3D prostate TRUS segmentation using globally optimized volume-preserving prior
An efficient and accurate segmentation of 3D transrectal ultrasound (TRUS) images plays an important role in the planning and treatment of the practical 3D TRUS guided prostate biopsy. However, a meaningful segmentation of 3D TRUS images tends to suffer from US speckles, shadowing and missing edges etc, which make it a challenging task to delineate the correct prostate boundaries. In this paper, we propose a novel convex optimization based approach to extracting the prostate surface from the given 3D TRUS image, while preserving a new global volume-size prior. We, especially, study the proposed combinatorial optimization problem by convex relaxation and introduce its dual continuous max-flow formulation with the new bounded flow conservation constraint, which results in an efficient numerical solver implemented on GPUs. Experimental results using 12 patient 3D TRUS images show that the proposed approach while preserving the volume-size prior yielded a mean DSC of 89.5% +/- 2.4%, a MAD of 1.4 +/- 0.6 mm, a MAXD of 5.2 +/- 3.2 mm, and a VD of 7.5% +/- 6.2% in - 1 minute, deomonstrating the advantages of both accuracy and efficiency. In addition, the low standard deviation of the segmentation accuracy shows a good reliability of the proposed approach.
Medienart: |
Artikel |
---|
Erscheinungsjahr: |
2014 |
---|---|
Erschienen: |
2014 |
Enthalten in: |
Zur Gesamtaufnahme - volume:17 |
---|---|
Enthalten in: |
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention - 17(2014), Pt 1 vom: 02., Seite 796-803 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Qiu, Wu [VerfasserIn] |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 13.11.2014 Date Revised 07.09.2019 published: Print Citation Status MEDLINE |
---|
Förderinstitution / Projekttitel: |
|
---|
PPN (Katalog-ID): |
NLM24295331X |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM24295331X | ||
003 | DE-627 | ||
005 | 20231224131506.0 | ||
007 | tu | ||
008 | 231224s2014 xx ||||| 00| ||eng c | ||
028 | 5 | 2 | |a pubmed24n0809.xml |
035 | |a (DE-627)NLM24295331X | ||
035 | |a (NLM)25333192 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Qiu, Wu |e verfasserin |4 aut | |
245 | 1 | 0 | |a 3D prostate TRUS segmentation using globally optimized volume-preserving prior |
264 | 1 | |c 2014 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ohne Hilfsmittel zu benutzen |b n |2 rdamedia | ||
338 | |a Band |b nc |2 rdacarrier | ||
500 | |a Date Completed 13.11.2014 | ||
500 | |a Date Revised 07.09.2019 | ||
500 | |a published: Print | ||
500 | |a Citation Status MEDLINE | ||
520 | |a An efficient and accurate segmentation of 3D transrectal ultrasound (TRUS) images plays an important role in the planning and treatment of the practical 3D TRUS guided prostate biopsy. However, a meaningful segmentation of 3D TRUS images tends to suffer from US speckles, shadowing and missing edges etc, which make it a challenging task to delineate the correct prostate boundaries. In this paper, we propose a novel convex optimization based approach to extracting the prostate surface from the given 3D TRUS image, while preserving a new global volume-size prior. We, especially, study the proposed combinatorial optimization problem by convex relaxation and introduce its dual continuous max-flow formulation with the new bounded flow conservation constraint, which results in an efficient numerical solver implemented on GPUs. Experimental results using 12 patient 3D TRUS images show that the proposed approach while preserving the volume-size prior yielded a mean DSC of 89.5% +/- 2.4%, a MAD of 1.4 +/- 0.6 mm, a MAXD of 5.2 +/- 3.2 mm, and a VD of 7.5% +/- 6.2% in - 1 minute, deomonstrating the advantages of both accuracy and efficiency. In addition, the low standard deviation of the segmentation accuracy shows a good reliability of the proposed approach | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a Rajchl, Martin |e verfasserin |4 aut | |
700 | 1 | |a Guo, Fumin |e verfasserin |4 aut | |
700 | 1 | |a Sun, Yue |e verfasserin |4 aut | |
700 | 1 | |a Ukwatta, Eranga |e verfasserin |4 aut | |
700 | 1 | |a Fenster, Aaron |e verfasserin |4 aut | |
700 | 1 | |a Yuan, Jing |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention |d 1998 |g 17(2014), Pt 1 vom: 02., Seite 796-803 |w (DE-627)NLM162677847 |7 nnns |
773 | 1 | 8 | |g volume:17 |g year:2014 |g number:Pt 1 |g day:02 |g pages:796-803 |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 17 |j 2014 |e Pt 1 |b 02 |h 796-803 |