M5L, a Web-based fully automated Computer-Aided Detection (CAD) system for the automated detection of lung nodules in thoracic Computed Tomography (CT), is based on a multi-thread analysis with two independent CAD subsystems, the lung Channeler Ant Model (lungCAM) and the Voxel-Based Neural Analysis (VBNA), and on the combination of their results. The M5L performance, extensively validated on 1043 CT scans from 3 independent data-sets, including the full LIDC/IDRI database, is homogeneous across the databases: the sensitivity is about 0.8 at 6-8 False Positive findings per scan, despite the different annotation criteria and acquisition and reconstruction conditions. In order to make CAD algorithms and their results available to users without requiring the installation of CAD software or new hardware for CAD computations, the project has proposed a Cloud SaaS (Software as a Service) approach composed by three main building blocks: a front-end web which handles the workflow, image upload, CAD results notification and direct on-line annotation of the exam by the radiologist; the OpenNebula-based cloud Iaas (Infrastructure as a Service) batch farm allocates virtual computing and storage resources; the M5L CAD provides the nodule detection functionality.

M5L: A web-based Computer Aided Detection system for automated search of lung nodules in thoracic Computed Tomography scans / Traverso, Alberto; Agnello, Michelangelo; Cerello, P; Saletta, M; Bagnasco, S; Peroni, C; Fiorina, E; Fantacci, M; Retico, A; Torres, E.. - STAMPA. - (2015), pp. 193-199. ((Intervento presentato al convegno Computational Vision and Medical Image Processing V tenutosi a Tenerife, Spagna nel 19-21 ottobre 2015 [10.1201/b19241-33].

M5L: A web-based Computer Aided Detection system for automated search of lung nodules in thoracic Computed Tomography scans

TRAVERSO, ALBERTO;AGNELLO, MICHELANGELO;
2015

Abstract

M5L, a Web-based fully automated Computer-Aided Detection (CAD) system for the automated detection of lung nodules in thoracic Computed Tomography (CT), is based on a multi-thread analysis with two independent CAD subsystems, the lung Channeler Ant Model (lungCAM) and the Voxel-Based Neural Analysis (VBNA), and on the combination of their results. The M5L performance, extensively validated on 1043 CT scans from 3 independent data-sets, including the full LIDC/IDRI database, is homogeneous across the databases: the sensitivity is about 0.8 at 6-8 False Positive findings per scan, despite the different annotation criteria and acquisition and reconstruction conditions. In order to make CAD algorithms and their results available to users without requiring the installation of CAD software or new hardware for CAD computations, the project has proposed a Cloud SaaS (Software as a Service) approach composed by three main building blocks: a front-end web which handles the workflow, image upload, CAD results notification and direct on-line annotation of the exam by the radiologist; the OpenNebula-based cloud Iaas (Infrastructure as a Service) batch farm allocates virtual computing and storage resources; the M5L CAD provides the nodule detection functionality.
9781138029262
File in questo prodotto:
File Dimensione Formato  
M5L a web-based computer aided detection full_paper_VIPIMAGE.pdf

non disponibili

Descrizione: M5L: A web-based Computer Aided Detection system for automated search of lung nodules in thoracic Computed Tomography scans
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 212.21 kB
Formato Adobe PDF
212.21 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Caricamento 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/11583/2644374
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo