Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy

Denis Dudas; Paymen Ghasemi Saghand; Thomas J Dilling; Bradford A Perez; Stephen A Rosenberg; Issam El Naqa

doi:10.1016/j.ijrobp.2023.11.059

Deep Learning-Guided Dosimetry for Mitigating Local Failure of Patients With Non-Small Cell Lung Cancer Receiving Stereotactic Body Radiation Therapy

Int J Radiat Oncol Biol Phys. 2023 Dec 5:S0360-3016(23)08185-3. doi: 10.1016/j.ijrobp.2023.11.059. Online ahead of print.

Authors

Denis Dudas¹, Paymen Ghasemi Saghand², Thomas J Dilling³, Bradford A Perez³, Stephen A Rosenberg³, Issam El Naqa⁴

Affiliations

¹ Departments of Machine Learning. Electronic address: dudasden@fjfi.cvut.cz.
² Departments of Machine Learning.
³ Radiation Oncology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida.
⁴ Departments of Machine Learning; Radiation Oncology, H. Lee Moffitt Cancer Center and Research Institute, Tampa, Florida.

PMID: 38056778
DOI: 10.1016/j.ijrobp.2023.11.059

Abstract

Purpose: Non-small cell lung cancer (NSCLC) stereotactic body radiation therapy with 50 Gy/5 fractions is sometimes considered controversial, as the nominal biologically effective dose (BED) of 100 Gy is felt by some to be insufficient for long-term local control of some lesions. In this study, we analyzed such patients using explainable deep learning techniques and consequently proposed appropriate treatment planning criteria. These novel criteria could help planners achieve optimized treatment plans for maximal local control.

Methods and materials: A total of 535 patients treated with 50 Gy/5 fractions were used to develop a novel deep learning local response model. A multimodality approach, incorporating computed tomography images, 3-dimensional dose distribution, and patient demographics, combined with a discrete-time survival model, was applied to predict time to failure and the probability of local control. Subsequently, an integrated gradient-weighted class activation mapping method was used to identify the most significant dose-volume metrics predictive of local failure and their optimal cut-points.

Results: The model was cross-validated, showing an acceptable performance (c-index: 0.72, 95% CI, 0.68-0.75); the testing c-index was 0.69. The model's spatial attention was concentrated mostly in the tumors' periphery (planning target volume [PTV] - internal gross target volume [IGTV]) region. Statistically significant dose-volume metrics in improved local control were BED D_near-min ≥ 103.8 Gy in IGTV (hazard ratio [HR], 0.31; 95% CI, 015-0.63), V104 ≥ 98% in IGTV (HR, 0.30; 95% CI, 0.15-0.60), gEUD ≥ 103.8 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.50), and D_mean ≥ 104.5 Gy in PTV-IGTV (HR, 0.25; 95% CI, 0.12-0.51).

Conclusions: Deep learning-identified dose-volume metrics have shown significant prognostic power (log-rank, P = .003) and could be used as additional actionable criteria for treatment planning in NSCLC stereotactic body radiation therapy patients receiving 50 Gy in 5 fractions. Although our data do not confirm or refute that a significantly higher BED for the prescription dose is necessary for tumor control in NSCLC, it might be clinically effective to escalate the nominal prescribed dose from BED 100 to 105 Gy.