Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Randomized Controlled Trial
. 2023 Oct;14(28):2839-2845.
doi: 10.1111/1759-7714.15068. Epub 2023 Aug 19.

Enhanced prediction of postoperative radiotherapy-induced esophagitis in non-small cell lung cancer: Dosiomic model development in a real-world cohort and validation in the PORT-C randomized controlled trial

Zeliang Ma  1 , Bin Liang  1 , Ran Wei  1 , Yunsong Liu  1 , Yongxing Bao  1 , Meng Yuan  1 , Yu Men  2 , Jianyang Wang  1 , Lei Deng  1 , Yirui Zhai  1 , Nan Bi  1 , Luhua Wang  1 , Jianrong Dai  1 , Zhouguang Hui  2
Affiliations
Randomized Controlled Trial

Enhanced prediction of postoperative radiotherapy-induced esophagitis in non-small cell lung cancer: Dosiomic model development in a real-world cohort and validation in the PORT-C randomized controlled trial

Zeliang Ma et al. Thorac Cancer. 2023 Oct.

Abstract

Background: Radiotherapy-induced esophagitis (RE) diminishes the quality of life and interrupts treatment in patients with non-small cell lung cancer (NSCLC) undergoing postoperative radiotherapy. Dosimetric models showed limited capability in predicting RE. We aimed to develop dosiomic models to predict RE.

Methods: Models were trained with a real-world cohort and validated with PORT-C randomized controlled trial cohort. Patients with NSCLC undergoing resection followed by postoperative radiotherapy between 2004 and 2015 were enrolled. The endpoint was grade ≥2 RE. Esophageal three-dimensional dose distribution features were extracted using handcrafted and convolutional neural network (CNN) methods, screened using an entropy-based method, and selected using minimum redundancy and maximum relevance. Prediction models were built using logistic regression. The areas under the receiver operating characteristic curve (AUC) and precision-recall curve were used to evaluate prediction model performance. A dosimetric model was built for comparison.

Results: A total of 190 and 103 patients were enrolled in the training and validation sets, respectively. Using handcrafted and CNN methods, 107 and 4096 features were derived, respectively. Three handcrafted, four CNN-extracted and three dosimetric features were selected. AUCs of training and validation sets were 0.737 and 0.655 for the dosimetric features, 0.730 and 0.724 for handcrafted features, and 0.812 and 0.785 for CNN-extracted features, respectively. Precision-recall curves revealed that CNN-extracted features outperformed dosimetric and handcrafted features.

Conclusions: Prediction models may identify patients at high risk of developing RE. Dosiomic models outperformed the dosimetric-feature model in predicting RE. CNN-extracted features were more predictive but less interpretable than handcrafted features.

Keywords: convolution neural network; dosiomics; non-small cell lung cancer; prediction model; radiation esophagitis.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

FIGURE 1
FIGURE 1
AUC and Fn feature values. AUC as a function of Fn values of handcrafted (a) and CNN‐extracted (b) features are shown. For each specific Fn, the logistic regression model was hyperparameter‐tuned, and the mean AUC of 100 bootstraps was calculated, along with the 95% confidence interval. The value of Fn was tuned from 1 to 10. AUC, area under receiver operating characteristic curve; CNN, convolutional neural network; Fn, number of features.
FIGURE 2
FIGURE 2
ROC analysis. ROC curves of dosimetric features (a), handcrafted features (b), and CNN‐extracted features (c) are shown. CNN, convolutional neural network; ROC, receiver operating characteristics.
FIGURE 3
FIGURE 3
Precision‐recall curves. Curves of dosimetric (a), handcrafted (b), and CNN‐extracted (c) features are shown. CNN, convolutional neural network.
See this image and copyright information in PMC

References

    1. Hui Z, Men Y, Hu C, Kang J, Sun X, Bi N, et al. Effect of postoperative radiotherapy for patients with pIIIA‐N2 non‐small cell lung cancer after complete resection and adjuvant chemotherapy: the phase 3 PORT‐C randomized clinical trial. JAMA Oncol. 2021;7:1178–1185. 10.1001/jamaoncol.2021.1910 - DOI - PMC - PubMed
    1. Le Pechoux C, Pourel N, Barlesi F, Lerouge D, Antoni D, Lamezec B, et al. Postoperative radiotherapy versus no postoperative radiotherapy in patients with completely resected non‐small‐cell lung cancer and proven mediastinal N2 involvement (lung ART): an open‐label, randomised, phase 3 trial. Lancet Oncol. 2022;23:104–114. 10.1016/S1470-2045(21)00606-9 - DOI - PubMed
    1. Machtay M, Hsu C, Komaki R, Sause WT, Swann RS, Langer CJ, et al. Effect of overall treatment time on outcomes after concurrent chemoradiation for locally advanced non‐small‐cell lung carcinoma: analysis of the radiation therapy oncology group (RTOG) experience. Int J Radiat Oncol Biol Phys. 2005;63:667–671. 10.1016/j.ijrobp.2005.03.037 - DOI - PubMed
    1. Ozgen A, Hayran M, Kahraman F. Mean esophageal radiation dose is predictive of the grade of acute esophagitis in lung cancer patients treated with concurrent radiotherapy and chemotherapy. J Radiat Res. 2012;53:916–922. 10.1093/jrr/rrs056 - DOI - PMC - PubMed
    1. Kuroda Y, Sekine I, Sumi M, Sekii S, Takahashi K, Inaba K, et al. Acute radiation esophagitis caused by high‐dose involved field radiotherapy with concurrent cisplatin and vinorelbine for stage III non‐small cell lung cancer. Technol Cancer Res Treat. 2013;12:333–339. 10.7785/tcrt.2012.500319 - DOI - PubMed

Publication types