Automated applicator digitization for high-dose-rate cervix brachytherapy using image thresholding and density-based clustering

Abstract

The purpose of the study was to develop and evaluate an automated digitization algorithm for high-dose-rate cervix brachytherapy, with the goal of reducing the duration of treatment planning, staff resources, variability, and potential for human error. METHODS: An automated digitization algorithm was developed and retrospectively evaluated using treatment planning data from 10 patients with cervix cancer who were treated with a titanium tandem and ovoids applicator set. Applicators were segmented, without human interaction, by thresholding CT images to isolate high-density voxels and assigning the voxels to applicator and nonapplicator structures using HDBSCAN, a density-based linkage clustering algorithm. The applicator contours were determined from the centroid of the clustered voxels on each image slice and written to a treatment plan file. Automated contours were evaluated against manual digitization using distance and dosimetric metrics. RESULTS: A close agreement between automatic and manual digitization was observed. The mean magnitude of contour disagreement for 10 patients equaled 0.3 mm. Hausdorff distances were #1.0 mm. The applicator tip coordinates had submillimeter agreement. The median and mean dose volume histogram parameter differences were less than or equal to 1% for high-risk clinical target volume D 90 , high-risk clinical target volume D 95 , bladder D 2cc , rectum D 2cc , large bowel D 2cc , and small bowel D 2cc. The average execution time for the automated algorithm was less than 30 s. CONCLUSION: The digitization of titanium tandem and ovoids applicators for high-dose-rate brachytherapy treatment planning can be automated using straightforward thresholding and clustering algorithms. The adoption of automated digitization is expected to improve the consistency of treatment plans and reduce the duration of treatment planning.

Deep learning applications in automatic segmentation and reconstruction in CT-based cervix brachytherapy

“…Deufel et al applied image thresholding and densitybased clustering in applicator digitization. Their HDs were ≤ 1.0 mm, and the differences for HR-CTV D 90% , D 95% , and OARs D 2cc were less or equal to 1% [12]. In the present study, the DSC was 0.89, HD was 1.66 mm, the dosimetric differences for the target were less than 0.30%, and the maximum 2.64% for OARs D 2cc .…”

“…Before deep learning, researchers usually used threshold-based method to segment the applicator; however, this method still requires planners to define some points manually in clinical practice [5]. In recent years, more studies on automatic applicator reconstruction have been conducted based on deep learning [6][7][8][9][10][11][12].…”

“…The segmented applicator contour was composed by multiple points. We used a clustering method to create applicator contours as showed in reference [12]. For each channel, the average coordinate value of all points in one slice was calculated to obtain the trajectory of the channel central path.…”

AAPM task group report 303 endorsed by the ABS: MRI implementation in HDR brachytherapy—Considerations from simulation to treatment

“…92 The impact on dosimetric indices and DVHs (e.g., D2cc and D90, for OARs and targets, respectively) due to uncertainties in the applicator/needle reconstruction in 3D image-guided cervical BT has been well characterized by various investigators. [93][94][95][96][97] In general, the overall conclusion is that if the reconstruction error is within ±2 mm, the major dosimetric indices for both the target and OARs remain within 1-2%, on average, with variations of up to σ = 1-3% for individual cases, and with the magnitude being larger for OARs than targets.This is due to the geometric location of the OARs that generally are in higher dose gradient regions. Individual findings include Schindel et al, 93 who simulated the applicator shifts and concluded that to avoid a greater than 10% variation in the relevant dosimetric indices, the reconstruction uncertainty should be managed to be less than 3 mm.…”

Texture Feature Extraction and Morphological Analysis of Landslide Based on Image Edge Detection

“…e purpose of image digitization is to convert continuous analog images into discrete digital images [17]. Sampling quantization or coding is usually used to convert the original continuous space and brightness into discrete space and brightness.…”