Advanced Raman Spectroscopy Based on Transfer Learning by Using a Convolutional Neural Network for Personalized Colorectal Cancer Diagnosis
Dimitris Kalatzis,
Ellas Spyratou,
Maria Karnachoriti,
Maria Anthi Kouri,
Spyros Orfanoudakis,
Nektarios Koufopoulos,
Abraham Pouliakis,
Nikolaos Danias,
Ioannis Seimenis,
Athanassios G. Kontos,
Efstathios P. Efstathopoulos
Affiliations
Dimitris Kalatzis
2nd Department of Radiology, Medical School, National and Kapodistrian University of Athens, 12462 Athens, Greece
Ellas Spyratou
2nd Department of Radiology, Medical School, National and Kapodistrian University of Athens, 12462 Athens, Greece
Maria Karnachoriti
Department of Medicine, Democritus University of Thrace, 68100 Alexandroupolis, Greece
Maria Anthi Kouri
2nd Department of Radiology, Medical School, National and Kapodistrian University of Athens, 12462 Athens, Greece
Spyros Orfanoudakis
Alpha Information Technology S.A., Software & System Development, 39 Dimokratias Avenue, 68131 Alexandroupolis, Greece
Nektarios Koufopoulos
2nd Department of Pathology, School of Medicine, Attikon University Hospital, National and Kapodistrian University of Athens, 12462 Athens, Greece
Abraham Pouliakis
2nd Department of Pathology, School of Medicine, Attikon University Hospital, National and Kapodistrian University of Athens, 12462 Athens, Greece
Nikolaos Danias
4th Department of Surgery, School of Medicine, Attikon University Hospital, University of Athens, 1 Rimini Street, 12462 Athens, Greece
Ioannis Seimenis
Medical School, National and Kapodistrian University of Athens, 75 Mikras Assias Str., 11527 Athens, Greece
Athanassios G. Kontos
Physics Department, School of Applied Mathematical and Physical Sciences, National Technical University of Athens, Iroon Politechniou 9, Zografou, 15780 Athens, Greece
Efstathios P. Efstathopoulos
2nd Department of Radiology, Medical School, National and Kapodistrian University of Athens, 12462 Athens, Greece
Advanced Raman spectroscopy (RS) systems have gained new interest in the field of medicine as an emerging tool for in vivo tissue discrimination. The coupling of RS with artificial intelligence (AI) algorithms has given a boost to RS to analyze spectral data in real time with high specificity and sensitivity. However, limitations are still encountered due to the large amount of clinical data which are required for the pre-training process of AI algorithms. In this study, human healthy and cancerous colon specimens were surgically resected from different sites of the ascending colon and analyzed by RS. Two transfer learning models, the one-dimensional convolutional neural network (1D-CNN) and the 1D–ResNet transfer learning (1D-ResNet) network, were developed and evaluated using a Raman open database for the pre-training process which consisted of spectra of pathogen bacteria. According to the results, both models achieved high accuracy of 88% for healthy/cancerous tissue discrimination by overcoming the limitation of the collection of a large number of spectra for the pre-training process. This gives a boost to RS as an adjuvant tool for real-time biopsy and surgery guidance.
