The early diagnosis of colorectal cancer (CRC) traditionally leverages upon the microscopic examination of histological slides by experienced pathologists, which is very time-consuming and rises many issues about the reliability of the results. In this paper we propose using Convolutional Neural Networks (CNNs), a class of deep networks that are successfully used in many contexts of pattern recognition, to automatically distinguish the cancerous tissues from either healthy or benign lesions. For this purpose, we designed and compared different CNN-based classification frameworks, involving either training CNNs from scratch on three classes of colorectal images, or transfer learning from a different classification problem. While a CNN trained from scratch obtained very good (about 90%) classification accuracy in our tests, the same CNN model pre-trained on the ImageNet dataset obtained even better accuracy (around 96%) on the same testing samples, requiring much lesser computational resources.

Going Deeper into Colorectal Cancer Histopathology / Ponzio, Francesco; Macii, Enrico; Ficarra, Elisa; DI CATALDO, Santa. - ELETTRONICO. - 1024:(2019), pp. 114-131. (Intervento presentato al convegno BIOIMAGING 2018) [10.1007/978-3-030-29196-9_7].

Going Deeper into Colorectal Cancer Histopathology

Ponzio Francesco;Macii Enrico;Ficarra Elisa;Di Cataldo Santa
2019

Abstract

The early diagnosis of colorectal cancer (CRC) traditionally leverages upon the microscopic examination of histological slides by experienced pathologists, which is very time-consuming and rises many issues about the reliability of the results. In this paper we propose using Convolutional Neural Networks (CNNs), a class of deep networks that are successfully used in many contexts of pattern recognition, to automatically distinguish the cancerous tissues from either healthy or benign lesions. For this purpose, we designed and compared different CNN-based classification frameworks, involving either training CNNs from scratch on three classes of colorectal images, or transfer learning from a different classification problem. While a CNN trained from scratch obtained very good (about 90%) classification accuracy in our tests, the same CNN model pre-trained on the ImageNet dataset obtained even better accuracy (around 96%) on the same testing samples, requiring much lesser computational resources.
2019
9783030291952
File in questo prodotto:
File Dimensione Formato  
Biostec2018_SPRINGER (1)-compresso.pdf

Open Access dal 14/08/2020

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 495.22 kB
Formato Adobe PDF
495.22 kB Adobe PDF Visualizza/Apri
10.1007_978-3-030-29196-9_selected.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 6.35 MB
Formato Adobe PDF
6.35 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2752172