Radiotherapy dose-volume parameters predict facial lymphedema after concurrent chemoradiation for nasopharyngeal carcinoma

Determining risk and predictors of head and neck cancer treatment-related lymphedema: A clinicopathologic and dosimetric data mining approach using interpretable machine learning and ensemble feature selection

Background and purpose

The ability to determine the risk and predictors of lymphedema is vital in improving the quality of life for head and neck (HN) cancer patients. However, selecting robust features is challenging due to the multicollinearity and high dimensionality of radiotherapy (RT) data. This study aims to overcome these challenges using an ensemble feature selection technique with machine learning (ML).

Materials and methods

Thirty organs-at-risk, including bilateral cervical lymph node levels, were contoured, and dose-volume data were extracted from 76 HN treatment plans. Clinicopathologic data was collected. Ensemble feature selection was used to reduce the number of features. Using the reduced features as input to ML and competing risk models, internal and external lymphedema prediction capability was evaluated with the ML models, and time to lymphedema event and risk stratification were estimated using the risk models.

Results

Two ML models, XGBoost and random forest, exhibited robust prediction performance. They achieved average F1-scores and AUCs of 84 ± 3.3 % and 79 ± 11.9 % (external lymphedema), and 64 ± 12 % and 78 ± 7.9 % (internal lymphedema). Predictive ML and risk models identified common predictors, including bulky node involvement, high dose to various lymph node levels, and lymph nodes removed during surgery. At 180 days, removing 0-25, 26-50, and > 50 lymph nodes increased external lymphedema risk to 72.1 %, 95.6 %, and 57.7 % respectively (p = 0.01).

Conclusion

Our approach, involving the reduction of HN RT data dimensionality, resulted in effective ML models for HN lymphedema prediction. Predictive dosimetric features emerged from both predictive and competing risk models. Consistency with clinicopathologic features from other studies supports our methodology.

Refining Target Volume Coverage After Parotidectomy for Cutaneous Squamous Cell Carcinoma: Omission of the Cervical Neck From the Radiation Field

Purpose

For patients without pathologic evidence of cervical disease after neck dissection for cutaneous squamous cell carcinoma involving the parotid region, inclusion of the ipsilateral cervical neck in the postparotidectomy radiation volume is routinely performed. We report our experience with selective avoidance of the ipsilateral neck for patients undergoing postoperative radiation to the parotid bed.

Methods and Materials

From January 2014 to December 2023, a total of 30 consecutive patients underwent postoperative radiation after parotidectomy for cutaneous squamous cell carcinoma involving the parotid area. All patients had previously had a neck dissection confirming pathologic N0 disease. Treatment was delivered using intensity modulated radiation therapy to a median dose of 60 Gy (range, 56-66 Gy). The radiation target volumes included the parotid bed only, with deliberate avoidance of the ipsilateral cervical neck. The median pathologic tumor size of the parotid tumor was 3.3 cm (range, 0.2-9.4 cm). Final pathologic evaluation showed positive microscopic margins in 8 patients (27%), perineural invasion in 17 patients (57%), and facial nerve involvement in 6 patients (20%).

Results

There were no isolated nodal failures. One patient developed an ipsilateral neck recurrence approximately 8 months after completion of radiation therapy. This occurred 2 months subsequent to the development of local recurrence. The 5-year actuarial rates of local (parotid) control, neck control, and overall survival were 87%, 97%, and 76%, respectively.

Conclusions

Omission of the ipsilateral neck from the parotid volume does not compromise disease control for pathologically N0 patients undergoing postoperative radiation for cutaneous squamous cell carcinoma involving the parotid region. Practical implications are discussed.