Implementation of Deep Learning-Based Auto-Segmentation for Radiotherapy Planning Structures: A Multi-Center Workflow Study

Transformer guided progressive fusion network for 3D pancreas and pancreatic mass segmentation

Pancreatic masses are diverse in type, often making their clinical management challenging. This study aims to address the task of various types of pancreatic mass segmentation and detection while accurately segmenting the pancreas. Although convolution operation performs well at extracting local details, it experiences difficulty capturing global representations. To alleviate this limitation, we propose a transformer guided progressive fusion network (TGPFN) that utilizes the global representation captured by the transformer to supplement long-range dependencies lost by convolution operations at different resolutions. TGPFN is built on a branch-integrated network structure, where the convolutional neural network and transformer branches first perform separate feature extraction in the encoder, and then the local and global features are progressively fused in the decoder. To effectively integrate the information of the two branches, we design a transformer guidance flow to ensure feature consistency, and present a cross-network attention module to capture the channel dependencies. Extensive experiments with nnUNet (3D) show that TGPFN improves the mass segmentation (Dice: 73.93% vs. 69.40%) and detection accuracy (detection rate: 91.71% vs. 84.97%) on 416 private CTs, and also obtains performance improvements of mass segmentation (Dice: 43.86% vs. 42.07%) and detection (detection rate: 83.33% vs. 71.74%) on 419 public CTs.

Evaluating the Effectiveness of Deep Learning Contouring across Multiple Radiotherapy Centres

Background and purpose

Deep learning contouring (DLC) has the potential to decrease contouring time and variability of organ contours. This work evaluates the effectiveness of DLC for prostate and head and neck across four radiotherapy centres using a commercial system.

Materials and methods

Computed tomography scans of 123 prostate and 310 head and neck patients were evaluated. Besides one head and neck model, generic DLC models were used. Contouring time using centres' existing clinical methods and contour editing time after DLC were compared. Timing was evaluated using paired and non-paired studies. Commercial software or in-house scripts assessed dice similarity coefficient (DSC) and distance to agreement (DTA). One centre assessed head and neck inter-observer variability.

Results

The mean contouring time saved for prostate structures using DLC compared to the existing clinical method was 5.9 ± 3.5 min. The best agreement was shown for the femoral heads (median DSC 0.92 ± 0.03, median DTA 1.5 ± 0.3 mm) and the worst for the rectum (median DSC 0.68 ± 0.04, median DTA 4.6 ± 0.6 mm). The mean contouring time saved for head and neck structures using DLC was 16.2 ± 8.6 min. For one centre there was no DLC time-saving compared to an atlas-based method. DLC contours reduced inter-observer variability compared to manual contours for the brainstem, left parotid gland and left submandibular gland.

Conclusions

Generic prostate and head and neck DLC models can provide time-savings which can be assessed with paired or non-paired studies to integrate with clinical workload. Reducing inter-observer variability potential has been shown.

Training and Validation of Deep Learning-Based Auto-Segmentation Models for Lung Stereotactic Ablative Radiotherapy Using Retrospective Radiotherapy Planning Contours

PURPOSE

Deep learning-based auto-segmented contour (DC) models require high quality data for their development, and previous studies have typically used prospectively produced contours, which can be resource intensive and time consuming to obtain. The aim of this study was to investigate the feasibility of using retrospective peer-reviewed radiotherapy planning contours in the training and evaluation of DC models for lung stereotactic ablative radiotherapy (SABR).

METHODS

Using commercial deep learning-based auto-segmentation software, DC models for lung SABR organs at risk (OAR) and gross tumor volume (GTV) were trained using a deep convolutional neural network and a median of 105 contours per structure model obtained from 160 publicly available CT scans and 50 peer-reviewed SABR planning 4D-CT scans from center A. DCs were generated for 50 additional planning CT scans from center A and 50 from center B, and compared with the clinical contours (CC) using the Dice Similarity Coefficient (DSC) and 95% Hausdorff distance (HD).

RESULTS

Comparing DCs to CCs, the mean DSC and 95% HD were 0.93 and 2.85mm for aorta, 0.81 and 3.32mm for esophagus, 0.95 and 5.09mm for heart, 0.98 and 2.99mm for bilateral lung, 0.52 and 7.08mm for bilateral brachial plexus, 0.82 and 4.23mm for proximal bronchial tree, 0.90 and 1.62mm for spinal cord, 0.91 and 2.27mm for trachea, and 0.71 and 5.23mm for GTV. DC to CC comparisons of center A and center B were similar for all OAR structures.

CONCLUSIONS

The DCs developed with retrospective peer-reviewed treatment contours approximated CCs for the majority of OARs, including on an external dataset. DCs for structures with more variability tended to be less accurate and likely require using a larger number of training cases or novel training approaches to improve performance. Developing DC models from existing radiotherapy planning contours appears feasible and warrants further clinical workflow testing.