Deep learning techniques for detecting preneoplastic and neoplastic lesions in human colorectal histological images

Sena,Paola; Fioresi,Rita; Faglioni,Francesco; Losi,Lorena; Faglioni,Giovanni; Roncucci,Luca

doi:10.3892/ol.2019.10928

Deep learning techniques for detecting preneoplastic and neoplastic lesions in human colorectal histological images

Authors:
- Paola Sena
- Rita Fioresi
- Francesco Faglioni
- Lorena Losi
- Giovanni Faglioni
- Luca Roncucci
View Affiliations

Affiliations: Department of Biomedical, Metabolic and Neurosciences, University of Modena and Reggio Emilia, I-41125 Modena, Italy, Department of Mathematics, University of Bologna, I-40126 Bologna, Italy, Department of Chemistry and Geology, University of Modena and Reggio Emiliaa, I-41125 Modena, Italy, Department of Life Sciences, University of Modena and Reggio Emiliaa, I-41125 Modena, Italy, Nabla 2, Srl, I-41124 Modena, Italy, Department of Diagnostic and Clinical Medicine, and Public Health, University of Modena and Reggio Emilia, I-41125 Modena, Italy
Published online on: September 27, 2019 https://doi.org/10.3892/ol.2019.10928
Pages: 6101-6107
Copyright: © Sena et al. This is an open access article distributed under the terms of Creative Commons Attribution License.

Metrics: Total Views: 0 (Spandidos Publications: | PMC Statistics: )

Metrics: Total PDF Downloads: 0 (Spandidos Publications: | PMC Statistics: )

Cited By (CrossRef): 0 citations Loading Articles...

Abstract

Trained pathologists base colorectal cancer identification on the visual interpretation of microscope images. However, image labeling is not always straightforward and this repetitive task is prone to mistakes due to human distraction. Significant efforts are underway to develop informative tools to assist pathologists and decrease the burden and frequency of errors. The present study proposes a deep learning approach to recognize four different stages of cancerous tissue development, including normal mucosa, early preneoplastic lesion, adenoma and cancer. A dataset of human colon tissue images collected and labeled over a 10‑year period by a team of pathologists was partitioned into three sets. These were used to train, validate and test the neural network, comprising several convolutional and a few linear layers. The approach used in the present study is ‘direct’; it labels raw images and bypasses the segmentation step. An overall accuracy of >95% was achieved, with the majority of mislabeling referring to a near category. Tests on an external dataset with a different resolution yielded accuracies >80%. The present study demonstrated that the neural network, when properly trained, can provide fast, accurate and reproducible labeling for colon cancer images, with the potential to significantly improve the quality and speed of medical diagnoses.

View Figures

View References

1	Torre LA, Bray F, Siegel RL, Ferlay J, Lortet-Tieulent J and Jemal A: Global cancer statistics, 2012. CA Cancer J Clin. 65:87–108. 2015. View Article : Google Scholar : PubMed/NCBI
2	Das V, Kalita J and Pal M: Predictive and prognostic biomarkers in colorectal cancer: A systematic review of recent advances and challenges. Biomed Pharmacother. 87:8–19. 2017. View Article : Google Scholar : PubMed/NCBI
3	Favoriti P, Carbone G, Greco M, Pirozzi F, Pirozzi RE and Corcione F: Worldwide burden of colorectal cancer: A review. Updates Surg. 68:7–11. 2016. View Article : Google Scholar : PubMed/NCBI
4	Center MM, Jemal A, Smith RA and Ward E: Worldwide variations in colorectal cancer. CA Cancer J Clin. 59:366–378. 2009. View Article : Google Scholar : PubMed/NCBI
5	Ferlay J, Steliarova-Foucher E, Lortet-Tieulent J, Rosso S, Coebergh JW, Comber H, Forman D and Bray F: Cancer incidence and mortality patterns in Europe: Estimates for 40 countries in 2012. Eur J Cancer. 49:1374–1403. 2013. View Article : Google Scholar : PubMed/NCBI
6	Ahnen DJ, Wade SW, Jones WF, Sifri R, Mendoza Silveiras J, Greenamyer J, Guiffre S, Axilbund J, Spiegel A and You YN: The increasing incidence of young-onset colorectal cancer: A call to action. Mayo Clin Proc. 89:216–224. 2014. View Article : Google Scholar : PubMed/NCBI
7	I Numeri Del Cancro in Italia 2016. Il Pensiero Scientifico Editore, . 2016.
8	Altobelli E, Lattanzi A, Paduano R, Varassi G and di Orio F: Colorectal cancer prevention in Europe: Burden of disease and status of screening programs. Prev Med. 62:132–141. 2014. View Article : Google Scholar : PubMed/NCBI
9	Vogelstein B, Fearon ER, Hamilton SR, Kern SE, Preisinger AC, Leppert M, Nakamura Y, White R, Smits AM and Bos JL: Genetic alterations during colorectal-tumor development. N Engl J Med. 319:525–532. 1988. View Article : Google Scholar : PubMed/NCBI
10	Di Gregorio C, Losi L, Fante R, Modica S, Ghidoni M, Pedroni M, Tamassia MG, Gafà L, Ponz de Leon M and Roncucci L: Histology of aberrant crypt foci in the human colon. Histopathology. 30:328–334. 1997. View Article : Google Scholar : PubMed/NCBI
11	Bird RP: Observation and quantification of aberrant crypts in the murine colon treated with a colon carcinogen: Preliminary findings. Cancer Lett. 37:147–151. 1987. View Article : Google Scholar : PubMed/NCBI
12	Losi L, Roncucci L, di Gregorio C, de Leon MP and Benhattar J: K-ras and p53 mutations in human colorectal aberrant crypt foci. J Pathol. 178:259–263. 1996. View Article : Google Scholar : PubMed/NCBI
13	Lopez-Ceron M and Pellise M: Biology and diagnosis of aberrant crypt foci. Colorectal Dis. 14:e157–e164. 2012. View Article : Google Scholar : PubMed/NCBI
14	Roncucci L, Pedroni M, Vaccina F, Benatti P, Marzona L and De Pol A: Aberrant crypt foci in colorectal carcinogenesis. Cell and crypt dynamics. Cell Prolif. 33:1–18. 2000. View Article : Google Scholar : PubMed/NCBI
15	Roncucci L, Stamp D and Medline AA: Identification and quantification of aberrant crypt foci and microadenomas in the human colon. Hum Pathol. 22:287–294. 1991. View Article : Google Scholar : PubMed/NCBI
16	Kowalczyk M, Siermontowski P, Mucha D, Ambroży T, Orłowski M, Zinkiewicz K, Kurpiewski W, Paśnik K, Kowalczyk I and Pedrycz A: Chromoendoscopy with a standard-resolution colonoscope for evaluation of rectal aberrant crypt foci. PLoS One. 11:e01482862016. View Article : Google Scholar : PubMed/NCBI
17	Nascimbeni R, Villanacci V, Mariani PP, Di Betta E, Ghirardi M, Donato F and Salerni B: Aberrant crypt foci in the human colon: Frequency and histologic patterns in patients with colorectal cancer or diverticular disease. Am J Surg Pathol. 23:1256–1263. 1999. View Article : Google Scholar : PubMed/NCBI
18	Gupta AK, Pinsky P, Rall C, Mutch M, Dry S, Seligson D and Schoen RE: Reliability and accuracy of the endoscopic appearance in the identification of aberrant crypt foci. Gastrointest Endosc. 70:322–330. 2009. View Article : Google Scholar : PubMed/NCBI
19	Andrion A, Magnani C, Betta PG, Donna A, Mollo F, Scelsi M, Bernardi P, Botta M and Terracini B: Malignant mesothelioma of the pleura: Interobserver variability. J Clin Pathol. 48:856–860. 1995. View Article : Google Scholar : PubMed/NCBI
20	Van Putten PG, Hol L, Van Dekken H, Han van Krieken J, van Ballegooijen M, Kuipers EJ and van Leerdam ME: Inter-observer variation in the histological diagnosis of polyps in colorectal cancer screening. Histopathology. 58:974–981. 2011. View Article : Google Scholar : PubMed/NCBI
21	Hadsell R, Sermanet P, Ben J, Erkan A, Scoffier M, Kavukcuoglu K, Muller U and Lecun Y: Learning long-range vision for autonomous off-road driving. J Field Robot. 26:120–144. 2009. View Article : Google Scholar
22	Sirinukunwattana K, Ahmed Raza SE, Yee-Wah Tsang, Snead DR, Cree IA and Rajpoot NM: Locality sensitive deep learning for detection and classification of nuclei in routine colon cancer histology images. IEEE Trans Med Imaging. 35:1196–1206. 2016. View Article : Google Scholar : PubMed/NCBI
23	Janowczyk A and Madabhushi A: Deep learning for digital pathology image analysis: A comprehensive tutorial with selected use cases. J Pathol Inform. 7:292016. View Article : Google Scholar : PubMed/NCBI
24	Cruz-Roa AA, Ovalle JE, Madabhushi A and Osorio FAG: International conference on medical image computing and computer-assisted intervention. A deep learning architecture for image representation, visual interpretability and automated basal-cell carcinoma cancer detectionSpringer; pp. 403–410. 2013, PubMed/NCBI
25	Ertosun MG and Rubin DL: Automated grading of gliomas using deep learning in digital pathology images: A modular approach with ensemble of convolutional neural networks. AMIA Annu Symp Proc. 2015:1899–1908. 2015.PubMed/NCBI
26	Malon CD and Cosatto E: Classification of mitotic figures with convolutional neural networks and seeded blob features. J Pathol Inform. 4:92013. View Article : Google Scholar : PubMed/NCBI
27	Wang H, Cruz-Roa A, Basavanhally A, Gilmore H, Shih N, Feldman M, Tomaszewski J, Gonzalez F and Madabhushi A: Cascaded ensemble of convolutional neural networks and handcrafted features for mitosis detection. SPIE Med Imaging. 941:90410B2014.
28	Sirinukunwattana K, Pluim JPW, Chen H, Qi X, Heng PA, Guo YB, Wang LY, Matuszewski BJ, Bruni E, Sanchez U, et al: Gland segmentation in colon histology images: The glas challenge contest. Med Image Anal. 35:489–502. 2017. View Article : Google Scholar : PubMed/NCBI
29	Kainz P, Pfeiffer M and Urschler M: Segmentation and classification of colon glands with deep convolutional neural networks and total variation regularization. PeerJ. 5:e38742017. View Article : Google Scholar : PubMed/NCBI
30	Sirinukunwattana K, Snead DR and Rajpoot NM: A stochastic polygons model for glandular structures in colon histology images. IEEE Trans Med Imaging. 34:2366–2378. 2015. View Article : Google Scholar : PubMed/NCBI
31	Losi L, Baisse B, Bouzourene H and Benhattar J: Evolution of intratumoral genetic heterogeneity during colorectal cancer progression. Carcinogenesis. 26:916–922. 2005. View Article : Google Scholar : PubMed/NCBI