Prostate segmentation in transrectal ultrasound using magnetic resonance imaging priors

Zeng, Qi; Samei, Golnoosh; Karimi, Davood; Kesch, Claudia; Mahdavi, Sara; Abolmaesumi, Purang; Salcudean, Septimiu E.

doi:10.1007/s11548-018-1742-6

Cited by 29 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhu et al involved a deep supervision strategy into CNN for prostate segmentation . Zeng et al utilized magnetic resonance imaging priors for TRUS prostate segmentation …”

Section: Introductionmentioning

confidence: 99%

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Lei

Tian²,

He³

et al. 2019

Medical Physics

113

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

“…Zhu et al involved a deep supervision strategy into CNN for prostate segmentation . Zeng et al utilized magnetic resonance imaging priors for TRUS prostate segmentation …”

Section: Introductionmentioning

confidence: 99%

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Lei

Tian²,

He³

et al. 2019

Medical Physics

113

View full text Add to dashboard Cite

show abstract

“…Manual segmentation of the prostate on TRUS imaging is time-consuming and often not reproducible. For these reasons, several studies have applied deep learning to automatically segment the prostate using TRUS imaging [25][26][27][28][29][30][31].…”

Section: Challenges Applying Deep Learning To Abdominal Us Imagingmentioning

confidence: 99%

Current status of deep learning applications in abdominal ultrasonography

Song

2021

Ultrasonography

View full text Add to dashboard Cite

Ultrasonography. 2020 Sep 2. Epub ahead of print Deep learning is one of the most popular artificial intelligence techniques used in the medical field. Although it is at an early stage compared to deep learning analyses of computed tomography or magnetic resonance imaging, studies applying deep learning to ultrasound imaging have been actively conducted. This review analyzes recent studies that applied deep learning to ultrasound imaging of various abdominal organs and explains the challenges encountered in these applications.

show abstract

“…CNNs have outperformed other existing methods in the domain of sequence-based problems. CNNs were successfully applied to model sequence specificity of protein binding [15,16]. A convolutional three-layer network of CNN models was developed to predict the effects of noncoding variants of TF binding, DNA accessibility and histone marks of sequences from the only genomic sequence.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…A convolutional three-layer network of CNN models was developed to predict the effects of noncoding variants of TF binding, DNA accessibility and histone marks of sequences from the only genomic sequence. Research has shown that CNN has surpassed other existing methods [15], so developing structures that are not appropriate would yield a poorer result than convolutional models. The ability to match a CNN architecture to a given task lies in harnessing the power of CNNs.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

Deep Learning Methodologies for Genomic Data Prediction: Review

Abass¹,

Adeshina²

2021

JoAIMS

View full text Add to dashboard Cite

The last few years have seen an advancement in genomic research in bioinformatics. With the introduction of high-throughput sequencing techniques, researchers now can analyze and produce a large amount of genomic datasets and this has aided the classification of genomic studies as a "big data" discipline. There is a need to develop a robust and powerful algorithm and deep learning methodologies can provide better performance accuracy than other computational methodologies. In this review, we captured the most frequently used deep learning architectures for the genomic domain. We outline the limitations of deep learning methodologies when dealing with genomic data and we conclude that advancement in deep learning methodologies will help rejuvenate genomic research and build a better architecture that will promote a genomic task.

show abstract

Prostate segmentation in transrectal ultrasound using magnetic resonance imaging priors

Abstract: Our results suggest that utilizing MRI priors in TRUS prostate segmentation could potentially improve the performance at base and apex.

Cited by 29 publications

References 25 publications

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Ultrasound prostate segmentation based on multidirectional deeply supervised V‐Net

Current status of deep learning applications in abdominal ultrasonography

Deep Learning Methodologies for Genomic Data Prediction: Review

Contact Info

Product

Resources

About