Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection

Sang Hyun Park, Yaozong Gao, Yinghuan Shi, Dinggang Shen

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, locationadaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm.

Results: The proposed interactive segmentation methodwas applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to evaluate both the efficiency and the robustness. The automatic segmentation results with the original average Dice similarity coefficient of 0.78 were improved to 0.865-0.872 after conducting 55-59 interactions by using the proposed method, where each editing procedure took less than 3 s. In addition, the proposed method obtained the most consistent editing results with respect to different user interactions, compared to other methods.

Conclusions: The proposed method obtains robust editing results with few interactions for various wrong segmentation cases, by selecting the location-adaptive features and further imposing the manifold regularization. The authors expect the proposed method to largely reduce the laborious burdens of manual editing, as well as both the intra- and interobserver variability across clinicians.

Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very timeconsuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. 2014 American Association of Physicists in Medicine.

Original languageEnglish
Article number111715
JournalMedical Physics
Volume41
Issue number11
DOIs
Publication statusPublished - 2014 Nov 1

Fingerprint

Atlases
Prostate
Observer Variation
Supervised Machine Learning
Politics
Prostatic Neoplasms
Radiotherapy
Medicine

ASJC Scopus subject areas

  • Biophysics
  • Radiology Nuclear Medicine and imaging

Cite this

Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection. / Park, Sang Hyun; Gao, Yaozong; Shi, Yinghuan; Shen, Dinggang.

In: Medical Physics, Vol. 41, No. 11, 111715, 01.11.2014.

Research output: Contribution to journalArticle

@article{d6ba0f2006f843ce8400d05ff37a1167,
title = "Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection",
abstract = "Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, locationadaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm.Results: The proposed interactive segmentation methodwas applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to evaluate both the efficiency and the robustness. The automatic segmentation results with the original average Dice similarity coefficient of 0.78 were improved to 0.865-0.872 after conducting 55-59 interactions by using the proposed method, where each editing procedure took less than 3 s. In addition, the proposed method obtained the most consistent editing results with respect to different user interactions, compared to other methods.Conclusions: The proposed method obtains robust editing results with few interactions for various wrong segmentation cases, by selecting the location-adaptive features and further imposing the manifold regularization. The authors expect the proposed method to largely reduce the laborious burdens of manual editing, as well as both the intra- and interobserver variability across clinicians.Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very timeconsuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. 2014 American Association of Physicists in Medicine.",
keywords = "feature selection, interactive segmentation, manifold regularization, prostate, semisupervised learning",
author = "Park, {Sang Hyun} and Yaozong Gao and Yinghuan Shi and Dinggang Shen",
year = "2014",
month = "11",
day = "1",
doi = "10.1118/1.4898200",
language = "English",
volume = "41",
journal = "Medical Physics",
issn = "0094-2405",
publisher = "AAPM - American Association of Physicists in Medicine",
number = "11",

}

TY - JOUR

T1 - Interactive prostate segmentation using atlas-guided semi-supervised learning and adaptive feature selection

AU - Park, Sang Hyun

AU - Gao, Yaozong

AU - Shi, Yinghuan

AU - Shen, Dinggang

PY - 2014/11/1

Y1 - 2014/11/1

N2 - Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, locationadaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm.Results: The proposed interactive segmentation methodwas applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to evaluate both the efficiency and the robustness. The automatic segmentation results with the original average Dice similarity coefficient of 0.78 were improved to 0.865-0.872 after conducting 55-59 interactions by using the proposed method, where each editing procedure took less than 3 s. In addition, the proposed method obtained the most consistent editing results with respect to different user interactions, compared to other methods.Conclusions: The proposed method obtains robust editing results with few interactions for various wrong segmentation cases, by selecting the location-adaptive features and further imposing the manifold regularization. The authors expect the proposed method to largely reduce the laborious burdens of manual editing, as well as both the intra- and interobserver variability across clinicians.Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very timeconsuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. 2014 American Association of Physicists in Medicine.

AB - Methods: The authors formulate the editing problem as a semisupervised learning problem which can utilize a priori knowledge of training data and also the valuable information from user interactions. Specifically, from a region of interest near the given user interactions, the appropriate training labels, which are well matched with the user interactions, can be locally searched from a training set. With voting from the selected training labels, both confident prostate and background voxels, as well as unconfident voxels can be estimated. To reflect informative relationship between voxels, locationadaptive features are selected from the confident voxels by using regression forest and Fisher separation criterion. Then, the manifold configuration computed in the derived feature space is enforced into the semisupervised learning algorithm. The labels of unconfident voxels are then predicted by regularizing semisupervised learning algorithm.Results: The proposed interactive segmentation methodwas applied to correct automatic segmentation results of 30 challenging CT images. The correction was conducted three times with different user interactions performed at different time periods, in order to evaluate both the efficiency and the robustness. The automatic segmentation results with the original average Dice similarity coefficient of 0.78 were improved to 0.865-0.872 after conducting 55-59 interactions by using the proposed method, where each editing procedure took less than 3 s. In addition, the proposed method obtained the most consistent editing results with respect to different user interactions, compared to other methods.Conclusions: The proposed method obtains robust editing results with few interactions for various wrong segmentation cases, by selecting the location-adaptive features and further imposing the manifold regularization. The authors expect the proposed method to largely reduce the laborious burdens of manual editing, as well as both the intra- and interobserver variability across clinicians.Purpose: Accurate prostate segmentation is necessary for maximizing the effectiveness of radiation therapy of prostate cancer. However, manual segmentation from 3D CT images is very timeconsuming and often causes large intra- and interobserver variations across clinicians. Many segmentation methods have been proposed to automate this labor-intensive process, but tedious manual editing is still required due to the limited performance. In this paper, the authors propose a new interactive segmentation method that can (1) flexibly generate the editing result with a few scribbles or dots provided by a clinician, (2) fast deliver intermediate results to the clinician, and (3) sequentially correct the segmentations from any type of automatic or interactive segmentation methods. 2014 American Association of Physicists in Medicine.

KW - feature selection

KW - interactive segmentation

KW - manifold regularization

KW - prostate

KW - semisupervised learning

UR - http://www.scopus.com/inward/record.url?scp=84908441410&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84908441410&partnerID=8YFLogxK

U2 - 10.1118/1.4898200

DO - 10.1118/1.4898200

M3 - Article

C2 - 25370629

AN - SCOPUS:84908441410

VL - 41

JO - Medical Physics

JF - Medical Physics

SN - 0094-2405

IS - 11

M1 - 111715

ER -