Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning

Abstract In aneurysmal subarachnoid hemorrhage (aSAH), accurate diagnosis of aneurysm is essential for subsequent treatment to prevent rebleeding. However, aneurysm detection proves to be challenging and time-consuming. The purpose of this study was to develop and evaluate a deep learning model (DLM...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Rahil Shahzad, Lenhard Pennig, Lukas Goertz, Frank Thiele, Christoph Kabbasch, Marc Schlamann, Boris Krischek, David Maintz, Michael Perkuhn, Jan Borggrefe
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/c3980af84cce4858a634dcf7b6dc04c8
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c3980af84cce4858a634dcf7b6dc04c8
record_format	dspace
spelling	oai:doaj.org-article:c3980af84cce4858a634dcf7b6dc04c82021-12-02T12:33:14ZFully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning10.1038/s41598-020-78384-12045-2322https://doaj.org/article/c3980af84cce4858a634dcf7b6dc04c82020-12-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-78384-1https://doaj.org/toc/2045-2322Abstract In aneurysmal subarachnoid hemorrhage (aSAH), accurate diagnosis of aneurysm is essential for subsequent treatment to prevent rebleeding. However, aneurysm detection proves to be challenging and time-consuming. The purpose of this study was to develop and evaluate a deep learning model (DLM) to automatically detect and segment aneurysms in patients with aSAH on computed tomography angiography. In this retrospective single-center study, three different DLMs were trained on 68 patients with 79 aneurysms treated for aSAH (2016–2017) using five-fold-cross-validation. Their outputs were combined to a single DLM via ensemble-learning. The DLM was evaluated on an independent test set consisting of 185 patients with 215 aneurysms (2010–2015). Independent manual segmentations of aneurysms in a 3D voxel-wise manner by two readers (neurosurgeon, radiologist) provided the reference standard. For aneurysms > 30 mm3 (mean diameter of ~ 4 mm) on the test set, the DLM provided a detection sensitivity of 87% with false positives (FPs)/scan of 0.42. Automatic segmentations achieved a median dice similarity coefficient (DSC) of 0.80 compared to the reference standard. Aneurysm location (anterior vs. posterior circulation; P = .07) and bleeding severity (Fisher grade ≤ 3 vs. 4; P = .33) did not impede detection sensitivity or segmentation performance. For aneurysms > 100 mm3 (mean diameter of ~ 6 mm), a sensitivity of 96% with DSC of 0.87 and FPs/scan of 0.14 were obtained. In the present study, we demonstrate that the proposed DLM detects and segments aneurysms > 30 mm3 in patients with aSAH with high sensitivity independent of cerebral circulation and bleeding severity while producing FP findings of less than one per scan. Hence, the DLM can potentially assist treating physicians in aSAH by providing automated detection and segmentations of aneurysms.Rahil ShahzadLenhard PennigLukas GoertzFrank ThieleChristoph KabbaschMarc SchlamannBoris KrischekDavid MaintzMichael PerkuhnJan BorggrefeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-12 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Rahil Shahzad Lenhard Pennig Lukas Goertz Frank Thiele Christoph Kabbasch Marc Schlamann Boris Krischek David Maintz Michael Perkuhn Jan Borggrefe Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
description	Abstract In aneurysmal subarachnoid hemorrhage (aSAH), accurate diagnosis of aneurysm is essential for subsequent treatment to prevent rebleeding. However, aneurysm detection proves to be challenging and time-consuming. The purpose of this study was to develop and evaluate a deep learning model (DLM) to automatically detect and segment aneurysms in patients with aSAH on computed tomography angiography. In this retrospective single-center study, three different DLMs were trained on 68 patients with 79 aneurysms treated for aSAH (2016–2017) using five-fold-cross-validation. Their outputs were combined to a single DLM via ensemble-learning. The DLM was evaluated on an independent test set consisting of 185 patients with 215 aneurysms (2010–2015). Independent manual segmentations of aneurysms in a 3D voxel-wise manner by two readers (neurosurgeon, radiologist) provided the reference standard. For aneurysms > 30 mm3 (mean diameter of ~ 4 mm) on the test set, the DLM provided a detection sensitivity of 87% with false positives (FPs)/scan of 0.42. Automatic segmentations achieved a median dice similarity coefficient (DSC) of 0.80 compared to the reference standard. Aneurysm location (anterior vs. posterior circulation; P = .07) and bleeding severity (Fisher grade ≤ 3 vs. 4; P = .33) did not impede detection sensitivity or segmentation performance. For aneurysms > 100 mm3 (mean diameter of ~ 6 mm), a sensitivity of 96% with DSC of 0.87 and FPs/scan of 0.14 were obtained. In the present study, we demonstrate that the proposed DLM detects and segments aneurysms > 30 mm3 in patients with aSAH with high sensitivity independent of cerebral circulation and bleeding severity while producing FP findings of less than one per scan. Hence, the DLM can potentially assist treating physicians in aSAH by providing automated detection and segmentations of aneurysms.
format	article
author	Rahil Shahzad Lenhard Pennig Lukas Goertz Frank Thiele Christoph Kabbasch Marc Schlamann Boris Krischek David Maintz Michael Perkuhn Jan Borggrefe
author_facet	Rahil Shahzad Lenhard Pennig Lukas Goertz Frank Thiele Christoph Kabbasch Marc Schlamann Boris Krischek David Maintz Michael Perkuhn Jan Borggrefe
author_sort	Rahil Shahzad
title	Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
title_short	Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
title_full	Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
title_fullStr	Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
title_full_unstemmed	Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning
title_sort	fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on cta using deep learning
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/c3980af84cce4858a634dcf7b6dc04c8
work_keys_str_mv	AT rahilshahzad fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT lenhardpennig fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT lukasgoertz fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT frankthiele fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT christophkabbasch fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT marcschlamann fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT boriskrischek fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT davidmaintz fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT michaelperkuhn fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning AT janborggrefe fullyautomateddetectionandsegmentationofintracranialaneurysmsinsubarachnoidhemorrhageonctausingdeeplearning
_version_	1718393883669299200

Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning

Ejemplares similares