IMPT of head and neck cancer: unsupervised machine learning treatment planning strategy for reducing radiation dermatitis

Padannayil, Noufal Manthala; Sharma, Dayananda Shamurailatpam; Nangia, Sapna; Patro, Kartikeswar; Gaikwad, Utpal; Burela, Nagarjuna

doi:10.1186/s13014-023-02201-y

Cited by 3 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The role of treatment plan physical quantities including skin dose distribution and dose volume histograms (DVHs) [ 7 , 8 ], as well as patient’s demographic and clinical characteristics have been investigated in predicting AST in breast RT by several investigators [ 9 , 10 ]. However, DVHs lack spatial information of the dose of treatment plans [ 11 ].…”

Section: Introductionmentioning

confidence: 99%

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

Saadatmand,

Mahdavi,

Nikoofar

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

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.

show abstract

Section: Introductionmentioning

confidence: 99%

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

Saadatmand,

Mahdavi,

Nikoofar

et al. 2024

Eur J Med Res

View full text Add to dashboard Cite

show abstract

Impact of Dosimetric Compromises on Early Outcomes of Chordomas and Chondrosarcomas Treated With Image-guided Pencil Beam Scanning Proton Beam Therapy

Chilukuri,

Burela,

Sundar

et al. 2024

Advances in Radiation Oncology

View full text Add to dashboard Cite

Quantifying the Dosimetric Impact of Proton Range Uncertainties on RBE-Weighted Dose Distributions in Intensity-Modulated Proton Therapy for Bilateral Head and Neck Cancer

Rana,

Manthala Padannayil,

Tran

et al. 2024

Current Oncology

View full text Add to dashboard Cite

Background: In current clinical practice, intensity-modulated proton therapy (IMPT) head and neck cancer (HNC) plans are generated using a constant relative biological effectiveness (cRBE) of 1.1. The primary goal of this study was to explore the dosimetric impact of proton range uncertainties on RBE-weighted dose (RWD) distributions using a variable RBE (vRBE) model in the context of bilateral HNC IMPT plans. Methods: The current study included the computed tomography (CT) datasets of ten bilateral HNC patients who had undergone photon therapy. Each patient’s plan was generated using three IMPT beams to deliver doses to the CTV_High and CTV_Low for doses of 70 Gy(RBE) and 54 Gy(RBE), respectively, in 35 fractions through a simultaneous integrated boost (SIB) technique. Each nominal plan calculated with a cRBE of 1.1 was subjected to the range uncertainties of ±3%. The McNamara vRBE model was used for RWD calculations. For each patient, the differences in dosimetric metrices between the RWD and nominal dose distributions were compared. Results: The constrictor muscles, oral cavity, parotids, larynx, thyroid, and esophagus showed average differences in mean dose (Dmean) values up to 6.91 Gy(RBE), indicating the impact of proton range uncertainties on RWD distributions. Similarly, the brachial plexus, brain, brainstem, spinal cord, and mandible showed varying degrees of the average differences in maximum dose (Dmax) values (2.78–10.75 Gy(RBE)). The Dmean and Dmax to the CTV from RWD distributions were within ±2% of the dosimetric results in nominal plans. Conclusion: The consistent trend of higher mean and maximum doses to the OARs with the McNamara vRBE model compared to cRBE model highlighted the need for consideration of proton range uncertainties while evaluating OAR doses in bilateral HNC IMPT plans.

show abstract

IMPT of head and neck cancer: unsupervised machine learning treatment planning strategy for reducing radiation dermatitis

Cited by 3 publications

References 26 publications

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

A dosiomics model for prediction of radiation-induced acute skin toxicity in breast cancer patients: machine learning-based study for a closed bore linac

Impact of Dosimetric Compromises on Early Outcomes of Chordomas and Chondrosarcomas Treated With Image-guided Pencil Beam Scanning Proton Beam Therapy

Quantifying the Dosimetric Impact of Proton Range Uncertainties on RBE-Weighted Dose Distributions in Intensity-Modulated Proton Therapy for Bilateral Head and Neck Cancer

Contact Info

Product

Resources

About