Rapid Polyp Classification in Colonoscopy Using Textural and Convolutional Features

Overview

Journal Healthcare (Basel)

Specialty Health Services

Date 2022 Aug 26

PMID 36011151

Authors

Chung-Ming Lo

Yu-Hsuan Yeh

Jui-Hsiang Tang

Chun-Chao Chang

Hsing-Jung Yeh

Affiliations

Soon will be listed here.

Abstract

Colorectal cancer is the leading cause of cancer-associated morbidity and mortality worldwide. One of the causes of developing colorectal cancer is untreated colon adenomatous polyps. Clinically, polyps are detected in colonoscopy and the malignancies are determined according to the biopsy. To provide a quick and objective assessment to gastroenterologists, this study proposed a quantitative polyp classification via various image features in colonoscopy. The collected image database was composed of 1991 images including 1053 hyperplastic polyps and 938 adenomatous polyps and adenocarcinomas. From each image, textural features were extracted and combined in machine learning classifiers and machine-generated features were automatically selected in deep convolutional neural networks (DCNN). The DCNNs included AlexNet, Inception-V3, ResNet-101, and DenseNet-201. AlexNet trained from scratch achieved the best performance of 96.4% accuracy which is better than transfer learning and textural features. Using the prediction models, the malignancy level of polyps can be evaluated during a colonoscopy to provide a rapid treatment plan.

Citing Articles

Detecting microsatellite instability in colorectal cancer using Transformer-based colonoscopy image classification and retrieval.

Lo C, Jiang J, Lin C PLoS One. 2024; 19(1):e0292277.

PMID: 38271352 PMC: 10810505. DOI: 10.1371/journal.pone.0292277.

Analyzing drama metadata through machine learning to gain insights into social information dissemination patterns.

Lo C, Syu Z PLoS One. 2023; 18(11):e0288932.

PMID: 38032993 PMC: 10688626. DOI: 10.1371/journal.pone.0288932.

Identification of LncPVT1 and CircPVT1 as prognostic biomarkers in human colorectal polyps.

Rezasoltani M, Forouzesh F, Salehi Z, Zabihi M, Rejali L, Nazemalhosseini-Mojarad E Sci Rep. 2023; 13(1):13113.

PMID: 37573419 PMC: 10423217. DOI: 10.1038/s41598-023-40288-1.

Automated classification of polyps using deep learning architectures and few-shot learning.

Krenzer A, Heil S, Fitting D, Matti S, Zoller W, Hann A BMC Med Imaging. 2023; 23(1):59.

PMID: 37081495 PMC: 10120204. DOI: 10.1186/s12880-023-01007-4.

Detection of Colorectal Polyps from Colonoscopy Using Machine Learning: A Survey on Modern Techniques.

ELKarazle K, Raman V, Then P, Chua C Sensors (Basel). 2023; 23(3).

PMID: 36772263 PMC: 9953705. DOI: 10.3390/s23031225.

References

Siegel R, Fedewa S, Anderson W, Miller K, Ma J, Rosenberg P . Colorectal Cancer Incidence Patterns in the United States, 1974-2013. J Natl Cancer Inst. 2017; 109(8). PMC: 6059239. DOI: 10.1093/jnci/djw322. View

Hsu Y, Wu T, Lo Y, Wang L . Gastrointestinal complications and extraintestinal manifestations of inflammatory bowel disease in Taiwan: A population-based study. J Chin Med Assoc. 2016; 80(2):56-62. DOI: 10.1016/j.jcma.2016.08.009. View

Ay B, Turker C, Emre E, Ay K, Aydin G . Automated classification of nasal polyps in endoscopy video-frames using handcrafted and CNN features. Comput Biol Med. 2022; 147:105725. DOI: 10.1016/j.compbiomed.2022.105725. View

Shalman D, Gerson L . Systematic review with meta-analysis: the risk of gastrointestinal haemorrhage post-polypectomy in patients receiving anti-platelet, anti-coagulant and/or thienopyridine medications. Aliment Pharmacol Ther. 2015; 42(8):949-56. DOI: 10.1111/apt.13367. View

Carethers J, Jung B . Genetics and Genetic Biomarkers in Sporadic Colorectal Cancer. Gastroenterology. 2015; 149(5):1177-1190.e3. PMC: 4589489. DOI: 10.1053/j.gastro.2015.06.047. View

Chaddad A, Desrosiers C, Bouridane A, Toews M, Hassan L, Tanougast C . Multi Texture Analysis of Colorectal Cancer Continuum Using Multispectral Imagery. PLoS One. 2016; 11(2):e0149893. PMC: 4764026. DOI: 10.1371/journal.pone.0149893. View

Hiramatsu K, Sakata H, Horita Y, Orita N, Kida A, Mizukami A . Mesenteric phlebosclerosis associated with long-term oral intake of geniposide, an ingredient of herbal medicine. Aliment Pharmacol Ther. 2012; 36(6):575-86. DOI: 10.1111/j.1365-2036.2012.05221.x. View

Torres J, Mehandru S, Colombel J, Peyrin-Biroulet L . Crohn's disease. Lancet. 2016; 389(10080):1741-1755. DOI: 10.1016/S0140-6736(16)31711-1. View

Zauber A, Winawer S, OBrien M, Lansdorp-Vogelaar I, van Ballegooijen M, Hankey B . Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N Engl J Med. 2012; 366(8):687-96. PMC: 3322371. DOI: 10.1056/NEJMoa1100370. View

10.

Corley D, Jensen C, Marks A, Zhao W, Lee J, Doubeni C . Adenoma detection rate and risk of colorectal cancer and death. N Engl J Med. 2014; 370(14):1298-306. PMC: 4036494. DOI: 10.1056/NEJMoa1309086. View

11.

Liu X, Faes L, Kale A, Wagner S, Fu D, Bruynseels A . A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2020; 1(6):e271-e297. DOI: 10.1016/S2589-7500(19)30123-2. View

12.

Siegel R, Miller K, Jemal A . Cancer statistics, 2020. CA Cancer J Clin. 2020; 70(1):7-30. DOI: 10.3322/caac.21590. View

13.

Beaugerie L, Itzkowitz S . Cancers complicating inflammatory bowel disease. N Engl J Med. 2015; 372(15):1441-52. DOI: 10.1056/NEJMra1403718. View

14.

Lee J, Kim J, Kim S, Park H, Choi B . A straightforward approach to computer-aided polyp detection using a polyp-specific volumetric feature in CT colonography. Comput Biol Med. 2011; 41(9):790-801. DOI: 10.1016/j.compbiomed.2011.06.015. View

15.

Mann R, Gajendran M, Umapathy C, Perisetti A, Goyal H, Saligram S . Endoscopic Management of Complex Colorectal Polyps: Current Insights and Future Trends. Front Med (Lausanne). 2022; 8:728704. PMC: 8811151. DOI: 10.3389/fmed.2021.728704. View

16.

Yoshida H, Nappi J, MacEneaney P, Rubin D, Dachman A . Computer-aided diagnosis scheme for detection of polyps at CT colonography. Radiographics. 2002; 22(4):963-79. DOI: 10.1148/radiographics.22.4.g02jl16963. View

17.

Pacal I, Karaman A, Karaboga D, Akay B, Basturk A, Nalbantoglu U . An efficient real-time colonic polyp detection with YOLO algorithms trained by using negative samples and large datasets. Comput Biol Med. 2021; 141:105031. DOI: 10.1016/j.compbiomed.2021.105031. View

18.

Bengio Y, Courville A, Vincent P . Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell. 2013; 35(8):1798-828. DOI: 10.1109/TPAMI.2013.50. View

19.

Hu K, Zhao L, Feng S, Zhang S, Zhou Q, Gao X . Colorectal polyp region extraction using saliency detection network with neutrosophic enhancement. Comput Biol Med. 2022; 147:105760. DOI: 10.1016/j.compbiomed.2022.105760. View

20.

Cai W, Hong G . Quantitative image analysis for evaluation of tumor response in clinical oncology. Chronic Dis Transl Med. 2018; 4(1):18-28. PMC: 5938243. DOI: 10.1016/j.cdtm.2018.01.002. View