The impact of contour variation on tumour control probability in anal cancer

A deep learning-based self-adapting ensemble method for segmentation in gynecological brachytherapy

Purpose

Fast and accurate outlining of the organs at risk (OARs) and high-risk clinical tumor volume (HRCTV) is especially important in high-dose-rate brachytherapy due to the highly time-intensive online treatment planning process and the high dose gradient around the HRCTV. This study aims to apply a self-configured ensemble method for fast and reproducible auto-segmentation of OARs and HRCTVs in gynecological cancer.

Materials and methods

We applied nnU-Net (no new U-Net), an automatically adapted deep convolutional neural network based on U-Net, to segment the bladder, rectum and HRCTV on CT images in gynecological cancer. In nnU-Net, three architectures, including 2D U-Net, 3D U-Net and 3D-Cascade U-Net, were trained and finally ensembled. 207 cases were randomly chosen for training, and 30 for testing. Quantitative evaluation used well-established image segmentation metrics, including dice similarity coefficient (DSC), 95% Hausdorff distance (HD95%), and average surface distance (ASD). Qualitative analysis of automated segmentation results was performed visually by two radiation oncologists. The dosimetric evaluation was performed by comparing the dose-volume parameters of both predicted segmentation and human contouring.

Results

nnU-Net obtained high qualitative and quantitative segmentation accuracy on the test dataset and performed better than previously reported methods in bladder and rectum segmentation. In quantitative evaluation, 3D-Cascade achieved the best performance in the bladder (DSC: 0.936 ± 0.051, HD95%: 3.503 ± 1.956, ASD: 0.944 ± 0.503), rectum (DSC: 0.831 ± 0.074, HD95%: 7.579 ± 5.857, ASD: 3.6 ± 3.485), and HRCTV (DSC: 0.836 ± 0.07, HD95%: 7.42 ± 5.023, ASD: 2.094 ± 1.311). According to the qualitative evaluation, over 76% of the test data set had no or minor visually detectable errors in segmentation.

Conclusion

This work showed nnU-Net’s superiority in segmenting OARs and HRCTV in gynecological brachytherapy cases in our center, among which 3D-Cascade shows the highest accuracy in segmentation across different applicators and patient anatomy.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13014-022-02121-3.

Overview of Radiation Treatment Volume Variations in Anal Cancer Contouring Guidelines

Recently, the XXX guideline was published to describe recommended treatment volumes in patients with diagnosis of early-stage anal cancer. There are notable differences in descriptions for the both the primary target and elective nodal volumes when comparing this guideline with established guidelines from the United Kingdom National Cancer Research Institute, Australasian Gastrointestinal Trials Group and Radiation Therapy Oncology Group. Support for these volume differences is based on retrospective data, but ultimately, prospective data from ongoing clinical trials are needed to validate these approaches.

Impact of Peer Review in the Radiation Treatment Planning Process: Experience of a Tertiary Care University Hospital in Pakistan

PURPOSE

To evaluate and report the frequency of changes in radiation therapy treatment plans after peer review in a simulation review meeting once a week.

MATERIALS AND METHODS

Between July 1 and August 31, 2016, the radiation plans of 116 patients were discussed in departmental simulation review meetings. All plans were finalized by the primary radiation oncologist before presenting them in the meeting. A team of radiation oncologists reviewed each plan, and their suggestions were documented as no change, major change, minor change, or missing contour. Changes were further classified as changes in clinical target volume, treatment field, or dose. All recommendations were stratified on the basis of treatment intent, site, and technique. Data were analyzed by Statistical Package for the Social Sciences and are presented descriptively.

RESULTS

Out of 116 plans, 26 (22.4%) were recommended for changes. Minor changes were suggested in 15 treatment plans (12.9%) and a major change in 10 (8.6%), and only one plan was suggested for missing contour. The frequency of change recommendations was greater in radical radiation plans than in palliative plans (92.3% v 7.7%). The head and neck was the most common treatment site recommended for any changes (42.3%). Most of the changes were recommended in the technique planned with three-dimensional conformal radiation therapy (50%). Clinical target volume (73.1%) was identified as the most frequent parameter suggested for any change, followed by treatment field (19.2%) and dose (0.08%).

CONCLUSION

Peer review is an important tool that can be used to overcome deficiencies in radiation treatment plans, with a goal of improved and individualized patient care. Our study reports changes in up to a quarter of radiotherapy plans.