arXiv subjects

A. Retico

Publications and source records attributed to A. Retico.

At least 19 recordsLinked to original sources

arXiv2022

Analysis methods for in-beam PET images in proton therapy treatment verification: a comparison based on Monte Carlo simulations

Background and purpose: In-beam Positron Emission Tomography (PET) is one of the modalities that can be used for in-vivo non-invasive treatment monitoring in proton therapy. PET distributions obtained during various treatment sessions can be compared in order to identify regions that have anatomical changes. The purpose of this work is to test and compare different analysis methods in the context of inter-fractional PET image comparison for proton treatment verification. Methods: For our study we used the FLUKA Monte Carlo code and artificially generated CT scans to simulate in-beam PET distributions at different stages during proton therapy treatment. We compared the Beam-Eye-View method, the Most-Likely-Shift method, the Voxel-Based-Morphology method and the gamma evaluation method to compare PET images at the start of treatment, and after a few weeks of treatment. The results were compared to the CT scan. Results and conclusions: Three-dimensional methods like VBM and gamma are preferred above two-dimensional methods like MLS and BEV if much statistics is available, since the these methods allow to identify the regions with anomalous activity. The VBM approach has as disadvantage that a larger number of MC simulations is needed. The gamma analysis has the disadvantage that no clinical indication exist on tolerance criteria. In terms of calculation time, the BEV and MLS method are preferred. We recommend to use the four methods together, in order to best identify the location and cause of the activity changes.

physics.med-ph↗

arXiv2014

First tests for an online treatment monitoring system with in-beam PET for proton therapy

PET imaging is a non-invasive technique for particle range verification in proton therapy. It is based on measuring the beta+ annihilations caused by nuclear interactions of the protons in the patient. In this work we present measurements for proton range verification in phantoms, performed at the CNAO particle therapy treatment center in Pavia, Italy, with our 10 x 10 cm^2 planar PET prototype DoPET. PMMA phantoms were irradiated with mono-energetic proton beams and clinical treatment plans, and PET data were acquired during and shortly after proton irradiation. We created 1-D profiles of the beta+ activity along the proton beam-axis, and evaluated the difference between the proximal rise and the distal fall-off position of the activity distribution. A good agreement with FLUKA Monte Carlo predictions was obtained. We also assessed the system response when the PMMA phantom contained an air cavity. The system was able to detect these cavities quickly after irradiation.

physics.med-ph↗

arXiv2009

Multi-scale analysis of lung computed tomography images

A computer-aided detection (CAD) system for the identification of lung internal nodules in low-dose multi-detector helical Computed Tomography (CT) images was developed in the framework of the MAGIC-5 project. The three modules of our lung CAD system, a segmentation algorithm for lung internal region identification, a multi-scale dot-enhancement filter for nodule candidate selection and a multi-scale neural technique for false positive finding reduction, are described. The results obtained on a dataset of low-dose and thin-slice CT scans are shown in terms of free response receiver operating characteristic (FROC) curves and discussed.

physics.med-ph↗

arXiv2008

Characterization of mammographic masses using a gradient-based segmentation algorithm and a neural classifier

The computer-aided diagnosis system we developed for the mass characterization is mainly based on a segmentation algorithm and on the neural classification of several features computed on the segmented mass. Mass segmentation plays a key role in most computerized systems. Our technique is a gradient-based one, showing the main characteristic that no free parameters have been evaluated on the dataset used in this analysis, thus it can directly be applied to datasets acquired in different conditions without any ad-hoc modification. A dataset of 226 masses (109 malignant and 117 benign) has been used in this study. The segmentation algorithm works with a comparable efficiency both on malignant and benign masses. Sixteen features based on shape, size and intensity of the segmented masses are analyzed by a multi-layered perceptron neural network. A feature selection procedure has been carried out on the basis of the feature discriminating power and of the linear correlations interplaying among them. The comparison of the areas under the ROC curves obtained by varying the number of features to be classified has shown that 12 selected features out of the 16 computed ones are powerful enough to achieve the best classifier performances. The radiologist assigned the segmented masses to three different categories: correctly-, acceptably- and non-acceptably-segmented masses. We initially estimated the area under ROC curve only on the first category of segmented masses (the 88.5% of the dataset), then extending the dataset to the second sub-class (reaching the 97.8% of the dataset) and finally to the whole dataset, obtaining Az = 0.805+-0.030, 0.787+-0.024 and 0.780+-0.023, respectively.

physics.med-ph↗

arXiv2007

Automated detection of lung nodules in low-dose computed tomography

A computer-aided detection (CAD) system for the identification of pulmonary nodules in low-dose multi-detector computed-tomography (CT) images has been developed in the framework of the MAGIC-5 Italian project. One of the main goals of this project is to build a distributed database of lung CT scans in order to enable automated image analysis through a data and cpu GRID infrastructure. The basic modules of our lung-CAD system, consisting in a 3D dot-enhancement filter for nodule detection and a neural classifier for false-positive finding reduction, are described. The system was designed and tested for both internal and sub-pleural nodules. The database used in this study consists of 17 low-dose CT scans reconstructed with thin slice thickness (~300 slices/scan). The preliminary results are shown in terms of the FROC analysis reporting a good sensitivity (85% range) for both internal and sub-pleural nodules at an acceptable level of false positive findings (1-9 FP/scan); the sensitivity value remains very high (75% range) even at 1-6 FP/scan

physics.med-ph↗

arXiv2007

An automated system for lung nodule detection in low-dose computed tomography

A computer-aided detection (CAD) system for the identification of pulmonary nodules in low-dose multi-detector helical Computed Tomography (CT) images was developed in the framework of the MAGIC-5 Italian project. One of the main goals of this project is to build a distributed database of lung CT scans in order to enable automated image analysis through a data and cpu GRID infrastructure. The basic modules of our lung-CAD system, a dot-enhancement filter for nodule candidate selection and a neural classifier for false-positive finding reduction, are described. The system was designed and tested for both internal and sub-pleural nodules. The results obtained on the collected database of low-dose thin-slice CT scans are shown in terms of free response receiver operating characteristic (FROC) curves and discussed.

physics.med-ph↗

arXiv2007

A multi-scale approach to the computer-aided detection of microcalcification clusters in digital mammograms

A computer-aided detection (CADe) system for the identification of microcalcification clusters in digital mammograms has been developed. It is mainly based on the application of wavelet transforms for image filtering and neural networks for both the feature extraction and the classification procedures. This CADe system is easily adaptable to different databases. We report and compare the FROC curves obtained on the private database we used for developing the CADe system and on the publicly available MIAS database. The results achieved on the two databases show the same trend, thus demonstrating the good generalization capability of the system.

physics.med-ph↗

arXiv2007

An automatic system to discriminate malignant from benign massive lesions in mammograms

Evaluating the degree of malignancy of a massive lesion on the basis of the mere visual analysis of the mammogram is a non-trivial task. We developed a semi-automated system for massive-lesion characterization with the aim to support the radiological diagnosis. A dataset of 226 masses has been used in the present analysis. The system performances have been evaluated in terms of the area under the ROC curve, obtaining A_z=0.80+-0.04.

physics.med-ph↗

arXiv2007

Lung nodule detection in low-dose and high-resolution CT scans

We are developing a computer-aided detection (CAD) system for the identification of small pulmonary nodules in screening CT scans. The main modules of our system, i.e. a dot-enhancement filter for nodule candidate selection and a neural classifier for false positive finding reduction, are described. The preliminary results obtained on the so-far collected database of lung CT are discussed.

physics.med-ph↗

arXiv2007

Lung Nodule Detection in Screening Computed Tomography

A computer-aided detection (CAD) system for the identification of pulmonary nodules in low-dose multi-detector helical Computed Tomography (CT) images with 1.25 mm slice thickness is presented. The basic modules of our lung-CAD system, a dot-enhancement filter for nodule candidate selection and a neural classifier for false-positive finding reduction, are described. The results obtained on the collected database of lung CT scans are discussed.

physics.med-ph↗

arXiv2007

Computer-aided detection of pulmonary nodules in low-dose CT

A computer-aided detection (CAD) system for the identification of pulmonary nodules in low-dose multi-detector helical CT images with 1.25 mm slice thickness is being developed in the framework of the INFN-supported MAGIC-5 Italian project. The basic modules of our lung-CAD system, a dot enhancement filter for nodule candidate selection and a voxel-based neural classifier for false-positive finding reduction, are described. Preliminary results obtained on the so-far collected database of lung CT scans are discussed.

physics.med-ph↗

arXiv2007

A scalable system for microcalcification cluster automated detection in a distributed mammographic database

physics.med-ph↗

arXiv2007

An Automatic System to Discriminate Malignant from Benign Massive Lesions on Mammograms

Mammography is widely recognized as the most reliable technique for early detection of breast cancers. Automated or semi-automated computerized classification schemes can be very useful in assisting radiologists with a second opinion about the visual diagnosis of breast lesions, thus leading to a reduction in the number of unnecessary biopsies. We present a computer-aided diagnosis (CADi) system for the characterization of massive lesions in mammograms, whose aim is to distinguish malignant from benign masses. The CADi system we realized is based on a three-stage algorithm: a) a segmentation technique extracts the contours of the massive lesion from the image; b) sixteen features based on size and shape of the lesion are computed; c) a neural classifier merges the features into an estimated likelihood of malignancy. A dataset of 226 massive lesions (109 malignant and 117 benign) has been used in this study. The system performances have been evaluated terms of the receiver-operating characteristic (ROC) analysis, obtaining A_z = 0.80+-0.04 as the estimated area under the ROC curve.

physics.med-ph↗

arXiv2007

A scalable Computer-Aided Detection system for microcalcification cluster identification in a pan-European distributed database of mammograms

A computer-aided detection (CADe) system for microcalcification cluster identification in mammograms has been developed in the framework of the EU-founded MammoGrid project. The CADe software is mainly based on wavelet transforms and artificial neural networks. It is able to identify microcalcifications in different kinds of mammograms (i.e. acquired with different machines and settings, digitized with different pitch and bit depth or direct digital ones). The CADe can be remotely run from GRID-connected acquisition and annotation stations, supporting clinicians from geographically distant locations in the interpretation of mammographic data. We report the FROC analyses of the CADe system performances on three different dataset of mammograms, i.e. images of the CALMA INFN-founded database collected in the Italian National screening program, the MIAS database and the so-far collected MammoGrid images. The sensitivity values of 88% at a rate of 2.15 false positive findings per image (FP/im), 88% with 2.18 FP/im and 87% with 5.7 FP/im have been obtained on the CALMA, MIAS and MammoGrid database respectively.

physics.med-ph↗

arXiv2005

Pre-processing methods for nodule detection in lung CT

The use of automatic systems in the analysis of medical images has proven to be very useful to radiologists, especially in the framework of screening programs, in which radiologists make their first diagnosis on the basis of images only, most of those corresponding to healthy patients, and have to distinguish pathological findings from non-pathological ones at an early stage. In particular, we are developing preprocessing methods to be applied for pulmonary nodule Computer Aided Detection in low-dose lung Multi Slice CT (Computed Tomography) images.

physics.med-ph↗

arXiv2004

CADe tools for early detection of breast cancer

A breast neoplasia is often marked by the presence of microcalcifications and massive lesions in the mammogram: hence the need for tools able to recognize such lesions at an early stage. Our collaboration, among italian physicists and radiologists, has built a large distributed database of digitized mammographic images and has developed a Computer Aided Detection (CADe) system for the automatic analysis of mammographic images and installed it in some Italian hospitals by a GRID connection. Regarding microcalcifications, in our CADe digital mammogram is divided into wide windows which are processed by a convolution filter; after a self-organizing map analyzes each window and produces 8 principal components which are used as input of a neural network (FFNN) able to classify the windows matched to a threshold. Regarding massive lesions we select all important maximum intensity position and define the ROI radius. From each ROI found we extract the parameters which are used as input in a FFNN to distinguish between pathological and non-pathological ROI. We present here a test of our CADe system, used as a second reader and a comparison with another (commercial) CADe system.

physics.med-ph↗

arXiv2004

GPCALMA: a Grid-based tool for Mammographic Screening

The next generation of High Energy Physics (HEP) experiments requires a GRID approach to a distributed computing system and the associated data management: the key concept is the Virtual Organisation (VO), a group of distributed users with a common goal and the will to share their resources. A similar approach is being applied to a group of Hospitals which joined the GPCALMA project (Grid Platform for Computer Assisted Library for MAmmography), which will allow common screening programs for early diagnosis of breast and, in the future, lung cancer. HEP techniques come into play in writing the application code, which makes use of neural networks for the image analysis and proved to be useful in improving the radiologists' performances in the diagnosis. GRID technologies allow remote image analysis and interactive online diagnosis, with a potential for a relevant reduction of the delays presently associated to screening programs. A prototype of the system, based on AliEn GRID Services, is already available, with a central Server running common services and several clients connecting to it. Mammograms can be acquired in any location; the related information required to select and access them at any time is stored in a common service called Data Catalogue, which can be queried by any client. The result of a query can be used as input for analysis algorithms, which are executed on nodes that are in general remote to the user (but always local to the input images) thanks to the PROOF facility. The selected approach avoids data transfers for all the images with a negative diagnosis (about 95% of the sample) and allows an almost real time diagnosis for the 5% of images with high cancer probability.

physics.med-ph↗

arXiv2004

GPCALMA: A Tool For Mammography With A GRID-Connected Distributed Database

The GPCALMA (Grid Platform for Computer Assisted Library for MAmmography) collaboration involves several departments of physics, INFN sections, and italian hospitals. The aim of this collaboration is developing a tool that can help radiologists in early detection of breast cancer. GPCALMA has built a large distributed database of digitised mammographic images (about 5500 images corresponding to 1650 patients) and developed a CAD (Computer Aided Detection) software which is integrated in a station that can also be used for acquire new images, as archive and to perform statistical analysis. The images are completely described: pathological ones have a consistent characterization with radiologist's diagnosis and histological data, non pathological ones correspond to patients with a follow up at least three years. The distributed database is realized throught the connection of all the hospitals and research centers in GRID tecnology. In each hospital local patients digital images are stored in the local database. Using GRID connection, GPCALMA will allow each node to work on distributed database data as well as local database data. Using its database the GPCALMA tools perform several analysis. A texture analysis, i.e. an automated classification on adipose, dense or glandular texture, can be provided by the system. GPCALMA software also allows classification of pathological features, in particular massive lesions analysis and microcalcification clusters analysis. The performance of the GPCALMA system will be presented in terms of the ROC (Receiver Operating Characteristic) curves. The results of GPCALMA system as "second reader" will also be presented.

physics.med-ph↗