Tuberculosis (TB) is still considered a leading cause of death and a substantial threat to global child health. Both TB infection and disease are curable using antibiotics. However, most children who die of TB are never diagnosed or treated. In clinical practice, experienced physicians assess TB by examining chest X-rays (CXR). Pediatric CXR has specific challenges compared to adult CXR, which makes TB diagnosis in children more difficult. Computer-aided diagnosis systems supported by Artificial Intelligence have shown performance comparable to experienced radiologist TB readings, which could ease mass TB screening and reduce clinical burden. We propose a multi-view deep learning-based solution which, by following a proposed template, aims to automatically regionalize and extract lung and mediastinal regions of interest from pediatric CXR images where key TB findings may be present. Experimental results have shown accurate region extraction, which can be used for further analysis to confirm TB finding presence and severity assessment.
A relevant percentage of COVID-19 patients present bilateral pneumonia. Disease progression and healing is characterized by the presence of different parenchymal lesion patterns. Artificial intelligence algorithms have been developed to identify and assess the related lesions and properly segment affected lungs, however very little attention has been paid to automatic lesion subtyping. In this work we present artificial intelligence algorithms based on CNN to automatically identify and quantify COVID-19 pneumonia patterns. A Dense-efficient CNN architecture is presented to automatically segment the different lesion subtypes. The proposed technique has been independently tested in a multicentric cohort of 100 patients, showing Dice coefficients of 0.988±0.01 for ground glass opacities, 0.948±0.05 for consolidations, and 0.999±0.0003 for healthy tissue with respect to radiologist’s reference segmentations, and high correlations with respect to radiologist severity visual scores.
KEYWORDS: Optical coherence tomography, Wavelets, Digital filtering, Speckle, Signal to noise ratio, Denoising, Image filtering, Skin, Optical filters, Imaging systems
Significance: Speckle noise limits the diagnostic capabilities of optical coherence tomography (OCT) images, causing both a reduction in contrast and a less accurate assessment of the microstructural morphology of the tissue.
Aim: We present a speckle-noise reduction method for OCT volumes that exploits the advantages of adaptive-noise wavelet thresholding with a wavelet compounding method applied to several frames acquired from consecutive positions. The method takes advantage of the wavelet representation of the speckle statistics, calculated properly from a homogeneous sample or a region of the noisy volume.
Approach: The proposed method was first compared quantitatively with different state-of-the-art approaches by being applied to three different clinical dermatological OCT volumes with three different OCT settings. The method was also applied to a public retinal spectral-domain OCT dataset to demonstrate its applicability to different imaging modalities.
Results: The results based on four different metrics demonstrate that the proposed method achieved the best performance among the tested techniques in suppressing noise and preserving structural information.
Conclusions: The proposed OCT denoising technique has the potential to adapt to different image OCT settings and noise environments and to improve image quality prior to clinical diagnosis based on visual assessment.
Many automatic image analysis algorithms in medical imaging require a good initialization to work properly. A similar problem occurs in many imaging-based clinical workflows, which depend on anatomical landmarks. The localization of anatomic structures based on a defined context provides with a solution to that problem, which turns out to be more challenging in medical imaging where labeled images are difficult to obtain. We propose a two-stage process to detect and regress 2D bounding boxes of predefined anatomical structures based on a 2D surrounding context. First, we use a deep convolutional neural network (DCNN) architecture to detect the optimal slice where an anatomical structure is present, based on relevant landmark features. After this detection, we employ a similar architecture to perform a 2D regression with the aim of proposing a bounding box where the structure is encompassed. We trained and tested our system for 57 anatomical structures defined in axial, sagittal and coronal planes with a dataset of 504 labeled Computed Tomography (CT) scans. We compared our method with a well-known object detection algorithm (Viola Jones) and with the inter-rater error for two human experts. Despite the relatively small number of scans and the exhaustive number of structures analyzed, our method obtained promising and consistent results, which proves our architecture very generalizable to other anatomical structures.
Optical Coherence Tomography (OCT) has shown a great potential as a complementary imaging tool in the diagnosis of skin diseases. Speckle noise is the most prominent artifact present in OCT images and could limit the interpretation and detection capabilities. In this work we propose a new speckle reduction process and compare it with various denoising filters with high edge-preserving potential, using several sets of dermatological OCT B-scans. To validate the performance we used a custom-designed spectral domain OCT and two different data set groups. The first group consisted in five datasets of a single B-scan captured N times (with N<20), the second were five 3D volumes of 25 Bscans. As quality metrics we used signal to noise (SNR), contrast to noise (CNR) and equivalent number of looks (ENL) ratios. Our results show that a process based on a combination of a 2D enhanced sigma digital filter and a wavelet compounding method achieves the best results in terms of the improvement of the quality metrics. In the first group of individual B-scans we achieved improvements in SNR, CNR and ENL of 16.87 dB, 2.19 and 328 respectively; for the 3D volume datasets the improvements were 15.65 dB, 3.44 and 1148. Our results suggest that the proposed enhancement process may significantly reduce speckle, increasing SNR, CNR and ENL and reducing the number of extra acquisitions of the same frame.
Myocardial motion analysis and quantification is of utmost importance for analyzing contractile heart abnormalities and
it can be a symptom of a coronary artery disease. A fundamental problem in processing sequences of images is the
computation of the optical flow, which is an approximation to the real image motion. This paper presents a new
algorithm for optical flow estimation based on a spatiotemporal-frequency (STF) approach, more specifically on the
computation of the Wigner-Ville distribution (WVD) and the Hough Transform (HT) of the motion sequences. The later
is a well-known line and shape detection method very robust against incomplete data and noise. The rationale of using
the HT in this context is because it provides a value of the displacement field from the STF representation. In addition, a
probabilistic approach based on Gaussian mixtures has been implemented in order to improve the accuracy of the motion
detection. Experimental results with synthetic sequences are compared against an implementation of the variational
technique for local and global motion estimation, where it is shown that the results obtained here are accurate and robust
to noise degradations. Real cardiac magnetic resonance images have been tested and evaluated with the current method.
Andres Santos, Cristina Ramiro, Manuel Desco, Norberto Malpica, Alberto Tejedor, Ana Torres, Maria Ledesma-Carbayo, Manuela Castilla, Pedro Garcia-Barreno
Automatic discrimination and quantification of alive and dead cells in phase contrast microscopy images allows in vivo analysis of the viability of cultured cells without staining. Unsupervised segmentation, based on texture analysis, classifies each image region into three groups: live cells, necrotic cells and background. The segmentation is based on three discriminant functions, built using a total of 12 parameters derived from the histogram and the co-occurrence matrix. These parameters were selected performing a discriminant analysis on a training set that included images from three different cultures. Once images are automatically segmented, the approximate number of live and dead cells is obtained by dividing each area by the average size of each cell type. The number and percentage of live and necrotic cells have been obtained for primary cellular cultures in intervals of 48 hr. during two weeks. The results have been compared with the figures given by an experienced human observer, showing a very good correlation (Pearson's coefficient 0.95, kappa 0.87). A reliable and easy-to-use tool has been developed. It provides quantitative results on phase contrast microscopy images of cell cultures, with preliminary results showing accuracy similar to that provided by an expert, allowing to count a higher number of fields.
Strain Rate (SR) Imaging is a recent imaging technique that provides information about regional myocardial deformation by measuring local compression and expansion rates. SR can be obtained by calculating the local in-plane velocity gradients along the ultrasound beam from Doppler Tissue velocity data. However, SR calculations are very dependent on the image noise and artifacts, and different calculation algorithms may provide inconsistent results. This paper compares techniques to calculate SR. 2D Doppler Tissue Images (DTI) are acquired with an Acuson Sequoia scanner. Noise was measured with the aid of a rotating phantom. Processing is performed on polar coordinates. For each image, after removal of black spot artifacts by a selective median filter, two different SR calculation methods have been implemented. In the first one, SR is computed as the discrete velocity derivative, and noise is reduced with a variable-width gaussian filter. In the second method a smoothing cubic spine is calculated for every scan line according to the noise level and the derivative is obtained from an analytical expression. Both methods have been tested with DTI data from synthetic phantoms and normal volunteers. Results show that noise characteristics, border effects and the adequate scale are critical to obtain meaningful results.
Manuel Desco, Maria Ledesma-Carbayo, Andres Santos, Miguel Garcia-Fernandez, Pedro Marcos-Alberca, Norberto Malpica, Jose Antoranz, Pedro Garcia-Barreno
Assessment of intramyocardial perfusion by contrast echocardiography is a promising new technique that allows to obtain quantitative parameters for the assessment of ischemic disease. In this work, a new methodology and a software prototype developed for this task are presented. It has been validated with Coherent Contrast Imaging (CCI) images acquired with an Acuson Sequoia scanner. Contrast (Optison microbubbles) is injected continuously during the scan. 150 images are acquired using low mechanical index U/S pulses. A burst of high mechanical index pulses is used to destroy bubbles, thus allowing to detect the contrast wash-in. The stud is performed in two conditions: rest and pharmacologically induced stress. The software developed allows to visualized the study (cine) and to select several ROIs within the heart wall. The position of these ROIs along the cardiac cycle is automatically corrected on the basis of the gradient field, and they can also be manually corrected in case the automatic procedure fails. Time curves are analyzed according to a parametric model that incorporates both contrast inflow rate and cyclic variations. Preliminary clinical results on 80 patients have allowed us to identify normal and pathological patterns and to establish the correlation of quantitative parameters with the real diagnosis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.