1
|
Hong CS, Park YI, Cho MS, Son J, Kim C, Han MC, Kim H, Lee H, Kim DW, Choi SH, Kim JS. Dose-toxicity surface histogram-based prediction of radiation dermatitis severity and shape. Phys Med Biol 2024; 69:115041. [PMID: 38759672 DOI: 10.1088/1361-6560/ad4d4e] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2023] [Accepted: 05/17/2024] [Indexed: 05/19/2024]
Abstract
Objective.This study aimed to develop a new approach to predict radiation dermatitis (RD) by using the skin dose distribution in the actual area of RD occurrence to determine the predictive dose by grade.Approach.Twenty-three patients with head and neck cancer treated with volumetric modulated arc therapy were prospectively and retrospectively enrolled. A framework was developed to segment the RD occurrence area in skin photography by matching the skin surface image obtained using a 3D camera with the skin dose distribution. RD predictive doses were generated using the dose-toxicity surface histogram (DTH) calculated from the skin dose distribution within the segmented RD regions classified by severity. We then evaluated whether the developed DTH-based framework could visually predict RD grades and their occurrence areas and shapes according to severity.Main results.The developed framework successfully generated the DTH for three different RD severities: faint erythema (grade 1), dry desquamation (grade 2), and moist desquamation (grade 3); 48 DTHs were obtained from 23 patients: 23, 22, and 3 DTHs for grades 1, 2, and 3, respectively. The RD predictive doses determined using DTHs were 28.9 Gy, 38.1 Gy, and 54.3 Gy for grades 1, 2, and 3, respectively. The estimated RD occurrence area visualized by the DTH-based RD predictive dose showed acceptable agreement for all grades compared with the actual RD region in the patient. The predicted RD grade was accurate, except in two patients.Significance. The developed DTH-based framework can classify and determine RD predictive doses according to severity and visually predict the occurrence area and shape of different RD severities. The proposed approach can be used to predict the severity and shape of potential RD in patients and thus aid physicians in decision making.
Collapse
Affiliation(s)
- Chae-Seon Hong
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Ye-In Park
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Min-Seok Cho
- Department of Radiation Oncology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Gyeonggi do, Republic of Korea
| | - Junyoung Son
- Department of Radiation Oncology, Yongin Severance Hospital, Yonsei University College of Medicine, Yongin, Gyeonggi do, Republic of Korea
| | - Changhwan Kim
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Min Cheol Han
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Hojin Kim
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Ho Lee
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Dong Wook Kim
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Seo Hee Choi
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Jin Sung Kim
- Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| |
Collapse
|
2
|
Saadatmand P, Mahdavi SR, Nikoofar A, Jazaeri SZ, Ramandi FL, Esmaili G, Vejdani S. A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac. Eur J Med Res 2024; 29:282. [PMID: 38735974 PMCID: PMC11089719 DOI: 10.1186/s40001-024-01855-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/10/2024] [Accepted: 04/23/2024] [Indexed: 05/14/2024] Open
Abstract
BACKGROUND Radiation induced acute skin toxicity (AST) is considered as a common side effect of breast radiation therapy. The goal of this study was to design dosiomics-based machine learning (ML) models for prediction of AST, to enable creating optimized treatment plans for high-risk individuals. METHODS Dosiomics features extracted using Pyradiomics tool (v3.0.1), along with treatment plan-derived dose volume histograms (DVHs), and patient-specific treatment-related (PTR) data of breast cancer patients were used for modeling. Clinical scoring was done using the Common Terminology Criteria for Adverse Events (CTCAE) V4.0 criteria for skin-specific symptoms. The 52 breast cancer patients were grouped into AST 2 + (CTCAE ≥ 2) and AST 2 - (CTCAE < 2) toxicity grades to facilitate AST modeling. They were randomly divided into training (70%) and testing (30%) cohorts. Multiple prediction models were assessed through multivariate analysis, incorporating different combinations of feature groups (dosiomics, DVH, and PTR) individually and collectively. In total, seven unique combinations, along with seven classification algorithms, were considered after feature selection. The performance of each model was evaluated on the test group using the area under the receiver operating characteristic curve (AUC) and f1-score. Accuracy, precision, and recall of each model were also studied. Statistical analysis involved features differences between AST 2 - and AST 2 + groups and cutoff value calculations. RESULTS Results showed that 44% of the patients developed AST 2 + after Tomotherapy. The dosiomics (DOS) model, developed using dosiomics features, exhibited a noteworthy improvement in AUC (up to 0.78), when spatial information is preserved in the dose distribution, compared to DVH features (up to 0.71). Furthermore, a baseline ML model created using only PTR features for comparison with DOS models showed the significance of dosiomics in early AST prediction. By employing the Extra Tree (ET) classifiers, the DOS + DVH + PTR model achieved a statistically significant improved performance in terms of AUC (0.83; 95% CI 0.71-0.90), accuracy (0.70), precision (0.74) and sensitivity (0.72) compared to other models. CONCLUSIONS This study confirmed the benefit of dosiomics-based ML in the prediction of AST. However, the combination of dosiomics, DVH, and PTR yields significant improvement in AST prediction. The results of this study provide the opportunity for timely interventions to prevent the occurrence of radiation induced AST.
Collapse
Affiliation(s)
- Pegah Saadatmand
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Seied Rabi Mahdavi
- Department of Medical Physics, School of Medicine, Iran University of Medical Sciences, Tehran, Iran.
- Radiation Biology Research Center, Iran University of Medical Sciences, Tehran, Iran.
| | - Alireza Nikoofar
- Department of Radiation Oncology, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
| | - Seyede Zohreh Jazaeri
- Department of Neuroscience, Faculty of Advanced Technologies in Medicine, Iran University of Medical Sciences, Tehran, Iran
- Division of NeuroscienceCellular and Molecular Research Center, Iran University of Medical Sciences, Tehran, Iran
| | | | | | - Soheil Vejdani
- Department of Radiation Oncology, School of Medicine, Iran University of Medical Sciences, Tehran, Iran
- Department of Radiation Oncology, Firoozgar Hospital, Iran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
3
|
Hamada K, Fujibuchi T, Arakawa H, Yokoyama Y, Yoshida N, Ohura H, Kunitake N, Masuda M, Honda T, Tokuda S, Sasaki M. A novel approach to predict acute radiation dermatitis in patients with head and neck cancer using a model based on Bayesian probability. Phys Med 2023; 116:103181. [PMID: 38000101 DOI: 10.1016/j.ejmp.2023.103181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/19/2023] [Revised: 10/04/2023] [Accepted: 11/17/2023] [Indexed: 11/26/2023] Open
Abstract
PURPOSE In this study, we aimed to establish a method for predicting the probability of each acute radiation dermatitis (ARD) grade during the head and neck Volumetric Modulated Arc Therapy (VMAT) radiotherapy planning phase based on Bayesian probability. METHODS The skin dose volume >50 Gy (V50), calculated using the treatment planning system, was used as a factor related to skin toxicity. The empirical distribution of each ARD grade relative to V50 was obtained from the ARD grades of 119 patients (55, 50, and 14 patients with G1, G2, and G3, respectively) determined by head and neck cancer specialists. Using Bayes' theorem, the Bayesian probabilities of G1, G2, and G3 for each value of V50 were calculated with an empirical distribution. Conversely, V50 was obtained based on the Bayesian probabilities of G1, G2, and G3. RESULTS The empirical distribution for each graded patient group demonstrated a normal distribution. The method predicted ARD grades with 92.4 % accuracy and provided a V50 value for each grade. For example, using the graph, we could predict that V50 should be ≤24.5 cm3 to achieve G1 with 70 % probability. CONCLUSIONS The Bayesian probability-based ARD prediction method could predict the ARD grade at the treatment planning stage using limited patient diagnostic data that demonstrated a normal distribution. If the probability of an ARD grade is high, skin care can be initiated in advance. Furthermore, the V50 value during treatment planning can provide radiation oncologists with data for strategies to reduce ARD.
Collapse
Affiliation(s)
- Keisuke Hamada
- Department of Radiological Technology, National Hospital Organization Kyushu Cancer Center, 3-1-1, Notame, Minami-ku, Fukuoka City, Fukuoka 811-1395, Japan; Department of Health Sciences, Graduate School of Medicine, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Japan.
| | - Toshioh Fujibuchi
- Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Japan.
| | - Hiroyuki Arakawa
- Department of Health Sciences, Faculty of Medical Sciences, Kyushu University, 3-1-1 Maidashi, Higashi-ku, Fukuoka 812-8582, Japan.
| | - Yuichi Yokoyama
- Department of Radiological Technology, National Hospital Organization Kyushu Cancer Center, 3-1-1, Notame, Minami-ku, Fukuoka City, Fukuoka 811-1395, Japan.
| | - Naoki Yoshida
- Department of Radiological Technology, National Hospital Organization Kyushu Cancer Center, 3-1-1, Notame, Minami-ku, Fukuoka City, Fukuoka 811-1395, Japan.
| | - Hiroki Ohura
- Department of Radiological Technology, National Hospital Organization Kyushu Medical Center, 1-8-1 Jigyohama, Chuo-ku, Fukuoka City, Fukuoka 810-8563, Japan.
| | - Naonobu Kunitake
- Department of Radiation Oncology, National Hospital Organization Kyushu Cancer Center, 3-1-1, Notame, Minami-ku, Fukuoka City, Fukuoka 811-1395, Japan.
| | - Muneyuki Masuda
- Department of Head and Neck Surgery, National Hospital Organization Kyushu Cancer Center, 3-1-1, Notame, Minami-ku, Fukuoka City, Fukuoka 811-1395, Japan.
| | - Takeo Honda
- Department of Radiological Technology, National Hospital Organization Kyushu Cancer Center, 3-1-1, Notame, Minami-ku, Fukuoka City, Fukuoka 811-1395, Japan.
| | - Satoru Tokuda
- Research Institute for Information Technology, Kyushu University, 6-1, Kasuga koen, Kasuga City, Fukuoka 816-8580, Japan.
| | - Makoto Sasaki
- College of Industrial Technology, Nihon University, 1-2-1 Izumi-cho, Narashino City, Chiba 275-8575, Japan.
| |
Collapse
|
4
|
Gobbo M, Rico V, Marta GN, Caini S, Ryan Wolf J, van den Hurk C, Beveridge M, Lam H, Bonomo P, Chow E, Behroozian T. Photobiomodulation therapy for the prevention of acute radiation dermatitis: a systematic review and meta-analysis. Support Care Cancer 2023; 31:227. [PMID: 36952036 PMCID: PMC10034256 DOI: 10.1007/s00520-023-07673-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Accepted: 03/07/2023] [Indexed: 03/24/2023]
Abstract
PURPOSE Approximately 95% of patients undergoing radiotherapy (RT) experience radiation dermatitis (RD). Evidence has suggested that photobiomodulation therapy (PBMT) can stimulate skin renewal and minimize RD. The aim of the present paper was to investigate the efficacy of PBMT in RD prevention through a comprehensive literature review. METHODS A literature search of Ovid MEDLINE, Embase, and Cochrane databases was conducted from 1980 to March 2021 to identify RCT on the use of PBMT for RD prevention. Forest plots were developed using RevMan software to quantitatively compare data between studies. RESULTS Five papers were identified: four in breast and one in head and neck cancer patients. Patients receiving PBMT experienced less severe RD than the control groups after 40 Gray (Gy) of RT (grade 3 toxicity: Odds Ratio (OR): 0.57, 95% CI 0.14-2.22, p = 0.42) and at the end of RT (grade 0 + 1 vs. 2 + 3 toxicity: OR: 0.28, 95% CI 0.15-0.53, p < 0.0001). RT interruptions due to RD severity were more frequent in the control group (OR: 0.81, 95% CI 0.10-6.58, p = 0.85). CONCLUSION Preventive PBMT may be protective against the development of severe grades of RD and reduce the frequency of RT interruptions. Larger sample sizes and other cancer sites at-risk of RD should be evaluated in future studies to confirm the true efficacy of PBMT, also in preventing the onset of RD and to finalize a standardized protocol to optimize the technique. At present, starting PBMT when RT starts is recommendable, as well as performing 2 to 3 laser sessions weekly.
Collapse
Affiliation(s)
- Margherita Gobbo
- Unit of Oral and Maxillofacial Surgery, Ca'Foncello Hospital, Treviso, Italy
| | - Victoria Rico
- Faculty of Health Sciences, McMaster University, Hamilton, ON, Canada
| | | | - Saverio Caini
- Cancer Risk Factors and Lifestyle Epidemiology Unit, Institute for Cancer Research, Prevention and Clinical Network (ISPO), Florence, Italy
| | - Julie Ryan Wolf
- Departments of Dermatology and Radiation Oncology, University of Rochester Medical Centre, Rochester, NY, USA
| | | | - Mara Beveridge
- Department of Dermatology, University Hospitals, Cleveland, OH, USA
| | - Henry Lam
- Sunnybrook Health Sciences Centre, University of Toronto, Toronto, ON, Canada
| | - Pierluigi Bonomo
- Department of Radiation Oncology, Azienda Ospedaliero-Universitaria Careggi, Florence, Italy
| | - Edward Chow
- Department of Radiation Oncology, University of Toronto, Toronto, ON, Canada
| | - Tara Behroozian
- Michael G. DeGroote School of Medicine, McMaster University, Hamilton, ON, Canada.
| |
Collapse
|
5
|
A pilot study of a novel method to visualize three-dimensional dose distribution on skin surface images to evaluate radiation dermatitis. Sci Rep 2022; 12:2729. [PMID: 35177737 PMCID: PMC8854641 DOI: 10.1038/s41598-022-06713-7] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/12/2021] [Accepted: 01/27/2022] [Indexed: 11/09/2022] Open
Abstract
Predicting the radiation dose‒toxicity relationship is important for local tumor control and patients’ quality of life. We developed a first intuitive evaluation system that directly matches the three-dimensional (3D) dose distribution with the skin surface image of patients with radiation dermatitis (RD) to predict RD in patients undergoing radiotherapy. Using an RGB-D camera, 82 3D skin surface images (3DSSIs) were acquired from 19 patients who underwent radiotherapy. 3DSSI data acquired included 3D skin surface shape and optical imaging of the area where RD occurs. Surface registration between 3D skin dose (3DSD) and 3DSSI is performed using the iterative closest point algorithm, then reconstructed as a two-dimensional color image. The developed system successfully matched 3DSSI and 3DSD, and visualized the planned dose distribution onto the patient's RD image. The dose distribution pattern was consistent with the occurrence pattern of RD. This new approach facilitated the evaluation of the direct correlation between skin-dose distribution and RD and, therefore, provides a potential to predict the probability of RD and thereby decrease RD severity by enabling informed treatment decision making by physicians. However, the results need to be interpreted with caution due to the small sample size.
Collapse
|
6
|
Morbidity in Patients with Nasopharyngeal Carcinoma and Radiation-Induced Skin Lesions: Cause, Risk Factors, and Dermatitis Evolution and Severity. Adv Skin Wound Care 2021; 34:1-8. [PMID: 34807900 DOI: 10.1097/01.asw.0000797952.41753.f4] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/14/2023]
Abstract
OBJECTIVE Radiation-induced skin injuries such as lesions (RSLs) and dermatitis are the most common complication during radiotherapy (RT) for nasopharyngeal carcinoma, but little is known about risk factors unique to oncology. This study sought a greater understanding of these risk factors to stratify patients based on risk and guide clinical decision-making. METHODS Investigators analyzed the data of 864 consecutive patients referred to the RT center of the Southern Theater General Hospital for a new RSL from 2013 to 2019. These patients were followed up for an average of approximately 16 months until their death or March 30, 2020, whichever came first. Multivariate logistic regression analysis and Cox proportional hazards model were used to identify predictors of grade 3 or 4 dermatitis. RESULTS The main causes of treatment interruption included dermatitis and oral mucositis. Significant patient-specific risk factors for RSLs included current smoking, current drinking, and lower Karnofsky Performance Scale score and significant procedure-specific risk factors included receiving intensity-modulated radiation therapy (IMRT), hyperfractionated RT, induction chemotherapy, multicycle chemotherapy, and taxol- and cisplatin-based drugs. The three factors that independently predicted risk of RSL were IMRT, lower Karnofsky Performance Scale score, and multicycle chemotherapy. Comparing predictive factors among patients with severe RSL revealed that patients who received IMRT were more likely to develop grade 3 or 4 dermatitis. CONCLUSIONS Oncology providers should note that IMRT is an aggressive technique with a trend toward increased RSL. Providers should pay special attention to adverse effects to skin in patients with nasopharyngeal carcinoma.
Collapse
|
7
|
Radiation-induced acute injury of intensity-modulated radiotherapy versus three-dimensional conformal radiotherapy in induction chemotherapy followed by concurrent chemoradiotherapy for locoregionally advanced nasopharyngeal carcinoma: a prospective cohort study. Sci Rep 2021; 11:7693. [PMID: 33833301 PMCID: PMC8032760 DOI: 10.1038/s41598-021-87170-6] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/06/2020] [Accepted: 03/22/2021] [Indexed: 11/26/2022] Open
Abstract
To address whether the addition of intensity-modulated radiotherapy (IMRT) compared to three-dimensional conformal radiotherapy (3D-CRT) aggravate radiation-induced acute injury of locoregionally advanced nasopharyngeal carcinoma (LANPC) patients with induction chemotherapy (IC) followed by concurrent chemoradiotherapy (CCRT). We conducted a prospective study of 182 patients in the stage III to IVb with biopsy-proven nonmetastatic LANPC who newly underwent radiotherapy and sequentially received IC, followed by CCRT at our institution. Occurring time of radiation-induced toxicities were estimated and compared using the Kaplan–Meier method and Log-rank test. The most severe acute toxicities included oral mucositis in 97.25% and dermatitis in 90.11%. Subset analysis revealed that Grade 3–4 acute dermatitis were significantly higher in the IMRT than 3D-CRT. Oral mucositis and dermatitis were the earliest occurrence of acute injuries (2 years: 60.44% and 17.58%). Patients in IMRT group achieved significantly lower risk of bone marrow toxicity, but higher risk of leukopenia and gastrointestinal injury. Multivariate analyses also demonstrated that IMRT, female gender and hepatitis were the independent prognostic factors for bone marrow toxicity. In a combined regimen of IC followed by CCRT for the treatment of LANPC, IMRT seems to be an aggressive technique with a trend towards increased gastrointestinal and hematological toxicities, but decreased bone marrow toxicity than those treated with 3D-CRT. This study provides a comprehensive summary of prospective evidence reporting the side effects in the management of LANPC patients. We quantify the occurrence risks of chemoradiotherapy-induced acute injuries through analysis of time-to-event.
Collapse
|
8
|
Yamazaki H, Suzuki G, Takenaka T, Yoshida K. Is there clinical meaningful threshold in dose volume analysis between grade 0-2 and 3-4 radiation dermatitis? Head Neck 2020; 42:2217-2218. [PMID: 32149452 DOI: 10.1002/hed.26115] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2020] [Accepted: 02/12/2020] [Indexed: 01/09/2023] Open
Affiliation(s)
- Hideya Yamazaki
- Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Gen Suzuki
- Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Tadashi Takenaka
- Department of Radiology, Graduate School of Medical Science, Kyoto Prefectural University of Medicine, Kyoto, Japan
| | - Ken Yoshida
- Department of Radiology, Osaka Medical College, Osaka, Japan
| |
Collapse
|
9
|
Bonomo P, Talamonti C, Caini S. Reply to Yamazaki et al (HED-19-525.R1). Head Neck 2020; 42:2219-2220. [PMID: 32149454 DOI: 10.1002/hed.26113] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2020] [Accepted: 02/12/2020] [Indexed: 11/07/2022] Open
Affiliation(s)
- Pierluigi Bonomo
- Azienda Ospedaliero-Universitaria Careggi, Radiation Oncology, Florence, Italy
| | - Cinzia Talamonti
- Azienda Ospedaliero-Universitaria Careggi, Medical Physics, Florence, Italy
| | - Saverio Caini
- Institute for Cancer Research, Prevention, and Clinical Network (ISPRO), Cancer Risk Factors and Lifestyle Epidemiology Unit, Florence, Italy
| |
Collapse
|