Renal Segmentation from 3D Ultrasound via Fuzzy Appearance Models and Patient-Specific Alpha Shapes

Juan J. Cerrolaza, Nabile Safdar, Elijah Biggs, James Jago, Craig A Peters, Marius George Linguraru

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Ultrasound (US) imaging is the primary imaging modality for pediatric hydronephrosis, which manifests as the dilation of the renal collecting system (CS). In this paper, we present a new framework for the segmentation of renal structures, kidney and CS, from 3DUS scans. First, the kidney is segmented using an active shape model-based approach, tailored to deal with the challenges raised by US images. A weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. The model is completed with a new fuzzy appearance model and a multi-scale omnidirectional Gabor-based appearance descriptor. Next, the CS is segmented using an active contour formulation, which combines contour-and intensity-based terms. The new positive alpha detector presented here allows to control the propagation process by means of a patient-specific stopping function created from the bands of adipose tissue within the kidney. The performance of the new segmentation approach was evaluated on a dataset of 39 cases, showing an average Dice's coefficient of 0.86±0.05 for the kidney, and 0.74 ± 0.10 for the CS segmentation, respectively. These promising results demonstrate the potential utility of this framework for the US-based assessment of the severity of pediatric hydronephrosis.

Original languageEnglish (US)
Article number7478056
Pages (from-to)2393-2402
Number of pages10
JournalIEEE Transactions on Medical Imaging
Volume35
Issue number11
DOIs
StatePublished - Nov 1 2016

Fingerprint

Ultrasonics
Kidney
Pediatrics
Hydronephrosis
Imaging techniques
Wavefronts
Statistical Models
Tissue
Detectors
Adipose Tissue
Dilatation
Ultrasonography

Keywords

  • Active shape model
  • alpha shape
  • collecting system
  • Gabor filters
  • hydronephrosis
  • image segmentation
  • kidney
  • Ultrasonography

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Renal Segmentation from 3D Ultrasound via Fuzzy Appearance Models and Patient-Specific Alpha Shapes. / Cerrolaza, Juan J.; Safdar, Nabile; Biggs, Elijah; Jago, James; Peters, Craig A; Linguraru, Marius George.

In: IEEE Transactions on Medical Imaging, Vol. 35, No. 11, 7478056, 01.11.2016, p. 2393-2402.

Research output: Contribution to journalArticle

Cerrolaza, Juan J. ; Safdar, Nabile ; Biggs, Elijah ; Jago, James ; Peters, Craig A ; Linguraru, Marius George. / Renal Segmentation from 3D Ultrasound via Fuzzy Appearance Models and Patient-Specific Alpha Shapes. In: IEEE Transactions on Medical Imaging. 2016 ; Vol. 35, No. 11. pp. 2393-2402.
@article{40820f843b65476c8e4066c6e0a79b62,
title = "Renal Segmentation from 3D Ultrasound via Fuzzy Appearance Models and Patient-Specific Alpha Shapes",
abstract = "Ultrasound (US) imaging is the primary imaging modality for pediatric hydronephrosis, which manifests as the dilation of the renal collecting system (CS). In this paper, we present a new framework for the segmentation of renal structures, kidney and CS, from 3DUS scans. First, the kidney is segmented using an active shape model-based approach, tailored to deal with the challenges raised by US images. A weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. The model is completed with a new fuzzy appearance model and a multi-scale omnidirectional Gabor-based appearance descriptor. Next, the CS is segmented using an active contour formulation, which combines contour-and intensity-based terms. The new positive alpha detector presented here allows to control the propagation process by means of a patient-specific stopping function created from the bands of adipose tissue within the kidney. The performance of the new segmentation approach was evaluated on a dataset of 39 cases, showing an average Dice's coefficient of 0.86±0.05 for the kidney, and 0.74 ± 0.10 for the CS segmentation, respectively. These promising results demonstrate the potential utility of this framework for the US-based assessment of the severity of pediatric hydronephrosis.",
keywords = "Active shape model, alpha shape, collecting system, Gabor filters, hydronephrosis, image segmentation, kidney, Ultrasonography",
author = "Cerrolaza, {Juan J.} and Nabile Safdar and Elijah Biggs and James Jago and Peters, {Craig A} and Linguraru, {Marius George}",
year = "2016",
month = "11",
day = "1",
doi = "10.1109/TMI.2016.2572641",
language = "English (US)",
volume = "35",
pages = "2393--2402",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "11",

}

TY - JOUR

T1 - Renal Segmentation from 3D Ultrasound via Fuzzy Appearance Models and Patient-Specific Alpha Shapes

AU - Cerrolaza, Juan J.

AU - Safdar, Nabile

AU - Biggs, Elijah

AU - Jago, James

AU - Peters, Craig A

AU - Linguraru, Marius George

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Ultrasound (US) imaging is the primary imaging modality for pediatric hydronephrosis, which manifests as the dilation of the renal collecting system (CS). In this paper, we present a new framework for the segmentation of renal structures, kidney and CS, from 3DUS scans. First, the kidney is segmented using an active shape model-based approach, tailored to deal with the challenges raised by US images. A weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. The model is completed with a new fuzzy appearance model and a multi-scale omnidirectional Gabor-based appearance descriptor. Next, the CS is segmented using an active contour formulation, which combines contour-and intensity-based terms. The new positive alpha detector presented here allows to control the propagation process by means of a patient-specific stopping function created from the bands of adipose tissue within the kidney. The performance of the new segmentation approach was evaluated on a dataset of 39 cases, showing an average Dice's coefficient of 0.86±0.05 for the kidney, and 0.74 ± 0.10 for the CS segmentation, respectively. These promising results demonstrate the potential utility of this framework for the US-based assessment of the severity of pediatric hydronephrosis.

AB - Ultrasound (US) imaging is the primary imaging modality for pediatric hydronephrosis, which manifests as the dilation of the renal collecting system (CS). In this paper, we present a new framework for the segmentation of renal structures, kidney and CS, from 3DUS scans. First, the kidney is segmented using an active shape model-based approach, tailored to deal with the challenges raised by US images. A weighted statistical shape model allows to compensate the image variation with the propagation direction of the US wavefront. The model is completed with a new fuzzy appearance model and a multi-scale omnidirectional Gabor-based appearance descriptor. Next, the CS is segmented using an active contour formulation, which combines contour-and intensity-based terms. The new positive alpha detector presented here allows to control the propagation process by means of a patient-specific stopping function created from the bands of adipose tissue within the kidney. The performance of the new segmentation approach was evaluated on a dataset of 39 cases, showing an average Dice's coefficient of 0.86±0.05 for the kidney, and 0.74 ± 0.10 for the CS segmentation, respectively. These promising results demonstrate the potential utility of this framework for the US-based assessment of the severity of pediatric hydronephrosis.

KW - Active shape model

KW - alpha shape

KW - collecting system

KW - Gabor filters

KW - hydronephrosis

KW - image segmentation

KW - kidney

KW - Ultrasonography

UR - http://www.scopus.com/inward/record.url?scp=84994491624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84994491624&partnerID=8YFLogxK

U2 - 10.1109/TMI.2016.2572641

DO - 10.1109/TMI.2016.2572641

M3 - Article

VL - 35

SP - 2393

EP - 2402

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 11

M1 - 7478056

ER -