Fully automatic prostate segmentation from transrectal ultrasound images based on radial bas-relief initialization and slice-based propagation

Yan, Yu; Chen, Yi-Min; Chiu, Bernard

doi:10.1016/j.compbiomed.2016.05.002

Cited by 11 publications

(8 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transrectal ultrasound (TRUS) is a standard imaging modality for image‐guided prostate‐cancer procedures (e.g., biopsy and brachytherapy) . Accurate segmentation of the prostate plays a key role in biopsy needle placement, radiotherapy treatment planning, and motion monitoring . Manual segmentation during biopsy or radiation therapy planning can be time‐consuming and subject to inter‐ and intraobserver variation .…”

Section: Introductionmentioning

confidence: 99%

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Lei

Tian²,

He³

et al. 2019

Medical Physics

107

View full text Add to dashboard Cite

Purpose: Transrectal ultrasound (TRUS) is a versatile and real-time imaging modality that is commonly used in image-guided prostate cancer interventions (e.g., biopsy and brachytherapy). Accurate segmentation of the prostate is key to biopsy needle placement, brachytherapy treatment planning, and motion management. Manual segmentation during these interventions is time-consuming and subject to inter-and intraobserver variation. To address these drawbacks, we aimed to develop a deep learning-based method which integrates deep supervision into a three-dimensional (3D) patch-based V-Net for prostate segmentation. Methods and materials: We developed a multidirectional deep-learning-based method to automatically segment the prostate for ultrasound-guided radiation therapy. A 3D supervision mechanism is integrated into the V-Net stages to deal with the optimization difficulties when training a deep network with limited training data. We combine a binary cross-entropy (BCE) loss and a batch-based Dice loss into the stage-wise hybrid loss function for a deep supervision training. During the segmentation stage, the patches are extracted from the newly acquired ultrasound image as the input of the well-trained network and the well-trained network adaptively labels the prostate tissue. The final segmented prostate volume is reconstructed using patch fusion and further refined through a contour refinement processing. Results: Forty-four patients' TRUS images were used to test our segmentation method. Our segmentation results were compared with the manually segmented contours (ground truth). The mean prostate volume Dice similarity coefficient (DSC), Hausdorff distance (HD), mean surface distance (MSD), and residual mean surface distance (RMSD) were 0.92 AE 0.03, 3.94 AE 1.55, 0.60 AE 0.23, and 0.90 AE 0.38 mm, respectively. Conclusion: We developed a novel deeply supervised deep learning-based approach with reliable contour refinement to automatically segment the TRUS prostate, demonstrated its clinical feasibility, and validated its accuracy compared to manual segmentation. The proposed technique could be a useful tool for diagnostic and therapeutic applications in prostate cancer.

show abstract

Section: Introductionmentioning

confidence: 99%

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Lei

Tian²,

He³

et al. 2019

Medical Physics

107

View full text Add to dashboard Cite

show abstract

“…Endorectal compression of the prostate under US guidance appears to improve whole‐gland and lesion‐targeted therapy . Automated segmentation has been developed for US‐guided HIFU treatments …”

Section: Magnetic Resonance Versus Us Guidance For Hifumentioning

confidence: 99%

Histotripsy: The Next Generation of High‐Intensity Focused Ultrasound for Focal Prostate Cancer Therapy

Dubinsky

Khokhlova

et al. 2019

J of Ultrasound Medicine

View full text Add to dashboard Cite

This article reviews the most current methods and technological aspects of highintensity focused ultrasound (HIFU), which is termed histotripsy. The rationale for focal therapy for prostate carcinoma rather than prostatectomy, which is being used extensively throughout Europe and Asia, is presented, and an argument for why HIFU is the modality of choice for primary therapy and recurrent disease is offered. The article presents a review of the technical advances including higher ultrasound beam energy than current thermal HIFU which allows for more accurate tissue targeting, less collateral tissue damage, and faster treatment times. Finally, the article presents a discussion about the advantage of ultrasound guidance for histotripsy in preference to magnetic resonance imaging guidance primarily based on cost, ease of application, and portability.

show abstract

“…More recent developments have seen more of a focus on supervised learning frameworks, based on shape and probability priors or level sets [54], [63], [64] and less focus on edge-guided or pixel region-based techniques. The implementation of these more advanced segmentation techniques make the method typically more robust to shape, contrast, and size of the object within the image.…”

Section: Prostatementioning

confidence: 99%

“…Many prostate segmentation techniques also tend to evaluate segmentation results in the mid-gland area, where the prostate boundaries are clearer. An interesting work in this application was presented by Yu et al [54] in 2016. Their technique was completely automatic, in which the initial first contour of the volume was found using a radial basrelief technique [251].…”

Section: Prostatementioning

confidence: 99%

Automated localization and segmentation techniques for B-mode ultrasound images: A review

Meiburger

Acharya

Molinari

2018

Computers in Biology and Medicine

108

View full text Add to dashboard Cite

Fully automatic prostate segmentation from transrectal ultrasound images based on radial bas-relief initialization and slice-based propagation

Cited by 11 publications

References 40 publications

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Histotripsy: The Next Generation of High‐Intensity Focused Ultrasound for Focal Prostate Cancer Therapy

Automated localization and segmentation techniques for B-mode ultrasound images: A review

Contact Info

Product

Resources

About