EUVIMEDEUVIMED entdecken
Crossref

Deep learning‐based ultrasound auto‐segmentation of the prostate with brachytherapy implanted needles

Prakash Hampole, Thomas Harding, Derek Gillies, Nathan Orlando, Chandima Edirisinghe, Lucas C Mendez, David D'Souza, Vikram Velker, Rohann Correa, Joelle Helou, Shuwei Xing, Aaron Fenster und 1 weitere

Medical Physics · 2024

DOI: 10.1002/mp.16811 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Medical Physics, 2024. Verfasst von Prakash Hampole und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Biophysics, Western University, London, ON, Canada. Hauptthemen laut MEDLINE: Deep Learning, Brachytherapy, Prostatic Neoplasms. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 21 Literaturangaben. Gefördert von: Ontario Institute of Cancer Research (OICR), the Canadian Institutes of Health Research, the Natural Sciences and Engineering Research Council of Canada (NSERC).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate segmentation of the clinical target volume (CTV) corresponding to the prostate with or without proximal seminal vesicles is required on transrectal ultrasound (TRUS) images during prostate brachytherapy procedures. Implanted needles cause artifacts that may make this task difficult and time‐consuming. Thus, previous studies have focused on the simpler problem of segmentation in the absence of needles at the cost of reduced clinical utility.

Purpose

To use a convolutional neural network (CNN) algorithm for segmentation of the prostatic CTV in TRUS images post‐needle insertion obtained from prostate brachytherapy procedures to better meet the demands of the clinical procedure.

Methods

A dataset consisting of 144 3‐dimensional (3D) TRUS images with implanted metal brachytherapy needles and associated manual CTV segmentations was used for training a 2‐dimensional (2D) U‐Net CNN using a Dice Similarity Coefficient (DSC) loss function. These were split by patient, with 119 used for training and 25 reserved for testing. The 3D TRUS training images were resliced at radial (around the axis normal to the coronal plane) and oblique angles through the center of the 3D image, as well as axial, coronal, and sagittal planes to obtain 3689 2D TRUS images and masks for training. The network generated boundary predictions on 300 2D TRUS images obtained from reslicing each of the 25 3D TRUS images used for testing into 12 radial slices (15° apart), which were then reconstructed into 3D surfaces. Performance metrics included DSC, recall, precision, unsigned and signed volume percentage differences (VPD/sVPD), mean surface distance (MSD), and Hausdorff distance (HD). In addition, we studied whether providing algorithm‐predicted boundaries to the physicians and allowing modifications increased the agreement between physicians. This was performed by providing a subset of 3D TRUS images of five patients to five physicians who segmented the CTV using clinical software and repeated this at least 1 week apart. The five physicians were given the algorithm boundary predictions and allowed to modify them, and the resulting inter‐ and intra‐physician variability was evaluated.

Results

Median DSC, recall, precision, VPD, sVPD, MSD, and HD of the 3D‐reconstructed algorithm segmentations were 87.2 [84.1, 88.8]%, 89.0 [86.3, 92.4]%, 86.6 [78.5, 90.8]%, 10.3 [4.5, 18.4]%, 2.0 [−4.5, 18.4]%, 1.6 [1.2, 2.0] mm, and 6.0 [5.3, 8.0] mm, respectively. Segmentation time for a set of 12 2D radial images was 2.46 [2.44, 2.48] s. With and without U‐Net starting points, the intra‐physician median DSCs were 97.0 [96.3, 97.8]%, and 94.4 [92.5, 95.4]% ( p < 0.0001), respectively, while the inter‐physician median DSCs were 94.8 [93.3, 96.8]% and 90.2 [88.7, 92.1]%, respectively ( p < 0.0001). The median segmentation time for physicians, with and without U‐Net‐generated CTV boundaries, were 257.5 [211.8, 300.0] s and 288.0 [232.0, 333.5] s, respectively ( p = 0.1034).

Conclusions

Our algorithm performed at a level similar to physicians in a fraction of the time. The use of algorithm‐generated boundaries as a starting point and allowing modifications reduced physician variability, although it did not significantly reduce the time compared to manual segmentations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningBrachytherapyProstatic NeoplasmsMaleHumansProstateUltrasonographyAlgorithmsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

TRUS image auto‐segmentationdeep learninghigh‐dose‐rate prostate brachytherapy

Autor:innen und Institutionen

  • Department of Medical Biophysics, Western University, London, ON, Canada.
  • Robarts Research Institute, Western University, London, ON, Canada.
  • Department of Oncology, London Health Sciences Centre, London, ON, Canada.
  • Department of Oncology, Western University, London, ON, Canada.
  • School of Biomedical Engineering, Western University, London, ON, Canada.
  • Department of Medical Imaging, Western University, London, ON, Canada.

Förderung

  • Ontario Institute of Cancer Research (OICR)
  • the Canadian Institutes of Health Research
  • the Natural Sciences and Engineering Research Council of Canada (NSERC)
  • the London Health Sciences Foundation

Zitieren

APA

Hampole, P., Harding, T., Gillies, D., Orlando, N., Edirisinghe, C., Mendez, L. C., D'Souza, D., Velker, V., Correa, R., Helou, J., Xing, S., Fenster, A., & Hoover, D. A. (2024). Deep learning‐based ultrasound auto‐segmentation of the prostate with brachytherapy implanted needles. Medical Physics. https://doi.org/10.1002/mp.16811

Vancouver

Hampole P, Harding T, Gillies D, Orlando N, Edirisinghe C, Mendez LC, et al. Deep learning‐based ultrasound auto‐segmentation of the prostate with brachytherapy implanted needles. Medical Physics. 2024. doi:10.1002/mp.16811

BibTeX
@article{Hampole2024,
  author = {Hampole, Prakash and Harding, Thomas and Gillies, Derek and Orlando, Nathan and Edirisinghe, Chandima and Mendez, Lucas C and D'Souza, David and Velker, Vikram and Correa, Rohann and Helou, Joelle and Xing, Shuwei and Fenster, Aaron and Hoover, Douglas A},
  title = {Deep learning‐based ultrasound auto‐segmentation of the prostate with brachytherapy implanted needles},
  journal = {Medical Physics},
  year = {2024},
  doi = {10.1002/mp.16811}
}
Kostenlos starten →