Search

Background and Objective: Age-related macular degeneration (AMD) is the most common cause of blindness in developed countries, especially in people over 60 years of age. The workload of specialists and the healthcare system in this field has increased in recent years mainly due to three reasons: 1) increased use of retinal optical coherence tomography (OCT) imaging technique, 2) prevalence of population aging worldwide, and 3) chronic nature of AMD. Recent advancements in the field of deep learning have provided a unique opportunity for the development of fully automated diagnosis frameworks. Considering the presence of AMD-related retinal pathologies in varying sizes in OCT images, our objective was to propose a multi-scale convolutional neural network (CNN) that can capture inter-scale variations and improve performance using a feature fusion strategy across convolutional blocks., Methods: Our proposed method introduces a multi-scale CNN based on the feature pyramid network (FPN) structure. This method is used for the reliable diagnosis of normal and two common clinical characteristics of dry and wet AMD, namely drusen and choroidal neovascularization (CNV). The proposed method is evaluated on the national dataset gathered at Hospital (NEH) for this study, consisting of 12649 retinal OCT images from 441 patients, and the UCSD public dataset, consisting of 108312 OCT images from 4686 patients., Results: Experimental results show the superior performance of our proposed multi-scale structure over several well-known OCT classification frameworks. This feature combination strategy has proved to be effective on all tested backbone models, with improvements ranging from 0.4% to 3.3%. In addition, gradual learning has proved to be effective in improving performance in two consecutive stages. In the first stage, the performance was boosted from 87.2%±2.5% to 92.0%±1.6% using pre-trained ImageNet weights. In the second stage, another performance boost from 92.0%±1.6% to 93.4%±1.4% was observed as a result of fine-tuning the previous model on the UCSD dataset. Lastly, generating heatmaps provided additional proof for the effectiveness of our multi-scale structure, enabling the detection of retinal pathologies appearing in different sizes., Conclusion: The promising quantitative results of the proposed architecture, along with qualitative evaluations through generating heatmaps, prove the suitability of the proposed method to be used as a screening tool in healthcare centers assisting ophthalmologists in making better diagnostic decisions., (Copyright © 2022 Elsevier Ltd. All rights reserved.)

Objectives: It is important to subdivide Parkinson's disease (PD) into subtypes, enabling potentially earlier disease recognition and tailored treatment strategies. We aimed to identify reproducible PD subtypes robust to variations in the number of patients and features., Methods: We applied multiple feature-reduction and cluster-analysis methods to cross-sectional and timeless data, extracted from longitudinal datasets (years 0, 1, 2 & 4; Parkinson's Progressive Marker Initiative; 885 PD/163 healthy-control visits; 35 datasets with combinations of non-imaging, conventional-imaging, and radiomics features from DAT-SPECT images). Hybrid machine-learning systems were constructed invoking 16 feature-reduction algorithms, 8 clustering algorithms, and 16 classifiers (C-index clustering evaluation used on each trajectory). We subsequently performed: i) identification of optimal subtypes, ii) multiple independent tests to assess reproducibility, iii) further confirmation by a statistical approach, iv) test of reproducibility to the size of the samples., Results: When using no radiomics features, the clusters were not robust to variations in features, whereas, utilizing radiomics information enabled consistent generation of clusters through ensemble analysis of trajectories. We arrived at 3 distinct subtypes, confirmed using the training and testing process of k-means, as well as Hotelling's T2 test. The 3 identified PD subtypes were 1) mild; 2) intermediate; and 3) severe, especially in terms of dopaminergic deficit (imaging), with some escalating motor and non-motor manifestations., Conclusion: Appropriate hybrid systems and independent statistical tests enable robust identification of 3 distinct PD subtypes. This was assisted by utilizing radiomics features from SPECT images (segmented using MRI). The PD subtypes provided were robust to the number of the subjects, and features., (Copyright © 2020 Elsevier Ltd. All rights reserved.)

Image registration is a basic task in medical image processing applications like group analysis and atlas construction. Similarity measure is a critical ingredient of image registration. Intensity distortion of medical images is not considered in most previous similarity measures. Therefore, in the presence of bias field distortions, they do not generate an acceptable registration. In this paper, we propose a sparse based similarity measure for mono-modal images that considers non-stationary intensity and spatially-varying distortions. The main idea behind this measure is that the aligned image is constructed by an analysis dictionary trained using the image patches. For this purpose, we use "Analysis K-SVD" to train the dictionary and find the sparse coefficients. We utilize image patches to construct the analysis dictionary and then we employ the proposed sparse similarity measure to find a non-rigid transformation using free form deformation (FFD). Experimental results show that the proposed approach is able to robustly register 2D and 3D images in both simulated and real cases. The proposed method outperforms other state-of-the-art similarity measures and decreases the transformation error compared to the previous methods. Even in the presence of bias field distortion, the proposed method aligns images without any preprocessing., (Copyright © 2016 Elsevier Ltd. All rights reserved.)

Classification of breast abnormalities such as masses is a challenging task for radiologists. Computer-aided Diagnosis (CADx) technology may enhance the performance of radiologists by assisting them in classifying patterns into benign and malignant categories. Although Neural Networks (NN) such as Multilayer Perceptron (MLP) have drawbacks, namely long training times, a considerable number of CADx systems employ NN-based classifiers. The reason being that they provide high accuracy when they are appropriately trained. In this paper, we introduce three novel learning rules called Opposite Weight Back Propagation per Pattern (OWBPP), Opposite Weight Back Propagation per Epoch (OWBPE), and Opposite Weight Back Propagation per Pattern in Initialization (OWBPI) to accelerate the training procedure of an MLP classifier. We then develop CADx systems for the diagnosis of breast masses employing the traditional Back Propagation (BP), OWBPP, OWBPE and OWBPI algorithms on MLP classifiers. We quantitatively analyze the accuracy and convergence rate of each system. The results suggest that the convergence rate of the proposed OWBPE algorithm is more than 4 times faster than that of the traditional BP. Moreover, the CADx systems which use OWBPE classifier on average yield an area under Receiver Operating Characteristic (ROC), i.e. Az, of 0.928, a False Negative Rate (FNR) of 9.9% and a False Positive Rate (FPR) of 11.94%., (Copyright © 2012 Elsevier Ltd. All rights reserved.)

Recently, automated segmentation of retinal vessels in optic fundus images has been an important focus of much research. In this paper, we propose a multi-scale method to segment retinal vessels based on a weighted two-dimensional (2D) medialness function. The results of the medialness function are first multiplied by the eigenvalues of the Hessian matrix. Next, centerlines of vessels are extracted using noise reduction and reconnection procedures. Finally, vessel radii are estimated and retinal vessels are segmented. The proposed method is evaluated and compared with several recent methods using images from the DRIVE and STARE databases., (Copyright © 2011 Elsevier Ltd. All rights reserved.)

White matter (WM) microstructure can be evaluated by diffusion tensor imaging (DTI). Tract-based spatial statistical (TBSS) analysis provides a means of assessing alterations in WM tracts. In this paper, both voxel-based morphometry (VBM) and TBSS are examined using DTI data of temporal lobe epilepsy (TLE) patients and nonepileptic subjects. In addition to fractional anisotropy (FA), ellipsoidal area ratio (EAR) is used in this study. Significant reductions of FA and EAR are identified by TBSS in the parahippocampal white matter. Because of methodological differences, TBSS detects more localized abnormalities than VBM, while the EAR is more sensitive to WM alteration than FA., (2011 Elsevier Ltd. All rights reserved.)

We present a novel and efficient method for localization of human brain structures such as hippocampus. Landmark localization is important for segmentation and registration. This method follows a statistical roadmap, consisting of anatomical landmarks, to reach the desired structures. Using a set of desired and undesired landmarks, identified on a training set, we estimate Gaussian models and determine optimal search areas for desired landmarks. The statistical models form a set of rules to evaluate the extracted landmarks during the search procedure. When applied on 900 MR images of 10 epileptic patients, this method demonstrated an overall success rate of 83%.

This paper presents an image processing approach for information extraction from three-dimensional (3-D) images of vasculature. It extracts quantitative information such as skeleton, length, diameter, and vessel-to-tissue ratio for different vessels as well as their branches. Furthermore, it generates 3-D visualization of vessels based on desired anatomical characteristics such as vessel diameter or 3-D connectivity. Steps of the proposed approach are: (1) pre-processing, (2) distance mappings, (3) branch labeling, (4) quantification, and (5) visualization. We have tested and evaluated the proposed algorithms using simulated images of multi-branch vessels and real confocal microscopic images of the vessels in rat brains. Experimental results illustrate performance of the methods and usefulness of the results for medical image analysis applications.