The aim of the study is to present a new Convolutional Neural Network (CNN) based system for the automatic segmentation of the colorectal cancer. The algorithm implemented consists of several steps: a pre-processing to normalize and highlights the tumoral area, the classification based on CNNs, and a post-processing aimed at reducing false positive elements. The classification is performed using three CNNs: each of them classifies the same regions of interest acquired from three different MR sequences. The final segmentation mask is obtained by a majority voting. Performances were evaluated using a semi-automatic segmentation revised by an experienced radiologist as reference standard. The system obtained Dice Similarity Coefficient (DSC) of 0.60, Precision (Pr) of 0.76 and Recall (Re) of 0.55 on the testing set. After applying the leave-one-out validation, we obtained a median DSC=0.58, Pr=0.74, Re=0.54. The promising results obtained by this system, if validated on a larger dataset, could strongly improve personalized medicine.

A Convolutional Neural Network based system for Colorectal cancer segmentation on MRI images / Panic, Jovana; Defeudis, Arianna; Mazzetti, Simone; Rosati, Samanta; Giannetto, Giuliana; Vassallo, Lorenzo; Regge, Daniele; Balestra, Gabriella; Giannini, Valentina. - ELETTRONICO. - (2020), pp. 1675-1678. (Intervento presentato al convegno 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) tenutosi a Montreal, QC, Canada nel 20-24 July 2020) [10.1109/EMBC44109.2020.9175804].

A Convolutional Neural Network based system for Colorectal cancer segmentation on MRI images

Panic, Jovana;Rosati, Samanta;Balestra, Gabriella;Giannini, Valentina
2020

Abstract

The aim of the study is to present a new Convolutional Neural Network (CNN) based system for the automatic segmentation of the colorectal cancer. The algorithm implemented consists of several steps: a pre-processing to normalize and highlights the tumoral area, the classification based on CNNs, and a post-processing aimed at reducing false positive elements. The classification is performed using three CNNs: each of them classifies the same regions of interest acquired from three different MR sequences. The final segmentation mask is obtained by a majority voting. Performances were evaluated using a semi-automatic segmentation revised by an experienced radiologist as reference standard. The system obtained Dice Similarity Coefficient (DSC) of 0.60, Precision (Pr) of 0.76 and Recall (Re) of 0.55 on the testing set. After applying the leave-one-out validation, we obtained a median DSC=0.58, Pr=0.74, Re=0.54. The promising results obtained by this system, if validated on a larger dataset, could strongly improve personalized medicine.
File in questo prodotto:
File Dimensione Formato  
Panic_EMBC2020.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 494.73 kB
Formato Adobe PDF
494.73 kB Adobe PDF Visualizza/Apri
09175804.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 517.48 kB
Formato Adobe PDF
517.48 kB 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/11583/2844432