Publication detail

Fully Automatic CAD System for Segmentation and Classification of Spinal Metastatic Lesions in CT Data

CHMELÍK, J. JAKUBÍČEK, R. JAN, J. OUŘEDNÍČEK, P. LAMBERT, L. AMADORI, E. GAVELLI, G.

Original Title

Fully Automatic CAD System for Segmentation and Classification of Spinal Metastatic Lesions in CT Data

English Title

Fully Automatic CAD System for Segmentation and Classification of Spinal Metastatic Lesions in CT Data

Type

conference paper

Language

en

Original Abstract

Our contribution presents a research progress in our long-term project that deals with spine analysis in computed tomography (CT) data. A fully automatic computer-aided diagnosis (CAD) system is presented, enabling the simultaneous segmentation and classification of metastatic tissues that can occur in the vertebrae of oncological patients. The task of the proposed CAD system is to segment metastatic lesions and classify them into two categories: osteolytic and osteoblastic. These lesions, especially osteolytic, are ill defined and it is difficult to detect them directly with only information about voxel intensity. The use of several local texture and shape features turned out to be useful for correct classification, however the exact determination of relevant image features is a difficult task. For this reason, the feature determination has been solved by automatic feature extraction provided by a deep convolutional neural network (CNN). The achieved mean sensitivity of detected lesions is greater than 92% with approximately three false positive detections per lesion for both types.

English abstract

Our contribution presents a research progress in our long-term project that deals with spine analysis in computed tomography (CT) data. A fully automatic computer-aided diagnosis (CAD) system is presented, enabling the simultaneous segmentation and classification of metastatic tissues that can occur in the vertebrae of oncological patients. The task of the proposed CAD system is to segment metastatic lesions and classify them into two categories: osteolytic and osteoblastic. These lesions, especially osteolytic, are ill defined and it is difficult to detect them directly with only information about voxel intensity. The use of several local texture and shape features turned out to be useful for correct classification, however the exact determination of relevant image features is a difficult task. For this reason, the feature determination has been solved by automatic feature extraction provided by a deep convolutional neural network (CNN). The achieved mean sensitivity of detected lesions is greater than 92% with approximately three false positive detections per lesion for both types.

Keywords

CAD; Convolution neural network; Spine analysis; Metastasis; CT data

Released

30.05.2018

Publisher

Springer

Location

Singapore

ISBN

978-981-10-9034-9

Book

World Congress on Medical Physics and Biomedical Engineering 2018

Pages from

155

Pages to

158

Pages count

4

URL

BibTex


@inproceedings{BUT147831,
  author="Jiří {Chmelík} and Roman {Jakubíček} and Jiří {Jan} and Petr {Ouředníček} and Lukáš {Lambert} and Elena {Amadori} and Giampaolo {Gavelli}",
  title="Fully Automatic CAD System for Segmentation and Classification of Spinal Metastatic Lesions in CT Data",
  annote="Our contribution presents a research progress in our long-term project that deals with spine analysis in computed tomography (CT) data. A fully automatic computer-aided diagnosis (CAD) system is presented, enabling the simultaneous segmentation and classification of metastatic tissues that can occur in the vertebrae of oncological patients. The task of the proposed CAD system is to segment metastatic lesions and classify them into two categories: osteolytic and osteoblastic. These lesions, especially osteolytic, are ill defined and it is difficult to detect them directly with only information about voxel intensity. The use of several local texture and shape features turned out to be useful for correct classification, however the exact determination of relevant image features is a difficult task. For this reason, the feature determination has been solved by automatic feature extraction provided by a deep convolutional neural network (CNN). The achieved mean sensitivity of detected lesions is greater than 92% with approximately three false positive detections per lesion for both types.",
  address="Springer",
  booktitle="World Congress on Medical Physics and Biomedical Engineering 2018",
  chapter="147831",
  doi="10.1007/978-981-10-9035-6_28",
  howpublished="print",
  institution="Springer",
  number="1",
  year="2018",
  month="may",
  pages="155--158",
  publisher="Springer",
  type="conference paper"
}