Automated region of interest retrieval and classification using spectral analysis

Abstract

Efficient use of whole slide imaging in pathology needs automated region of interest (ROI) retrieval and classification, through the use of image analysis and data sorting tools. One possible method for data sorting uses Spectral Analysis for Dimensionality Reduction. We present some interesting results in the field of histopathology and cytohematology.In histopathology, we developed a Computer-Aided Diagnosis system applied to low-resolution images representing the totality of histological breast tumour sections. The images can be digitized directly at low resolution or be obtained from sub-sampled high-resolution virtual slides. Spectral Analysis is used (1) for image segmentation (stroma, tumour epithelium), by determining a «distance» between all the images of the database, (2) for choosing representative images and characteristic patterns of each histological type in order to index them, and (3) for visualizing images or features similar to a sample provided by the pathologist.In cytohematology, we studied a blood smear virtual slide acquired through high resolution oil scanning and Spectral Analysis is used to sort selected nucleated blood cell classes so that the pathologist may easily focus on specific classes whose morphology could then be studied more carefully or which can be analyzed through complementary instruments, like Multispectral Imaging or Raman MicroSpectroscopy.

AI (artificial intelligence) in histopathology--from image analysis to automated diagnosis.

“…The significant module of automated assessment of the most significant field of view is in its test phase, and preliminary results are promising [20]. A different approach of Oger et al using fraction analysis has to be mentioned here too [24]. This approach offers a new strategy and should be tested in future too.…”

A model for predicting pathologist's velocity profiles when navigating virtual slides

“…Some recent works have shown that it is possible to automatically determine RoIs (Gómez et al, 2009;Oger et al, 2008) so that a probabilistic map could be associated to the image. In addition, such observation path should follow optimal sampling strategies (Kayser et al, 2009) which improve the diagnosis times, that is to say, a minimal number of RoIs would drive the navi-gation.…”

Heterogeneity assessment of histological tissue sections in whole slide images

“…In order to later compare feature vectors, and considering the sparse numerical range of their values, the symmetric Kullback-Leibler distance [3,4] has been retained for its ability to easily manage such a case, while remaining fast to implement. The distance between two vectors p 1 ,p 2 of length F is given by:…”

“…[1,2]) of individual structures to characterize heterogeneity, but to make use of classification of squared sub-images later called 'patches'. In some previous works dedicated to the development of a computer-aided diagnosis system (CADS) based on image retrieval and classification [3,5], we have used a http://dx.doi.org/10.1016/j.compmedimag.2014.11.006 0895-6111/© 2014 Elsevier Ltd. All rights reserved. method coming from spectral graph theory, the Diffusion Maps (DM) [6], to process WSI split in small squares called 'patches.'…”