Algorithms for contouring and analysis
ITA PACS Algorithms
Semi-automated 3D contouring algorithm for PET images
We co-funded an Italian multicenter study to assess robustness and reliability of an adaptive thresholding algorithm for the biological target volume estimation incorporating reconstruction parameters. The algorithm is described in [Brambilla et al., Med. Phys. 35 (4), 1207-1213, 2008]. Eleven PET/CT scanners were used [Brambilla et al., CMMM ID 571473, 2015].
A 3D version of the proposed 2D algorithm was developed and implemented into iTA PACS.
Multimodal 3D contouring algorithm
We developed an automated algorithm for 3D multi-modality image segmentation; it is based on the simultaneous use of co-registered images [Ermacora et al., UMB 41(10), 2646-2662, 2015]. The version available in iTA PACS was trained on co-registered CT-3DUS images of prostate. The development of the algorithm involved collaboration with several research centers.


Semi-automated 3D contouring algorithm for PET images
We co-funded an Italian multicenter study to assess robustness and reliability of an adaptive thresholding algorithm for the biological target volume estimation incorporating reconstruction parameters. The algorithm is described in [Brambilla et al., Med. Phys. 35 (4), 1207-1213, 2008]. Eleven PET/CT scanners were used [Brambilla et al., CMMM ID 571473, 2015].
A 3D version of the proposed 2D algorithm was developed and implemented into iTA PACS.
Multimodal 3D contouring algorithm
We developed an automated algorithm for 3D multi-modality image segmentation; it is based on the simultaneous use of co-registered images [Ermacora et al., UMB 41(10), 2646-2662, 2015]. The version available in iTA PACS was trained on co-registered CT-3DUS images of prostate. The development of the algorithm involved collaboration with several research centers.
Patent
We have patented a system that automatically selects the best segmentation algorithm or algorithms and parameters to be used in a given context: the algorithm uses the best imaging modality (s) available for a specific case and selects only the information that allows you to obtain the best possible contouring (EP2863360 – Multimodality Image Segmentation of Volumetric Data Sets).
Algorithm for the correction of 3DUS images
We developed and implemented a speed of sound aberration correction algorithm of 3DUS images co-registered with CT images and acquired using curvilinear ultrasound transducers [Fontanarosa, Pesente et al., PMB 58, 1341-1360, 2013; Fontanarosa et al., PMB 38 (5), 2665-2673, 2011].
The development of the algorithms was co-financed by POR FESR 2007-2013 FVG, within the project: “Stazione di segmentazione multimodale avanzata in Radioterapia – Advanced multimodal segmentation station for Radiotherapy” (2010-2012).