Medial axis segmentation of cranial nerves using shape statistics-aware discrete deformable models

Sultana, Sharmin; Agrawal, Praful; Elhabian, Shireen; Whitaker, Ross T.; Blatt, Jason E.; Gilles, Benjamin; Cetas, Justin S.; Rashid, Tanweer; Audette, Michel

doi:10.1007/s11548-019-02014-z

Cited by 4 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model-based segmentation utilizes a priori knowledge of the target such as shape, intensity, and texture to constrain the registration process. [15][16][17][18][19][20][21] It is often used in combination with other method, e.g., multi-atlas auto-segmentation, to further improve the segmentation. Such hybrid approaches that combine the atlas-and model-based segmentations have been applied for the delineation of head and neck structures on CT images, showing promising results.…”

Section: Introductionmentioning

confidence: 99%

CNN-based hierarchical coarse-to-fine segmentation of pelvic CT images for prostate cancer radiotherapy

Sultana

Robinson

Song

et al. 2020

Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling

Self Cite

View full text Add to dashboard Cite

Accurate segmentation of organs-at-risk is important inprostate cancer radiation therapy planning. However, poor soft tissue contrast in CT makes the segmentation task very challenging. We propose a deep convolutional neural network approach to automatically segment the prostate, bladder, and rectum from pelvic CT. A hierarchical coarse-to-fine segmentation strategy is used where the first step generates a coarse segmentation from which an organ-specific region of interest (ROI) localization map is produced. The second step produces detailed and accurate segmentation of the organs. The ROI localization map is generated using a 3D U-net. The localization map helps adjusting the ROI of each organ that needs to be segmented and hence improves computational efficiency by eliminating irrelevant background information. For the fine segmentation step, we designed a fully convolutional network (FCN) by combining a generative adversarial network (GAN) with a U-net. Specifically, the generator is a 3D U-net that is trained to predict individual pelvic structures, and the discriminator is an FCN which fine-tunes the generator predicted segmentation map by comparing it with the ground truth. The network was trained using 100 CT datasets and tested on 15 datasets to segment the prostate, bladder and rectum. The average Dice similarity (mean±SD) of the prostate, bladder and rectum are 0.90±0.05, 0.96±0.06 and 0.91±0.09, respectively, and Hausdorff distances of these three structures are 5.21±1.17, 4.37±0.56 and 6.11±1.47(mm), respectively. The proposed method produces accurate and reproducible segmentation of pelvic structures, which can be potentially valuable for prostate cancer radiotherapy treatment planning.

show abstract

Section: Introductionmentioning

confidence: 99%

CNN-based hierarchical coarse-to-fine segmentation of pelvic CT images for prostate cancer radiotherapy

Sultana

Robinson

Song

et al. 2020

Medical Imaging 2020: Image-Guided Procedures, Robotic Interventions, and Modeling

Self Cite

View full text Add to dashboard Cite

show abstract

“…Particle-based shape modeling (PSM) Cates et al (2007) and Cates et al (2017a) , in particular, is a state-of-the-art computational approach for constructing point distribution models (PDM) via automatically placing a dense set of corresponding landmarks on a set of shapes. The scientific and clinical utility of PSM have been demonstrated in image and shape analysis [e.g., Bhalodia et al (2021) and Shigwan et al (2020) ], neuroscience [e.g., Sultana et al (2019) and Audette et al (2017) ], biological phenotyping [e.g., Jones et al (2013) and Cates et al (2017b) ], cardiology [e.g., Bieging et al (2018) and Goparaju et al (2022) ], and orthopaedics [e.g., Lenz et al (2021) , Goparaju et al (2022) , Krähenbühl et al (2020) , Jacxsens et al (2020) , Atkins et al (2017a) , Atkins et al (2019) , Atkins et al (2017b) , and Atkins et al (2022) ].…”

Section: Introductionmentioning

confidence: 99%

Statistical multi-level shape models for scalable modeling of multi-organ anatomies

Khan

Peterson²,

Aubert³

et al. 2023

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Statistical shape modeling is an indispensable tool in the quantitative analysis of anatomies. Particle-based shape modeling (PSM) is a state-of-the-art approach that enables the learning of population-level shape representation from medical imaging data (e.g., CT, MRI) and the associated 3D models of anatomy generated from them. PSM optimizes the placement of a dense set of landmarks (i.e., correspondence points) on a given shape cohort. PSM supports multi-organ modeling as a particular case of the conventional single-organ framework via a global statistical model, where multi-structure anatomy is considered as a single structure. However, global multi-organ models are not scalable for many organs, induce anatomical inconsistencies, and result in entangled shape statistics where modes of shape variation reflect both within- and between-organ variations. Hence, there is a need for an efficient modeling approach that can capture the inter-organ relations (i.e., pose variations) of the complex anatomy while simultaneously optimizing the morphological changes of each organ and capturing the population-level statistics. This paper leverages the PSM approach and proposes a new approach for correspondence-point optimization of multiple organs that overcomes these limitations. The central idea of multilevel component analysis, is that the shape statistics consists of two mutually orthogonal subspaces: the within-organ subspace and the between-organ subspace. We formulate the correspondence optimization objective using this generative model. We evaluate the proposed method using synthetic shape data and clinical data for articulated joint structures of the spine, foot and ankle, and hip joint.

show abstract

CNTSeg: A multimodal deep-learning-based network for cranial nerves tract segmentation

Xie

Huang

et al. 2023

Medical Image Analysis

View full text Add to dashboard Cite

Medial axis segmentation of cranial nerves using shape statistics-aware discrete deformable models

Cited by 4 publications

References 17 publications

CNN-based hierarchical coarse-to-fine segmentation of pelvic CT images for prostate cancer radiotherapy

CNN-based hierarchical coarse-to-fine segmentation of pelvic CT images for prostate cancer radiotherapy

Statistical multi-level shape models for scalable modeling of multi-organ anatomies

CNTSeg: A multimodal deep-learning-based network for cranial nerves tract segmentation

Contact Info

Product

Resources

About