Evaluation of the accuracy of heart dose prediction by machine learning for selecting patients not requiring deep inspiration breath‑hold radiotherapy after breast cancer surgery

Kamizaki,Ryo; Kuroda,Masahiro; Al‑Hammad,Wlla E.; Tekiki,Nouha; Ishizaka,Hinata; Kuroda,Kazuhiro; Sugimoto,Kohei; Oita,Masataka; Tanabe,Yoshinori; Barham,Majd; Sugianto,Irfan; Nakamitsu,Yuki; Hirano,Masaki; Muto,Yuki; Ihara,Hiroki; Sugiyama,Soichi

doi:10.3892/etm.2023.12235

Evaluation of the accuracy of heart dose prediction by machine learning for selecting patients not requiring deep inspiration breath‑hold radiotherapy after breast cancer surgery

Authors:
- Ryo Kamizaki
- Masahiro Kuroda
- Wlla E. Al‑Hammad
- Nouha Tekiki
- Hinata Ishizaka
- Kazuhiro Kuroda
- Kohei Sugimoto
- Masataka Oita
- Yoshinori Tanabe
- Majd Barham
- Irfan Sugianto
- Yuki Nakamitsu
- Masaki Hirano
- Yuki Muto
- Hiroki Ihara
- Soichi Sugiyama
View Affiliations

Affiliations: Department of Radiological Technology, Graduate School of Health Sciences, Okayama University, Okayama 700‑8558, Japan, Department of Oral and Maxillofacial Radiology, Okayama University Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama 700‑8558, Japan, Graduate School of Interdisciplinary Sciences and Engineering in Health Systems, Okayama University, Okayama 770‑8558, Japan, Department of Dentistry and Dental Surgery, College of Medicine and Health Sciences, An‑Najah National University, Nablus 44839, Palestine, Department of Oral Radiology, Faculty of Dentistry, Hasanuddin University, Sulawesi 90245, Indonesia, Department of Radiology, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700‑8558, Japan, Department of Proton Beam Therapy, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, Okayama 700‑8558, Japan
Published online on: October 2, 2023 https://doi.org/10.3892/etm.2023.12235
Article Number: 536

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

Increased heart dose during postoperative radiotherapy (RT) for left‑sided breast cancer (BC) can cause cardiac injury, which can decrease patient survival. The deep inspiration breath‑hold technique (DIBH) is becoming increasingly common for reducing the mean heart dose (MHD) in patients with left‑sided BC. However, treatment planning and DIBH for RT are laborious, time‑consuming and costly for patients and RT staff. In addition, the proportion of patients with left BC with low MHD is considerably higher among Asian women, mainly due to their smaller breast volume compared with that in Western countries. The present study aimed to determine the optimal machine learning (ML) model for predicting the MHD after RT to pre‑select patients with low MHD who will not require DIBH prior to RT planning. In total, 562 patients with BC who received postoperative RT were randomly divided into the trainval (n=449) and external (n=113) test datasets for ML using Python (version 3.8). Imbalanced data were corrected using synthetic minority oversampling with Gaussian noise. Specifically, right‑left, tumor site, chest wall thickness, irradiation method, body mass index and separation were the six explanatory variables used for ML, with four supervised ML algorithms used. Using the optimal value of hyperparameter tuning with root mean squared error (RMSE) as an indicator for the internal test data, the model yielding the best F2 score evaluation was selected for final validation using the external test data. The predictive ability of MHD for true MHD after RT was the highest among all algorithms for the deep neural network, with a RMSE of 77.4, F2 score of 0.80 and area under the curve‑receiver operating characteristic of 0.88, for a cut‑off value of 300 cGy. The present study suggested that ML can be used to pre‑select female Asian patients with low MHD who do not require DIBH for the postoperative RT of BC.

View Figures

View References

1	Clarke M, Collins R, Darby S, Davies C, Elphinstone P, Evans V, Godwin J, Gray R, Hicks C, James S, et al: Effects of radiotherapy and of differences in the extent of surgery for early breast cancer on local recurrence and 15-year survival: An overview of the randomised trials. Lancet. 366:2087–2106. 2005.PubMed/NCBI View Article : Google Scholar
2	Darby S, McGale P, Correa C, Taylor C, Arriagada R, Clarke M, Cutter D, Davies C, Ewertz M, Godwin J, et al: Effect of radiotherapy after breast-conserving surgery on 10-year recurrence and 15-year breast cancer death: Meta-analysis of individual patient data for 10,801 women in 17 randomised trials. Lancet. 378:1707–1716. 2011.PubMed/NCBI View Article : Google Scholar
3	Beaton L, Bergman A, Nichol A, Aparicio M, Wong G, Gondara L, Speers C, Weir L, Davis M and Tyldesley S: Cardiac death after breast radiotherapy and the QUANTEC cardiac guidelines. Clin Transl Radiat Oncol. 19:39–45. 2019.PubMed/NCBI View Article : Google Scholar
4	Lu Y, Yang D, Zhang X, Teng Y, Yuan W, Zhang Y, He R, Tang F, Pang J, Han B, et al: Comparison of deep inspiration breath hold versus free breathing in radiotherapy for left sided breast cancer. Front Oncol. 12(845037)2022.PubMed/NCBI View Article : Google Scholar
5	Falco M, Masojć B, Macała A, Łukowiak M, Woźniak P and Malicki J: Deep inspiration breath hold reduces the mean heart dose in left breast cancer radiotherapy. Radiol Oncol. 55:212–220. 2021.PubMed/NCBI View Article : Google Scholar
6	Yamauchi R, Mizuno N, Itazawa T, Saitoh H and Kawamori J: Dosimetric evaluation of deep inspiration breath hold for left-sided breast cancer: Analysis of patient-specific parameters related to heart dose reduction. J Radiat Res. 61:447–456. 2020.PubMed/NCBI View Article : Google Scholar
7	Stowe HB, Andruska ND, Reynoso F, Thomas M and Bergom C: Heart sparing radiotherapy techniques in breast cancer: A focus on deep inspiration breath hold. Breast Cancer-Targets Ther. 14:175–186. 2022.PubMed/NCBI View Article : Google Scholar
8	Darapu A, Balakrishnan R, Sebastian P, Hussain MR, Ravindran P and John S: Is the deep inspiration breath-hold technique superior to the free breathing technique in cardiac and lung sparing while treating both left-sided post-mastectomy chest wall and supraclavicular regions? Case Rep Oncol. 10:37–51. 2017.PubMed/NCBI View Article : Google Scholar
9	Teshima T, Owen JB, Hanks GE, Sato S, Tsunemoto H and Inoue T: A comparison of the structure of radiation oncology in the United States and Japan. Int J Radiat Oncol Biol Phys. 34:235–242. 1996.PubMed/NCBI View Article : Google Scholar
10	Nakamura K, Konishi K, Komatsu T, Sasaki T and Shikama N: Patterns of radiotherapy infrastructure in Japan and in other countries with well-developed radiotherapy infrastructures, Jpn J Clin. Oncol. 48:476–479. 2018.PubMed/NCBI View Article : Google Scholar
11	Morganti AG, Cilla S, de Gaetano A, Panunzi S, Digesù C, Macchia G, Massaccesi M, Deodato F, Ferrandina G, Cellini N, et al: Forward planned intensity modulated radiotherapy (IMRT) for whole breast postoperative radiotherapy. Is it useful? When? J Appl Clin Med Phys. 12(3451)2011.PubMed/NCBI View Article : Google Scholar
12	Ishizaka H, Kuroda M, Tekiki N, Khasawneh A, Barham M, Hamada K, Konishi K, Sugimoto K, Katsui K, Sugiyama S, et al: Investigation into the effect of breast volume on irradiation dose distribution in Asian women with breast cancer. Acta Med Okayama. 75:307–314. 2021.PubMed/NCBI View Article : Google Scholar
13	Kim S and Kim M and Kim M: The affecting factors of breast anthropometry in Korean women. Breastfeed Med. 9:73–78. 2014.PubMed/NCBI View Article : Google Scholar
14	Li X, Zhou C, Wu Y and Chen X: . Relationship between formulaic breast volume and risk of breast cancer based on linear measurements. BMC Cancer. 20(989)2020.PubMed/NCBI View Article : Google Scholar
15	Tortorelli G, Di Murro L, Barbarino R, Cicchetti S, di Cristino D, Falco MD, Fedele D, Ingrosso G, Janniello D, Morelli P, et al: Standard or hypofractionated radiotherapy in the postoperative treatment of breast cancer: A retrospective analysis of acute skin toxicity and dose inhomogeneities. BMC Cancer. 13(230)2013.PubMed/NCBI View Article : Google Scholar
16	Kim T, Reardon K, Trifiletti DM, Geesey C, Sukovich K, Crandley E, Read PW and Wijesooriya K: How dose sparing of cardiac structures correlates with in-field heart volume and sternal displacement. J Appl Clin Med Phys. 17:60–68. 2016.PubMed/NCBI View Article : Google Scholar
17	Siddique S and Chow JCL: Artificial intelligence in radiotherapy. Rep Pract Oncol Radiother. 25:656–666. 2020.PubMed/NCBI View Article : Google Scholar
18	Kang J, Schwartz R, Flickinger J and Beriwal S: Machine learning approaches for predicting radiotherapy outcomes: A clinician's perspective. Int J Radiat Oncol Biol Phys. 93:1127–1135. 2015.PubMed/NCBI View Article : Google Scholar
19	Luo Y, Chen S and Valdes G: . Machine learning for radiation outcome modeling and prediction. Med Phys. 47:e178–e184. 2020.PubMed/NCBI View Article : Google Scholar
20	Brodin NP, Schulte L, Velten C, Martin W, Shen S, Shen J, Basavatia A, Ohri N, Garg MK, Carpenter C and Tomé WA: Organ-at-risk dose prediction using a machine learning algorithm: Clinical validation and treatment planning benefit for lung SBRT. J Appl Clin Med Phys. 23(e13609)2022.PubMed/NCBI View Article : Google Scholar
21	Koide Y, Aoyama T, Shimizu H, Kitagawa T, Miyauchi R, Tachibana H and Kodaira T: . Development of deep learning chest X-ray model for cardiac dose prediction in left-sided breast cancer radiotherapy. Sci Rep. 12(13706)2022.PubMed/NCBI View Article : Google Scholar
22	Ahn SH, Kim E, Kim C, Cheon W, Kim M, Lee SB, Lim YK, Kim H, Shin D, Kim DY, et al: Deep learning method for prediction of patient-specific dose distribution in breast cancer. Radiat Oncol. 16(154)2021.PubMed/NCBI View Article : Google Scholar
23	Koide Y, Shimizu H, Wakabayashi K, Kitagawa T, Aoyama T, Miyauchi R, Tachibana H and Kodaira T: Synthetic breath-hold CT generation from free-breathing CT: A novel deep learning approach to predict cardiac dose reduction in deep-inspiration breath-hold radiotherapy. J Radiat Res. 62:1065–1075. 2021.PubMed/NCBI View Article : Google Scholar
24	Tekiki N, Kuroda M, Ishizaka H, Khasawneh A, Barham M, Hamada K, Konishi K, Sugimoto K, Katsui K, Sugiyama S, et al: New field-in-field with two reference points method for whole breast radiotherapy: Dosimetric analysis and radiation-induced skin toxicities assessment. Mol Clin Oncol. 15(193)2021.PubMed/NCBI View Article : Google Scholar
25	International Classification of Diseases for Oncology. Available from: https://apps.who.int/iris/bitstream/handle/10665/96612/9789241548496_eng.pdf.
26	Chen T and Guestrin C: XGBoost: A Scalable Tree Boosting System. In proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. pp785-794, 2016.
27	Joseph VR: Optimal ratio for data splitting. Stat Anal Data Min. 15:531–538. 2022.
28	Branco P, Torgo L and Ribeiro RP: SMOGN: A pre-processing approach for imbalanced regression. Proc Mach Learn Res. 74:36–50. 2017.