Dosimetric impact of inter-observer catheter reconstruction variability in ultrasound-based high-dose-rate prostate brachytherapy

Nicolae, Alexandru; Murgić, Jure; Kruljac, Ivan; Dubnitzky, Lior; D’Alimonte, Laura; Lü, Lin; Cumal, Aaron; Law, Niki; Morton, Gerard; Loblaw, Andrew; Chung, Hans T.; Ravi, Ananth

doi:10.1016/j.brachy.2017.10.015

Cited by 4 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, our study used a larger dataset with a wide range of catheter difficulties, including obscured catheters reconstructed on live ultrasound. Secondly, their model was trained on retrospective catheters reconstructed by a single observer, allowing their model to predict well below the expected 2–3 mm interobserver variability 22 . In contrast, our true catheters were reconstructed during the clinical procedure by different planners.…”

Section: Discussionmentioning

confidence: 99%

“…Predictions were considered accurate if they were within 2 mm of the true catheter in the transverse plane, representing the expected interobserver variability. 22 The overall performance of the deep learning model prior to 3D catheter reconstruction was assessed using a confusion matrix. 23 Each 2D prediction was classified as either a true positive (i.e., within 2 mm of a true catheter) or a false positive.…”

Section: Analysis and Metricsmentioning

confidence: 99%

“…The reconstructed catheters imported into the treatment planning system below the expected 2-3 mm interobserver variability. 22 In contrast, our true catheters were reconstructed during the clinical procedure by different planners. Wang et al employed two deep learning models 17 : a 2D UNET architecture to detect the catheter shaft and a modified VGG16 model for tip detection.…”

Section: Other Literaturementioning

confidence: 99%

“…Nicolae et al investigated the dosimetric impact of interobserver catheter reconstruction variability. 22 Reconstruction variations of 1-3 mm were observed, potentially reducing target coverage and increasing dose to proximal critical structures. Under the proposed workflow, the planner modifies the catheters as needed to ensure accurate reconstruction.…”

Section: Proposed Clinical Workflowmentioning

confidence: 99%

See 3 more Smart Citations

The challenges facing deep learning–based catheter localization for ultrasound guided high‐dose‐rate prostate brachytherapy

et al. 2022

View full text Add to dashboard Cite

Background: Automated catheter localization for ultrasound guided high-doserate prostate brachytherapy faces challenges relating to imaging noise and artifacts. To date, catheter reconstruction during the clinical procedure is performed manually. Deep learning has been successfully applied to a wide variety of complex tasks and has the potential to tackle the unique challenges associated with multiple catheter localization on ultrasound. Such a task is well suited for automation, with the potential to improve productivity and reliability. Purpose: We developed a deep learning model for automated catheter reconstruction and investigated potential factors influencing model performance. The model was designed to integrate into a clinical workflow, with a proposed reconstruction confidence metric to aid in planner verification. Methods: Datasets from 242 patients treated from 2016 to 2020 were collected retrospectively. The anonymized dataset comprises 31,000 transverse images reconstructed from 3D sagittal ultrasound acquisitions and 3500 implanted catheters manually localized by the planner. Each catheter was retrospectively ranked based on the severity of imaging artifacts affecting reconstruction difficulty. The U-NET deep learning architecture was trained to localize implanted catheters on transverse images. A fivefold cross-validation method was used, allowing for evaluation over the entire dataset. The postprocessing software combined the predictions with patient-specific implant information to reconstructed catheters in 3D space,uniquely matched to the implanted grid positions. A reconstruction confidence metric was calculated based on the number and probability of localized predictions per catheter. For each patient, deep learning prediction and postprocessing reconstruction were completed in under 2 min on a nonperformance PC. Results: Overall, 80% of catheter reconstructions were accurate, within 2 mm along 90% of the length. The catheter tip was often not detected and required extrapolation during reconstruction. The reconstruction accuracy was 89% for the easiest catheter ranking and decreased to 13% for the highest difficulty ranking, when the aid of live ultrasound would have been recommended. Even when limited to the easiest ranked catheters, the reconstruction accuracy decreased at distal grid positions, down to 50%. Individual implantation style was found to influence the frequency of severe artifacts, slightly impacting the model accuracy. A reconstruction confidence metric identified the difficult catheters, removed the observed individual variation, and increased the overall accuracy to 91% while excluding 27% of the reconstructions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Analysis and Metricsmentioning

confidence: 99%

Section: Other Literaturementioning

confidence: 99%

Section: Proposed Clinical Workflowmentioning

confidence: 99%

See 2 more Smart Citations

The challenges facing deep learning–based catheter localization for ultrasound guided high‐dose‐rate prostate brachytherapy

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For a human operator, the mean time spent was 10 min 11 s per patient. Nicolae et al presented a mean time of 7.50 min per patient with 12-16 needles, 35 which would mean 10 min 42 s per patient if the patient had 20 needles. This is well in line with the time for manual digitization measured in this study.…”

Section: Discussionmentioning

confidence: 99%

Deep learning‐based digitization of prostate brachytherapy needles in ultrasound images

et al. 2020

View full text Add to dashboard Cite

To develop, and evaluate the performance of, a deep learning-based three-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) algorithm aimed at finding needles in ultrasound images used in prostate brachytherapy. Methods: Transrectal ultrasound (TRUS) image volumes from 1102 treatments were used to create a clinical ground truth (CGT) including 24422 individual needles that had been manually digitized by medical physicists during brachytherapy procedures. A 3D CNN U-net with 128 × 128 × 128 TRUS image volumes as input was trained using 17215 needle examples. Predictions of voxels constituting a needle were combined to yield a 3D linear function describing the localization of each needle in a TRUS volume. Manual and AI digitizations were compared in terms of the root-mean-square distance (RMSD) along each needle, expressed as median and interquartile range (IQR). The method was evaluated on a data set including 7207 needle examples. A subgroup of the evaluation data set (n = 188) was created, where the needles were digitized once more by a medical physicist (G1) trained in brachytherapy. The digitization procedure was timed. Results: The RMSD between the AI and CGT was 0.55 (IQR: 0.35-0.86) mm. In the smaller subset, the RMSD between AI and CGT was similar (0.52 [IQR: 0.33-0.79] mm) but significantly smaller (P < 0.001) than the difference of 0.75 (IQR: 0.49-1.20) mm between AI and G1. The difference between CGT and G1 was 0.80 (IQR: 0.48-1.18) mm, implying that the AI performed as well as the CGT in relation to G1. The mean time needed for human digitization was 10 min 11 sec, while the time needed for the AI was negligible. Conclusions: A 3D CNN can be trained to identify needles in TRUS images. The performance of the network was similar to that of a medical physicist trained in brachytherapy. Incorporating a CNN for needle identification can shorten brachytherapy treatment procedures substantially.

show abstract

A surrogate urethra for real-time planning of high-dose-rate prostate brachytherapy

et al. 2019

View full text Add to dashboard Cite

Dosimetric impact of inter-observer catheter reconstruction variability in ultrasound-based high-dose-rate prostate brachytherapy

Cited by 4 publications

References 26 publications

The challenges facing deep learning–based catheter localization for ultrasound guided high‐dose‐rate prostate brachytherapy

The challenges facing deep learning–based catheter localization for ultrasound guided high‐dose‐rate prostate brachytherapy

Deep learning‐based digitization of prostate brachytherapy needles in ultrasound images

A surrogate urethra for real-time planning of high-dose-rate prostate brachytherapy

Contact Info

Product

Resources

About