Universität zu Köln

Thummerer, Adrian ORCID: 0000-0002-1874-5030, Oria, Carmen Seller, Zaffino, Paolo, Meijers, Arturs ORCID: 0000-0002-3647-6647, Marmitt, Gabriel Guterres, Wijsman, Robin, Seco, Joao, Langendijk, Johannes Albertus, Knopf, Antje-Christin, Spadea, Maria Francesca and Both, Stefan (2021). Clinical suitability of deep learning based synthetic CTs for adaptive proton therapy of lung cancer. Med. Phys., 48 (12). S. 7673 - 7685. HOBOKEN: WILEY. ISSN 2473-4209

Full text not available from this repository.

Abstract

Purpose Adaptive proton therapy (APT) of lung cancer patients requires frequent volumetric imaging of diagnostic quality. Cone-beam CT (CBCT) can provide these daily images, but x-ray scattering limits CBCT-image quality and hampers dose calculation accuracy. The purpose of this study was to generate CBCT-based synthetic CTs using a deep convolutional neural network (DCNN) and investigate image quality and clinical suitability for proton dose calculations in lung cancer patients. Methods A dataset of 33 thoracic cancer patients, containing CBCTs, same-day repeat CTs (rCT), planning-CTs (pCTs), and clinical proton treatment plans, was used to train and evaluate a DCNN with and without a pCT-based correction method. Mean absolute error (MAE), mean error (ME), peak signal-to-noise ratio, and structural similarity were used to quantify image quality. The evaluation of clinical suitability was based on recalculation of clinical proton treatment plans. Gamma pass ratios, mean dose to target volumes and organs at risk, and normal tissue complication probabilities (NTCP) were calculated. Furthermore, proton radiography simulations were performed to assess the HU-accuracy of sCTs in terms of range errors. Results On average, sCTs without correction resulted in a MAE of 34 +/- 6 HU and ME of 4 +/- 8 HU. The correction reduced the MAE to 31 +/- 4HU (ME to 2 +/- 4HU). Average 3%/3 mm gamma pass ratios increased from 93.7% to 96.8%, when the correction was applied. The patient specific correction reduced mean proton range errors from 1.5 to 1.1 mm. Relative mean target dose differences between sCTs and rCT were below +/- 0.5% for all patients and both synthetic CTs (with/without correction). NTCP values showed high agreement between sCTs and rCT (<2%). Conclusion CBCT-based sCTs can enable accurate proton dose calculations for APT of lung cancer patients. The patient specific correction method increased the image quality and dosimetric accuracy but had only a limited influence on clinically relevant parameters.

Item Type:	Journal Article
Creators:	Creators Email ORCID ORCID Put Code Thummerer, Adrian UNSPECIFIED orcid.org/0000-0002-1874-5030 UNSPECIFIED Oria, Carmen Seller UNSPECIFIED UNSPECIFIED UNSPECIFIED Zaffino, Paolo UNSPECIFIED UNSPECIFIED UNSPECIFIED Meijers, Arturs UNSPECIFIED orcid.org/0000-0002-3647-6647 UNSPECIFIED Marmitt, Gabriel Guterres UNSPECIFIED UNSPECIFIED UNSPECIFIED Wijsman, Robin UNSPECIFIED UNSPECIFIED UNSPECIFIED Seco, Joao UNSPECIFIED UNSPECIFIED UNSPECIFIED Langendijk, Johannes Albertus UNSPECIFIED UNSPECIFIED UNSPECIFIED Knopf, Antje-Christin UNSPECIFIED UNSPECIFIED UNSPECIFIED Spadea, Maria Francesca UNSPECIFIED UNSPECIFIED UNSPECIFIED Both, Stefan UNSPECIFIED UNSPECIFIED UNSPECIFIED
URN:	urn:nbn:de:hbz:38-590089
DOI:	10.1002/mp.15333
Journal or Publication Title:	Med. Phys.
Volume:	48
Number:	12
Page Range:	S. 7673 - 7685
Date:	2021
Publisher:	WILEY
Place of Publication:	HOBOKEN
ISSN:	2473-4209
Language:	English
Faculty:	Unspecified
Divisions:	Unspecified
Subjects:	no entry
Uncontrolled Keywords:	Keywords Language CONE-BEAM CT; HEAD-AND-NECK; DOSE CALCULATION; COMPUTED-TOMOGRAPHY; TECHNICAL NOTE; IMAGE; RADIOTHERAPY; REGISTRATION; FEASIBILITY; RADIOGRAPHY Multiple languages Radiology, Nuclear Medicine & Medical Imaging Multiple languages
URI:	http://kups.ub.uni-koeln.de/id/eprint/59008