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

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.

Read full text

Zpracování a analýza CT obrazů

CT Image Processing

Jiří ChmelíkJiří Chmelík

Roman JakubíčekRoman Jakubíček

Petr Walek

Jiří JanJiří Jan

Petr Ouředníček

Lukáš Lambert

Elena Amadori

Giampaolo Gavelli

Follow Us

Get the latest news about our teaching and learning activities or get excited about scientific discoveries in biomedical engineering.

Partner With Us

We are committed to promote collaboration across biomedical disciplines creating mutual benefits with companies and research organizations. Explore opportunities to engage with our research teams, or find out more about our current research partners.

Giving

Donate to support research and education that translates into improved healthcare and people’s wellbeing. With a number of giving options, you can support the area you care about most. Gifts of any size help expand our positive impact throughout the society.