A non-parametric statistical inference framework for Deep Learning in current neuroimaging

In the task of music genre classification, feature extraction and classifier modeling are the two key parts that directly affect the classification accuracy. In the traditional classification method, the feature extraction and classification processes are designed separately. First, the features are extracted manually from the original music signal, and then a reasonable classifier is selected to build a model and classify the extracted features. Although the traditional methods have achieved good results in many classification tasks, the feature extraction process is complex and difficult to achieve, and the features required for different classification tasks need to be specially designed, and the extracted features lack of universality. With the successful application and continuous development of deep learning models in other fields, more and more studies begin to use music spectra as the input of deep learning models to classify music genres. However, so far, the accuracy of existing classification methods based on deep learning is not ideal, so this paper mainly studies a classification method based on deep learning to improve the classification accuracy of music genre classification model. In this paper, a parallel structured deep attention classification model is proposed. By training BRNN, it can automatically learn music features from samples. The linear attention model calculates the attention probability distribution on this feature according to the learned features, and reassigns it to the feature representation. Finally, the classification is realized according to the eigenvectors with different weights. Besides the linear attention model with simple structure, a CNN attention model with stronger learning ability is also designed. In order to verify the feasibility and validity of the model, validation experiments were conducted on two standard datasets, GTZAN and Extended Ballroom. The experimental results show that the classification model based on deep parallel attention mechanism has good classification robustness, and the accuracy of classification based on BRNN and parallel CNN attention model reaches 92.7% on Extended Ballroom data set, which is better than the existing classification method based on deep learning. The validity and feasibility of the classification model are proved.

Simple SummaryBreast cancer is one of the leading causes of cancer death among women. Developing machine learning-based diagnosis models receives great attention from researchers and scientists using histopathology images. Deep learning (DL) algorithms automatically extract features from raw data through convolutional operations. The generalization of the DL models’ results relies on large datasets, although they eliminate the expert knowledge in the feature extraction stage. This work aimed to compare the performance of the features extracted via deep learning and a knowledge-based approach in breast cancer detection from histopathology images.Cancer develops when a single or a group of cells grows and spreads uncontrollably. Histopathology images are used in cancer diagnosis since they show tissue and cell structures under a microscope. Knowledge-based and deep learning-based computer-aided detection is an ongoing research field in cancer diagnosis using histopathology images. Feature extraction is vital in both approaches since the feature set is fed to a classifier and determines the performance. This paper evaluates three feature extraction methods and their performance in breast cancer diagnosis. Features are extracted by (1) a Convolutional Neural Network, (2) a transfer learning architecture VGG16, and (3) a knowledge-based system. The feature sets are tested by seven classifiers, including Neural Network (64 units), Random Forest, Multilayer Perceptron, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Narrow Neural Network (10 units) on the BreakHis 400× image dataset. The CNN achieved up to 85% for the Neural Network and Random Forest, the VGG16 method achieved up to 86% for the Neural Network, and the knowledge-based features achieved up to 98% for Neural Network, Random Forest, Multilayer Perceptron classifiers.

Retinal disorders, including diabetic retinopathy and macular degeneration due to aging, can lead to preventable blindness in diabetics. Vision loss caused by diseases that affect the retinal fundus cannot be reversed if not diagnosed and treated on time. This paper employs deep-learned feature extraction with ensemble learning models to improve the multi-disease classification of fundus images. This research presents a novel approach to the multi-classification of fundus images, utilizing deep-learned feature extraction techniques and ensemble learning to diagnose retinal disorders and diagnosing eye illnesses involving feature extraction, classification, and preprocessing of fundus images. The study involves analysis of deep learning and implementation of image processing. The ensemble learning classifiers have used retinal photos to increase the classification accuracy. The results demonstrate improved accuracy in diagnosing retinal disorders using DL feature extraction and ensemble learning models. The study achieved an overall accuracy of 87.2%, which is a significant improvement over the previous study. The deep learning models utilized in the study, including NASNetMobile, InceptionResNetV4, VGG16, and Xception, were effective in extracting relevant features from the Fundus images. The average F1-score for Extra Tree was 99%, while for Histogram Gradient Boosting and Random Forest, it was 98.8% and 98.4%, respectively. The results show that all three algorithms are suitable for the classification task. The combination of DenseNet feature extraction technique and RF, ET, and HG classifiers outperforms other techniques and classifiers. This indicates that using DenseNet for feature extraction can effectively enhance the performance of classifiers in the task of image classification.

This paper examines the performance of different machine and deep learning algorithms in classifying colon histological images using different feature extraction methods. The relationship between the feature extraction methods and the selected machine learning methods to improve the classification accuracy is analyzed. Widely used methods like local binary patterns, histograms of oriented gradients, Gabor filter and Dobeshi wavelets are investigated for feature extraction from colon histological images. The features extracted by histogram of oriented gradients and Gabor filter methods were used as a single joint feature vector. And popular machine learning methods such as Support vector machine, Decision trees, Random forest, k-nearest neighbors and Naive Bayesian method were used to classify the selected images. The paper also investigates ensemble methods using gradient bousting and voting classifier as examples. The authors also focus on the study of convolutional neural networks as they are one of the main deep learning methods at the moment. The classification methods selected for analysis are compared in terms of classification accuracy and time taken for training and recognition. All pre-defined and adjustable parameters of both feature extraction methods and classification methods were personally selected by the authors as a result of experimental studies, which were conducted using a software tool created in the Python programming language on a set of LC25000 histological images. The software created is easily customizable and can be used in the future to investigate classification methods on other datasets.

Deep learning has become widely used in image analysis. Transfer learning can make use of information from other datasets for the analysis of the chosen dataset. When there is a small number of images at hand, transfer learning using pre-trained models with coefficients already estimated from other datasets is recommended. This is in contrast to deep learning, where most model parameters are re-estimated. Deep transfer learning uses pre-trained models with fixed weight parameters in the lower layers; thus, deep learning can be viewed as a two-stage approach: (1) feature extraction from a lower neural network layer and (2) estimation of a neural network using the extracted features as inputs. Since deep transfer learning is feature extraction, we can extend the two-stage approach to a more general two-stage framework: (1) feature extraction using multiple methods and (2) machine learning methods taking extracted features as inputs. We evaluate the performance of methods with different Stage 1 and Stage 2 approaches in predicting the phenotype leaf numbers based on a multi-view plant imaging dataset. This paper contains an evaluation of different two-stage machine learning methods for multi-view image data in plant image phenotyping.

Artificial intelligence has revolutionized medical diagnosis, particularly for cancers. Acute myeloid leukemia (AML) diagnosis is a tedious protocol that is prone to human and machine errors. In several instances, it is difficult to make an accurate final decision even after careful examination by an experienced pathologist. However, computer-aided diagnosis (CAD) can help reduce the errors and time associated with AML diagnosis. White Blood Cells (WBC) detection is a critical step in AML diagnosis, and deep learning is considered a state-of-the-art approach for WBC detection. However, the accuracy of WBC detection is strongly associated with the quality of the extracted features used in training the pixel-wise classification models. CAD depends on studying the different patterns of changes associated with WBC counts and features. In this study, a new hybrid feature extraction method was developed using image processing and deep learning methods. The proposed method consists of two steps: 1) a region of interest (ROI) is extracted using the CMYK-moment localization method and 2) deep learning-based features are extracted using a CNN-based feature fusion method. Several classification algorithms are used to evaluate the significance of the extracted features. The proposed feature extraction method was evaluated using an external dataset and benchmarked against other feature extraction methods. The proposed method achieved excellent performance, generalization, and stability using all the classifiers, with overall classification accuracies of 97.57% and 96.41% using the primary and secondary datasets, respectively. This method has opened a new alternative to improve the detection of WBCs, which could lead to a better diagnosis of AML.

The hybrid feature extraction method for classification of adolescence idiopathic scoliosis using Evolving Spiking Neural Network

The design of pattern recognition-based myoelectric interfaces has been heavily explored and contested in the research literature. A considerable proportion of the performance of these interfaces has been linked to the quality of the feature extraction (FE) stage used to describe the underlying myoelectric signal. In this paper, we address two important factors of FE that have not been fully exploited; 1) Spatial focus - traditional FE methods focus mainly on the concatenation of features extracted from individual channels and 2) Temporal focus - available FE methods are cross-sectional in nature, largely ignoring the temporal information that may exist between feature windows. To overcome these limitations, several spatiotemporal FE methods have been proposed including hand-crafted and deep learning (DL) models, with the latter showing significant performance enhancements at the cost of increased computational burden. This paper tackles the aforementioned limitations by 1) proposing novel extensions to simple time-domain FE methods, including the waveform length, zero crossings and root mean square, that can capture the relation between any number of channels, and 2) leveraging the long short-term memory concepts from deep neural networks to build a recursive framework that overcomes the cross-sectional nature of traditional methods. The advantages offered by the proposed Recursive Multi-Signal Temporal Fusion (RMTF) features include improved performance, competing with state-of-the-art FE methods without the computational costs associated with leading DL models, and the simplicity of the concepts making them suitable for real-time implementations. Experiments on 65 intact-limbed and amputee subjects reveal an approximate average of 15% reduction in classification errors as compared to models built with other feature sets.

Background Respiratory diseases, including chronic obstructive pulmonary disease (COPD), asthma, and pneumonia, are leading causes of global morbidity and mortality. Early and accurate diagnosis remains challenging, especially in resource-limited settings. Automated respiratory sound classification, supported by machine learning and deep learning, has emerged as a non-invasive and cost-effective diagnostic alternative. This systematic review examines the role of multistage classification frameworks and ensemble learning techniques in improving the accuracy, robustness, and clinical applicability of respiratory sound analysis. Methods A comprehensive literature search was conducted across major scientific databases, focusing on studies employing multistage, machine learning, or ensemble-based approaches for respiratory sound classification. Eligible studies were screened based on predefined inclusion criteria related to pulmonary acoustics, feature extraction, signal processing, and classification models. Extracted data were synthesized to compare methodologies, feature engineering strategies, ensemble algorithms, model architectures, benchmark datasets (ICBHI 2017, PhysioNet), and performance metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. Results Findings indicate that multistage classification pipelines significantly enhance model reliability by integrating sequential preprocessing, feature extraction, dimensionality reduction, and classifier fusion. Ensemble learning methods—including bagging, boosting, random forests, stacking, and deep hybrid models—consistently outperform single-stage classifiers in handling noisy, non-stationary respiratory sounds and imbalanced datasets. Deep learning models such as convolutional neural networks and transformer-based architectures show superior performance when combined with advanced feature representations. However, challenges persist related to dataset variability, limited annotations, lack of standardization, and insufficient real-time or wearable-device compatibility. Explainable AI approaches are increasingly incorporated to support clinical interpretability. Conclusion Multistage and ensemble learning techniques demonstrate strong potential to improve automated respiratory sound classification and support early diagnosis of respiratory diseases. Despite promising results, advancements are needed in dataset standardization, multimodal integration, self-supervised learning, and IoT-enabled real-time monitoring. Future research should prioritize clinically interpretable, scalable, and regulation-ready AI systems to enable widespread deployment in respiratory healthcare.

The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM) was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.

An analysis of the power of the statistical methods used is very important in designing any research project or investigation. The major concepts regarding statistical power include the sample size of the study, the desired detectable effect size, the specified Type I error rate, and the sensitivities of statistical testing. The purpose of this article is then to explain the procedures a researcher should employ in order to make such statistical power explicit in the design of his or her study. Two empirical investigations are described in order to illustrate Type I and Type II error by examining sample size, statistical tests, measures, treatment effects, and variability within the subject groups of these two studies. Finally, some procedures for the consideration of statistical power in experimental design are suggested.

This article investigates whether higher classification accuracy can always be achieved by utilizing a pre-trained deep learning model as the feature extractor in the Bag-of-Deep-Visual-Words (BoDVW) classification model, as opposed to directly using the new classification layer of the pre-trained model for classification. Considering the multiple factors related to the feature extractor -such as model architecture, fine-tuning strategy, number of training samples, feature extraction method, and feature encoding method—we investigate these factors through experiments and then provide detailed answers to the question. In our experiments, we use five feature encoding methods: hard-voting, soft-voting, locally constrained linear coding, super vector coding, and fisher vector (FV). We also employ two popular feature extraction methods: one (denoted as Ext-DFs(CP)) uses a convolutional or non-global pooling layer, and another (denoted as Ext-DFs(FC)) uses a fully-connected or global pooling layer. Three pre-trained models—VGGNet-16, ResNext-50(32×4d), and Swin-B—are utilized as feature extractors. Experimental results on six datasets (15-Scenes, TF-Flowers, MIT Indoor-67, COVID-19 CXR, NWPU-RESISC45, and Caltech-101) reveal that compared to using the pre-trained model with only the new classification layer re-trained for classification, employing it as the feature extractor in the BoDVW model improves the accuracy in 35 out of 36 experiments when using FV. With Ext-DFs(CP), the accuracy increases by 0.13% to 8.43% (averaged at 3.11%), and with Ext-DFs(FC), it increases by 1.06% to 14.63% (averaged at 5.66%). Furthermore, when all layers of the pre-trained model are fine-tuned and used as the feature extractor, the results vary depending on the methods used. If FV and Ext-DFs(FC) are used, the accuracy increases by 0.21% to 5.65% (averaged at 1.58%) in 14 out of 18 experiments. Our results suggest that while using a pre-trained deep learning model as the feature extractor does not always improve classification accuracy, it holds great potential as an accuracy improvement technique.

This paper presents a comprehensive investigation into the classification of Sundanese news articles, focusing on the evaluation of various classification models and feature extraction methods. Using a dataset obtained from Sundanese news websites, this study conducts a systematic comparison of Naive Bayes and Logistic Regression classifiers combined with TF-IDF and Bag-of-Words feature extraction methods. The research process involves critical steps such as data preprocessing, model training, hyperparameter optimization, and performance assessment based on standard metrics, including accuracy, precision, recall, and F1-score. Results demonstrate high accuracy across all combinations, with the Logistic Regression model using Bag-of-Words feature extraction achieving the highest accuracy of 98.20%. Beyond model evaluation, the research delves into qualitative data analysis. Word clouds and TF-IDF weighting are employed to uncover prominent themes and topics within the news articles, highlighting recurring patterns in the Sundanese language. The study identifies key challenges, including the scarcity of annotated datasets for low-resource languages like Sundanese and the limitations of traditional models in capturing complex linguistic structures. Future opportunities are highlighted, such as leveraging deep learning models, including transformers, to enhance classification performance and address current limitations. Additionally, ensemble methods and domain-specific adaptations could further improve accuracy. Overall, this research contributes to advancing Sundanese language processing and provides a roadmap for future innovations in text classification and natural language processing applications.

Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.

Purpose: The clustering of pediatric patients based on their unlabeled brain magnetic resonance (MR) images reveal the latent features and group structures. It is an unbiased approach to finding image-based markers and risk-stratification for neurocognitive functions. Analyzing large sets of MR images is time-intensive and challenging due to the MR images' high dimensionality and complexity. The extraction of low-dimension informative feature space instead of high-dimension MR image is an effective and fast solution to cluster images accurately. We aimed at developing a feature extraction method using deep learning. Our long-term research goal is to develop a feature extraction model using deep learning to automatically and accurately identify brain regions in association with neurocognitive outcomes. Methods: We used 124 registered fractional anisotropy (FA)-mapped of diffusion tensor (DT) images of pediatric medulloblastoma patients obtained after tumor surgery and before radiation from the SJMB03 clinical trial. First, we developed a 3D convolutional auto-encoder model based on a deep neural network for the voxel-wise analysis of 3D images to produce low-dimensional features, which can reconstruct input images accurately. Then, we applied the density-based clustering model, named OPTICS (Ordering Points To Identify the Clustering Structure), to the features. To train two models, we used a soft and dynamic algorithm to simultaneously combine two loss functions. Distance measure and CAHL (Cluster Assignment Loss Hardening) are used to measure feature learning and clustering performance. Results: Our experiment demonstrates that the proposed models yield results comparable in quality to manual clustering. The model trained regarding using a sufficient dataset and reducing dynamic loss function. Our model can cluster patients precisely and extract representative hidden features of the images, which is much more time- and labor-efficient compared to manual clustering by experts. Conclusions: In this study, we focused on a new feature extraction method and clustering of brain images. Because of the deep neural networks' unique advantages in image processing, we considered a 3D convolutional auto-encoder for the feature extraction part and OPTICS algorithm for the clustering part of the model. This method is highly useful in neuroimaging and neurocognitive research. Citation Format: Hadi Hosseini, Cheng Cheng, John Glass, Gene Reddick, Amar Gajjar, Zhaohua Lu. Image clustering of brain tumor patients using a deep neural network [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-077.