Hierarchical deep convolutional neural networks combine spectral and spatial information for highly accurate Raman‐microscopy‐based cytopathology. Issue 10 (5th July 2018)

• Record Type: Journal Article
• Authors: Krauß, Sascha D.; Roy, Raphael; Yosef, Hesham K.; Lechtonen, Tatjana; El‐Mashtoly, Samir F.; Gerwert, Klaus; Mosig, Axel
• Is Part Of: Journal of biophotonics. Volume 11:Issue 10(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-07-05
• Subjects: neural networks -- Raman spectroscopy -- supervised machine learning -- urinary bladder neoplasms; Photonics -- Periodicals; Optical materials -- Periodicals; Optics -- Periodicals; Medical instruments and apparatus -- Periodicals; 621.3605
• DOI: 10.1002/jbio.201800022
• Languages: English
• ISSNs: 1864-063X

Abstract

Abstract : Hierarchical variants of so‐called deep convolutional neural networks (DCNNs) have facilitated breakthrough results for numerous pattern recognition tasks in recent years. We assess the potential of these novel whole‐image classifiers for Raman‐microscopy‐based cytopathology. Conceptually, DCNNs facilitate a flexible combination of spectral and spatial information for classifying cellular images as healthy or cancer‐affected cells. As we demonstrate, this conceptual advantage translates into practice, where DCNNs exceed the accuracy of both conventional classifiers based on pixel spectra as well as classifiers based on morphological features extracted from Raman microscopic images. Remarkably, accuracies exceeding those of all previously proposed classifiers are obtained while using only a small fraction of the spectral information provided by the dataset. Overall, our results indicate a high potential for DCNNs in medical applications of not just Raman, but also infrared microscopy. Abstract : Current methods in bladder cancer diagnostics are either invasive or lack accuracy. All have in common, that they are less good in detecting early stages and that they are labor intensive and costly. The introduction of hierarchical deep convolutional neural networks (DCNNs) can automate the diagnostic process and handle much larger amounts of data. The positive impact of this will be countable in money, working hours and years of life saved.