Pauli Fält

Extending Diabetic Retinopathy Imaging from Color to Spectra

In this study, spectral images of 66 human retinas were collected. These spectral images were measured in vivo from 54 voluntary diabetic patients and 12 control subjects using a modified ophthalmic fundus camera system. This system incorporates the optics of a standard fundus microscope, 30 narrow bandpass interference filters ranging from 400 to 700 nanometers at 10 nm intervals, a steady-state broadband lightsource and a monochrome digital charge-coupled device camera. The introduced spectral fundus image database will be expanded in the future with professional annotations and will be made public.

Sub-micron resolution high-speed spectral domain optical coherence tomography in quality inspection for printed electronics

We present the use of sub-micron resolution optical coherence tomography (OCT) in quality inspection for printed electronics. The device used in the study is based on a supercontinuum light source, Michelson interferometer and high-speed spectrometer. The spectrometer in the presented spectral-domain optical coherence tomography setup (SD-OCT) is centered at 600 nm and covers a 400 nm wide spectral region ranging from 400 nm to 800 nm. Spectra were acquired at a continuous rate of 140,000 per second. The full width at half maximum of the point spread function obtained from a Parylene C sample was 0:98 m. In addition to Parylene C layers, the applicability of sub-micron SD-OCT in printed electronics was studied using PET and epoxy covered solar cell, a printed RFID antenna and a screen-printed battery electrode. A commercial SD-OCT system was used for reference measurements.

Performance comparison of publicly available retinal blood vessel segmentation methods

Retinal blood vessel structure is an important indicator of many retinal and systemic diseases, which has motivated the development of various image segmentation methods for the blood vessels. In this study, two supervised and three unsupervised segmentation methods with a publicly available implementation are reviewed and quantitatively compared with each other on five public databases with ground truth segmentation of the vessels. Each method is tested under consistent conditions with two types of preprocessing, and the parameters of the methods are optimized for each database. Additionally, possibility to predict the parameters of the methods by the linear regression model is tested for each database. Resolution of the input images and amount of the vessel pixels in the ground truth are used as predictors. The results show the positive influence of preprocessing on the performance of the unsupervised methods. The methods show similar performance for segmentation accuracy, with the best performance achieved by the method by Azzopardi et al. (Acc 94.0) on ARIADB, the method by Soares et al. (Acc 94.6, 94.7) on CHASEDB1 and DRIVE, and the method by Nguyen et al. (Acc 95.8, 95.5) on HRF and STARE. The method by Soares et al. performed better with regard to the area under the ROC curve. Qualitative differences between the methods are discussed. Finally, it was possible to predict the parameter settings that give performance close to the optimized performance of each method.

Objective identification of dental abnormalities with multispectral fluorescence imaging

Sensitive methods that can enable early detection of dental diseases (caries and calculus) are desirable in clinical practice. Optical spectroscopic approaches have emerged as promising alternatives owing to their wealth of molecular information and lack of sample preparation requirements. In the present study, using multispectral fluorescence imaging, we have demonstrated that dental caries and calculus can be objectively identified on extracted tooth. Spectral differences among control, carious and calculus conditions were attributed to the porphyrin pigment content, which is a byproduct of bacterial metabolism. Spectral maps generated using different porphyrin bands offer important clues to the spread of bacterial infection. Statistically significant differences utilizing fluorescence intensity ratios were observed among three groups. In contrast to laser induced fluorescence, these methods can provide information about exact spread of the infection and may aid in long term dental monitoring. Successful adoption of this approach for routine clinical usage can assist dentists in implementing timely remedial measures.

SPEED: SPectral eye vidEo database

A way to improve gaze tracking by spectral imaging is presented. Spectral still and video cameras enabled a collection of a novel database consisting of 180 multispectral eye movement videos and 30 spectral images of the eyes of 30 voluntary human subjects. Unfavorable conditions, such as eyewear reflections, extreme angles and make-up were incorporated. Unlike conventional RGB and gray scale eye tracking a seven-channel spectral video capture over the wavelength range of 380-1000 nm, in addition with spectral still images in the range of 450-950 nm, provided a detailed acquisition of spectral signatures of the eye and its surroundings. These signatures can be exploited to create new methodologies for imaging, training, analysis and interpretation of eye tracking data in harsh conditions.

Led-based spectrally tunable light source for camera characterization

In this study, a LED-based spectrally tunable light source is introduced and used for camera spectral sensitivity characterization. Three different camera types containing 1-, 3-, and 7- spectral channels were selected and tested under designed characterization instrument. The light source is based on narrowband light emitting diodes arranged in a circles. The system includes 46 spectral channels from 380nm to 950nm, where due to designed control board each channel is controllable with 8 bit resolution. The study was performed in terms of the sensor spectral sensitivity and final results are compared against data obtained by characterization system consisting of integrating sphere and a monochromator with a halogen light source. The preliminary results are promising. In conclusion, the developed LED-based spectrally tunable light source can be used as a lowcost, fast, and portable device for camera characterization.

Multichannel Spectral Image Enhancement for Visualizing Diabetic Retinopathy Lesions

Spectral imaging is a useful tool in many fields of scientific research and industry. Spectral images contain both spatial and spectral information of the scene. Spectral information can be used for effective visualization of the features-of-interest. One approach is to use spectral image enhancement techniques to improve the diagnostic accuracy of medical image technologies like retinal imaging. In this paper, two multichannel spectral image enhancement methods and a technique to further improve the visualization are presented. The methods are tested on four multispectral retinal images which contain diabetic retinopathy lesions. Both of the methods improved the detectability and quantitative contrast of the diabetic lesions when compared to standard color images and are potentially valuable for clinicians and automated image analyses.

Spectral Image Enhancement for the Visualization of Dental Lesions

Spectral imaging provides an image of a target over a relatively large number of wavelength bands. With the advances in imaging technology, spectral imaging is becoming increasingly popular in different areas of research. However, as spectral images typically contain more than three wavelength bands, visualization of the spectral data is often challenging. Spectral image enhancement is one approach for creating visualizations of spectral data. In spectral image enhancement, weights are applied to the wavelength bands before computing an RGB-presentation. In this paper, a method for automatic determination of optimal spectral band weights for enhanced visualization of dental lesions (caries and calculus) in extracted human teeth is described. Results are promising as the contrast and visibility of lesions was improved in all studied cases.

Contrast Enhancement of Dental Lesions by Light Source Optimisation

Dental lesions such as calculus and initial caries can be challenging to distinguish in RGB colour images due to a poor contrast. The visibility of dental lesions can be improved by using spectrally optimised light sources. In this paper, the optimal spectral shapes of illuminants for the visibility enhancement of various lesions are determined. These optimal spectral shapes are determined computationally by using spectral images captured from extracted human teeth, and numerical optimisation.

Evaluation of feature sensitivity to training data inaccuracy in detection of retinal lesions

Computer aided diagnostic and segmentation tools have become increasingly important in reducing the workload of medical experts performing diagnosis, monitoring and documentation of various eye diseases such as age-related macular degeneration (AMD), diabetic retinopathy (DR) and glaucoma. Supervised methods have been developed for the segmentation and detection of lesions, and the reported performance has been good. The supervised methods, however, need representative data to properly train the classifier. Inaccuracies in the ground truth may have a significant impact on the performance of a supervised method as the training data are not representative. In this study, a quantitative evaluation of the sensitivity of different image features, including colour, texture, edge and higher-level features, to inaccuracy in the ground truth on exudates is presented. A mean decrease of approx. 20% in sensitivity and 13% in specificity was observed when using the most inaccurate training data.