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

Publisher: Elsevier Inc Country of Publication: United States NLM ID: 101528849 Publication Model: eCollection Cited Medium: Print ISSN: 2229-5089 (Print) NLM ISO Abbreviation: J Pathol Inform Subsets: PubMed not MEDLINE

Publication: 2022- : [New York] : Elsevier Inc.
Original Publication: Ghatkopar, Mumbai : Medknow Publications and Media, 2010-

Competing Interests: There are no conflicts of interest.
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.
(Copyright: © 2021 Journal of Pathology Informatics.)

J Gastroenterol Hepatol. 2019 Dec;34(12):2144-2151. (PMID: 31265738)
J Biophotonics. 2019 Jul;12(7):e201800435. (PMID: 30868728)
J Pathol Inform. 2020 Aug 21;11:28. (PMID: 33042607)
Sci Rep. 2018 Oct 30;8(1):16016. (PMID: 30375454)
BMC Cancer. 2015 Mar 18;15:142. (PMID: 25885576)
J Biomed Opt. 2018 Jun;23(6):1-7. (PMID: 29900705)
Sci Rep. 2017 Jul 31;7(1):6959. (PMID: 28761050)
J Pathol Inform. 2020 Nov 26;11:38. (PMID: 33828896)
Artif Intell Med. 2020 Aug;108:101923. (PMID: 32972656)
JAMA Netw Open. 2020 Apr 1;3(4):e203398. (PMID: 32324237)
Methods Protoc. 2019 Jun 20;2(2):. (PMID: 31226732)
BMC Cancer. 2019 Apr 2;19(1):295. (PMID: 30940105)
Histopathology. 2020 Jan;76(2):182-188. (PMID: 31433515)
Surg Oncol. 2019 Dec;31:119-131. (PMID: 31654957)
Biomed Opt Express. 2013 Jun 24;4(7):1204-13. (PMID: 23847743)
Biomed Opt Express. 2019 Dec 10;11(1):186-199. (PMID: 32010509)
Sci Rep. 2020 May 14;10(1):7968. (PMID: 32409755)
Gut. 2015 Oct;64(10):1569-77. (PMID: 25387891)
J Clin Gastroenterol. 2013 Sep;47(8):657-65. (PMID: 23948754)

Keywords: Colorectal polyps; convolutional neural network; dataset; multiphoton microscopy; optical biopsy

Date Created: 20210827 Latest Revision: 20240814

20250114

PMC8359734

10.4103/jpi.jpi_113_20

34447607