' '
Deutsch | English    

Forschungsdatenbank PMU-SQQUID

Quantification of anomalies in rats spinal cords using autoencoders.
Tschuchnig, ME; Zillner, D; Romanelli, P; Hercher, D; Heimel, P; Oostingh, GJ; Couillard-Després, S; Gadermayr, M;
Comput Biol Med. 2021; 138: 104939
Originalarbeiten (Zeitschrift)

PMU-Autor/inn/en

Couillard-Després Sébastien
Romanelli Pasquale

Abstract

Computed tomography (CT) scans and magnetic resonance imaging (MRI) of spines are state-of-the-art for the evaluation of spinal cord lesions. This paper analyses micro-CT scans of rat spinal cords with the aim of generating lesion progression through the aggregation of anomaly-based scores. Since reliable labelling in spinal cords is only reasonable for the healthy class in the form of untreated spines, semi-supervised deviation-based anomaly detection algorithms are identified as powerful approaches. The main contribution of this paper is a large evaluation of different autoencoders and variational autoencoders for aggregated lesion quantification and a resulting spinal cord lesion quantification method that generates highly correlating quantifications. The conducted experiments showed that several models were able to generate 3D lesion quantifications of the data. These quantifications correlated with the weakly labelled true data with one model, reaching an average correlation of 0.83. We also introduced an area-based model, which correlated with a mean of 0.84. The possibility of the complementary use of the autoencoder-based method and the area feature were also discussed. Additionally to improving medical diagnostics, we anticipate features built on these quantifications to be useful for further applications like clustering into different lesions.


Useful keywords (using NLM MeSH Indexing)

Algorithms*

Animals

Cluster Analysis

Magnetic Resonance Imaging*

Rats

Spinal Cord/diagnostic imaging


Find related publications in this database (Keywords)

Digital pathology
Micro-CT
Anomaly detection
Autoencoder
Semi-supervised learning