Prediction of Consolidation Tumor Ratio on Planning CT Images of Lung Cancer Patients Treated with Radiotherapy Based on Deep Learning
Tong, Yizhi ; Arimura, Hidetaka ; Yoshitake, Tadamasa ; Cui, Yunhao ; Kodama, Takumi ; Shioyama, Yoshiyuki ; Wirestam, Ronnie LU
and Yabuuchi, Hidetake
(2024)
In Applied Sciences (Switzerland)
14(8).
- Abstract
This study aimed to propose an automated prediction approach of the consolidation tumor ratios (CTRs) of part-solid tumors of patients treated with radiotherapy on treatment planning computed tomography images using deep learning segmentation (DLS) models. For training the DLS model for cancer regions, a total of 115 patients with non-small cell lung cancer (NSCLC) who underwent stereotactic body radiation therapy were selected as the training dataset, including solid, part-solid, and ground-glass opacity tumors. For testing the automated prediction approach of CTRs based on segmented tumor regions, 38 patients with part-solid tumors were selected as an internal test dataset A (IN) from a same institute as the training dataset, and 49... (More)
This study aimed to propose an automated prediction approach of the consolidation tumor ratios (CTRs) of part-solid tumors of patients treated with radiotherapy on treatment planning computed tomography images using deep learning segmentation (DLS) models. For training the DLS model for cancer regions, a total of 115 patients with non-small cell lung cancer (NSCLC) who underwent stereotactic body radiation therapy were selected as the training dataset, including solid, part-solid, and ground-glass opacity tumors. For testing the automated prediction approach of CTRs based on segmented tumor regions, 38 patients with part-solid tumors were selected as an internal test dataset A (IN) from a same institute as the training dataset, and 49 patients as an external test dataset (EX) from a public database. The CTRs for part-solid tumors were predicted as ratios of the maximum diameters of solid components to those of whole tumors. Pearson correlations between reference and predicted CTRs for the two test datasets were 0.953 (IN) and 0.926 (EX) for one of the DLS models (p < 0.01). Intraclass correlation coefficients between reference and predicted CTRs for the two test datasets were 0.943 (IN) and 0.904 (EX) for the same DLS models. The findings suggest that the automated prediction approach could be robust in calculating the CTRs of part-solid tumors.
(Less)
- author
- Tong, Yizhi
; Arimura, Hidetaka
; Yoshitake, Tadamasa
; Cui, Yunhao
; Kodama, Takumi
; Shioyama, Yoshiyuki
; Wirestam, Ronnie
LU
and Yabuuchi, Hidetake
- organization
- publishing date
- 2024-04
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- consolidation tumor ratio, deep learning, independent test, non-small cell lung cancer (NSCLC), part-solid tumors
- in
- Applied Sciences (Switzerland)
- volume
- 14
- issue
- 8
- article number
- 3275
- publisher
- MDPI AG
- external identifiers
-
- scopus:85192515904
- ISSN
- 2076-3417
- DOI
- 10.3390/app14083275
- language
- English
- LU publication?
- yes
- id
- dc2a11b1-8605-42e4-b0d0-92806d885247
- date added to LUP
- 2024-05-23 15:51:42
- date last changed
- 2024-05-23 15:52:57
@article{dc2a11b1-8605-42e4-b0d0-92806d885247,
abstract = {{<p>This study aimed to propose an automated prediction approach of the consolidation tumor ratios (CTRs) of part-solid tumors of patients treated with radiotherapy on treatment planning computed tomography images using deep learning segmentation (DLS) models. For training the DLS model for cancer regions, a total of 115 patients with non-small cell lung cancer (NSCLC) who underwent stereotactic body radiation therapy were selected as the training dataset, including solid, part-solid, and ground-glass opacity tumors. For testing the automated prediction approach of CTRs based on segmented tumor regions, 38 patients with part-solid tumors were selected as an internal test dataset A (IN) from a same institute as the training dataset, and 49 patients as an external test dataset (EX) from a public database. The CTRs for part-solid tumors were predicted as ratios of the maximum diameters of solid components to those of whole tumors. Pearson correlations between reference and predicted CTRs for the two test datasets were 0.953 (IN) and 0.926 (EX) for one of the DLS models (p < 0.01). Intraclass correlation coefficients between reference and predicted CTRs for the two test datasets were 0.943 (IN) and 0.904 (EX) for the same DLS models. The findings suggest that the automated prediction approach could be robust in calculating the CTRs of part-solid tumors.</p>}},
author = {{Tong, Yizhi and Arimura, Hidetaka and Yoshitake, Tadamasa and Cui, Yunhao and Kodama, Takumi and Shioyama, Yoshiyuki and Wirestam, Ronnie and Yabuuchi, Hidetake}},
issn = {{2076-3417}},
keywords = {{consolidation tumor ratio; deep learning; independent test; non-small cell lung cancer (NSCLC); part-solid tumors}},
language = {{eng}},
number = {{8}},
publisher = {{MDPI AG}},
series = {{Applied Sciences (Switzerland)}},
title = {{Prediction of Consolidation Tumor Ratio on Planning CT Images of Lung Cancer Patients Treated with Radiotherapy Based on Deep Learning}},
url = {{http://dx.doi.org/10.3390/app14083275}},
doi = {{10.3390/app14083275}},
volume = {{14}},
year = {{2024}},
}