Radiotherapy for mediastinal lymphoma in breath hold using surface monitoring and nasal high flow oxygen: Clinical experiences and breath hold stability

PURPOSE

In this study we describe the clinical introduction and evaluation of radiotherapy in mediastinal lymphoma in breath hold using surface monitoring combined with nasal high flow therapy (NHFT) to prolong breath hold duration.

MATERIALS AND METHODS

11 Patients with mediastinal lymphoma were evaluated. 6 Patients received NHFT, 5 patients were treated in breath hold without NHFT. Breath hold stability as measured by a surface scanning system was evaluated, as well as internal movement based on cone beam computed tomography (CBCT) before and after treatment. Based on internal movement, margins were determined. In a parallel planning study we compared free breathing plans with breath hold plans using the determined margins.

RESULTS

Average inter breath hold stability was 0.6 mm for NHFT treatments, and 0.5 mm for non-NHFT treatments (p > 0.1). Intra breath hold stability was 0.8 vs. 0.6 mm (p > 0.1) on average. Using NHFT, average breath hold duration increased from 34 s to 60 s (p < 0.01). Residual CTV motion derived from CBCTs before and after each fraction was 2.0 mm for NHFT vs 2.2 mm for non-NHFT (p > 0.1). Combined with inter-fraction motion, a uniform mediastinal margin of 5 mm appears to be sufficient. In breath hold, mean lung dose is reduced by 2.6 Gy (p < 0.001), while mean heart dose is reduced by 2.0 Gy (p < 0.001).

CONCLUSION

Treatment of mediastinal lymphoma in breath hold is feasible and safe. The addition of NHFT approximately increases breath hold durations with a factor two while stability is maintained. By reducing breathing motion, margins can be decreased to 5 mm. A considerable dose reduction in heart, lungs, esophagus, and breasts can be achieved with this method.

Real-world analysis of manual editing of deep learning contouring in the thorax region

•

Deep-learning contouring for radiotherapy is evaluated in the thorax region.

•

Specific regions-of-adjustment and variability in editing per organ were found.

•

The consistency and accuracy of training data remains crucial to model performance.

•

Separate models for specific indications or acquisition protocols may be necessary.

•

Subsampling and post-processing make the clinical workflow more efficient.

Background and purpose

User-adjustments after deep-learning (DL) contouring in radiotherapy were evaluated to get insight in real-world editing during clinical practice. This study assessed the amount, type and spatial regions of editing of auto-contouring for organs-at-risk (OARs) in routine clinical workflow for patients in the thorax region.

Materials and methods

A total of 350 lung cancer and 362 breast cancer patients, contoured between March 2020 and March 2021 using a commercial DL-contouring method followed by manual adjustments were retrospectively analyzed. Subsampling was performed for some OARs, using an inter-slice gap of 1–3 slices. Commonly-used whole-organ contouring assessment measures were calculated, and all cases were registered to a common reference shape per OAR to identify regions of manual adjustment. Results were expressed as the median, 10th-90th percentile of adjustment and visualized using 3D renderings.

Results

Per OAR, the median amount of editing was below 1 mm. However, large adjustments were found in some locations for most OARs. In general, enlarging of the auto-contours was needed. Subsampling DL-contours showed less adjustments were made in the interpolated slices compared to simulated no-subsampling for these OARs.

Conclusion

The real-world performance of automatic DL-contouring software was evaluated and proven useful in clinical practice. Specific regions-of-adjustment were identified per OAR in the thorax region, and separate models were found to be necessary for specific clinical indications different from training data. This analysis showed the need to perform routine clinical analysis especially when procedures or acquisition protocols change to have the best configuration of the workflow.