ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy

There has been a recent effort to treat high-risk ventricular tachycardia (VT) patients through radio-ablation. However, manual segmentation of the VT target is complex and time-consuming. This work introduces ASSET, or Auto-segmentation of the Seventeen SEgments for Tachycardia ablation, to aid in...

Full description

Bibliographic Details
Main Authors: Eric Morris, Robert Chin, Trudy Wu, Clayton Smith, Siamak Nejad-Davarani, Minsong Cao
Format: Article
Language:English
Published: MDPI AG 2023-08-01
Series:Cancers
Subjects:
Online Access:https://www.mdpi.com/2072-6694/15/16/4062
_version_ 1797585279481020416
author Eric Morris
Robert Chin
Trudy Wu
Clayton Smith
Siamak Nejad-Davarani
Minsong Cao
author_facet Eric Morris
Robert Chin
Trudy Wu
Clayton Smith
Siamak Nejad-Davarani
Minsong Cao
author_sort Eric Morris
collection DOAJ
description There has been a recent effort to treat high-risk ventricular tachycardia (VT) patients through radio-ablation. However, manual segmentation of the VT target is complex and time-consuming. This work introduces ASSET, or Auto-segmentation of the Seventeen SEgments for Tachycardia ablation, to aid in radiation therapy (RT) planning. ASSET was retrospectively applied to CTs for 26 thoracic RT patients (13 undergoing VT ablation). The physician-defined parasternal long-axis of the left ventricle (LV) and the axes generated from principal component analysis (PCA) were compared using mean distance to agreement (MDA) and angle of separation. The manually selected right ventricle insertion point and LVs were used to apply the ASSET model to automatically generate the 17 segments of the LV myocardium (LVM). Physician-defined parasternal long-axis differed from PCA by 1.2 ± 0.3 mm MDA and 6.9 ± 0.7 degrees. Segments differed by 0.69 ± 0.29 mm MDA and 0.89 ± 0.03 Dice similarity coefficient. Running ASSET takes <5 min where manual segmentation took >2 h/patient. Agreement between ASSET and expert contours was comparable to inter-observer variability. Qualitative scoring conducted by three experts revealed automatically generated segmentations were clinically useable as-is. ASSET offers efficient and reliable automatic segmentations for the 17 segments of the LVM for target generation in RT planning.
first_indexed 2024-03-11T00:03:54Z
format Article
id doaj.art-e2dd28ac40d145d8890302d65af315c0
institution Directory Open Access Journal
issn 2072-6694
language English
last_indexed 2024-03-11T00:03:54Z
publishDate 2023-08-01
publisher MDPI AG
record_format Article
series Cancers
spelling doaj.art-e2dd28ac40d145d8890302d65af315c02023-11-19T00:32:39ZengMDPI AGCancers2072-66942023-08-011516406210.3390/cancers15164062ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation TherapyEric Morris0Robert Chin1Trudy Wu2Clayton Smith3Siamak Nejad-Davarani4Minsong Cao5Department of Radiation Oncology, Washington University, St. Louis, MO 63110, USADepartment of Radiation Oncology, UCLA Health, Los Angeles, CA 90095, USADepartment of Radiation Oncology, UCLA Health, Los Angeles, CA 90095, USADepartment of Radiation Oncology, UCLA Health, Los Angeles, CA 90095, USADepartment of Radiation Oncology, University of Miami Miller School of Medicine, Miami, FL 33136, USADepartment of Radiation Oncology, UCLA Health, Los Angeles, CA 90095, USAThere has been a recent effort to treat high-risk ventricular tachycardia (VT) patients through radio-ablation. However, manual segmentation of the VT target is complex and time-consuming. This work introduces ASSET, or Auto-segmentation of the Seventeen SEgments for Tachycardia ablation, to aid in radiation therapy (RT) planning. ASSET was retrospectively applied to CTs for 26 thoracic RT patients (13 undergoing VT ablation). The physician-defined parasternal long-axis of the left ventricle (LV) and the axes generated from principal component analysis (PCA) were compared using mean distance to agreement (MDA) and angle of separation. The manually selected right ventricle insertion point and LVs were used to apply the ASSET model to automatically generate the 17 segments of the LV myocardium (LVM). Physician-defined parasternal long-axis differed from PCA by 1.2 ± 0.3 mm MDA and 6.9 ± 0.7 degrees. Segments differed by 0.69 ± 0.29 mm MDA and 0.89 ± 0.03 Dice similarity coefficient. Running ASSET takes <5 min where manual segmentation took >2 h/patient. Agreement between ASSET and expert contours was comparable to inter-observer variability. Qualitative scoring conducted by three experts revealed automatically generated segmentations were clinically useable as-is. ASSET offers efficient and reliable automatic segmentations for the 17 segments of the LVM for target generation in RT planning.https://www.mdpi.com/2072-6694/15/16/4062radiation therapycardiac ablationventricular tachycardiaautomatic segmentation
spellingShingle Eric Morris
Robert Chin
Trudy Wu
Clayton Smith
Siamak Nejad-Davarani
Minsong Cao
ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy
Cancers
radiation therapy
cardiac ablation
ventricular tachycardia
automatic segmentation
title ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy
title_full ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy
title_fullStr ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy
title_full_unstemmed ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy
title_short ASSET: Auto-Segmentation of the Seventeen SEgments for Ventricular Tachycardia Ablation in Radiation Therapy
title_sort asset auto segmentation of the seventeen segments for ventricular tachycardia ablation in radiation therapy
topic radiation therapy
cardiac ablation
ventricular tachycardia
automatic segmentation
url https://www.mdpi.com/2072-6694/15/16/4062
work_keys_str_mv AT ericmorris assetautosegmentationoftheseventeensegmentsforventriculartachycardiaablationinradiationtherapy
AT robertchin assetautosegmentationoftheseventeensegmentsforventriculartachycardiaablationinradiationtherapy
AT trudywu assetautosegmentationoftheseventeensegmentsforventriculartachycardiaablationinradiationtherapy
AT claytonsmith assetautosegmentationoftheseventeensegmentsforventriculartachycardiaablationinradiationtherapy
AT siamaknejaddavarani assetautosegmentationoftheseventeensegmentsforventriculartachycardiaablationinradiationtherapy
AT minsongcao assetautosegmentationoftheseventeensegmentsforventriculartachycardiaablationinradiationtherapy