Prostate lesion detection and localization based on locality alignment discriminant analysis

Mingquan LIN; Weifu Chen; Mingbo Zhao; Eli Gibson; Matthew Bastian-Jordan; Derek W. Cool; Zahra Kassam; Wai Shing Tommy CHOW; Aaron  Ward; Bernard CHIU

doi:10.1117/12.2255621

Prostate lesion detection and localization based on locality alignment discriminant analysis

Mingquan LIN
, Weifu Chen
, Mingbo Zhao
, Eli Gibson
, Matthew Bastian-Jordan
, Derek W. Cool
, Zahra Kassam
, Wai Shing Tommy CHOW
, Aaron Ward
, Bernard CHIU^*

^*Corresponding author for this work

Department of Electrical Engineering

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

3 Citations (Scopus)

Abstract

Prostatic adenocarcinoma is one of the most commonly occurring cancers among men in the world, and it also the most curable cancer when it is detected early. Multiparametric MRI (mpMRI) combines anatomic and functional prostate imaging techniques, which have been shown to produce high sensitivity and specificity in cancer localization, which is important in planning biopsies and focal therapies. However, in previous investigations, lesion localization was achieved mainly by manual segmentation, which is time-consuming and prone to observer variability. Here, we developed an algorithm based on locality alignment discriminant analysis (LADA) technique, which can be considered as a version of linear discriminant analysis (LDA) localized to patches in the feature space. Sensitivity, specificity and accuracy generated by the proposed algorithm in five prostates by LADA were 52.2%, 89.1% and 85.1% respectively, compared to 31.3%, 85.3% and 80.9% generated by LDA. The delineation accuracy attainable by this tool has a potential in increasing the cancer detection rate in biopsies and in minimizing collateral damage of surrounding tissues in focal therapies.

Original language	English
Title of host publication	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Publisher	SPIE
Volume	10134
ISBN (Print)	9781510607132
DOIs	https://doi.org/10.1117/12.2255621
Publication status	Published - 3 Mar 2017
Event	Medical Imaging 2017: Computer-Aided Diagnosis - Orlando, United States Duration: 13 Feb 2017 → 16 Feb 2017

Publication series

Name
Volume	10134
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2017: Computer-Aided Diagnosis
Place	United States
City	Orlando
Period	13/02/17 → 16/02/17

Bibliographical note

Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Research Keywords

Lesion localization
Locality alignment discriminant analysis (LADA)
Multiparametric MRI (mpMRI)
Prostate cancer

Access Output

10.1117/12.2255621

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{16990e154ce74ffd9b14edb27f187a97,

title = "Prostate lesion detection and localization based on locality alignment discriminant analysis",

abstract = "Prostatic adenocarcinoma is one of the most commonly occurring cancers among men in the world, and it also the most curable cancer when it is detected early. Multiparametric MRI (mpMRI) combines anatomic and functional prostate imaging techniques, which have been shown to produce high sensitivity and specificity in cancer localization, which is important in planning biopsies and focal therapies. However, in previous investigations, lesion localization was achieved mainly by manual segmentation, which is time-consuming and prone to observer variability. Here, we developed an algorithm based on locality alignment discriminant analysis (LADA) technique, which can be considered as a version of linear discriminant analysis (LDA) localized to patches in the feature space. Sensitivity, specificity and accuracy generated by the proposed algorithm in five prostates by LADA were 52.2\%, 89.1\% and 85.1\% respectively, compared to 31.3\%, 85.3\% and 80.9\% generated by LDA. The delineation accuracy attainable by this tool has a potential in increasing the cancer detection rate in biopsies and in minimizing collateral damage of surrounding tissues in focal therapies.",

keywords = "Lesion localization, Locality alignment discriminant analysis (LADA), Multiparametric MRI (mpMRI), Prostate cancer",

author = "Mingquan LIN and Weifu Chen and Mingbo Zhao and Eli Gibson and Matthew Bastian-Jordan and Cool, \{Derek W.\} and Zahra Kassam and CHOW, \{Wai Shing Tommy\} and Aaron Ward and Bernard CHIU",

note = "Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).; Medical Imaging 2017: Computer-Aided Diagnosis ; Conference date: 13-02-2017 Through 16-02-2017",

year = "2017",

month = mar,

day = "3",

doi = "10.1117/12.2255621",

language = "English",

isbn = "9781510607132",

volume = "10134",

publisher = "SPIE",

booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

address = "United States",

}

LIN, M, Chen, W, Zhao, M, Gibson, E, Bastian-Jordan, M, Cool, DW, Kassam, Z, CHOW, WST, Ward, A & CHIU, B 2017, Prostate lesion detection and localization based on locality alignment discriminant analysis. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 10134, 101344A, SPIE, Medical Imaging 2017: Computer-Aided Diagnosis, Orlando, United States, 13/02/17. https://doi.org/10.1117/12.2255621

Prostate lesion detection and localization based on locality alignment discriminant analysis. / LIN, Mingquan; Chen, Weifu; Zhao, Mingbo et al.
Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 10134 SPIE, 2017. 101344A.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Prostate lesion detection and localization based on locality alignment discriminant analysis

AU - LIN, Mingquan

AU - Chen, Weifu

AU - Zhao, Mingbo

AU - Gibson, Eli

AU - Bastian-Jordan, Matthew

AU - Cool, Derek W.

AU - Kassam, Zahra

AU - CHOW, Wai Shing Tommy

AU - Ward, Aaron

AU - CHIU, Bernard

N1 - Full text of this publication does not contain sufficient affiliation information. With consent from the author(s) concerned, the Research Unit(s) information for this record is based on the existing academic department affiliation of the author(s).

PY - 2017/3/3

Y1 - 2017/3/3

N2 - Prostatic adenocarcinoma is one of the most commonly occurring cancers among men in the world, and it also the most curable cancer when it is detected early. Multiparametric MRI (mpMRI) combines anatomic and functional prostate imaging techniques, which have been shown to produce high sensitivity and specificity in cancer localization, which is important in planning biopsies and focal therapies. However, in previous investigations, lesion localization was achieved mainly by manual segmentation, which is time-consuming and prone to observer variability. Here, we developed an algorithm based on locality alignment discriminant analysis (LADA) technique, which can be considered as a version of linear discriminant analysis (LDA) localized to patches in the feature space. Sensitivity, specificity and accuracy generated by the proposed algorithm in five prostates by LADA were 52.2%, 89.1% and 85.1% respectively, compared to 31.3%, 85.3% and 80.9% generated by LDA. The delineation accuracy attainable by this tool has a potential in increasing the cancer detection rate in biopsies and in minimizing collateral damage of surrounding tissues in focal therapies.

AB - Prostatic adenocarcinoma is one of the most commonly occurring cancers among men in the world, and it also the most curable cancer when it is detected early. Multiparametric MRI (mpMRI) combines anatomic and functional prostate imaging techniques, which have been shown to produce high sensitivity and specificity in cancer localization, which is important in planning biopsies and focal therapies. However, in previous investigations, lesion localization was achieved mainly by manual segmentation, which is time-consuming and prone to observer variability. Here, we developed an algorithm based on locality alignment discriminant analysis (LADA) technique, which can be considered as a version of linear discriminant analysis (LDA) localized to patches in the feature space. Sensitivity, specificity and accuracy generated by the proposed algorithm in five prostates by LADA were 52.2%, 89.1% and 85.1% respectively, compared to 31.3%, 85.3% and 80.9% generated by LDA. The delineation accuracy attainable by this tool has a potential in increasing the cancer detection rate in biopsies and in minimizing collateral damage of surrounding tissues in focal therapies.

KW - Lesion localization

KW - Locality alignment discriminant analysis (LADA)

KW - Multiparametric MRI (mpMRI)

KW - Prostate cancer

UR - https://www.scopus.com/pages/publications/85020239143

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-85020239143&origin=recordpage

U2 - 10.1117/12.2255621

DO - 10.1117/12.2255621

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781510607132

VL - 10134

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

PB - SPIE

T2 - Medical Imaging 2017: Computer-Aided Diagnosis

Y2 - 13 February 2017 through 16 February 2017

ER -

Prostate lesion detection and localization based on locality alignment discriminant analysis

Abstract

Publication series

Conference

Bibliographical note

UN SDGs

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this