Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging

Nesrine Bnouni, Olfa Mechi, Islem Rekik, Mohamed Salah Rhim, Najoua Essoukri Ben Amara

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

  • 1 Citations

Abstract

The segmentation and classification of Lymph Nodes (LNs) is a fundamental but challenging step in the analysis of medical images of cervical cancer. Both tasks can leverage morphological features such as size, shape, contour, and heterogeneous appearance. However, these features might vary with the progressive state of LNs. Hence, accurate detection of LNs boundary is an essential step sing to classify LN as suspect (malignant) and non-suspect (benign). However, manual delineation of LNs might produce classification errors due to the inter and intra-observer variability. Semi-automatic and automatic LNs segmentation methods are greatly desired as they would help improve patient diagnosis and treatment processes. Currently, Magnetic Resonance Imaging (MRI) is widely used to diagnose cervical cancer and LN involvement. Diffusion Weighted (DW)-MRI exhibits metastatic LN as bright regions. This paper presents a semi-automatic segmentation and classification method of LNs. Specifically, we propose a novel approach which leverages (1) the complementarity of structural and diffusion MR images through a fusion step and (2) morphological features of the segmented metastatic LNs for classification. The contribution of our proposed algorithm is threefold. First, we fuse the axial T2-Weighted (T2-w) anatomical image and the DW image. Second, we detect LNs using region-growing method in order to compute the final classification. Third, segmentation results are then used to classify LNs based on a gray level dependency matrix technique which extracts LN features. We evaluated our method using 10 MR images T2-w and DW with 47 metastatic LNs. We obtained an average accuracy of 70.21% for cervical cancer nodule classification.

LanguageEnglish
Title of host publication2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
ISBN (Electronic)9781538652398
DOIs
Publication statusPublished - 23 May 2018
Event4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018 - Sousse, Tunisia
Duration: 21 Mar 201824 Mar 2018

Conference

Conference4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018
CountryTunisia
CitySousse
Period21/03/1824/03/18

Fingerprint

Imaging techniques
Electric fuses
Fusion reactions
Magnetic Resonance Imaging

Keywords

  • abnormal node detection
  • cervical cancer
  • classification
  • lymph nodes
  • MR imaging
  • multimodal image fusion
  • segmentation

Cite this

Bnouni, N., Mechi, O., Rekik, I., Rhim, M. S., & Ben Amara, N. E. (2018). Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging. In 2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018 (pp. 1-6). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ATSIP.2018.8364480
Bnouni, Nesrine ; Mechi, Olfa ; Rekik, Islem ; Rhim, Mohamed Salah ; Ben Amara, Najoua Essoukri. / Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging. 2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 1-6
@inproceedings{147b69cce35c4ffeb5f1499493787c03,
title = "Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging",
abstract = "The segmentation and classification of Lymph Nodes (LNs) is a fundamental but challenging step in the analysis of medical images of cervical cancer. Both tasks can leverage morphological features such as size, shape, contour, and heterogeneous appearance. However, these features might vary with the progressive state of LNs. Hence, accurate detection of LNs boundary is an essential step sing to classify LN as suspect (malignant) and non-suspect (benign). However, manual delineation of LNs might produce classification errors due to the inter and intra-observer variability. Semi-automatic and automatic LNs segmentation methods are greatly desired as they would help improve patient diagnosis and treatment processes. Currently, Magnetic Resonance Imaging (MRI) is widely used to diagnose cervical cancer and LN involvement. Diffusion Weighted (DW)-MRI exhibits metastatic LN as bright regions. This paper presents a semi-automatic segmentation and classification method of LNs. Specifically, we propose a novel approach which leverages (1) the complementarity of structural and diffusion MR images through a fusion step and (2) morphological features of the segmented metastatic LNs for classification. The contribution of our proposed algorithm is threefold. First, we fuse the axial T2-Weighted (T2-w) anatomical image and the DW image. Second, we detect LNs using region-growing method in order to compute the final classification. Third, segmentation results are then used to classify LNs based on a gray level dependency matrix technique which extracts LN features. We evaluated our method using 10 MR images T2-w and DW with 47 metastatic LNs. We obtained an average accuracy of 70.21{\%} for cervical cancer nodule classification.",
keywords = "abnormal node detection, cervical cancer, classification, lymph nodes, MR imaging, multimodal image fusion, segmentation",
author = "Nesrine Bnouni and Olfa Mechi and Islem Rekik and Rhim, {Mohamed Salah} and {Ben Amara}, {Najoua Essoukri}",
year = "2018",
month = "5",
day = "23",
doi = "10.1109/ATSIP.2018.8364480",
language = "English",
pages = "1--6",
booktitle = "2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Bnouni, N, Mechi, O, Rekik, I, Rhim, MS & Ben Amara, NE 2018, Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging. in 2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018. Institute of Electrical and Electronics Engineers Inc., pp. 1-6, 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018, Sousse, Tunisia, 21/03/18. https://doi.org/10.1109/ATSIP.2018.8364480

Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging. / Bnouni, Nesrine; Mechi, Olfa; Rekik, Islem; Rhim, Mohamed Salah; Ben Amara, Najoua Essoukri.

2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 1-6.

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

TY - GEN

T1 - Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging

AU - Bnouni, Nesrine

AU - Mechi, Olfa

AU - Rekik, Islem

AU - Rhim, Mohamed Salah

AU - Ben Amara, Najoua Essoukri

PY - 2018/5/23

Y1 - 2018/5/23

N2 - The segmentation and classification of Lymph Nodes (LNs) is a fundamental but challenging step in the analysis of medical images of cervical cancer. Both tasks can leverage morphological features such as size, shape, contour, and heterogeneous appearance. However, these features might vary with the progressive state of LNs. Hence, accurate detection of LNs boundary is an essential step sing to classify LN as suspect (malignant) and non-suspect (benign). However, manual delineation of LNs might produce classification errors due to the inter and intra-observer variability. Semi-automatic and automatic LNs segmentation methods are greatly desired as they would help improve patient diagnosis and treatment processes. Currently, Magnetic Resonance Imaging (MRI) is widely used to diagnose cervical cancer and LN involvement. Diffusion Weighted (DW)-MRI exhibits metastatic LN as bright regions. This paper presents a semi-automatic segmentation and classification method of LNs. Specifically, we propose a novel approach which leverages (1) the complementarity of structural and diffusion MR images through a fusion step and (2) morphological features of the segmented metastatic LNs for classification. The contribution of our proposed algorithm is threefold. First, we fuse the axial T2-Weighted (T2-w) anatomical image and the DW image. Second, we detect LNs using region-growing method in order to compute the final classification. Third, segmentation results are then used to classify LNs based on a gray level dependency matrix technique which extracts LN features. We evaluated our method using 10 MR images T2-w and DW with 47 metastatic LNs. We obtained an average accuracy of 70.21% for cervical cancer nodule classification.

AB - The segmentation and classification of Lymph Nodes (LNs) is a fundamental but challenging step in the analysis of medical images of cervical cancer. Both tasks can leverage morphological features such as size, shape, contour, and heterogeneous appearance. However, these features might vary with the progressive state of LNs. Hence, accurate detection of LNs boundary is an essential step sing to classify LN as suspect (malignant) and non-suspect (benign). However, manual delineation of LNs might produce classification errors due to the inter and intra-observer variability. Semi-automatic and automatic LNs segmentation methods are greatly desired as they would help improve patient diagnosis and treatment processes. Currently, Magnetic Resonance Imaging (MRI) is widely used to diagnose cervical cancer and LN involvement. Diffusion Weighted (DW)-MRI exhibits metastatic LN as bright regions. This paper presents a semi-automatic segmentation and classification method of LNs. Specifically, we propose a novel approach which leverages (1) the complementarity of structural and diffusion MR images through a fusion step and (2) morphological features of the segmented metastatic LNs for classification. The contribution of our proposed algorithm is threefold. First, we fuse the axial T2-Weighted (T2-w) anatomical image and the DW image. Second, we detect LNs using region-growing method in order to compute the final classification. Third, segmentation results are then used to classify LNs based on a gray level dependency matrix technique which extracts LN features. We evaluated our method using 10 MR images T2-w and DW with 47 metastatic LNs. We obtained an average accuracy of 70.21% for cervical cancer nodule classification.

KW - abnormal node detection

KW - cervical cancer

KW - classification

KW - lymph nodes

KW - MR imaging

KW - multimodal image fusion

KW - segmentation

UR - http://www.scopus.com/inward/record.url?scp=85048505305&partnerID=8YFLogxK

U2 - 10.1109/ATSIP.2018.8364480

DO - 10.1109/ATSIP.2018.8364480

M3 - Conference contribution

SP - 1

EP - 6

BT - 2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bnouni N, Mechi O, Rekik I, Rhim MS, Ben Amara NE. Semi-automatic lymph node segmentation and classification using cervical cancer MR imaging. In 2018 4th International Conference on Advanced Technologies for Signal and Image Processing, ATSIP 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 1-6 https://doi.org/10.1109/ATSIP.2018.8364480