Brain age gap estimation using attention-based ResNet method for Alzheimer's disease detection.

This study investigates the correlation between brain age and chronological age in healthy individuals using brain MRI images, aiming to identify potential biomarkers for neurodegenerative diseases like Alzheimer's. To achieve this, a novel attention-based ResNet method, 3D-Attention-Resent-SVR, is proposed to accurately estimate brain age and distinguish between Cognitively Normal (CN) and Alzheimer's disease (AD) individuals by computing the brain age gap (BAG). Unlike conventional methods, which often rely on single datasets, our approach addresses potential biases by employing four datasets for training and testing. The results, based on a combined dataset from four public sources comprising 3844 data points, demonstrate the model's efficacy with a mean absolute error (MAE) of 2.05 for brain age gap estimation. Moreover, the model's generalizability is showcased by training on three datasets and testing on a separate one, yielding a remarkable MAE of 2.4. Furthermore, leveraging BAG as the sole biomarker, our method achieves an accuracy of 92% and an AUC of 0.87 in Alzheimer's disease detection on the ADNI dataset. These findings underscore the potential of our approach in assisting with early detection and disease monitoring, emphasizing the strong correlation between BAG and AD.

Prediction of Acute Kidney Injury After Cardiac Surgery Using Interpretable Machine Learning.

Background: Acute kidney injury (AKI) is a complication that occurs for various reasons after surgery, especially cardiac surgery. This complication can lead to a prolonged treatment process, increased costs, and sometimes death. Prediction of postoperative AKI can help anesthesiologists to implement preventive and early treatment strategies to reduce the risk of AKI. Objectives: This study tries to predict postoperative AKI using interpretable machine learning models. Methods: For this study, the information of 1435 patients was collected from multiple centers. The gathered data are in six categories: demographic characteristics and type of surgery, past medical history (PMH), drug history (DH), laboratory information, anesthesia and surgery information, and postoperative variables. Machine learning methods, including support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), random forest (RF), logistic regression, XGBoost, and AdaBoost, were used to predict postoperative AKI. Local interpretable model-agnostic explanations (LIME) and the Shapley methods were then leveraged to check the interpretability of models. Results: Comparing the area under the curves (AUCs) obtained for different machine learning models show that the RF and XGBoost methods with values of 0.81 and 0.80 best predict postoperative AKI. The interpretations obtained for the machine learning models show that creatinine (Cr), cardiopulmonary bypass time (CPB time), blood sugar (BS), and albumin (Alb) have the most significant impact on predictions. Conclusions: The treatment team can be informed about the possibility of postoperative AKI before cardiac surgery using machine learning models such as RF and XGBoost and adjust the treatment procedure accordingly. Interpretability of predictions for each patient ensures the validity of obtained predictions.

Deep learning approaches for automated classification and segmentation of head and neck cancers and brain tumors in magnetic resonance images: a meta-analysis study.

PURPOSE: Deep learning (DL) has led to widespread changes in automated segmentation and classification for medical purposes. This study is an attempt to use statistical methods to analyze studies related to segmentation and classification of head and neck cancers (HNCs) and brain tumors in MRI images. METHODS: PubMed, Web of Science, Embase, and Scopus were searched to retrieve related studies published from January 2016 to January 2020. Studies that evaluated the performance of DL-based models in the segmentation, and/or classification and/or grading of HNCs and/or brain tumors were included. Selected studies for each analysis were statistically evaluated based on the diagnostic performance metrics. RESULTS: The search results retrieved 1,664 related studies, of which 30 studies were eligible for meta-analysis. The overall performance of DL models for the complete tumor in terms of the pooled Dice score, sensitivity, and specificity was 0.8965 (95% confidence interval (95% CI): 0.76-0.9994), 0.9132 (95% CI: 0.71-0.994) and 0.9164 (95% CI: 0.78-1.00), respectively. The DL methods achieved the highest performance for classifying three types of glioma, meningioma, and pituitary tumors with overall accuracies of 96.01%, 99.73%, and 96.58%, respectively. Stratification of glioma tumors by high and low grading revealed overall accuracies of 94.32% and 94.23% for the DL methods, respectively. CONCLUSION: Based on the obtained results, we can acknowledge the significant ability of DL methods in the mentioned applications. Poor reporting in these studies challenges the analysis process, so it is recommended that future studies report comprehensive results based on different metrics.

An unsupervised hierarchical approach for automatic intra-retinal cyst segmentation in spectral-domain optical coherence tomography images.

PURPOSE: Intra-retinal cyst (IRC) is a symptom of macular disorders that occurs due to retinal blood vessel damage and fluid leakage to the macula area. These abnormalities are efficiently visualized using optical coherence tomography (OCT) imaging. These patients need to be regularly monitored for the presence and changes of IRC regions. Thus, automatic segmentation of IRCs can be beneficial to investigate disease progression. METHODS: In this study, automatic IRC segmentation is accomplished by building three different masks in three unsupervised segmentation levels of a hierarchical framework. In the first level, the ROI-mask (R-mask) is built, and the retina area is cropped based on this mask. In the second level, the prune-mask (P-mask) is built, and the searching space is significantly reduced toward the target objects using this mask; and finally in the third level, by applying the Markov random field (MRF) model and employing intensity and contextual information, the cyst mask (C-mask) is extracted. RESULTS: The proposed method is evaluated on three datasets including OPTIMA, UMN, and KERMANY datasets. The experimental results showed that the proposed method is effective with a mean dice coefficient rate of 0.74, 0.75 and 0.79 by the intersection of ground truths on the OPTIMA, UMN and KERMANY datasets, respectively. CONCLUSION: The proposed method outperforms the state-of-the-art methods on the OPTIMA and UMN datasets while achieving comparable results to the most recently proposed method on the KERMANY dataset.

A Multimodal Fusion Approach for Bullet Identification Systems.

In the field of forensic science, bullet identification is based on the fact that firing the cartridge from a barrel leaves exclusive microscopic striation on the fired bullets as the fingerprint of the firearm. The bullet identification methods are categorized in 2-D and 3-D based on their image acquisition techniques. In this study, we focus on 2-D optical images using a multimodal technique and propose several distinct methods as its modalities. The proposed method uses a multimodal rule-based linear weighted fusion approach which combines the semantic level decisions from different modalities with a linear technique that its optimized modalities weights have been identified by the genetic algorithm. The proposed approach was applied on a dataset, which includes 180 2-D bullet images fired from 90 different AK-47 barrels. The experimentations showed that our approach attained better results compared to common methods in the field of bullet identification.

A correlation based bullet identification method using empirical mode decomposition.

The striations on bullet surface are 3D micro structures formed when a bullet is forcing its way out of barrel. Each barrel leaves individual striation patterns on bullets. Hence, the striation information of bullets is helpful for firearm identification. Common automatic identification methods process these images using linear time invariant (LTI) filters based on correlation. These methods do not consider the sensitivity of correlation based comparisons to nonlinear baseline drifts. The striations are undeniably random unique micro structures caused by random non-model-based imperfections in the tools used in rifling process, therefore any characteristic profile that is extracted from a bullet image is statistically non-stationary. Due to limitations of LTI filters, using them in smoothing bullet images and profiles may cause information loss and impact the process of identification. To address these problems, in this article, we consider bullet images as nonlinear non-stationary processes and propose a novel method which uses ensemble empirical mode decomposition (EEMD) as a preprocessing algorithm for smoothing and feature extraction. The features extracted by EEMD algorithm not only contain less noise, but also have no nonlinear baseline drifts. These improvements help the correlation based comparison methods to perform more robustly and efficiently. The experiments showed that our proposed method attained better results compared with two common methods in the field of automatic bullet identification.

Blind Detection of Region Duplication Forgery Using Fractal Coding and Feature Matching.

Digital image forgery detection is important because of its wide use in applications such as medical diagnosis, legal investigations, and entertainment. Copy-move forgery is one of the famous techniques, which is used in region duplication. Many of the existing copy-move detection algorithms cannot effectively blind detect duplicated regions that are made by powerful image manipulation software like Photoshop. In this study, a new method is proposed for blind detecting manipulations in digital images based on modified fractal coding and feature vector matching. The proposed method not only detects typical copy-move forgery, but also finds multiple copied forgery regions for images that are subjected to rotation, scaling, reflection, and a mixture of these postprocessing operations. The proposed method is robust against tampered images undergoing attacks such as Gaussian blurring, contrast scaling, and brightness adjustment. The experimental results demonstrated the validity and efficiency of the method.