Share Email Print

Proceedings Paper

Deep learning approaches for intraoperative pixel-based diagnosis of colon cancer metastasis in a liver from phase-contrast images of unstained specimens
Author(s): Dario Sitnik; Gorana Aralica; Arijana Pačić; Marijana Popović Hadžija; Mirko Hadžija; Ivica Kopriva
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

There is a need for computer-aided diagnosis (CAD) systems to relieve the workload on pathologists. This seems to be especially important for intraoperative diagnosis during surgery, for which diagnostic time is very limited. This paper presents preliminary results of intraoperative pixel-based CAD of colon cancer metastasis in a liver from phase-contrast images of unstained frozen sections. In particular, two deep learning networks: the U-net and the structured autoencoder for deep subspace clustering, were trained on eighteen phase-contrast images belonging to five patients and tested on eight images belonging to three patients. Spectrum angle mapper was also used in comparative performance analysis. The best result achieved by the U-net yielded balanced accuracy of 83.70%±8%, sensitivity of 94.50%±8%, specificity of 72.9%±8% and Dice coefficient of 45.20%±25.4%. However, factors such as absence of tissue fixation and ethanol-induced dehydration, melting of the specimen under the microscope and/or frozen crystals in the specimen cause variations in quality of phase-contrast images of unstained frozen sections. This, in return, affects reproducibility of diagnostic performance.

Paper Details

Date Published: 16 March 2020
PDF: 10 pages
Proc. SPIE 11320, Medical Imaging 2020: Digital Pathology, 1132009 (16 March 2020); doi: 10.1117/12.2542799
Show Author Affiliations
Dario Sitnik, Ruđer Bošković Institute (Croatia)
Gorana Aralica, Clinical Hospital Dubrava (Croatia)
School of Medicine, Univ. of Zagreb (Croatia)
Arijana Pačić, Clinical Hospital Dubrava (Croatia)
Marijana Popović Hadžija, Ruđer Bošković Institute (Croatia)
Mirko Hadžija, Ruđer Bošković Institute (Croatia)
Ivica Kopriva, Ruđer Bošković Institute (Croatia)

Published in SPIE Proceedings Vol. 11320:
Medical Imaging 2020: Digital Pathology
John E. Tomaszewski; Aaron D. Ward, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?