textquoteright}s Disease Dementia, Parkinson{\textquoteright}s Disease, Magnetic Resonance Imaging, Convolutional Neural Network",

author = "CALLUM ALTHAM and HUAIZHONG ZHANG and MARCELLO TROVATI and ELLA PEREIRA and Nicola Ray and Simon Keller and Antonella Macerollo",

year = "2023",

month = dec,

day = "19",

language = "English",

volume = "810",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer",

pages = "191--201",

editor = "Ruidan Su and Yudong Zhang and Han Liu and {F Frang}, Alejandro",

booktitle = "Medical Imaging and Computer-Aided Diagnosis",

note = "MICAD2022 ; Conference date: 20-11-2022 Through 21-11-2022",

}

ALTHAM, CALLUM , ZHANG, HUAIZHONG , TROVATI, MARCELLO , PEREIRA, ELLA, Ray, N, Keller, S & Macerollo, A 2023, Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN). in R Su, Y Zhang, H Liu & A F Frang (eds), Medical Imaging and Computer-Aided Diagnosis: Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022). vol. 810, Lecture Notes in Electrical Engineering, Springer, pp. 191-201, MICAD2022, Leicester, United Kingdom, 20/11/22.

Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN). / ALTHAM, CALLUM ; ZHANG, HUAIZHONG ; TROVATI, MARCELLO et al.
Medical Imaging and Computer-Aided Diagnosis: Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022). ed. / Ruidan Su; Yudong Zhang; Han Liu; Alejandro F Frang. Vol. 810 Springer, 2023. p. 191-201 (Lecture Notes in Electrical Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding (ISBN) › peer-review

TY - GEN

T1 - Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN)

AU - ALTHAM, CALLUM

AU - ZHANG, HUAIZHONG

AU - TROVATI, MARCELLO

AU - PEREIRA, ELLA

AU - Ray, Nicola

AU - Keller, Simon

AU - Macerollo, Antonella

PY - 2023/12/19

Y1 - 2023/12/19

N2 - Detecting the potential for Parkinson’s Disease Dementia(PDD) as early as possible is crucial to ensure that quality of life can bemaintained. However, the full origins of this condition are unknown andanalysing potential causes such as the influence of the Cholinergic BasalForebrain (cBF) can be challenging due to variation in brain tissue aswell as low scan resolution. Additionally, the structure and function ofthe cBF can span both brain hemispheres, and therefore prove difficult toanalyse using a singular deep learning method. In this paper, we proposea multi-scale, dual-sided approach to analysis of regions with low surfacearea such as the cBF. Initially, images are parsed using super-resolutionto increase resolution and contrast. Then, a dual sided multi-scale convolutional neural network (DSMS-CNN) model is proposed to classifysubjects as either normal cognition or PDD based on both hemispheresof the cBF together. Ablation studies and comparison experiments withstate-of-the-art CNN models show that DSMS-CNN can achieve promising and superior performance

AB - Detecting the potential for Parkinson’s Disease Dementia(PDD) as early as possible is crucial to ensure that quality of life can bemaintained. However, the full origins of this condition are unknown andanalysing potential causes such as the influence of the Cholinergic BasalForebrain (cBF) can be challenging due to variation in brain tissue aswell as low scan resolution. Additionally, the structure and function ofthe cBF can span both brain hemispheres, and therefore prove difficult toanalyse using a singular deep learning method. In this paper, we proposea multi-scale, dual-sided approach to analysis of regions with low surfacearea such as the cBF. Initially, images are parsed using super-resolutionto increase resolution and contrast. Then, a dual sided multi-scale convolutional neural network (DSMS-CNN) model is proposed to classifysubjects as either normal cognition or PDD based on both hemispheresof the cBF together. Ablation studies and comparison experiments withstate-of-the-art CNN models show that DSMS-CNN can achieve promising and superior performance

KW - Parkinson’s Disease Dementia

KW - Parkinson’s Disease

KW - Magnetic Resonance Imaging

KW - Convolutional Neural Network

UR - https://www.micad.org/

UR - https://link.springer.com/book/10.1007/978-981-16-6775-6

M3 - Conference proceeding (ISBN)

VL - 810

T3 - Lecture Notes in Electrical Engineering

SP - 191

EP - 201

BT - Medical Imaging and Computer-Aided Diagnosis

A2 - Su, Ruidan

A2 - Zhang, Yudong

A2 - Liu, Han

A2 - F Frang, Alejandro

PB - Springer

T2 - MICAD2022

Y2 - 20 November 2022 through 21 November 2022

ER -

ALTHAM CALLUM , ZHANG HUAIZHONG , TROVATI MARCELLO , PEREIRA ELLA, Ray N, Keller S et al. Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN). In Su R, Zhang Y, Liu H, F Frang A, editors, Medical Imaging and Computer-Aided Diagnosis: Proceedings of 2022 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2022). Vol. 810. Springer. 2023. p. 191-201. (Lecture Notes in Electrical Engineering). Epub 2023 Dec 19.

Early Detection of Parkinson's Disease Dementia Using Dual-Sided Multi-Scale Convolutional Neural Networks (DSMS-CNN)

Abstract

Publication series

Conference

Keywords

Research Centres

Other files and links

Embargoed Document

Fingerprint

Cite this