Leticia Ortega Maynez

Lung nodule classification in frequency domain using support vector machines

In this paper a computational alternative to classify lung nodules inside CT thorax images in the frequency domain is presented. After image acquisition, a region of interest is manually selected. Then, the spectrums of the two dimensional Discrete Cosine Transform (2D-DCT) and the two dimensional Fast Fourier Transform (2D-FFT) were calculated. Later, two statistical texture features were extracted from the histogram computed from the spectrum of each CT image. Finally, a support vector machine with a radial basis function as a kernel was used as the classifier. Seventy five tests with different diagnosis and number of images were used to validate the methodology presented. After experimentation and results, ten false negatives (FN) and two false positives (FP) were obtained, and a sensitivity and specificity of 96.15% and 52.17% respectively. The total preciseness obtained with the methodology proposed was 82.66%.

Noise reduction in small-animal PET images using a multiresolution transform.

In this paper, we address the problem of denoising reconstructed small animal positron emission tomography (PET) images, based on a multiresolution approach which can be implemented with any transform such as contourlet, shearlet, curvelet, and wavelet. The PET images are analyzed and processed in the transform domain by modeling each subband as a set of different regions separated by boundaries. Homogeneous and heterogeneous regions are considered. Each region is independently processed using different filters: a linear estimator for homogeneous regions and a surface polynomial estimator for the heterogeneous region. The boundaries between the different regions are estimated using a modified edge focusing filter. The proposed approach was validated by a series of experiments. Our method achieved an overall reduction of up to 26% in the %STD of the reconstructed image of a small animal NEMA phantom. Additionally, a test on a simulated lesion showed that our method yields better contrast preservation than other state-of-the art techniques used for noise reduction. Thus, the proposed method provides a significant reduction of noise while at the same time preserving contrast and important structures such as lesions.

The Nonsubsampled Contourlet Transform for Enhancement of Microcalcifications in Digital Mammograms

Microcalcifications detection plays a crucial role in the early detection of breast cancer. The enhancement of the mammographic images is one of the most important tasks during the detection process. This paper presents an algorithm for the enhancement of microcalcifications in digital mammograms. The main novelty is the application of the nonsubsampled contourlet transform and a specific edge filter to enhance the directional structures of the image in the contourlet domain. The inverse contourlet transform is applied to recover an approximation of the mammogram with the microcalcifications enhanced. Results show that the proposed method outperforms the current method based on the discrete wavelet transform.

Visual perception substitution by the auditory sense

This paper presents the methodology to develop a sensory substitution system. We deal with the absence of visual inputs in humans, and we substitute the blindness by the auditory sense. Visual to auditory substitution involves delivering information about the visual world using auditory signals. The system allows the transformation of digital images captured from a web cam into sound patterns, using a novel scanning method from the center to the left and right side of the image. We define a robust correspondence between the image features and the sound features. The results provided by the system seems high enough to address many practical situations that normally require the sense of sight. Navigation experiments with blind people, have demonstrated the ability of the system to offer a permanent sensory substitution device in the future.

Noise Reduction in Small Animal PET Images Using a Variational Non-Convex Functional

Positron emission tomography (PET) imaging is widely used in nuclear medicine. However, data acquired by a PET system are generally contaminated with heavy noise, which often persists after image reconstruction. In this paper, a novel non-convex functional is introduced to suitably attenuate noise in PET images. The proposed functional contains a new regularization term defined as a convex combination of two terms: a robust function for border preserving and the L2 semi-norm. The combination coefficient depends on the gradient of the noisy image, so that it allows a selective smoothing of image regions according to their local characteristics. The proposed method has been qualitatively and quantitatively tested on both simulated and measured data, demonstrating its better performance against well-established methods for PET denoising.

Determination of temperature in neonates based in a face IR thermography image segmentation algorithm

The temperature is a factor for the health of a newborn. In this paper, an algorithm for automatic face segmentation in digital thermal images of is proposed. A one hundred thermal images database was belonging to five different neonates, twenty images for each one. For the neonate facial segmentation, the active contour method Chan-Vese was used and for the separation of interest regions, fuzzy sets were implemented. The temperature data obtained using two mathematical equations. For interpretation of the data, a graphical user interface was created, where the user can choose between automatic or manual mode, for the analysis of the temperature. Finally, the proposed algorithm was tested using metric of segmentation.

Wavelet-based regularization strategies within the 3D list-mode ML-EM reconstruction process, for high resolution small animal PET data

The measurements obtained from the acquiring PET system tend to be very noisy, since randoms and scatter contamination events as well as detector efficiency are strong sources of noise. In particular, for the small animal reconstructed images, this problem becomes severe corrupting areas of interest between organs, making the identification process even more difficult. For that reason, a regularization step is of crucial importance. In this paper, performance evaluations for two different strategies to include wavelet-based regularization within the list-mode Maximum Likelihood Expectation-Maximization (MLEM) reconstruction process are established. Results are compared against the standard noise reduction PSF methods (Gaussian smoothing) used for resolution recovery. For each reconstruction model proposed, investigations on the effects of image quality were addressed. Results show that reconstruction process given by the Model 2, significantly improves the quantity accuracy of the images, especially incrementing the image contrast values in comparison with the standard noise reduction method, which tends to blur the image data. Reconstruction models were tested using list-mode measured data from the high-resolution quad-HIDAC small animal PET scanner.

SAR image denoising using the non-subsampled contourlet transform and morphological operators

This paper introduces a novel algorithm that combines the Non-Subsampled Contourlet Transform (NSCT) and morphological operators to reduce the multiplicative noise of synthetic aperture radar images. The image corrupted by multiplicative noise is preprocessed and decomposed into several scales and directions using the NSCT. Then, the contours and uniform regions of each subband are separated from noise. Finally, the resulting denoised subbands are transformed back into the spatial domain and applied the exponential function to obtain the denoised image. Experimental results show that the proposed method drastically reduces the multiplicative noise and outperforms other denoising methods, while achieving a better preservation of the visual details.

Characterization of Magnetic Particles Using a Wavelet Function

The second derivative of the remission function of several magnetic materials is calculated for the parameterization of the position and intensity of the absorption bands of diffuse reflectance spectroscopy. The reflectance spectra are obtained by ultraviolet-visible spectroscopy (UV-VIS) from 400 to 1100 nm at increments of 1nm. The noise of the remission function results on errors after calculating the second derivative. Therefore, filtering of the remission function is needed before taking any action on this signal. Several methods are tested in order to calculate the second derivative. The best polynomial resulted on a second order wavelet function which is applied to the filtered remission function. Light scattering Mie theory is used to prove the behaviour of the reflected light. This research provides a method to identify and quantify magnetic particles, as well as the crystal size.