Developing an automatic decision-assistance tool to choose proton/photon radiotherapy for patients with prostate cancer.
[PURPOSE] It is important to guide staff in choosing appropriately between photon and proton radiotherapy.
- p-value p = 0.057
APA
Li M, Shen L, et al. (2026). Developing an automatic decision-assistance tool to choose proton/photon radiotherapy for patients with prostate cancer.. Journal of applied clinical medical physics, 27(2), e70497. https://doi.org/10.1002/acm2.70497
MLA
Li M, et al.. "Developing an automatic decision-assistance tool to choose proton/photon radiotherapy for patients with prostate cancer.." Journal of applied clinical medical physics, vol. 27, no. 2, 2026, pp. e70497.
PMID
41704219
Abstract
[PURPOSE] It is important to guide staff in choosing appropriately between photon and proton radiotherapy. This study develops an automatic decision method to select the most clinically beneficial radiotherapy technique (proton or photon) for patients with prostate cancer. An automatic decision method was developed to help staff in choosing appropriately between photon and proton radiotherapy for patients with prostate cancer.
[MATERIALS AND METHODS] Forty-eight patients with prostate cancer were enrolled. First, photon and proton dose prediction models (M and M) were trained using reference plans from previous patients' data. Second, the predicted values of V (rectum wall) were obtained using the trained models, M and M, and these values were used to calculate the Normal Tissue Complication Probability (NTCP). Finally, if the photon NTCP exceeded 10%, the proton NTCP was calculated, and the difference (ΔNTCP) between the two was used to guide treatment selection. The accuracy of the decision support system was evaluated by comparing dose distributions, NTCPs, and decision outcomes between manual and automatic plans using paired t-tests.
[RESULTS] The deep learning (DL) model showed a mean absolute error (MAE) of 4.60 ± 1.80 for the rectum wall in the photon group and 3.64 ± 1.27 in the proton group. There was no statistically significant difference in V (rectum wall) between manual plans and model predictions (photon group p = 0.594, proton group p = 0.057). Similarly, no significant differences were observed in NTCP values for the rectum wall (photon group p = 0.383, proton group p = 0.100). The system correctly predicted the treatment modality in 45 of 48 cases, resulting in an accuracy rate of 93.75%, with AUC values for the decision method at 0.88.
[CONCLUSION] The proposed automatic decision method matches dose distributions, accurately calculates NTCPs, and supports precise radiotherapy technique selection, enhancing the clinical efficiency.
[MATERIALS AND METHODS] Forty-eight patients with prostate cancer were enrolled. First, photon and proton dose prediction models (M and M) were trained using reference plans from previous patients' data. Second, the predicted values of V (rectum wall) were obtained using the trained models, M and M, and these values were used to calculate the Normal Tissue Complication Probability (NTCP). Finally, if the photon NTCP exceeded 10%, the proton NTCP was calculated, and the difference (ΔNTCP) between the two was used to guide treatment selection. The accuracy of the decision support system was evaluated by comparing dose distributions, NTCPs, and decision outcomes between manual and automatic plans using paired t-tests.
[RESULTS] The deep learning (DL) model showed a mean absolute error (MAE) of 4.60 ± 1.80 for the rectum wall in the photon group and 3.64 ± 1.27 in the proton group. There was no statistically significant difference in V (rectum wall) between manual plans and model predictions (photon group p = 0.594, proton group p = 0.057). Similarly, no significant differences were observed in NTCP values for the rectum wall (photon group p = 0.383, proton group p = 0.100). The system correctly predicted the treatment modality in 45 of 48 cases, resulting in an accuracy rate of 93.75%, with AUC values for the decision method at 0.88.
[CONCLUSION] The proposed automatic decision method matches dose distributions, accurately calculates NTCPs, and supports precise radiotherapy technique selection, enhancing the clinical efficiency.
MeSH Terms
Humans; Prostatic Neoplasms; Male; Radiotherapy Planning, Computer-Assisted; Radiotherapy Dosage; Proton Therapy; Photons; Organs at Risk; Radiotherapy, Intensity-Modulated; Deep Learning; Aged
같은 제1저자의 인용 많은 논문 (5)
- Icariside II suppresses NF-κB/STAT3 signaling to prevent the progression of chronic atrophic gastritis toward gastric cancer.
- The protective role of a moderate protein diet in ETEC-infected piglets: Optimization of growth, immunity, and microbial balance.
- STOML2 promotes hepatocellular carcinoma cell proliferation, invasion and migration by activating the PI3K/AKT signaling pathway (Review).
- Kinesin Family Member 26A Disrupts DNA-Dependent Protein Kinase Complex Formation to Enhance Chemoradiotherapy Sensitivity in Colorectal Cancer.
- Real-world evaluation of immunotherapy in multi-line treatment of small cell lung cancer.