Fully Automatic Treatment Planning for External-Beam Radiation Therapy of Locally Advanced Cervical Cancer: A Tool for Low-Resource Clinics

Abstract

Purpose: The purpose of this study was to validate a fully automatic treatment planning system for conventional radiotherapy of cervical cancer. This system was developed to mitigate staff shortages in low-resource clinics.

Methods: In collaboration with hospitals in South Africa and the United States, we have developed the Radiation Planning Assistant (RPA), which includes algorithms for automating every step of planning: delineating the body contour, detecting the marked isocenter, designing the treatment-beam apertures, and optimizing the beam weights to minimize dose heterogeneity. First, we validated the RPA retrospectively on 150 planning computed tomography (CT) scans. We then tested it remotely on 14 planning CT scans at two South African hospitals. Finally, automatically planned treatment beams were clinically deployed at our institution.

Results: The automatically and manually delineated body contours agreed well (median mean surface distance, 0.6 mm; range, 0.4 to 1.9 mm). The automatically and manually detected marked isocenters agreed well (mean difference, 1.1 mm; range, 0.1 to 2.9 mm). In validating the automatically designed beam apertures, two physicians, one from our institution and one from a South African partner institution, rated 91% and 88% of plans acceptable for treatment, respectively. The use of automatically optimized beam weights reduced the maximum dose significantly (median, -1.9%; P < .001). Of the 14 plans from South Africa, 100% were rated clinically acceptable. Automatically planned treatment beams have been used for 24 patients with cervical cancer by physicians at our institution, with edits as needed, and its use is ongoing.

Conclusion: We found that fully automatic treatment planning is effective for cervical cancer radiotherapy and may provide a reliable option for low-resource clinics. Prospective studies are ongoing in the United States and are planned with partner clinics.

Fig 1

Automatically created treatment fields. Beam’s eye view of the (A) anteroposterior (AP) and (B) right lateral beam angles. The beam apertures are designed on the basis of the bony anatomy and will be collimated using the multileaf collimator.

Fig 2

Body contour and marked isocenter. (A-C) Three views, (A) axial, (B) sagittal, and (C) coronal, of the computed tomography scan of a patient. The automatically segmented body contour is outlined in red. The views intersect at the location of the marked isocenter (green), which is determined on the basis of the radiopaque external fiducials. The intersecting planes are denoted by the dashed yellow line.

Fig 3

Workflow of the algorithm that automatically designs four-field box treatment beams. For automated planning, the only input is a computed tomography scan and a prescription. No other human input is required, and a plan is presented for physician review. 2D, two dimensional; 3D, three dimensional; BEV, beam’s eye view

Fig 4

Maximum dose was reduced using automatic beam-weight optimization. The maximum dose (hottest 1 cc) is shown for each patient (n = 149) as a percentage of the prescription dose for optimized versus equal beam weights (nonoptimized). The dotted line represents no change in the maximum dose, and all points below this line showed a reduction in the maximum dose. The reduction was especially large for patients who had very high maximum doses using equal beam weights.

Fig 5

Patient plans with high maximum doses experience a substantial reduction in the maximum dose with automatic beam-weight optimization. The resulting dose distribution for an (A) automatically planned four-field box with equal beam weights (nonoptimized) and (B) automatically optimized beam weights. The maximum dose was reduced from 117% to 107% of the prescription dose for this patient.