Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion

Ling Ma, Rongrong Guo, Guoyi Zhang, Funmilayo Tade, David M. Schuster, Peter Nieh, Viraj Master, Baowei Fei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Citations (Scopus)

Abstract

Automatic segmentation of the prostate on CT images has many applications in prostate cancer diagnosis and therapy. However, prostate CT image segmentation is challenging because of the low contrast of soft tissue on CT images. In this paper, we propose an automatic segmentation method by combining a deep learning method and multi-atlas refinement. First, instead of segmenting the whole image, we extract the region of interesting (ROI) to delete irrelevant regions. Then, we use the convolutional neural networks (CNN) to learn the deep features for distinguishing the prostate pixels from the non-prostate pixels in order to obtain the preliminary segmentation results. CNN can automatically learn the deep features adapting to the data, which are different from some handcrafted features. Finally, we select some similar atlases to refine the initial segmentation results. The proposed method has been evaluated on a dataset of 92 prostate CT images. Experimental results show that our method achieved a Dice similarity coefficient of 86.80% as compared to the manual segmentation. The deep learning based method can provide a useful tool for automatic segmentation of the prostate on CT images and thus can have a variety of clinical applications.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2017
Subtitle of host publicationImage Processing
EditorsElsa D. Angelini, Martin A. Styner, Elsa D. Angelini
PublisherSPIE
ISBN (Electronic)9781510607118
DOIs
StatePublished - Jan 1 2017
Externally publishedYes
EventMedical Imaging 2017: Image Processing - Orlando, United States
Duration: Feb 12 2017Feb 14 2017

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume10133
ISSN (Print)1605-7422

Other

OtherMedical Imaging 2017: Image Processing
CountryUnited States
CityOrlando
Period2/12/172/14/17

Fingerprint

Atlases
learning
Prostate
Fusion reactions
fusion
Pixels
Learning
Neural networks
Image segmentation
Tissue
pixels
Prostatic Neoplasms
Deep learning
therapy
cancer
coefficients

Keywords

  • Computed tomography (CT)
  • Convolutional neural networks (CNN)
  • Deep learning
  • Image segmentation
  • Multiatlas segmentation
  • Prostate
  • Prostate cancer

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Ma, L., Guo, R., Zhang, G., Tade, F., Schuster, D. M., Nieh, P., ... Fei, B. (2017). Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion. In E. D. Angelini, M. A. Styner, & E. D. Angelini (Eds.), Medical Imaging 2017: Image Processing [101332O] (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10133). SPIE. https://doi.org/10.1117/12.2255755

Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion. / Ma, Ling; Guo, Rongrong; Zhang, Guoyi; Tade, Funmilayo; Schuster, David M.; Nieh, Peter; Master, Viraj; Fei, Baowei.

Medical Imaging 2017: Image Processing. ed. / Elsa D. Angelini; Martin A. Styner; Elsa D. Angelini. SPIE, 2017. 101332O (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10133).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ma, L, Guo, R, Zhang, G, Tade, F, Schuster, DM, Nieh, P, Master, V & Fei, B 2017, Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion. in ED Angelini, MA Styner & ED Angelini (eds), Medical Imaging 2017: Image Processing., 101332O, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10133, SPIE, Medical Imaging 2017: Image Processing, Orlando, United States, 2/12/17. https://doi.org/10.1117/12.2255755
Ma L, Guo R, Zhang G, Tade F, Schuster DM, Nieh P et al. Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion. In Angelini ED, Styner MA, Angelini ED, editors, Medical Imaging 2017: Image Processing. SPIE. 2017. 101332O. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). https://doi.org/10.1117/12.2255755
Ma, Ling ; Guo, Rongrong ; Zhang, Guoyi ; Tade, Funmilayo ; Schuster, David M. ; Nieh, Peter ; Master, Viraj ; Fei, Baowei. / Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion. Medical Imaging 2017: Image Processing. editor / Elsa D. Angelini ; Martin A. Styner ; Elsa D. Angelini. SPIE, 2017. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
@inproceedings{feb472a3c19d4df583a628ffa9481b4f,
title = "Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion",
abstract = "Automatic segmentation of the prostate on CT images has many applications in prostate cancer diagnosis and therapy. However, prostate CT image segmentation is challenging because of the low contrast of soft tissue on CT images. In this paper, we propose an automatic segmentation method by combining a deep learning method and multi-atlas refinement. First, instead of segmenting the whole image, we extract the region of interesting (ROI) to delete irrelevant regions. Then, we use the convolutional neural networks (CNN) to learn the deep features for distinguishing the prostate pixels from the non-prostate pixels in order to obtain the preliminary segmentation results. CNN can automatically learn the deep features adapting to the data, which are different from some handcrafted features. Finally, we select some similar atlases to refine the initial segmentation results. The proposed method has been evaluated on a dataset of 92 prostate CT images. Experimental results show that our method achieved a Dice similarity coefficient of 86.80{\%} as compared to the manual segmentation. The deep learning based method can provide a useful tool for automatic segmentation of the prostate on CT images and thus can have a variety of clinical applications.",
keywords = "Computed tomography (CT), Convolutional neural networks (CNN), Deep learning, Image segmentation, Multiatlas segmentation, Prostate, Prostate cancer",
author = "Ling Ma and Rongrong Guo and Guoyi Zhang and Funmilayo Tade and Schuster, {David M.} and Peter Nieh and Viraj Master and Baowei Fei",
year = "2017",
month = "1",
day = "1",
doi = "10.1117/12.2255755",
language = "English (US)",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Angelini, {Elsa D.} and Styner, {Martin A.} and Angelini, {Elsa D.}",
booktitle = "Medical Imaging 2017",

}

TY - GEN

T1 - Automatic segmentation of the prostate on CT images using deep learning and multi-atlas fusion

AU - Ma, Ling

AU - Guo, Rongrong

AU - Zhang, Guoyi

AU - Tade, Funmilayo

AU - Schuster, David M.

AU - Nieh, Peter

AU - Master, Viraj

AU - Fei, Baowei

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Automatic segmentation of the prostate on CT images has many applications in prostate cancer diagnosis and therapy. However, prostate CT image segmentation is challenging because of the low contrast of soft tissue on CT images. In this paper, we propose an automatic segmentation method by combining a deep learning method and multi-atlas refinement. First, instead of segmenting the whole image, we extract the region of interesting (ROI) to delete irrelevant regions. Then, we use the convolutional neural networks (CNN) to learn the deep features for distinguishing the prostate pixels from the non-prostate pixels in order to obtain the preliminary segmentation results. CNN can automatically learn the deep features adapting to the data, which are different from some handcrafted features. Finally, we select some similar atlases to refine the initial segmentation results. The proposed method has been evaluated on a dataset of 92 prostate CT images. Experimental results show that our method achieved a Dice similarity coefficient of 86.80% as compared to the manual segmentation. The deep learning based method can provide a useful tool for automatic segmentation of the prostate on CT images and thus can have a variety of clinical applications.

AB - Automatic segmentation of the prostate on CT images has many applications in prostate cancer diagnosis and therapy. However, prostate CT image segmentation is challenging because of the low contrast of soft tissue on CT images. In this paper, we propose an automatic segmentation method by combining a deep learning method and multi-atlas refinement. First, instead of segmenting the whole image, we extract the region of interesting (ROI) to delete irrelevant regions. Then, we use the convolutional neural networks (CNN) to learn the deep features for distinguishing the prostate pixels from the non-prostate pixels in order to obtain the preliminary segmentation results. CNN can automatically learn the deep features adapting to the data, which are different from some handcrafted features. Finally, we select some similar atlases to refine the initial segmentation results. The proposed method has been evaluated on a dataset of 92 prostate CT images. Experimental results show that our method achieved a Dice similarity coefficient of 86.80% as compared to the manual segmentation. The deep learning based method can provide a useful tool for automatic segmentation of the prostate on CT images and thus can have a variety of clinical applications.

KW - Computed tomography (CT)

KW - Convolutional neural networks (CNN)

KW - Deep learning

KW - Image segmentation

KW - Multiatlas segmentation

KW - Prostate

KW - Prostate cancer

UR - http://www.scopus.com/inward/record.url?scp=85020260855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020260855&partnerID=8YFLogxK

U2 - 10.1117/12.2255755

DO - 10.1117/12.2255755

M3 - Conference contribution

C2 - 30220767

AN - SCOPUS:85020260855

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2017

A2 - Angelini, Elsa D.

A2 - Styner, Martin A.

A2 - Angelini, Elsa D.

PB - SPIE

ER -