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.

Deep learning techniques for detecting preneoplastic and neoplastic lesions in human colorectal histological images / Sena, P.; Fioresi, R.; Faglioni, F.; Losi, L.; Faglioni, G.; Roncucci, L.. - In: ONCOLOGY LETTERS. - ISSN 1792-1074. - 18:6(2019), pp. 6101-6107. [10.3892/ol.2019.10928]

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

Sena P.;Faglioni F.;Losi L.;Faglioni G.;Roncucci L.
2019

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.
2019
27-set-2019
18
6
6101
6107
Deep learning techniques for detecting preneoplastic and neoplastic lesions in human colorectal histological images / Sena, P.; Fioresi, R.; Faglioni, F.; Losi, L.; Faglioni, G.; Roncucci, L.. - In: ONCOLOGY LETTERS. - ISSN 1792-1074. - 18:6(2019), pp. 6101-6107. [10.3892/ol.2019.10928]
Sena, P.; Fioresi, R.; Faglioni, F.; Losi, L.; Faglioni, G.; Roncucci, L.
File in questo prodotto:
File Dimensione Formato  
Oncology_Letters_18.6101.2019.pdf

Accesso riservato

Descrizione: articolo
Tipologia: Versione pubblicata dall'editore
Dimensione 513.69 kB
Formato Adobe PDF
513.69 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1194563
Citazioni
  • ???jsp.display-item.citation.pmc??? 19
  • Scopus 35
  • ???jsp.display-item.citation.isi??? 32
social impact