Spectrogram Images Research Articles

A temporal–spectral fusion transformer with subject-specific adapter for enhancing RSVP-BCI decoding

The Rapid Serial Visual Presentation (RSVP)-based Brain–Computer Interface (BCI) is an efficient technology for target retrieval using electroencephalography (EEG) signals. The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subjects, which increases preparation time for BCI systems. Several studies introduce data from existing subjects to reduce the dependence of performance improvement on data from new subjects, but their optimization strategy based on adversarial learning with extensive data increases training time during the preparation procedure. Moreover, most previous methods only focus on the single-view information of EEG signals, but ignore the information from other views which may further improve performance. To enhance decoding performance while reducing preparation time, we propose a Temporal-Spectral fusion transformer with Subject-specific Adapter (TSformer-SA). Specifically, a cross-view interaction module is proposed to facilitate information transfer and extract common representations across two-view features extracted from EEG temporal signals and spectrogram images. Then, an attention-based fusion module fuses the features of two views to obtain comprehensive discriminative features for classification. Furthermore, a multi-view consistency loss is proposed to maximize the feature similarity between two views of the same EEG signal. Finally, we propose a subject-specific adapter to rapidly transfer the knowledge of the model trained on data from existing subjects to decode data from new subjects. Experimental results show that TSformer-SA significantly outperforms comparison methods and achieves outstanding performance with limited training data from new subjects. This facilitates efficient decoding and rapid deployment of BCI systems in practical use.

Fusing convolutional learning and attention-based Bi-LSTM networks for early Alzheimer’s diagnosis from EEG signals towards IoMT

The Internet of Medical Things (IoMT) is poised to play a pivotal role in future medical support systems, enabling pervasive health monitoring in smart cities. Alzheimer’s disease (AD) afflicts millions globally, and this paper explores the potential of electroencephalogram (EEG) data in addressing this challenge. We propose the Convolutional Learning Attention-Bidirectional Time-Aware Long-Short-Term Memory (CL-ATBiLSTM) model, a deep learning approach designed to classify different AD phases through EEG data analysis. The model utilizes Discrete Wavelet Transform (DWT) to decompose EEG data into distinct frequency bands, allowing for targeted analysis of AD-related brain activity patterns. Additionally, the data is segmented into smaller windows to handle the dynamic nature of EEG signals, and these segments are transformed into spectrogram images, visually depicting brain activity distribution over time and frequency. The CL-ATBiLSTM model incorporates convolutional layers to capture spatial features, attention mechanisms to emphasize crucial data, and BiLSTM networks to explore temporal relationships within the sequences. To optimize the model’s performance, Bayesian optimization is employed to fine-tune the hyperparameters of the ATBiLSTM network, enhancing its ability to generalize and accurately classify AD stages. Incorporating Bayesian learning ensures the most effective model configuration, improving sensitivity and specificity for identifying AD-related patterns. Our model extracts discriminative features from EEG data to differentiate between AD, Mild Cognitive Impairment (MCI), and healthy controls (CO), offering a more comprehensive approach than existing two-class detection algorithms. By including the MCI category, our method facilitates earlier identification and potentially more impactful therapy interventions. Achieving a 96.52% accuracy on Figshare datasets containing AD, MCI, and CO groups, our approach demonstrates strong potential for practical use, accelerating AD identification, enhancing patient care, and contributing to the development of targeted treatments for this debilitating condition.

Enhancing Situational Awareness with VAS-Compass Net for the Recognition of Directional Vehicle Alert Sounds

People with hearing impairments often face increased risks related to traffic accidents due to their reduced ability to perceive surrounding sounds. Given the cost and usage limitations of traditional hearing aids and cochlear implants, this study aims to develop a sound alert assistance system (SAAS) to enhance situational awareness and improve travel safety for people with hearing impairments. We proposed the VAS-Compass Net (Vehicle Alert Sound–Compass Net), which integrates three lightweight convolutional neural networks: EfficientNet-lite0, MobileNetV3-Small, and GhostNet. Through employing a fuzzy ranking ensemble technique, our proposed model can identify different categories of vehicle alert sounds and directions of sound sources on an edge computing device. The experimental dataset consisted of images derived from the sounds of approaching police cars, ambulances, fire trucks, and car horns from various directions. The audio signals were converted into spectrogram images and Mel-frequency cepstral coefficient images, and they were fused into a complete image using image stitching techniques. We successfully deployed our proposed model on a Raspberry Pi 5 microcomputer, paired with a customized smartwatch to realize an SAAS. Our experimental results demonstrated that VAS-Compass Net achieved an accuracy of 84.38% based on server-based computing and an accuracy of 83.01% based on edge computing. Our proposed SAAS has the potential to significantly enhance the situational awareness, alertness, and safety of people with hearing impairments on the road.

High performance method for COPD features extraction using complex network.

Objectives. The paper proposes a novel methodology for the classification of Chronic Obstructive Pulmonary Disease (COPD) utilizing respiratory sound attributes.Methods. The approach involves segmenting respiratory sounds into individual breaths and conducting extensive studies on this dataset. Spectral Transforms, various Wavelet Transforms are applied to capture distinct signal features. Complex Network is also employed to extract characteristic elements, generating novel representations of spectrogram data based on graph factors, including entropy, density, and position. The normalized and enriched data is then used to develop COPD classifiers using six machine learning algorithms, fine-tuning with appropriate training details and hyperparameter tuning.Results. Our results demonstrate robust performance, with ROC curves consistently exhibiting an Area Under the Curve (AUC) > 96% across different time-frequency transformations. Notably, the Random Forest algorithm achieves an AUC of 99.67%, outperforming other algorithms. Moreover, the Wavelet Daubechies 2 (Db2) consistently approaches 98% accuracy, particularly noteworthy in conjunction with the Naive Bayes algorithm.Conclusion. This study diagnosis patients through spectrogram images extracted from lung sounds. The application of Inverse Transforms, Complex Network, and Optimized Classification Algorithms yielded results beyond expectations. This methodology provides a promising approach for accurate COPD diagnosis, leveraging Machine Learning techniques applied to respiratory sound analysis.

A study on classifying BSR noise in automotive door trim using a deep learning method

In this paper, we demonstrated a deep learning model that can automatically classifies BSR(Buzz, Squeak, Rattle) noise in automotive door trim using convolutional neural networks. In the preprocessing process, sound features of door trim noises are extracted by using STFT(Short-time Fourier Transform) algorithm to obtain spectrogram images for each noises we obtained from experiment. To classify various noises of door trim, those image data are labeled with its root cause, then it is trained with deep convolutional neural network. Furthermore, t-SNE (t-Stochastic Neighbor Embedding) algorithm was used to visualize the effect of deep convolutional neural network we demonstrated. The classifier of the demonstrated method achieved with the accuracy of 96%.

Enhancing human computer interaction with coot optimization and deep learning for multi language identification

Human-Computer Interaction (HCI) is a multidisciplinary field focused on designing and utilizing computer technology, underlining the interaction interface between computers and humans. HCI aims to generate systems that allow consumers to relate to computers effectively, efficiently, and pleasantly. Multiple Spoken Language Identification (SLI) for HCI (MSLI for HCI) denotes the ability of a computer system to recognize and distinguish various spoken languages to enable more complete and handy interactions among consumers and technology. SLI utilizing deep learning (DL) involves using artificial neural networks (ANNs), a subset of DL models, to automatically detect and recognize the language spoken in an audio signal. DL techniques, particularly neural networks (NNs), have succeeded in various pattern detection tasks, including speech and language processing. This paper develops a novel Coot Optimizer Algorithm with a DL-Driven Multiple SLI and Detection (COADL-MSLID) technique for HCI applications. The COADL-MSLID approach aims to detect multiple spoken languages from the input audio regardless of gender, speaking style, and age. In the COADL-MSLID technique, the audio files are transformed into spectrogram images as a primary step. Besides, the COADL-MSLID technique employs the SqueezeNet model to produce feature vectors, and the COA is applied to the hyperparameter range of the SqueezeNet method. The COADL-MSLID technique exploits the SLID process’s convolutional autoencoder (CAE) model. To underline the importance of the COADL-MSLID technique, a series of experiments were conducted on the benchmark dataset. The experimentation validation of the COADL-MSLID technique exhibits a greater accuracy result of 98.33% over other techniques.

Advancing automobile dry clutch fault diagnosis through innovative imaging techniques and Vision transformer integration

The study investigates the significance of clutch condition monitoring in automotive transmissions to preempt mechanical failures, enhance efficiency, and mitigate risks to human safety and maintenance costs. It explores the integration of Vision Transformer (ViT) with imaging techniques, such as scalograms, spectrograms, polar plots, radar plots, and Hilbert-Huang transforms, to diagnose faults in dry friction clutches. By transforming vibration signals into image representations and utilizing ViT for fault classification, the study aims to identify the most effective imaging technique and optimal hyperparameters for accurate fault diagnosis. Experimental studies on a test rig with varying fault conditions demonstrate the effectiveness of ViT in diagnosing clutch faults when coupled with different image conversion techniques. The results highlight the potential of integrating spectrogram image processing with ViT, achieving a 100% accuracy in fault diagnosis for clutch systems, thus advancing the analysis of faults in clutch systems.

ResNet152: A Deep Learning Approach for Robust Spoof Detection in Speaker Verification Systems

In human life, we know that sound is the most important factor. From the normal perspective to the intelligent perspective, sound develops automated systems for various fields for several purposes. However, within contemporary conventional systems, there is significant abuse leading to the proliferation of forgery and other crimes, with sound often playing a central role. With the help of the latest technology such as deep learning, there comes a vast possibility of integrating with many systems for boosting the efficiency of existing systems. So, in this paper, we bring an effective classification of audio using ResNet152. The audio signals are converted to spectrogram images and are passed to a classifier for generating binary classification such as genuine or spoof. We also evaluated our model with existing methods such as VGG16, CNN, VGG19, and AlexNet under performance measures such as Accuracy, EER, and t-DCF in which the proposed model outperforms with 92.2% testing accuracy and 82.2% inference accuracy.

FPGA‐Based Implementation of Real‐Time Cardiologist‐Level Arrhythmia Detection and Classification in Electrocardiograms Using Novel Deep Learning

ABSTRACTCardiac arrhythmia refers to irregular heartbeats caused by anomalies in electrical transmission in the heart muscle, and it is an important threat to cardiovascular health. Conventional monitoring and diagnosis still depend on the laborious visual examination of electrocardiogram (ECG) devices, even though ECG signals are dynamic and complex. This paper discusses the need for an automated system to assist clinicians in efficiently recognizing arrhythmias. The existing machine‐learning (ML) algorithms have extensive training cycles and require manual feature selection; to eliminate this, we present a novel deep learning (DL) architecture. Our research introduces a novel approach to ECG classification by combining the vision transformer (ViT) and the capsule network (CapsNet) into a hybrid model named ViT‐Cap. We conduct necessary preprocessing operations, including noise removal and signal‐to‐image conversion using short‐time Fourier transform (SIFT) and continuous wavelet transform (CWT) algorithms, on both normal and abnormal ECG data obtained from the MIT‐BIH database. The proposed model intelligently focuses on crucial features by leveraging global and local attention to explore spectrogram and scalogram image data. Initially, the model divides the images into smaller patches and linearly embeds each patch. Features are then extracted using a transformer encoder, followed by classification using the capsule module with feature vectors from the ViT module. Comparisons with existing conventional models show that our proposed model outperforms the original ViT and CapsNet in terms of classification accuracy for both binary and multi‐class ECG classification. The experimental findings demonstrate an accuracy of 99% on both scalogram and spectrogram images. Comparative analysis with state‐of‐the‐art methodologies confirms the superiority of our framework. Additionally, we configure a field‐programmable gate array (FPGA) to implement the proposed model for real‐time arrhythmia classification, aiming to enhance user‐friendliness and speed. Despite numerous suggestions for high‐performance FPGA accelerators in the literature, our FPGA‐based accelerator utilizes optimization of loop parallelization, FP data, and multiply accumulation (MAC) unit. Our accelerator architecture achieves a 57% reduction in processing time and utilizes fewer resources compared to a floating‐point (FlP) design.

Lassi onk: a system framework to annotate and classify vehicular honk from road traffic.

Some recent studies highlight that vehicular traffic and honking contribute to more than 50% of noise pollution in urban or sub-urban areas in developing countries, including Indian cities. Frequent honking has an adverse effect on health and hampers road safety, the environment, etc. Therefore, recognizing the various vehicle honks and classifying the honk of different vehicles can provide good insights into environmental noise pollution. Moreover, classifying honks based on vehicle types allows for the inference of contextual information of a location, area, or traffic. So far, the researchers have done outdoor sound classification and honk detection, where vehicular honks are collected in a controlled environment or in theabsence of ambient noise. Such classification models fail to classify honk based on vehicle types. Therefore, it becomes imperative to design a system that can detect and classify honks of different types of vehicles to infer some contextual information. This paper presents a novel framework lassi onk that performs raw vehicular honk sensing, data labeling, and classifies the honk into three major groups, i.e., light-weight vehicles, medium-weight vehicles, and heavy-weight vehicles. Raw audio samples of different vehicular honking are collected based on spatio-temporal characteristics and converted them into spectrogram images. A deep learning-based multi-label autoencoder model (MAE) is proposed for automated labeling of the unlabeled data samples, which provides 97.64% accuracy in contrast to existing deep learning-based data labeling methods. Further, various pre-trained models, namely Inception V3, ResNet50, MobileNet, and ShuffleNet are used and proposed an Ensembled Transfer Learning model (EnTL) for vehicle honks classification and performed comparative analysis. Results reveal that EnTL exhibits the best performance compared to pre-trained models and achieves 96.72% accuracy in our dataset. In addition, context of a location is identified based on these classified honk signatures in a city.

Baby Cry Sound Detection: A Comparison of Mel Spectrogram Image on Convolutional Neural Network Models

Baby cries contain patterns that indicate their needs, such as pain, hunger, discomfort, colic, or fatigue. This study explores the use of Convolutional Neural Network (CNN) architectures for classifying baby cries using Mel Spectrogram images. The primary objective of this research is to compare the effectiveness of various CNN architectures such as VGG-16, VGG-19, LeNet-5, AlexNet, ResNet-50, and ResNet-152 in detecting baby needs based on their cries. The datasets used include the Donate-a-Cry Corpus and Dunstan Baby Language. The results show that AlexNet achieved the best performance with an accuracy of 84.78% on the Donate-a-Cry Corpus dataset and 72.73% on the Dunstan Baby Language dataset. Other models like ResNet-50 and LeNet-5 also demonstrated good performance although their computational efficiency varied, while VGG-16 and VGG-19 exhibited lower performance. This research provides significant contributions to the understanding and application of CNN models for baby cry classification. Practical implications include the development of baby cry detection applications that can assist parents and healthcare provide.

Prediction of Vascular Access Stenosis by Lightweight Convolutional Neural Network Using Blood Flow Sound Signals.

This research examines the application of non-invasive acoustic analysis for detecting obstructions in vascular access (fistulas) used by kidney dialysis patients. Obstructions in these fistulas can interrupt essential dialysis treatment. In this study, we utilized a condenser microphone to capture the blood flow sounds before and after angioplasty surgery, analyzing 3819 sound samples from 119 dialysis patients. These sound signals were transformed into spectrogram images to classify obstructed and unobstructed vascular accesses, that is fistula conditions before and after the angioplasty procedure. A novel lightweight two-dimension convolutional neural network (CNN) was developed and benchmarked against pretrained CNN models such as ResNet50 and VGG16. The proposed model achieved a prediction accuracy of 100%, surpassing the ResNet50 and VGG16 models, which recorded 99% and 95% accuracy, respectively. Additionally, the study highlighted the significantly smaller memory size of the proposed model (2.37 MB) compared to ResNet50 (91.3 MB) and VGG16 (57.9 MB), suggesting its suitability for edge computing environments. This study underscores the efficacy of diverse deep-learning approaches in the obstructed detection of dialysis fistulas, presenting a scalable solution that combines high accuracy with reduced computational demands.

A Combined CNN Architecture for Speech Emotion Recognition.

Emotion recognition through speech is a technique employed in various scenarios of Human-Computer Interaction (HCI). Existing approaches have achieved significant results; however, limitations persist, with the quantity and diversity of data being more notable when deep learning techniques are used. The lack of a standard in feature selection leads to continuous development and experimentation. Choosing and designing the appropriate network architecture constitutes another challenge. This study addresses the challenge of recognizing emotions in the human voice using deep learning techniques, proposing a comprehensive approach, and developing preprocessing and feature selection stages while constructing a dataset called EmoDSc as a result of combining several available databases. The synergy between spectral features and spectrogram images is investigated. Independently, the weighted accuracy obtained using only spectral features was 89%, while using only spectrogram images, the weighted accuracy reached 90%. These results, although surpassing previous research, highlight the strengths and limitations when operating in isolation. Based on this exploration, a neural network architecture composed of a CNN1D, a CNN2D, and an MLP that fuses spectral features and spectogram images is proposed. The model, supported by the unified dataset EmoDSc, demonstrates a remarkable accuracy of 96%.

EEGDepressionNet: A Novel Self Attention-Based Gated DenseNet With Hybrid Heuristic Adopted Mental Depression Detection Model Using EEG Signals.

World Health Organization (WHO) has identified depression as a significant contributor to global disability, creating a complex thread in both public and private health. Electroencephalogram (EEG) can accurately reveal the working condition of the human brain, and it is considered an effective tool for analyzing depression. However, manual depression detection using EEG signals is time-consuming and tedious. To address this, fully automatic depression identification models have been designed using EEG signals to assist clinicians. In this study, we propose a novel automated deep learning-based depression detection system using EEG signals. The required EEG signals are gathered from publicly available databases, and three sets of features are extracted from the original EEG signal. Firstly, spectrogram images are generated from the original EEG signal, and 3-dimensional Convolutional Neural Networks (3D-CNN) are employed to extract deep features. Secondly, 1D-CNN is utilized to extract deep features from the collected EEG signal. Thirdly, spectral features are extracted from the collected EEG signal. Following feature extraction, optimal weights are fused with the three sets of features. The selection of optimal features is carried out using the developed Chaotic Owl Invasive Weed Search Optimization (COIWSO) algorithm. Subsequently, the fused features undergo analysis using the Self-Attention-based Gated Densenet (SA-GDensenet) for depression detection. The parameters within the detection network are optimized with the assistance of the same COIWSO. Finally, implementation results are analyzed in comparison to existing detection models. The experimentation findings of the developed model show 96% of accuracy. Throughout the empirical result, the findings of the developed model show better performance than traditional approaches.

Deep transfer learning-based bird species classification using mel spectrogram images.

The classification of bird species is of significant importance in the field of ornithology, as it plays an important role in assessing and monitoring environmental dynamics, including habitat modifications, migratory behaviors, levels of pollution, and disease occurrences. Traditional methods of bird classification, such as visual identification, were time-intensive and required a high level of expertise. However, audio-based bird species classification is a promising approach that can be used to automate bird species identification. This study aims to establish an audio-based bird species classification system for 264 Eastern African bird species employing modified deep transfer learning. In particular, the pre-trained EfficientNet technique was utilized for the investigation. The study adapts the fine-tune model to learn the pertinent patterns from mel spectrogram images specific to this bird species classification task. The fine-tuned EfficientNet model combined with a type of Recurrent Neural Networks (RNNs) namely Gated Recurrent Unit (GRU) and Long short-term memory (LSTM). RNNs are employed to capture the temporal dependencies in audio signals, thereby enhancing bird species classification accuracy. The dataset utilized in this work contains nearly 17,000 bird sound recordings across a diverse range of species. The experiment was conducted with several combinations of EfficientNet and RNNs, and EfficientNet-B7 with GRU surpasses other experimental models with an accuracy of 84.03% and a macro-average precision score of 0.8342.

An explainable Artificial Intelligence software system for predicting diabetes

Implementing diabetes surveillance systems is paramount to mitigate the risk of incurring substantial medical expenses. Currently, blood glucose is measured by minimally invasive methods, which involve extracting a small blood sample and transmitting it to a blood glucose meter. This method is deemed discomforting for individuals who are undergoing it. The present study introduces an Explainable Artificial Intelligence (XAI) system, which aims to create an intelligible machine capable of explaining expected outcomes and decision models. To this end, we analyze abnormal glucose levels by utilizing Bi-directional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Network (CNN). In this regard, the glucose levels are acquired through the glucose oxidase (GOD) strips placed over the human body. Later, the signal data is converted to the spectrogram images, classified as low glucose, average glucose, and abnormal glucose levels. The labeled spectrogram images are then used to train the individualized monitoring model. The proposed XAI model to track real-time glucose levels uses the XAI-driven architecture in its feature processing. The model's effectiveness is evaluated by analyzing the performance of the proposed model and several evolutionary metrics used in the confusion matrix. The data revealed in the study demonstrate that the proposed model effectively identifies individuals with elevated glucose levels.

Enhancing the rationale of convolutional neural networks for glitch classification in gravitational wave detectors: a visual explanation

In the pursuit of detecting gravitational waves, ground-based interferometers (e.g. LIGO, Virgo, and KAGRA) face a significant challenge: achieving the extremely high sensitivity required to detect fluctuations at distances significantly smaller than the diameter of an atomic nucleus. Cutting-edge materials and innovative engineering techniques have been employed to enhance the stability and precision of the interferometer apparatus over the years. These efforts are crucial for reducing the noise that masks the subtle gravitational wave signals. Various sources of interference, such as seismic activity, thermal fluctuations, and other environmental factors, contribute to the total noise spectra characteristic of the detector. Therefore, addressing these sources is essential to enhance the interferometer apparatus’s stability and precision. Recent research has emphasised the importance of classifying non-stationary and non-Gaussian glitches, employing sophisticated algorithms and machine learning methods to distinguish genuine gravitational wave signals from instrumental artefacts. The time-frequency-amplitude representation of these transient disturbances exhibits a wide range of new shapes, variability, and features, reflecting the evolution of interferometer technology. In this study, we developed a convolutional neural network model to classify glitches using spectrogram images from the Gravity Spy O1 dataset. We employed score-class activation mapping and the uniform manifold approximation and projection algorithm to visualise and understand the classification decisions made by our model. We assessed the model’s validity and investigated the causes of misclassification from these results.

Spectro-ViT: A vision transformer model for GABA-edited MEGA-PRESS reconstruction using spectrograms

This study investigated the use of a Vision Transformer (ViT) for reconstructing GABA-edited Magnetic Resonance Spectroscopy (MRS) data from a reduced number of transients. Transients refer to the samples collected during an MRS acquisition by repeating the experiment to generate a signal of sufficient quality. Specifically, 80 transients were used instead of the typical 320 transients, aiming to reduce scan time. The 80 transients were pre-processed and converted into a spectrogram image representation using the Short-Time Fourier Transform (STFT). A pre-trained ViT, named Spectro-ViT, was fine-tuned and then tested using in-vivo GABA-edited MEGA-PRESS data. Its performance was compared against other pipelines in the literature using quantitative quality metrics and estimated metabolite concentration values, with the typical 320-transient scans serving as the reference for comparison. The Spectro-ViT model exhibited the best overall quality metrics among all other pipelines against which it was compared. The metabolite concentrations from Spectro-ViT's reconstructions for GABA+ achieved the best average R2 value of 0.67 and the best average Mean Absolute Percentage Error (MAPE) value of 9.68%, with no significant statistical differences found compared to the 320-transient reference. The code to reproduce this research is available at https://github.com/MICLab-Unicamp/Spectro-ViT

Deep learning and feature fusion-based lung sound recognition model to diagnoses the respiratory diseases

This paper proposed a novel approach for detecting lung sound disorders using deep learning feature fusion. The lung sound dataset are oversampled and converted into spectrogram images. Then, extracting deep features from CNN architectures, which are pre-trained on large-scale image datasets. These deep features capture rich representations of spectrogram images from the input signals, allowing for a comprehensive analysis of lung disorders. Next, a fusion technique is employed to combine the extracted features from multiple CNN architectures totlaly 8064 feature. This fusion process enhances the discriminative power of the features, facilitating more accurate and robust detection of lung disorders. To further improve the detection performance, an improved CNN Architecture is employed. To evaluate the effectiveness of the proposed approach, an experiments conducted on a large dataset of lung disorder signals. The results demonstrate that the deep feature fusion from different CNN architectures, combined with different CNN Layers, achieves superior performance in lung disorder detection. Compared to individual CNN architectures, the proposed approach achieves higher accuracy, sensitivity, and specificity, effectively reducing false negatives and false positives. The proposed model achieves 96.03% accuracy, 96.53% Sensitivity, 99.424% specificity, 96.52% precision, and 96.50% F1 Score when predicting lung diseases from sound files. This approach has the potential to assist healthcare professionals in the early detection and diagnosis of lung disorders, ultimately leading to improved patient outcomes and enhanced healthcare practices.

Lightweight deep learning model for automated STN localization using MER in Parkinson’s disease

Deep brain stimulation (DBS) of Subthalamic nucleus (STN), using a permanent electrode has emerged as an effective treatment for Parkinson’s disease patients. However, accurately localizing STN region during DBS surgery remains a challenging task. Microelectrode recording (MER) is used to identify STN by neurosurgeons. Nevertheless, manual interpretation of STN functional activity might prompt false alarms. Although the existing technology based on deep learning (DL) can outline the STN anatomical borders, it suffers from computational complexity and skewed findings. An end-to-end attention-based lightweight model with residual connections and soft thresholding is designed specifically for STN region detection. Scalogram and spectrogram images are generated from MER to mimic the observation of neurosurgeons and gather contextual information in a more intuitive manner. Proposed model exhibits a simplified architecture with only 15 layers, distinguishing it from previous DL models that tend to be more complex. Spatial attention helped to focus on relevant patterns within the data, while residual connections enhanced the gradient flow throughout the developed network. Soft thresholding offered noise reduction and robustness to signal variability. This approach eliminated the requirement for excessively deep layers and the necessity for separate feature extraction and classification stages by integrating them into a single pipeline. Our model identified STN with an accuracy of 97.42%. Proposed model outperformed 15 existing cutting-edge techniques. Our findings highlight the effectiveness of lightweight DL framework to achieve precise STN localization. The proposed method has significant potential in improving the efficiency of DBS surgery by reducing reliance on the neurosurgeon experience.