Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI

Abstract This study used explainable artificial intelligence for data-driven identification of extrastriatal brain regions that can contribute to the interpretation of dopamine transporter SPECT with 123I-FP-CIT in parkinsonian syndromes. A total of 1306 123I-FP-CIT-SPECT were included retrospective...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mahmood Nazari, Andreas Kluge, Ivayla Apostolova, Susanne Klutmann, Sharok Kimiaei, Michael Schroeder, Ralph Buchert
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/413a6f3cef2541759c9ff4545fdd65d7
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:413a6f3cef2541759c9ff4545fdd65d7
record_format	dspace
spelling	oai:doaj.org-article:413a6f3cef2541759c9ff4545fdd65d72021-11-28T12:21:01ZData-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI10.1038/s41598-021-02385-x2045-2322https://doaj.org/article/413a6f3cef2541759c9ff4545fdd65d72021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-02385-xhttps://doaj.org/toc/2045-2322Abstract This study used explainable artificial intelligence for data-driven identification of extrastriatal brain regions that can contribute to the interpretation of dopamine transporter SPECT with 123I-FP-CIT in parkinsonian syndromes. A total of 1306 123I-FP-CIT-SPECT were included retrospectively. Binary classification as ‘reduced’ or ‘normal’ striatal 123I-FP-CIT uptake by an experienced reader served as standard-of-truth. A custom-made 3-dimensional convolutional neural network (CNN) was trained for classification of the SPECT images with 1006 randomly selected images in three different settings: “full image”, “striatum only” (3-dimensional region covering the striata cropped from the full image), “without striatum” (full image with striatal region removed). The remaining 300 SPECT images were used to test the CNN classification performance. Layer-wise relevance propagation (LRP) was used for voxelwise quantification of the relevance for the CNN-based classification in this test set. Overall accuracy of CNN-based classification was 97.0%, 95.7%, and 69.3% in the “full image”, “striatum only”, and “without striatum” setting. Prominent contributions in the LRP-based relevance maps beyond the striatal signal were detected in insula, amygdala, ventromedial prefrontal cortex, thalamus, anterior temporal cortex, superior frontal lobe, and pons, suggesting that 123I-FP-CIT uptake in these brain regions provides clinically useful information for the differentiation of neurodegenerative and non-neurodegenerative parkinsonian syndromes.Mahmood NazariAndreas KlugeIvayla ApostolovaSusanne KlutmannSharok KimiaeiMichael SchroederRalph BuchertNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Mahmood Nazari Andreas Kluge Ivayla Apostolova Susanne Klutmann Sharok Kimiaei Michael Schroeder Ralph Buchert Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI
description	Abstract This study used explainable artificial intelligence for data-driven identification of extrastriatal brain regions that can contribute to the interpretation of dopamine transporter SPECT with 123I-FP-CIT in parkinsonian syndromes. A total of 1306 123I-FP-CIT-SPECT were included retrospectively. Binary classification as ‘reduced’ or ‘normal’ striatal 123I-FP-CIT uptake by an experienced reader served as standard-of-truth. A custom-made 3-dimensional convolutional neural network (CNN) was trained for classification of the SPECT images with 1006 randomly selected images in three different settings: “full image”, “striatum only” (3-dimensional region covering the striata cropped from the full image), “without striatum” (full image with striatal region removed). The remaining 300 SPECT images were used to test the CNN classification performance. Layer-wise relevance propagation (LRP) was used for voxelwise quantification of the relevance for the CNN-based classification in this test set. Overall accuracy of CNN-based classification was 97.0%, 95.7%, and 69.3% in the “full image”, “striatum only”, and “without striatum” setting. Prominent contributions in the LRP-based relevance maps beyond the striatal signal were detected in insula, amygdala, ventromedial prefrontal cortex, thalamus, anterior temporal cortex, superior frontal lobe, and pons, suggesting that 123I-FP-CIT uptake in these brain regions provides clinically useful information for the differentiation of neurodegenerative and non-neurodegenerative parkinsonian syndromes.
format	article
author	Mahmood Nazari Andreas Kluge Ivayla Apostolova Susanne Klutmann Sharok Kimiaei Michael Schroeder Ralph Buchert
author_facet	Mahmood Nazari Andreas Kluge Ivayla Apostolova Susanne Klutmann Sharok Kimiaei Michael Schroeder Ralph Buchert
author_sort	Mahmood Nazari
title	Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI
title_short	Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI
title_full	Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI
title_fullStr	Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI
title_full_unstemmed	Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI
title_sort	data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter spect using explainable ai
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/413a6f3cef2541759c9ff4545fdd65d7
work_keys_str_mv	AT mahmoodnazari datadrivenidentificationofdiagnosticallyusefulextrastriatalsignalindopaminetransporterspectusingexplainableai AT andreaskluge datadrivenidentificationofdiagnosticallyusefulextrastriatalsignalindopaminetransporterspectusingexplainableai AT ivaylaapostolova datadrivenidentificationofdiagnosticallyusefulextrastriatalsignalindopaminetransporterspectusingexplainableai AT susanneklutmann datadrivenidentificationofdiagnosticallyusefulextrastriatalsignalindopaminetransporterspectusingexplainableai AT sharokkimiaei datadrivenidentificationofdiagnosticallyusefulextrastriatalsignalindopaminetransporterspectusingexplainableai AT michaelschroeder datadrivenidentificationofdiagnosticallyusefulextrastriatalsignalindopaminetransporterspectusingexplainableai AT ralphbuchert datadrivenidentificationofdiagnosticallyusefulextrastriatalsignalindopaminetransporterspectusingexplainableai
_version_	1718408007692320768

Data-driven identification of diagnostically useful extrastriatal signal in dopamine transporter SPECT using explainable AI

Ejemplares similares