A5049693882- Retinal Imaging and Analysis
- Glaucoma and retinal disorders
- Retinal Diseases and Treatments
- Optical Imaging and Spectroscopy Techniques
- Photoacoustic and Ultrasonic Imaging
- Spectroscopy Techniques in Biomedical and Chemical Research
- Infrared Thermography in Medicine
- Retinal and Optic Conditions
- Digital Imaging for Blood Diseases
- AI in cancer detection
- Medical Image Segmentation Techniques
- Medical Imaging and Analysis
- Speech and Audio Processing
- Breast Cancer Treatment Studies
- Advanced Neural Network Applications
- Ultrasound Imaging and Elastography
- Advanced Adaptive Filtering Techniques
- Radiomics and Machine Learning in Medical Imaging
- Surgical Simulation and Training
- Digital Radiography and Breast Imaging
- Prostate Cancer Diagnosis and Treatment
- Ultrasound and Hyperthermia Applications
- Composite Material Mechanics
- Artificial Intelligence in Healthcare and Education
- Mechanical Behavior of Composites
The Netherlands Cancer Institute
2018-2025
Eindhoven University of Technology
2015-2023
Northeastern University
2018
Institute of Mechanical Engineering and Industrial Mangement
2013-2015
Universidade do Porto
2013-2014
Yazd University
2008-2011
This paper presents a robust and fully automatic filter-based approach for retinal vessel segmentation. We propose new filters based on 3D rotating frames in so-called orientation scores, which are functions the Lie-group domain of positions orientations [Formula: see text]. By means wavelet-type transform, 2D image is lifted to score, where elongated structures disentangled into their corresponding planes. In text], vessels enhanced by multi-scale second-order Gaussian derivatives...
The classification of retinal vessels into artery/vein (A/V) is an important phase for automating the detection vascular changes, and calculation characteristic signs associated with several systemic diseases such as diabetes, hypertension, other cardiovascular conditions. This paper presents automatic approach A/V based on analysis a graph extracted from vasculature. proposed method classifies entire tree deciding type each intersection point (graph nodes) assigning one two labels to vessel...
Retinal microaneurysms are the earliest clinical sign of diabetic retinopathy disease. Detection is crucial for early diagnosis and prevention blindness. In this paper, a novel reliable method automatic detection in retinal images proposed. first stage proposed method, several preliminary microaneurysm candidates extracted using gradient weighting technique an iterative thresholding approach. next stage, addition to intensity shape descriptors, new set features based on local convergence...
There are a wide variety of microstructural parameters which affect the macro-mechanical response short fiber reinforced composites. Effects these could be captured using different micromechanics-based models. However, in some cases, it is very challenging and computationally expensive. In this study, Artificial Neural Networks (ANN) model developed to predict elastic properties materials, accurately quickly. The required data for training validating created two-step approach, combining...
The retinal fractal dimension (FD) is a measure of vasculature branching pattern complexity. FD has been considered as potential biomarker for the detection several diseases like diabetes and hypertension. However, conflicting findings were found in reported literature regarding association between this diseases. In paper, we examine stability measurement with respect to (1) different vessel annotations obtained from human observers, (2) automatic segmentation methods, (3) various regions...
Complete tumor removal during breast-conserving surgery remains challenging due to the lack of optimal intraoperative margin assessment techniques. Here, we use hyperspectral imaging for detection in fresh breast tissue. We evaluated different wavelength ranges and two classification algorithms; a pixel-wise algorithm convolutional neural network that combines spectral spatial information. The highest performance was obtained using full range (450-1650 nm). Adding information mainly improved...
Abstract The macroscopic response of short fiber reinforced composites (SFRCs) is dependent on an extensive range microstructural parameters. Thus, micromechanical modeling these materials challenging and in some cases, computationally expensive. This particularly important when path‐dependent plastic behavior needed to be predicted. A solution this challenge enhance solutions with machine learning techniques such as artificial neural networks. In work, a recurrent deep network model trained...
Background and objectives: The automatic classification of retinal blood vessels into artery vein (A/V) is still a challenging task in image analysis. Recent works on A/V mainly focus the graph analysis vasculature, which exploits connectivity to improve performance. While they have overlooked importance pixel-wise final results. This paper shows that complicated feature set efficient for vessel centerline pixels classification. Methods: We extract enormous amount features pixels, apply...
Several ocular and systemic diseases such as hypertension arteriosclerosis cause geometrical functional changes to the vasculature in retinal images, including alterations shape of vascular bifurcations crossings. To use diagnostic information junctions, it is important detect them first. In this work, a novel BIfurcation CRossing detection method using Orientations Scores (BICROS) introduced. The Brain-inspired orientation score transformation lifts image joint space positions orientations...
Automatic artery/vein (A/V) classification is one of the important topics in retinal image analysis. It allows researchers to investigate association between biomarkers and disease progression on a huge amount data for arteries veins separately. Recent proposed methods, which employ contextual information vessels achieve better A/V accuracy, still rely performance pixel-wise classification, has received limited attention recent years. In this paper, we show that these methods can be markedly...
This ex-vivo study evaluates the feasibility of diffuse reflectance spectroscopy (DRS) for discriminating tumor from healthy tissue, with aim to develop a technology that can assess resection margins presence cells during oral cavity cancer surgery. Diffuse spectra were acquired on fresh surgical specimens 28 patients squamous cell carcinoma. The (400 1600 nm) detected after illuminating tissue source fiber at 0.3-, 0.7-, 1.0-, and 2.0-mm distances detection fiber, obtaining spectral...
Multi-modal retinal image registration is often required to utilize the complementary information from different imaging modalities.However, a robust and accurate still challenge due modality-varied resolution, contrast, luminosity.In this paper, two step method proposed address problem.Descriptor matching on mean phase images used globally register in first step.Deformable based modality independent neighbourhood descriptor (MIND) followed locally refine result second step.The extensively...
Prostate cancer is a leading health concern among men, requiring accurate and accessible methods for early detection risk stratification. volume (PV) key parameter in multivariate stratification prostate detection, commonly estimated using transrectal ultrasound (TRUS). While TRUS provides precise measurements, its invasive nature often compromises patient comfort. Transabdominal (TAUS) non-invasive alternative but faces challenges such as lower image quality, complex interpretation,...
Margin assessment in breast-conserving surgery (BSC) remains a critical challenge, with 20-25% of cases resulting inadequate tumor resection, increasing the risk local recurrence and need for additional treatment. In this study, we evaluate diagnostic performance hyperspectral imaging (HSI) as non-invasive technique assessing resection margins ex vivo lumpectomy specimens. A dataset over 200 specimens was collected using two cameras, classification algorithm developed to distinguish between...
There is an unmet clinical need for accurate, rapid and reliable tool margin assessment during breast-conserving surgeries. Ultrasound offers the potential a rapid, reproducible, non-invasive method to assess margins. However, it challenged by certain drawbacks, including low signal-to-noise ratio, artifacts, experience with acquirement interpretation of images. A possible solution might be computer-aided ultrasound evaluation. In this study, we have developed new ensemble approaches...
(1) Background: Hyperspectral imaging has emerged as a promising margin assessment technique for breast-conserving surgery. However, to be implicated intraoperatively, it should both fast and capable of yielding high-quality images provide accurate guidance decision-making throughout the As there exists trade-off between image quality data acquisition time, higher resolution come at cost longer times vice versa. (2) Methods: Therefore, in this study, we introduce deep learning...
SignificanceDuring breast-conserving surgeries, it is essential to evaluate the resection margins (edges of breast specimen) determine whether tumor has been removed completely. In current surgical practice, there are no methods available aid in accurate real-time margin evaluation.AimIn this study, we investigated diagnostic accuracy diffuse reflectance spectroscopy (DRS) combined with tissue classification models discriminating tumorous from healthy up 2 mm depth on actual vivo...
The accurate correlation between optical measurements and pathology relies on precise image registration, often hindered by deformations in histology images. We investigate an automated multi-modal registration method using deep learning to align breast specimen images with corresponding
Retinal image analysis is a challenging problem due to the precise quantification required and huge numbers of images produced in screening programs. This paper describes series innovative brain-inspired algorithms for automated retinal analysis, recently developed RetinaCheck project, large-scale program diabetic retinopathy other diseases Northeast China. The discusses theory orientation scores, inspired by cortical multi-orientation pinwheel structures, presents applications quality...
Retinal microvascular diameters are biomarkers of cardio-metabolic risk. However, the association (pre)diabetes with retinal remains unclear. We aimed to investigate prediabetes (impaired fasting glucose or impaired tolerance) and type 2 diabetes in a predominantly white population.In population-based cohort study oversampling (N = 2876; n 1630 normal metabolism [NGM], 433 813 diabetes, 51.2% men, aged 59.8 ± 8.2 years; 98.6% white), we determined (measurement unit as measured by health...
Abstract During oncological surgery, it can be challenging to identify the tumor and establish adequate resection margins. This study proposes a new two-layer approach in which diffuse reflectance spectroscopy (DRS) is used predict top layer thickness classify layers two-layered phantom animal tissue. Using wavelet-based peak-based DRS spectral features, proposed method could with an accuracy of up 0.35 mm. In addition, tissue types first second were classified 0.95 0.99. Distinguishing...