Search

Brain aging is a complex and dynamic process, leading to functional and structural changes in the brain. These changes could lead to the increased risk of neurodegenerative diseases and cognitive decline. Accurate brain-age estimation utilizing neuroimaging data has become necessary for detecting initial signs of neurodegeneration. Here, we propose a novel deep learning approach using the Residual Neural Network 101 Version 2 (ResNet101V2) model to predict brain age from MRI scans. To train, validate and test our proposed model, we used a large dataset of 2102 images which were selected randomly from the International Consortium for Brain Mapping (ICBM). Next, we applied data preprocessing techniques, including normalizing the images and using outlier detection via Isolation Forest method. Then, we evaluated various pre-trained approaches (namely: MobileNetV2, ResNet50V2, ResNet101V2, Xception). The results demonstrated that the ResNet101V2 model has higher performance compared with the other models, attaining MAEs of 0.9136 and 0.8242 years for before and after using Isolation Forest process. Our method achieved a high accuracy in brain age estimation in ICBM dataset and it provides a reliable brain age prediction.

For the early identification, diagnosis, and treatment of mental health illnesses, the integration of deep learning (DL) and machine learning (ML) has started playing a significant role. By evaluating complex data from imaging, genetics, and behavioral assessments, these technologies have the potential to significantly improve clinical outcomes. However, they also present unique challenges related to data integration and ethical issues. This survey reviews the development of ML and DL methods for the early diagnosis and treatment of mental health issues. It examines a range of applications, with a particular emphasis on behavioral assessments, genetic and biomarker analysis, and medical imaging for diagnosing diseases like depression, bipolar disorder, and schizophrenia. Predictive modeling for illness progression is further discussed, focusing on the role of risk prediction models and longitudinal studies. Key findings highlight how ML and DL can improve diagnostic accuracy and treatment outcomes while addressing methodological inconsistencies, data integration challenges, and ethical concerns. The study emphasizes the importance of building real-time monitoring systems for individualized treatment, enhancing data fusion techniques, and fostering interdisciplinary collaboration. Future research should focus on overcoming these obstacles to ensure the valuable and ethical application of ML and DL in mental health services., Comment: 20 pages, 3 figures, 3 tables

In recent years, the integration of advanced imaging techniques and deep learning methods has significantly advanced computer-aided diagnosis (CAD) systems for breast cancer detection and classification. Transformers, which have shown great promise in computer vision, are now being applied to medical image analysis. However, their application to histopathological images presents challenges due to the need for extensive manual annotations of whole-slide images (WSIs), as these models require large amounts of data to work effectively, which is costly and time-consuming. Furthermore, the quadratic computational cost of Vision Transformers (ViTs) is particularly prohibitive for large, high-resolution histopathological images, especially on edge devices with limited computational resources. In this study, we introduce a novel lightweight breast cancer classification approach using transformers that operates effectively without large datasets. By incorporating parallel processing pathways for Discrete Cosine Transform (DCT) Attention and MobileConv, we convert image data from the spatial domain to the frequency domain to utilize the benefits such as filtering out high frequencies in the image, which reduces computational cost. This demonstrates the potential of our approach to improve breast cancer classification in histopathological images, offering a more efficient solution with reduced reliance on extensive annotated datasets. Our proposed model achieves an accuracy of 96.00% $\pm$ 0.48% for binary classification and 87.85% $\pm$ 0.93% for multiclass classification, which is comparable to state-of-the-art models while significantly reducing computational costs. This demonstrates the potential of our approach to improve breast cancer classification in histopathological images, offering a more efficient solution with reduced reliance on extensive annotated datasets., Comment: 7 pages, 5 figures, Accepted for 2024 9th International Iranian Conference on Biomedical Engineering (ICBME)

Transformer-based language models have shown an excellent ability to effectively capture and utilize contextual information. Although various analysis techniques have been used to quantify and trace the contribution of single contextual cues to a target task such as subject-verb agreement or coreference resolution, scenarios in which multiple relevant cues are available in the context remain underexplored. In this paper, we investigate how language models handle gender agreement when multiple gender cue words are present, each capable of independently disambiguating a target gender pronoun. We analyze two widely used Transformer-based models: BERT, an encoder-based, and GPT-2, a decoder-based model. Our analysis employs two complementary approaches: context mixing analysis, which tracks information flow within the model, and a variant of activation patching, which measures the impact of cues on the model's prediction. We find that BERT tends to prioritize the first cue in the context to form both the target word representations and the model's prediction, while GPT-2 relies more on the final cue. Our findings reveal striking differences in how encoder-based and decoder-based models prioritize and use contextual information for their predictions., Comment: Accepted to BlackboxNLP 2024

Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity makes it difficult to track the extent to which such representations rely on textual and acoustic information, or to suppress the encoding of acoustic features that may pose privacy risks (e.g., gender or speaker identity) in critical, real-world applications. In this paper, we build upon the Information Bottleneck principle to propose a disentanglement framework that separates complex speech representations into two distinct components: one encoding content (i.e., what can be transcribed as text) and the other encoding acoustic features relevant to a given downstream task. We apply and evaluate our framework to emotion recognition and speaker identification downstream tasks, quantifying the contribution of textual and acoustic features at each model layer. Additionally, we explore the application of our disentanglement framework as an attribution method to identify the most salient speech frame representations from both the textual and acoustic perspectives.

Drones are increasingly used in fields like industry, medicine, research, disaster relief, defense, and security. Technical challenges, such as navigation in GPS-denied environments, hinder further adoption. Research in visual odometry is advancing, potentially solving GPS-free navigation issues. Traditional visual odometry methods use geometry-based pipelines which, while popular, often suffer from error accumulation and high computational demands. Recent studies utilizing deep neural networks (DNNs) have shown improved performance, addressing these drawbacks. Deep visual odometry typically employs convolutional neural networks (CNNs) and sequence modeling networks like recurrent neural networks (RNNs) to interpret scenes and deduce visual odometry from video sequences. This paper presents a novel real-time monocular visual odometry model for drones, using a deep neural architecture with a self-attention module. It estimates the ego-motion of a camera on a drone, using consecutive video frames. An inference utility processes the live video feed, employing deep learning to estimate the drone's trajectory. The architecture combines a CNN for image feature extraction and a long short-term memory (LSTM) network with a multi-head attention module for video sequence modeling. Tested on two visual odometry datasets, this model converged 48% faster than a previous RNN model and showed a 22% reduction in mean translational drift and a 12% improvement in mean translational absolute trajectory error, demonstrating enhanced robustness to noise., Comment: 22 Pages, 3 Tables, 9 Figures

Hydrodynamic interactions between swimming or flying organisms can lead to complex flows on the scale of the group. These emergent fluid dynamics are often more complex than a linear superposition of individual organism flows, especially at intermediate Reynolds numbers. This paper presents an approach to estimate the flow induced by multiple swimmer wakes in proximity using a semianalytical model that conserves mass and momentum in the aggregation. The key equations are derived analytically, while the implementation and solution of these equations are carried out numerically. This model was informed by and compared with empirical measurements of induced vertical migrations of brine shrimp, Artemia salina. The response of individual swimmers to ambient background flow and light intensity was evaluated. In addition, the time-resolved three-dimensional spatial configuration of the swimmers was measured using a recently developed laser scanning system. Numerical results using the model found that the induced flow at the front of the aggregation was insensitive to the presence of downstream swimmers, with the induced flow tending towards asymptotic beyond a threshold aggregation length. Closer swimmer spacing led to higher induced flow speeds, in some cases leading to model predictions of induced flow exceeding swimmer speeds required to maintain a stable spatial configuration. This result was reconciled by comparing two different models for the near-wake of each swimmer. The results demonstrate that aggregation-scale flows result from a complex, yet predictable interplay between individual organism wake structure and aggregation configuration and size.

We consider a mass-spring system immersed in an incompressible fluid flow governed by the Navier-Stokes equations subject to a prescribed time-periodic flow rate (and possibly external time-periodic body forces on the fluid and the mass). We show that, with no restriction on the period of the flow rate (and of the external forces), when the flow rate is "small", there exits a weak time-periodic solution to the coupled system. Under some more regularity and "smallness" conditions on the flow rate (and the external forces) we also show that these solutions are, indeed, strong solutions., Comment: 22 pages, 1 figure