In vivo MRI based prostate cancer localization with random forests and auto-context model

Chunjun Qian, Li Wang, Yaozong Gao, Ambereen Yousuf, Xiaoping Yang, Aytekin Oto, Dinggang Shen

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Prostate cancer is one of the major causes of cancer death for men. Magnetic resonance (MR) imaging is being increasingly used as an important modality to localize prostate cancer. Therefore, localizing prostate cancer in MRI with automated detection methods has become an active area of research. Many methods have been proposed for this task. However, most of previous methods focused on identifying cancer only in the peripheral zone (PZ), or classifying suspicious cancer ROIs into benign tissue and cancer tissue. Few works have been done on developing a fully automatic method for cancer localization in the entire prostate region, including central gland (CG) and transition zone (TZ). In this paper, we propose a novel learning-based multi-source integration framework to directly localize prostate cancer regions from in vivo MRI. We employ random forests to effectively integrate features from multi-source images together for cancer localization. Here, multi-source images include initially the multi-parametric MRIs (i.e., T2, DWI, and dADC) and later also the iteratively-estimated and refined tissue probability map of prostate cancer. Experimental results on 26 real patient data show that our method can accurately localize cancerous sections. The higher section-based evaluation (SBE), combined with the ROC analysis result of individual patients, shows that the proposed method is promising for in vivo MRI based prostate cancer localization, which can be used for guiding prostate biopsy, targeting the tumor in focal therapy planning, triage and follow-up of patients with active surveillance, as well as the decision making in treatment selection. The common ROC analysis with the AUC value of 0.832 and also the ROI-based ROC analysis with the AUC value of 0.883 both illustrate the effectiveness of our proposed method.

Original languageEnglish
JournalComputerized Medical Imaging and Graphics
DOIs
Publication statusAccepted/In press - 2015 Sep 21

Fingerprint

Magnetic resonance imaging
Prostatic Neoplasms
Neoplasms
Tissue
ROC Curve
Area Under Curve
Prostate
Biopsy
Tumors
Triage
Decision making
Forests
Planning
Cause of Death
Decision Making
Magnetic Resonance Imaging
Learning
Therapeutics
Research

Keywords

  • Auto-context model
  • Cancer localization
  • MRI segmentation
  • Prostate cancer
  • Random forests

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging
  • Health Informatics
  • Radiological and Ultrasound Technology
  • Computer Graphics and Computer-Aided Design
  • Computer Vision and Pattern Recognition

Cite this

In vivo MRI based prostate cancer localization with random forests and auto-context model. / Qian, Chunjun; Wang, Li; Gao, Yaozong; Yousuf, Ambereen; Yang, Xiaoping; Oto, Aytekin; Shen, Dinggang.

In: Computerized Medical Imaging and Graphics, 21.09.2015.

Research output: Contribution to journalArticle

Qian, Chunjun ; Wang, Li ; Gao, Yaozong ; Yousuf, Ambereen ; Yang, Xiaoping ; Oto, Aytekin ; Shen, Dinggang. / In vivo MRI based prostate cancer localization with random forests and auto-context model. In: Computerized Medical Imaging and Graphics. 2015.
@article{50097b8691b14917b61987f21dfb49e2,
title = "In vivo MRI based prostate cancer localization with random forests and auto-context model",
abstract = "Prostate cancer is one of the major causes of cancer death for men. Magnetic resonance (MR) imaging is being increasingly used as an important modality to localize prostate cancer. Therefore, localizing prostate cancer in MRI with automated detection methods has become an active area of research. Many methods have been proposed for this task. However, most of previous methods focused on identifying cancer only in the peripheral zone (PZ), or classifying suspicious cancer ROIs into benign tissue and cancer tissue. Few works have been done on developing a fully automatic method for cancer localization in the entire prostate region, including central gland (CG) and transition zone (TZ). In this paper, we propose a novel learning-based multi-source integration framework to directly localize prostate cancer regions from in vivo MRI. We employ random forests to effectively integrate features from multi-source images together for cancer localization. Here, multi-source images include initially the multi-parametric MRIs (i.e., T2, DWI, and dADC) and later also the iteratively-estimated and refined tissue probability map of prostate cancer. Experimental results on 26 real patient data show that our method can accurately localize cancerous sections. The higher section-based evaluation (SBE), combined with the ROC analysis result of individual patients, shows that the proposed method is promising for in vivo MRI based prostate cancer localization, which can be used for guiding prostate biopsy, targeting the tumor in focal therapy planning, triage and follow-up of patients with active surveillance, as well as the decision making in treatment selection. The common ROC analysis with the AUC value of 0.832 and also the ROI-based ROC analysis with the AUC value of 0.883 both illustrate the effectiveness of our proposed method.",
keywords = "Auto-context model, Cancer localization, MRI segmentation, Prostate cancer, Random forests",
author = "Chunjun Qian and Li Wang and Yaozong Gao and Ambereen Yousuf and Xiaoping Yang and Aytekin Oto and Dinggang Shen",
year = "2015",
month = "9",
day = "21",
doi = "10.1016/j.compmedimag.2016.02.001",
language = "English",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - In vivo MRI based prostate cancer localization with random forests and auto-context model

AU - Qian, Chunjun

AU - Wang, Li

AU - Gao, Yaozong

AU - Yousuf, Ambereen

AU - Yang, Xiaoping

AU - Oto, Aytekin

AU - Shen, Dinggang

PY - 2015/9/21

Y1 - 2015/9/21

N2 - Prostate cancer is one of the major causes of cancer death for men. Magnetic resonance (MR) imaging is being increasingly used as an important modality to localize prostate cancer. Therefore, localizing prostate cancer in MRI with automated detection methods has become an active area of research. Many methods have been proposed for this task. However, most of previous methods focused on identifying cancer only in the peripheral zone (PZ), or classifying suspicious cancer ROIs into benign tissue and cancer tissue. Few works have been done on developing a fully automatic method for cancer localization in the entire prostate region, including central gland (CG) and transition zone (TZ). In this paper, we propose a novel learning-based multi-source integration framework to directly localize prostate cancer regions from in vivo MRI. We employ random forests to effectively integrate features from multi-source images together for cancer localization. Here, multi-source images include initially the multi-parametric MRIs (i.e., T2, DWI, and dADC) and later also the iteratively-estimated and refined tissue probability map of prostate cancer. Experimental results on 26 real patient data show that our method can accurately localize cancerous sections. The higher section-based evaluation (SBE), combined with the ROC analysis result of individual patients, shows that the proposed method is promising for in vivo MRI based prostate cancer localization, which can be used for guiding prostate biopsy, targeting the tumor in focal therapy planning, triage and follow-up of patients with active surveillance, as well as the decision making in treatment selection. The common ROC analysis with the AUC value of 0.832 and also the ROI-based ROC analysis with the AUC value of 0.883 both illustrate the effectiveness of our proposed method.

AB - Prostate cancer is one of the major causes of cancer death for men. Magnetic resonance (MR) imaging is being increasingly used as an important modality to localize prostate cancer. Therefore, localizing prostate cancer in MRI with automated detection methods has become an active area of research. Many methods have been proposed for this task. However, most of previous methods focused on identifying cancer only in the peripheral zone (PZ), or classifying suspicious cancer ROIs into benign tissue and cancer tissue. Few works have been done on developing a fully automatic method for cancer localization in the entire prostate region, including central gland (CG) and transition zone (TZ). In this paper, we propose a novel learning-based multi-source integration framework to directly localize prostate cancer regions from in vivo MRI. We employ random forests to effectively integrate features from multi-source images together for cancer localization. Here, multi-source images include initially the multi-parametric MRIs (i.e., T2, DWI, and dADC) and later also the iteratively-estimated and refined tissue probability map of prostate cancer. Experimental results on 26 real patient data show that our method can accurately localize cancerous sections. The higher section-based evaluation (SBE), combined with the ROC analysis result of individual patients, shows that the proposed method is promising for in vivo MRI based prostate cancer localization, which can be used for guiding prostate biopsy, targeting the tumor in focal therapy planning, triage and follow-up of patients with active surveillance, as well as the decision making in treatment selection. The common ROC analysis with the AUC value of 0.832 and also the ROI-based ROC analysis with the AUC value of 0.883 both illustrate the effectiveness of our proposed method.

KW - Auto-context model

KW - Cancer localization

KW - MRI segmentation

KW - Prostate cancer

KW - Random forests

UR - http://www.scopus.com/inward/record.url?scp=84961895909&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961895909&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2016.02.001

DO - 10.1016/j.compmedimag.2016.02.001

M3 - Article

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

ER -