Document Type

Article

Publication Date

7-9-2018

Publication Title

IEEE Access

First page number:

1

Last page number:

9

Abstract

In this paper, we study the reliability of a novel deep learning framework for internal gross target volume (IGTV) delineation from four-dimensional computed tomography (4DCT), which is applied to patients with lung cancer treated by Stereotactic Body Radiation Therapy (SBRT). 77 patients who underwent SBRT followed by 4DCT scans were incorporated in a retrospective study. The IGTV_DL was delineated using a novel deep machine learning algorithm with a linear exhaustive optimal combination framework, for the purpose of comparison, three other IGTVs base on common methods was also delineated, we compared the relative volume difference (RVI), matching index (MI) and encompassment index (EI) for the above IGTVs. Then, multiple parameter regression analysis assesses the tumor volume and motion range as clinical influencing factors in the MI variation. Experimental results demonstrated that the deep learning algorithm with linear exhaustive optimal combination framework has a higher probability of achieving optimal MI compared with other currently widely used methods. For patients after simple breathing training by keeping the respiratory frequency in 10 BMP, the four phase combinations of 0%, 30%, 50% and 90% can be considered as a potential candidate for an optimal combination to synthesis IGTV in all respiration amplitudes.

Keywords

Deep learning; Computed tomography; Algorithm; Stereotactic ablative radiotherapy; Internal gross target volume; Lung cancer

Disciplines

Analytical, Diagnostic and Therapeutic Techniques and Equipment

File Format

application/pdf

File Size

1.450 Kb

Language

English

Download

UNLV article access

Search your library

Share

COinS