Biomedical images processing and analysis Biomedical images processing

Biomedical images processing and analysis

Biomedical images processing and analysis BIOENGINEERING Group members Alfredo Ruggeri Enrico Grisan Alfredo Giani (2003 -) Massimo De Luca (2004 -) Fabio Scarpa (2006 -) Lorenzo Marafatto (2005 -) Associate professor Marco Foracchia (-2003) Ph. D student Post doc Ph. D student Fellowship

Biomedical images processing and analysis Collaborations BIOENGINEERING J. Jaroszewski - Cornea Bank Berlin, Clinic of Ophthalmology, University School of Medicine, Berlin, Germany A. Neubauer - Dept. of Ophthalmology, Ludwig Maximilians University, Munich, Germany P. Gain - Ophthalmology Department, Bellevue Hospital, Saint-Etienne, France S. Klyce – Eye Center, Louisiana State University, New Orleans (LO), USA S. Piermarocchi – Dept. of Ophthalmology, University of Padova D. Ponzin - Veneto Eye Bank Foundation, Venice, Italy A. Pocobelli - Eye Bank, S. Giovanni-Addolorata Hospital, Rome, Italy A. Bezerianos - Dept. of Medical Physics, University of Patras, Greece G. Barbaro - Nidek Technologies, Padova, Italy P. Favaro - Siemens Corporate Research, Princeton (NJ), USA

Biomedical images processing and analysis BIOENGINEERING Grants Padova: € 60. 000 (shared) University of Padova: € 15. 000 (shared) University of Padova University: € 20. 000 Ministry of University Foundation: € 40. 000 CARIPARO Bank Foundation Technologies: € 25. 000 (+ 4 Ph. D fellowships) Nidek Technologies Imaging: under negotiation TESI Imaging

Biomedical images processing and analysis BIOENGINEERING Publications

Biomedical images processing and analysis BIOENGINEERING 1. Cell contour recognition for in-vivo microscopy of corneal endothelium

Cell contour recognition 1. Contour extraction Artificial Neural Network with weight-filters arrays BIOENGINEERING Mathematical morphology 2. Contour completion Connection of floating facing boundaries

Cell contour recognition BIOENGINEERING • The ENDO software is a module of the system for ophthalmology.

Cell contour recognition BIOENGINEERING Human visual processing is very powerful and complex … Kanisza triangles Kanisza square

Cell contour recognition Human visual processing is very powerful and complex … BIOENGINEERING Cell contours appear nice and clear on a broad view…. … but local gray-scale values do not give all the information necessary to identify all cell contours: false contours missed contours

BIOENGINEERING A glimpse of tomorrow …

Biomedical images processing and analysis 2. Fourier analysis for the estimation of endothelium cell density on eye bank images BIOENGINEERING Fully automatic technique in eye banks without cell contour detection. q A repetitive pattern of cell borders is clearly visible. q Spatial frequency of this pattern is proportional to cell density. q Frequency information is available through Fourier analysis.

Frequency-based density estimation Gray-scale image of 2 D-DFT log-magnitude. BIOENGINEERING A circular band indicates that the endothelium image contains a repetitive pattern at a specific frequency. Spatial frequency is the radius of the band Radius of circular band can be used to estimate cell density. (Foracchia et al. , Med Biol Eng Comput, 2004)

BIOENGINEERING Frequency-based density estimation (Ruggeri et al. , Br J Ophthalmol, 2005)

Nidek Technologies NAVIS-Eye. Bank system BIOENGINEERING • The Eye. Bank software is a module of the system for ophthalmology.

Biomedical images processing and analysis 3. Tracking techniques for vessel-like structure BIOENGINEERING Applications to: • vessels in retina • nerves in cornea Clinical parameters: • length • tortuosity • bifurcations • caliber course • optic disc detection

BIOENGINEERING Tracking techniques in retina (Foracchia et al. , Med Image Anal, 2005)

BIOENGINEERING Tracking techniques in retina (Foracchia et al. , IEEE TMI, 2004)

BIOENGINEERING Tracking techniques in cornea

Biomedical images processing and analysis 4. Methodologies in eye fundus analysis for the diagnosis of retinopathy Hypertensive and diabetic retinopathies are characterized by presence of fundus lesions. BIOENGINEERING Automatic and objective tools for image analysis: • patient screening • disease assessment & monitoring in time • (new) drugs efficacy

BIOENGINEERING Eye fundus analysis Steps: • Detection • Classification • Measurement • Clinical assessment (Grisan et al. , EMBEC’ 05 Conf. , 2005)

Biomedical images processing and analysis 5. Design and realization of an adaptive optics fundus camera BIOENGINEERING Eye Retinal Imaging Flash path Wavefront sensor Image Processing

Adaptive optics fundus camera BIOENGINEERING Simulation system with creation of aberrated image and correction system Acquired image Coma Mirror update Image Analysis Defocus Astigmatism Corrected image (Grisan et al. , IEEE EMBS Conf. , 2005)

Biomedical images processing and analysis BIOENGINEERING 6. Automatic cariotyping

Automatic cariotyping BIOENGINEERING 1. Segmentation of single chromosomes 2. Classification and pairing 1. - image enhancement - cluster segmentation - touching and overlapping elimination by cuts 2. - feature extraction (banding) - classification