Automatic segmentation for adaptive planning in nasopharyngeal carcinoma IMRT: Time, geometrical, and dosimetric analysis.

The aim of this study was to quantify the geometrical differences between manual contours and autocontours, the dosimetric impacts, and the time gain of using autosegmentation in adaptive nasopharyngeal carcinoma (NPC) intensity-modulated radiotherapy (IMRT) for a commercial system. A total of 20 consecutive Stages I to III NPC patients who had undergone adaptive radiation therapy (ART) re planning for IMRT treatment were retrospectively studied. Manually delineated organs at risks (OARs) on the replanning computed tomography (CT) were compared with the autocontours generated by VelocityAI using deformable registration from the original planning CT. Dice similarity coefficients and distance-to-agreements (DTAs) were used to quantify their geometric differences. IMRT test plans were generated with the assistance of RapidPlan based on the autocontours of OARs and manually segmented target volumes. The dose distributions were applied on the manually delineated OARs, their dose volume histograms and dose constraints compliances were analyzed. Times spent on target, OAR contouring, and IMRT replanning were recorded, and the total time of replanning using manual contouring and autocontouring were compared. The averaged mean DTA of all structures included in the study were less than 2 mm, and 90% of the patients fulfilled the mean distance agreement tolerance recommended by AAPM 132.1 The averaged maximum DTA for brainstem, cord, optic chiasm, and optic nerves were all less than 4 mm, whereas temporal lobes and parotids have larger average maximum DTA of 4.7 mm and 6.8 mm, respectively. It was found that large contour discrepancies in temporal lobes and parotids were often associated with large magnitude of deformation (warp distance) in image registrations. The resultant maximum dose of manually segmented brainstem, cord, and temporal lobe and the median dose of manually segmented parotids were found to be statistically higher than those to their autocontoured counter parts in test plans. Dose constraints of the manually segmented OARs in test plans were only met in 15% of the cases. The average time of manual contouring and autocontouring were 108 and 10 minutes, respectively (p < 0.001). More than 30% of the total replanning time would be spent in manual OAR contouring. Manual OAR delineation takes up a significant portion of time spent in ART replanning and OAR autocontouring could considerably enhance ART workflow efficiency. Geometrical discrepancies between auto- and manual contours in head and neck OARs were comparable to typical interobserver variation suggested in various literatures; however, some of the corresponding dosimetric differences were substantial, making it essential to carefully review the autocontours.

Fung NTC ，Hung WM ，Sze CK ，Lee MCH ，Ng WT ... -  《-》

The dosimetric impact of deep learning-based auto-segmentation of organs at risk on nasopharyngeal and rectal cancer.

Guo H ，Wang J ，Xia X ，Zhong Y ，Peng J ，Zhang Z ，Hu W ... -  《Radiation Oncology》

Determining appropriate timing of adaptive radiation therapy for nasopharyngeal carcinoma during intensity-modulated radiation therapy.

Huang H ，Lu H ，Feng G ，Jiang H ，Chen J ，Cheng J ，Pang Q ，Lu Z ，Gu J ，Peng L ，Deng S ，Mo Y ，Wu D ，Wei Y ... -  《-》

Dosimetric evaluation of automatic and manual plans for early nasopharyngeal carcinoma to radiotherapy.

To investigate dosimetric differences and plan qualities between manual plans and automatic plans for nasopharyngeal carcinoma (NPC) in early stage, and provide better options to maximize the benefits. Sixteen cases diagnosed with early NPC were retrospectively investigated. Conventional step and shoot IMRT with 7-fields and full arc volumetric-modulated arc therapy (VMAT) with double arcs were manually generated by experienced planners and automatically generated by Auto-Planning module in Pinnacle3 respectively, such as IMRT manual-planning (mIMRT), IMRT auto-planning (aIMRT), VMAT manual-planning (mVMAT), and VMAT auto-planning (aVMAT) for each patient. Target coverage, organs at risk sparing, monitor units, and planning times were compared and evaluated. All parameters of plans are able to fulfill International Commission on Radiation Units and Measurements repor (ICRU) 83 recommendations. Automatic plans are comparable or superior to manual plans without time-consuming planning process. The CI and HI for PTVs are better in aVMAT when compared with aIMRT and mVMAT, but those are similar between aIMRT and mVMAT. Automatic plans not only have superior dose homogeneity and conformity in PTVs, but also have better sparing for spinal cord or slightly reduce the doses received by other OARs, while the VMAT plans have better sparing for brain stem, especially the aVMAT plans. However, Dmax, V30, and V40 of brain stem are similar between aIMRT and mVMAT without significant difference. The monitor units and planning time for treatment plans have been significantly decreased through automatic planning technique. The automatic VMAT plan has greater clinical advantages and should be recommended to a better option for treating NPC in early stage, while automatic IMRT would be preferentially considered instead of manual VMAT.

Zhang Q ，Peng Y ，Song X ，Yu H ，Wang L ，Zhang S ... -  《-》

Dosimetric comparison between 2-dimensional radiation therapy and intensity modulated radiation therapy in treatment of advanced T-stage nasopharyngeal carcinoma: to treat less or more in the planning organ-at-risk volume of the brainstem and spinal cord.

Chau RM ，Teo PM ，Kam MK ，Leung SF ，Cheung KY ，Chan AT ... -  《-》