Format

Send to

Choose Destination
Med Image Anal. 2018 Oct;49:76-88. doi: 10.1016/j.media.2018.07.008. Epub 2018 Aug 3.

Deep convolutional neural network-based segmentation and classification of difficult to define metastatic spinal lesions in 3D CT data.

Author information

1
Faculty of Electrical Engineering and Communication, Department of Biomedical Engineering, Brno University of Technology, Brno, Technicka 3082/12, 616 00, Czechia. Electronic address: chmelikj@feec.vutbr.cz.
2
Faculty of Electrical Engineering and Communication, Department of Biomedical Engineering, Brno University of Technology, Brno, Technicka 3082/12, 616 00, Czechia.
3
Philips Healthcare, AE Eindhoven, High Tech Campus 34, 5656, Netherlands; Department of Medical Imaging, St. Anne's University Hospital Brno and Faculty of Medicine Masaryk University Brno, Brno, Pekarska 663/53, 656 91 Czechia.
4
Department of Radiology, First Faculty of Medicine, Charles University and General University Hospital in Prague, Prague, U Nemocnice 499/2, 128 08, Czechia.
5
Istituto Scientifico Romagnolo per lo Studio e la Cura dei Tumori (IRST), Istituto di Ricovero e Cura a Carattere Scientifico (IRCCS), Meldola FC, Via Piero Maroncelli 40, 470 14, Italy.

Abstract

This paper aims to address the segmentation and classification of lytic and sclerotic metastatic lesions that are difficult to define by using spinal 3D Computed Tomography (CT) images obtained from highly pathologically affected cases. As the lesions are ill-defined and consequently it is difficult to find relevant image features that would enable detection and classification of lesions by classical methods of texture and shape analysis, the problem is solved by automatic feature extraction provided by a deep Convolutional Neural Network (CNN). Our main contributions are: (i) individual CNN architecture, and pre-processing steps that are dependent on a patient data and a scan protocol - it enables work with different types of CT scans; (ii) medial axis transform (MAT) post-processing for shape simplification of segmented lesion candidates with Random Forest (RF) based meta-analysis; and (iii) usability of the proposed method on whole-spine CTs (cervical, thoracic, lumbar), which is not treated in other published methods (they work with thoracolumbar segments of spine only). Our proposed method has been tested on our own dataset annotated by two mutually independent radiologists and has been compared to other published methods. This work is part of the ongoing complex project dealing with spine analysis and spine lesion longitudinal studies.

KEYWORDS:

CT analysis; Computer aided detection; Convolutional neural network; Spinal metastasis

PMID:
30114549
DOI:
10.1016/j.media.2018.07.008
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center