Parnian Kasae

Automated Identification of Optic Disc in Retinal Images Using Local Entropy

Investigative Ophthalmology & Visual Science, Apr 17, 2010

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

Computers in Biology and Medicine, Oct 1, 2007

Computerized methods have recently shown a great potential in providing radiologists with a secon... more Computerized methods have recently shown a great potential in providing radiologists with a second opinion about the visual diagnosis of the malignancy of mammographic masses. The computer-aided diagnosis (CAD) 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 extracted and analyzed by a multi-layered perceptron neural network trained with the error back-propagation algorithm. The capability of the system in discriminating malignant from benign masses has been evaluated in terms of the receiver-operating characteristic (ROC) analysis. 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 classification to the second subclass (reaching the 97.8% of the dataset) and finally to the whole dataset, obtaining A z = 0.805 ± 0.030, 0.787 ± 0.024 and 0.780 ± 0.023, respectively.

Download

Pore3D: A software library for quantitative analysis of porous media

Nuclear Instruments and Methods in Physics Research, Apr 1, 2010

In recent years great interest has been posed in imaging techniques like X-ray computed microtomo... more In recent years great interest has been posed in imaging techniques like X-ray computed microtomography which in a nondestructive way produce three-dimensional (3D) images of the internal structure of, e.g. porous media. A major challenge lies in the quantitative analysis of the resulting images that allows a more comprehensive and objective characterization of the sample under investigation. A software able to handle and process large 3D image datasets with common hardware is therefore necessary in order to extract morphological and textural information directly from the images. In the present paper the Pore3D software library developed by the SYRMEP research group of the Elettra Synchrotron Light Laboratory in Trieste (Italy) is presented. The library consists of several state-of-the-art functions and procedures for performing filtering, segmentation and quantitative analysis of 3D images. The current status of the project and some applications are here reported.

Download

Automated Identification of Optic Disc in Retinal Images Using Local Entropy

Investigative Ophthalmology & Visual Science, 2010

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

Download

Lung Nodule Detection in Screening Computed Tomography

2006 IEEE Nuclear Science Symposium Conference Record, 2006

Download

A novel multithreshold method for nodule detection in lung CT

Medical Physics, 2009

Download

Pleural nodule identification in low-dose and thin-slice lung computed tomography

Computers in Biology and Medicine, 2009

Download

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

Computers in Biology and Medicine, 2007

Download

Pore3D: A software library for quantitative analysis of porous media

Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2010

In recent years great interest has been posed in imaging techniques like X-ray computed microtomo... more In recent years great interest has been posed in imaging techniques like X-ray computed microtomography which in a nondestructive way produce three-dimensional (3D) images of the internal structure of, e.g. porous media. A major challenge lies in the quantitative analysis of the resulting images that allows a more comprehensive and objective characterization of the sample under investigation. A software able to handle and process large 3D image datasets with common hardware is therefore necessary in order to extract morphological and textural information directly from the images. In the present paper the Pore3D software library developed by the SYRMEP research group of the Elettra Synchrotron Light Laboratory in Trieste (Italy) is presented. The library consists of several state-of-the-art functions and procedures for performing filtering, segmentation and quantitative analysis of 3D images. The current status of the project and some applications are here reported.

Download

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

Computers in Biology and Medicine, 2007

Computerized methods have recently shown a great potential in providing radiologists with a secon... more Computerized methods have recently shown a great potential in providing radiologists with a second opinion about the visual diagnosis of the malignancy of mammographic masses. The computer-aided diagnosis (CAD) 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 extracted and analyzed by a multi-layered perceptron neural network trained with the error back-propagation algorithm. The capability of the system in discriminating malignant from benign masses has been evaluated in terms of the receiver-operating characteristic (ROC) analysis. 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 classification to the second subclass (reaching the 97.8% of the dataset) and finally to the whole dataset, obtaining A z = 0.805 ± 0.030, 0.787 ± 0.024 and 0.780 ± 0.023, respectively.

Download

Lung Nodule Detection in Screening Computed Tomography

A computer-aided detection (CAD) system for the identification of pulmonary nodules in low-dose m... more 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.

Download

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

by Maria Fantacci and Parnian Kasae

Evaluating the degree of malignancy of a massive lesion on the basis of the mere visual analysis ... more 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 Az = 0.80 ± 0.04.

Download

Uploads

Papers by Parnian Kasae

Log In