Method for detecting enlarged lymph nodes from 3d abdominal CT images with a multi-shape and multi-scale ellipsoidal structure detection filter

Authors:
Masahiro Oda;Takayuki Kitasaka;Michitaka Fujiwara;Kazunari Misawa;Kensaku Mori
Affiliations:
Graduate School of Information Science, Nagoya University, Nagoya, Aichi, Japan;Faculty of Information Science, Aichi Institute of Technology, Toyota, Aichi, Japan;Graduate School of Medicine, Nagoya University, Nagoya, Aichi, Japan;Aichi Cancer Center, Nagoya, Aichi, Japan;Strategy Office, Information and Communications Headquarters, Nagoya University, Nagoya, Aichi, Japan,Graduate School of Information Science, Nagoya University, Nagoya, Aichi, Japan
Venue:
MICCAI'12 Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applications
Year:
2012

Citing 3
Cited 0

Tissue Classification Based on 3D Local Intensity Structures for Volume Rendering

IEEE Transactions on Visualization and Computer Graphics
Automated extraction of lymph nodes from 3-D abdominal CT images using 3-D minimum directional difference filter

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Automatic detection and segmentation of axillary lymph nodes

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a method for detecting gastric lymph nodes from abdominal CT images is proposed. The positions of metastatic cancers and metastatic lymph nodes should be accurately estimated in order to determine the optimal surgical plan for cancer removal. Ellipsoidal- and spherical-shaped lymph nodes are observed in medical images. However, the detection target of previous lymph node detection methods was only the spherical-shaped lymph nodes. We propose a method for detecting both ellipsoidal- and spherical-shaped lymph nodes by using a multi-shape and multi-scale ellipsoidal structure detection filter that detects the lymph nodes from CT images. The size and the shape of a detection target are specified by the parameters of the filter. The multi-shape and multi-scale detection is performed by applying the filter multiple times with different values for the parameters. Experimental results using 16 cases of CT images showed that the proposed method could detect 56.8% of lymph nodes.