An innovative strategy for the identification and 3D reconstruction of pancreatic cancer from CT images

S. Marconi, L. Pugliese, M. Del Chiaro, R. Pozzi Mucelli, F. Auricchio, A. Pietrabissa

Research output: Contribution to journalArticlepeer-review

Abstract

We propose an innovative tool for Pancreatic Ductal AdenoCarcinoma 3D reconstruction from Multi-Detector-Computed Tomography. The tumor mass is discriminated from health tissue, and the resulting segmentation labels are rendered preserving information on different hypodensity levels. The final 3D virtual model includes also pancreas and main peri-pancreatic vessels, and it is suitable for 3D printing. We performed a preliminary evaluation of the tool effectiveness presenting ten cases of Pancreatic Ductal AdenoCarcinoma processed with the tool to an expert radiologist who can correct the result of the discrimination. In seven of ten cases, the 3D reconstruction is accepted without any modification, while in three cases, only 1.88, 5.13, and 5.70 %, respectively, of the segmentation labels are modified, preliminary proving the high effectiveness of the tool.

Original languageEnglish
Pages (from-to)273-278
Number of pages6
JournalUpdates in Surgery
Volume68
Issue number3
DOIs
Publication statusPublished - Sep 1 2016

ASJC Scopus subject areas

  • Surgery

Fingerprint Dive into the research topics of 'An innovative strategy for the identification and 3D reconstruction of pancreatic cancer from CT images'. Together they form a unique fingerprint.

Cite this