Analysis on the Characterization of Multiphoton Microscopy Images for Malignant Neoplastic Colon Lesion Detection under Deep Learning Methods

Abstract

Background: Colorectal cancer has a high incidence rate worldwide, with over 1.8 million new cases and 880,792 deaths in 2018. Fortunately, its early detection significantly increases the survival rate, reaching a cure rate of 90% when diagnosed at a localized stage. Colonoscopy is the gold standard technique for detection and removal of colorectal lesions with potential to evolve into cancer. When polyps are found in a patient, the current procedure is their complete removal. However, in this process, gastroenterologists cannot assure complete resection and clean margins which are given by the histopathology analysis of the removed tissue, which is performed at laboratory. Aims: In this paper, we demonstrate the capabilities of multiphoton microscopy (MPM) technology to provide imaging biomarkers that can be extracted by deep learning techniques to identify malignant neoplastic colon lesions and distinguish them from healthy, hyperplastic, or benign neoplastic tissue, without the need for histopathological staining. Materials and Methods: To this end, we present a novel MPM public dataset containing 14,712 images obtained from 42 patients and grouped into 2 classes. A convolutional neural network is trained on this dataset and a spatially coherent predictions scheme is applied for performance improvement. Results: We obtained a sensitivity of 0.8228 ± 0.1575 and a specificity of 0.9114 ± 0.0814 on detecting malignant neoplastic lesions. We also validated this approach to estimate the self-confidence of the network on its own predictions, obtaining a mean sensitivity of 0.8697 and a mean specificity of 0.9524 with the 18.67% of the images classified as uncertain. Conclusions: This work lays the foundations for performing in vivo optical colon biopsies by combining this novel imaging technology together with deep learning algorithms, hence avoiding unnecessary polyp resection and allowing in situ diagnosis assessment.

Tissue classification and diagnosis of colorectal cancer histopathology images using deep learning algorithms. Is the time ripe for clinical practice implementation?

“…A comparison of handcrafted feature-based models versus automated deep learning models also showed the superiority of unsupervised training in classification models, rather than feature-based classification [ 53 ]. Another point raised by several authors, regarding the comparison of different classification models, is the quality of the initial annotation by the pathologist, which can influence solely the malignancy-containing slides [ 28 , 48 ]. Furthermore, the direct comparison of different models and classification architectures is further hindered by the variability of the tissue itself.…”

Deep Learning on Histopathological Images for Colorectal Cancer Diagnosis: A Systematic Review

“…The accurate identification of benign from malignant tissues achieved a sensitivity of 0.8228 and specificity of 0.9114 by a DL model trained with Multiphoton microscopy (MPM) images, although images were lacking biomarkers such as colonic crypts and goblet cells [51]. Holland et al used the same classification model and 7 training datasets consisting of a descending number of images [52].…”

Mucosal imaging in colon polyps: New advances and what the future may hold

“…The use of longer photons allows deeper tissue penetration and visualisation up to a depth of several hundred microns[ 232 ]. Recently, Terradillos et al [ 233 ] developed an AI system for interpretation of multiphoton microscopy images of colorectal polyps, with a specificity of 91% and sensitivity of 82% for malignant colorectal lesions. Further study is clearly required into the application of this technology, however the greater depth of visualisation may allow in vivo assessment of invasion depth for submucosal invasive adenocarcinoma.…”