Classifying Obsessive-Compulsive Disorder from Resting-State EEG Using Convolutional Neural Networks: A Pilot Study

Objective:Identifying obsessive-compulsive disorder (OCD) using brain data remains challenging. Resting-state electroencephalography (EEG) offers an affordable and noninvasive approach, but identifying predictive signals in EEG data has met with little success, even with the application of traditional machine learning methods. We explored whether convolutional neural networks (CNNs) applied to EEG time-frequency representations can distinguish individuals with OCD from healthy controls.Method:We collected resting-state EEG data from 20 unmedicated participants (10 with OCD, 10 healthy controls). Four-second EEG segments were transformed into time-frequency representations. We then trained a 2D CNN using a leave-one-subject-out cross-validation framework to perform subject-level classification and compared its performance to a more traditional support vector machine (SVM) approach. Next, using multimodal fusion, we examined whether adding clinical and demographic information improved classification.Results:The CNN classifier achieved high subject-level performance, distinguishing individuals with an accuracy of 85.0% and an area under the curve (AUC) of 0.88. This significantly outperformed the SVM baseline, which performed no better than chance (45.0% accuracy, AUC: 0.47). A subsequent multimodal analysis revealed that clinical and demographic variables did not contribute any additional independent information.Conclusion:CNNs applied to resting-state EEG show promise for identifying OCD, outperforming traditional machine learning methods. These findings highlight the potential of deep learning to uncover complex, diagnostically relevant patterns in neural data. While limited by sample size, this work supports further investigation into multimodal models for psychiatric classification, warranting replication in larger, more diverse samples.

Prostate Cancer Risk Prediction and Online Calculation Based on Machine Learning Algorithm

BackgroundSepsis is a life-threatening disease associated with a high mortality rate, emphasizing the need for the exploration of novel models to predict the prognosis of this patient population. This study compared the performance of traditional logistic regression and machine learning models in predicting adult sepsis mortality.ObjectiveTo develop an optimum model for predicting the mortality of adult sepsis patients based on comparing traditional logistic regression and machine learning methodology.MethodsRetrospective analysis was conducted on 606 adult sepsis inpatients at our medical center between January 2020 and December 2022, who were randomly divided into training and validation sets in a 7:3 ratio. Traditional logistic regression and machine learning methods were employed to assess the predictive ability of mortality in adult sepsis. Univariate analysis identified independent risk factors for the logistic regression model, while Least Absolute Shrinkage and Selection Operator (LASSO) regression facilitated variable shrinkage and selection for the machine learning model. Among various machine learning models, which included Bagged Tree, Boost Tree, Decision Tree, LightGBM, Naïve Bayes, Nearest Neighbors, Support Vector Machine (SVM), and Random Forest (RF), the one with the maximum area under the curve (AUC) was chosen for model construction. Model validation and comparison with the Sequential Organ Failure Assessment (SOFA) and the Acute Physiology and Chronic Health Evaluation (APACHE) scores were performed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA) curves in the validation set.ResultsUnivariate analysis was employed to assess 17 variables, namely gender, history of coronary heart disease (CHD), systolic pressure, white blood cell (WBC), neutrophil count (NEUT), lymphocyte count (LYMP), lactic acid, neutrophil-to-lymphocyte ratio (NLR), red blood cell distribution width (RDW), interleukin-6 (IL-6), prothrombin time (PT), international normalized ratio (INR), fibrinogen (FBI), D-dimer, aspartate aminotransferase (AST), total bilirubin (Tbil), and lung infection. Significant differences (p < 0.05) between the survival and non-survival groups were observed for these variables. Utilizing stepwise regression with the “backward” method, independent risk factors, including systolic pressure, lactic acid, NLR, RDW, IL-6, PT, and Tbil, were identified. These factors were then incorporated into a logistic regression model, chosen based on the minimum Akaike Information Criterion (AIC) value (98.65). Machine learning techniques were also applied, and the RF model, demonstrating the maximum Area Under the Curve (AUC) of 0.999, was selected. LASSO regression, employing the lambda.1SE criteria, identified systolic pressure, lactic acid, NEUT, RDW, IL6, INR, and Tbil as variables for constructing the RF model, validated through ten-fold cross-validation. For model validation and comparison with traditional logistic models, SOFA, and APACHE scoring.ConclusionBased on deep machine learning principles, the RF model demonstrates advantages over traditional logistic regression models in predicting adult sepsis prognosis. The RF model holds significant potential for clinical surveillance and interventions to enhance outcomes for sepsis patients.

Early detection of skin cancer, particularly melanoma, is crucial for improving patient outcomes and survival rates. Traditional diagnostic methods often require subjective interpretation by dermatologists, which can lead to inconsistent results. In recent years, machine learning algorithms, especially deep learning models such as Convolutional Neural Networks (CNNs), have shown promise in automating the analysis of medical images, enabling more accurate and efficient detection of skin cancer. This study investigates the performance of various machine learning models for skin cancer detection using the ISIC dataset, which consists of dermoscopic images. Six machine learning algorithms were evaluated: Logistic Regression, Decision Trees, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and CNN. The models were assessed based on their accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). The results demonstrated that CNN outperformed all other models in terms of accuracy, AUC, and F1-score, making it the most effective algorithm for skin cancer detection in this study. While traditional machine learning algorithms like Random Forest and SVM showed promising results, CNNs' ability to automatically extract relevant features from complex images provided a significant advantage. The findings suggest that CNNs are particularly well-suited for early-stage skin cancer detection, although challenges related to model interpretability and dataset variability remain. This study highlights the potential of machine learning in revolutionizing skin cancer diagnosis and paves the way for future research focused on improving model robustness and clinical integration.

Background: Pan-cancer analysis offers a holistic perspective on cancer, spanning 33 types and over 11,000 tumor samples from The Cancer Genome Atlas (TCGA). This analysis provides key insights into molecular features shared across cancers and aids in identifying immune subtypes, which are critical for developing personalized immunotherapies. Six distinct immune subtypes were identified in the immune landscape of cancer, offering a framework to explore tumor-immune interactions and their impact on prognosis. Methods: RNA sequencing (RNA-Seq) data were extracted from the TCGA Pan-Cancer Atlas, normalized, and processed for classification. Convolutional neural networks (CNNs), a subset of artificial intelligence, were employed to classify immune subtypes. The CNN model utilized convolutional layers with ReLU activation, dropout regularization, and batch normalization to enhance robustness and prevent overfitting. The dataset was split into training, validation, and testing subsets to evaluate model performance. Performance metrics, including accuracy and the area under the curve (AUC), were used to benchmark the CNN against traditional machine learning methods such as XGBoost, Random Forest, and TabNet. Results: The CNN model achieved an AUC of 0.993 and an overall accuracy of 98.85%, outperforming traditional classification methods. It demonstrated resilience to class imbalance and accurately classified underrepresented immune subtypes. The approach was validated against independent datasets, demonstrating consistent performance across diverse processing pipelines and normalization methods. Conclusions: This study highlights the utility of artificial intelligence, particularly CNNs, in accurately classifying immune subtypes across pan-cancer datasets. By leveraging RNA-Seq data, this approach offers a scalable and robust framework for pan-cancer analysis, paving the way for advancements in precision oncology and personalized immunotherapy. Future efforts will incorporate multi-omics data and validate these findings in clinical settings to enhance their translational potential. Citation Format: Minh Huu Nhat Le, Ha-Hieu Pham, Huy Quoc Nguyen, Hong Xuan Ong, Hien Quang Kha, Phat Ky Nguyen, Thanh-Huy Nguyen, Han Hong Huynh, Dang Nguyen, Thanh-Minh Nguyen, An Thuy Vo, Thuy Vu Minh Nguyen, Trung Minh Tu Tran, Lam Huu Phuc Nguyen, Nguyen Quoc Khanh Le. Convolutional neural network-based artificial intelligence for immune subtype classification in pan-cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_2):Abstract nr LB111.

<b><sc>Abstract.</sc></b> The realization of rapid non-destructive testing of moldy core in apple is of profound significance to protect consumer health and property safety. The moldy apple core discriminant model established by traditional machine learning methods has the problem of low accuracy. In this paper, the one-dimensional convolutional neural network (1D-CNN) based model for nondestructive detection of moldy apple core was proposed. Firstly, the apple transmission detection system with a spectral range of 200-1100nm independently built-in by the laboratory was used to obtain the visible/near-infrared transmission spectral information of the samples. The relationship between the topology of the convolutional neural network, the parameters of the convolutional kernel function (size, number) on the model is discussed separately. Principal component analysis (PCA) was utilized to reduce the dimensionality of the spectral data, and the first nine principal components that could represent 99.9% of the original spectral information were selected as the input data for the conventional model. Finally, the 1D-CNN was compared with traditional machine learning models partial least squares linear discriminant analysis (PLS-DA) models and support vector machine (SVM) nonlinear discriminant models, the discriminant accuracy of PCA-PLS-DA, PCA-SVM, and 1D-CNN models were 89.84%, 93.55%, and 98.39%, respectively. Compared with the traditional model, the proposed model based on1D-CNN has higher recognition accuracy. The results show that the deep learning method has significant research value and broad application potential in the field of fruit nondestructive testing.

Introduction: Neoadjuvant chemotherapy (NACT) is becoming standard of care for presurgical treatment of triple negative breast cancer (TNBC) patients. Achievement of pathological complete response (pCR) after NACT is associated with improved outcomes. There is currently an unmet need in development of imaging and clinical tools for prediction of pCR to NACT in TNBC. We investigated use of deep learning convolution neural networks (CNNs) for early prediction of pCR in a TNBC cohort on the basis of MRI acquired before the initiation and at the midpoint, after completion of four cycles of NACT (C4). Materials and Methods: Baseline and C4 MRIs of 112 TNBC patients were collected from an ongoing prospective clinical trial (NCT02276443). Four patients were excluded because they underwent different treatment for the second regimen. Among the 108 patients, 52 patients (48%) had pCR confirmed at surgery. Positive enhancement integral (PEI) derived from the early phases of DCE MRI, and apparent diffusion coefficients (ADC) derived from DWI MRI (b = 100 and 800 s/mm2), were used for our investigation. The images were aligned and the tumor regions were cropped from all images. All tumor patches were normalized between [0, 1], and were padded to form matrices of the same size of 192×192×64 for PEI, or the size of 192×192×16 for ADC. The CNN was constructed using stacked 3D convolution and MaxPooling layers. It consisted of up to four channels for the inputs (baseline and C4 PEI and ADC). Features extracted from each channel were concatenated and regressed for pCR prediction via three densely connected layers. Binary cross-entropy was used as the loss function for CNN training, and the loss was optimized using an Adam optimizer with the initial learning rate of 0.0001. Because of the currently limited sample size, four-fold cross-validation was used for CNN training and evaluation. The patients were divided into four groups, each group had 27 patients and the pCR:non-pCR ratio was controlled as 13:14. For each fold, one group was reserved as the independent testing group, and the other three groups were combined for network training and internal validation. Receiver operating characteristic (ROC) curve was plotted for each fold of testing, and area under the curve (AUC) was calculated. Final performance of the CNN was determined by averaging the AUCs of the four testing folds. Additionally, to test the prediction efficacy of each input, we trained the CNN under the same settings but used PEI or ADC only as input, and the results were compared. Results: The CNN trained with PEI only achieved an average AUC of 0.65 ± 0.09. The second CNN trained with ADC only achieved an average AUC of 0.72 ± 0.07. The third CNN trained with both PEI and ADC achieved an average AUC of 0.73 ± 0.06. Conclusion and Discussion: Using baseline and mid-treatment MRIs, deep learning CNN showed promising performance to predict pCR in the early course of NACT. The prediction AUC for the independent testing groups was largely improved by using ADC to train the network, indicating that ADC can have more critical information than PEI in assisting pCR prediction during the early course of NACT. Future work includes curation of a larger patient data for network training and evaluation to improve the prediction performance and further validate generalization of the network. We will also explore more advanced network structures, through which the prediction performance can be improved. Four-fold cross-validation AUCs of the network using different data as inputs.PEIADCPEI+ADCFold 10.570.640.66Fold 20.760.800.77Fold 30.660.700.68Fold 40.590.740.79Average0.65 ± 0.090.72 ± 0.070.73 ± 0.06 Citation Format: Zijian Zhou, Nabil A Elshafeey, David E Rauch, Beatriz E Adrada, Rosalind P Candelaria, Mary S Guirguis, Wei Yang, Medine Boge, Rania M Mohamed, Gary J Whitman, Deanna L Lane, Huong C Le-Petross, Jessica WT Leung, Lumarie Santiago, Marion E Scoggins, David A Spak, Miral M Patel, Frances Perez, Debu Tripathy, Vicente Valero, Clinton Yam, Stacy Moulder, Jason B White, Jong Bum Son, Mark D Pagel, Jingfei Ma. Deep learning for early prediction of neoadjuvant chemotherapy response in triple negative breast cancers [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P1-08-03.

Abstract: This review paper explores the development of a deep learning-based framework aimed at improving the security of cloud computing environments by detecting anomalous and malicious traffic. The paper emphasises the requirement of realtime detection in view of the growing issues presented by sophisticated threats including distributed denial of service (DDoS) assaults, botnet traffic, and data exfiltration. Combining recurrent neural networks (RNNs) with convolutional neural networks (CNNs), models and detects traffic anomalies rather effectively. Here we derive important characteristics obtained from a large cloud traffic dataset—such as packet size, source IP, and traffic patterns—which the model subsequently employs. The study contrasts the performance of the deep learning model with traditional machine learning techniques such decision trees and support vector machines (SVMs) using evaluation metrics including accuracy, precision, recall, F1-score, and area under the curve (AUC). The deep learning-based model reveals to be superior to more conventional techniques with enhanced accuracy and recall. It is versatile enough to match shifting attack patterns with minimal training and quite sensitive to known and novel anomalies. Moreover, our method excels in identifying sometimes ignored subtle and nuanced negative behaviours by conventional models. At last, the findings suggest that deep learning offers a scalable, adaptable, and effective solution to enhance negative traffic identification in cloud systems, therefore providing a strong means of managing evolving security challenges.

We aimed to assess the ability of deep learning (DL) and support vector machine (SVM) to detect a nonperfusion area (NPA) caused by retinal vein occlusion (RVO) with optical coherence tomography angiography (OCTA) images. The study included 322 OCTA images (normal: 148; NPA owing to RVO: 174 [128 branch RVO images and 46 central RVO images]). Training to construct the DL model using deep convolutional neural network (DNN) algorithms was provided using OCTA images. The SVM used a scikit-learn library with a radial basis function kernel. The area under the curve (AUC), sensitivity and specificity for detecting an NPA were examined. We compared the diagnostic ability (sensitivity, specificity and average required time) between the DNN, SVM and seven ophthalmologists. Heat maps were generated. With regard to the DNN, the mean AUC, sensitivity, specificity and average required time for distinguishing RVO OCTA images with an NPA from normal OCTA images were 0.986, 93.7%, 97.3% and 176.9 s, respectively. With regard to SVM, the mean AUC, sensitivity, and specificity were 0.880, 79.3%, and 81.1%, respectively. With regard to the seven ophthalmologists, the mean AUC, sensitivity, specificity and average required time were 0.962, 90.8%, 89.2%, and 700.6 s, respectively. The DNN focused on the foveal avascular zone and NPA in heat maps. The performance of the DNN was significantly better than that of SVM in all parameters (p < 0.01, all) and that of the ophthalmologists in AUC and specificity (p < 0.01, all). The combination of DL and OCTA images had high accuracy for the detection of an NPA, and it might be useful in clinical practice and retinal screening.

Recent advancements in text classification have focused on the application of machine learn-ing and deep learning techniques. Traditional methods such as Naive Bayes, Logistic Regression, and Support Vector Machines (SVM) have been widely utilized due to their efficiency and simplic-ity. However, the advent of deep learning has introduced more complex models like Artificial Neu-ral Networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN), which can automatically extract features and detect intricate patterns in textual data. Addi-tionally, transformer-based models such as BERT have set new benchmarks in text classification tasks. Despite their high accuracy, these models require substantial computational resources and are not always practical for every application. The ongoing research aims to balance accuracy and computational efficiency. Purpose of Research. The primary objective of this study is to review and compare various methods for automated text classification based on sentiment analysis. This research aims to evalu-ate the prediction accuracy of different models, including traditional machine learning algorithms and modern deep learning approaches, and to provide insights into their practical applications and limitations. Presentation of the Main Research Material. This study utilizes the “IMDB Dataset of 50K Movie Reviews” to train and test various text classification models. The dataset comprises movie reviews and their associated sentiment labels, either positive or negative. The research employs several preprocessing steps. For feature extraction, methods such as Bag-of-Words (BoW), TF-IDF (Term Frequency-Inverse Document Frequency), and Word2Vec are used. These features are then fed into various classifiers: Naive Bayes, Support Vector Machines (SVM), Logistic Regression, Deep Learning Models. Conclusions. The comparative analysis reveals that while traditional machine learning meth-ods like Naive Bayes, SVM and Logistic Regression are efficient and easy to implement, deep learn-ing models offer superior accuracy by capturing more complex patterns in the data. However, the computational demands of deep learning models, particularly transformers, limit their applicability in resource-constrained environments. Future research should focus on optimizing these models to balance accuracy and computational efficiency, making advanced text classification accessible for a broader range of applications. Recent advancements in text classification have focused on the application of machine learn-ing and deep learning techniques. Traditional methods such as Naive Bayes, Logistic Regression, and Support Vector Machines (SVM) have been widely utilized due to their efficiency and simplic-ity. However, the advent of deep learning has introduced more complex models like Artificial Neu-ral Networks (ANN), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN), which can automatically extract features and detect intricate patterns in textual data. Addi-tionally, transformer-based models such as BERT have set new benchmarks in text classification tasks. Despite their high accuracy, these models require substantial computational resources and are not always practical for every application. The ongoing research aims to balance accuracy and computational efficiency.

BackgroundThe accurate diagnosis of thyroid nodules represents a critical and frequently encountered challenge in clinical practice, necessitating enhanced precision in diagnostic methodologies. In this study, we investigate the predictive efficacy of distinguishing between benign and malignant thyroid nodules by employing traditional machine learning algorithms and a deep transfer learning model, aiming to advance the diagnostic paradigm in this field.MethodsIn this retrospective study, ITK-Snap software was utilized for image preprocessing and feature extraction from thyroid nodules. Feature screening and dimensionality reduction were conducted using the least absolute shrinkage and selection operator (LASSO) regression method. To identify the optimal model, both traditional machine learning and transfer learning approaches were employed, followed by model fusion using post-fusion techniques. The performance of the model was rigorously evaluated through the area under the curve (AUC), calibration curve analysis, and decision curve analysis (DCA).ResultsA total of 1134 images from 630 cases of thyroid nodules were included in this study, comprising 589 benign nodules and 545 malignant nodules. Through comparative analysis, the support vector machine (SVM), which demonstrated the best diagnostic performance among traditional machine learning models, and the Inception V3 convolutional neural network model, based on transfer learning, were selected for model construction. The SVM model achieved an AUC of 0.748 (95% CI: 0.684–0.811) for diagnosing malignant thyroid nodules, while the Inception V3 transfer learning model yielded an AUC of 0.763 (95% CI: 0.702–0.825). Following model fusion, the AUC improved to 0.783 (95% CI: 0.724–0.841). The difference in performance between the fusion model and the traditional machine learning model was statistically significant (p = 0.036). Decision curve analysis (DCA) further confirmed that the fusion model exhibits superior clinical utility, highlighting its potential for practical application in thyroid nodule diagnosis.ConclusionOur findings demonstrate that the fusion model, which integrates a convolutional neural network (CNN) with traditional machine learning and deep transfer learning techniques, can effectively differentiate between benign and malignant thyroid nodules through the analysis of ultrasound images. This model fusion approach significantly optimizes and enhances diagnostic performance, offering a robust and intelligent tool for the clinical detection of thyroid diseases.

This study aims to comprehensively analyze and classify the badminton players’ swing actions by combining the theoretical frameworks of quantum mechanics and machine learning. A badminton stroke recognition method based on Quantum Convolutional Neural Network (QCNN) is proposed. It is then compared with traditional Support Vector Machines (SVM) and Convolutional Neural Network (CNN). The comparison aims to assess the classification performance and robustness of each method. Firstly, this study collects the badminton players’ stroke action data using high-frame-rate cameras and inertial sensors to record posture information during different strokes. OpenPose is used for human posture estimation, and combined with sensor data, spatiotemporal features during the stroke are extracted. Next, during the data preprocessing stage, Gaussian filtering is applied to remove noise, followed by normalization and feature selection to ensure the quality of the model input data. Then, SVM, CNN, and QCNN models are trained to classify different stroke actions. To evaluate model performance, precision, recall, and F1-score are selected as metrics. Experiments with varying noise levels (low, medium, and high noise) are designed to test the models’ robustness. Finally, decision tree feature importance analysis is conducted to assess the contribution of different features to stroke action classification. Experimental results show that QCNN outperforms all other models in all classification tasks, with an F1-score of 0.860 for backhand intercept, significantly better than CNN (0.792) and SVM (0.753). In robustness tests under low, medium, and high noise environments, the classification precision of QCNN is 0.95, 0.92, and 0.89, respectively. This clearly surpasses both CNN and SVM. The results indicate that QCNN has strong adaptability to noisy data. Further feature analysis reveals that arm angle, twist angle, and step position are key factors affecting classification accuracy, with the highest contribution in the QCNN model. This study validates the superiority of QCNN in badminton action recognition and provides reliable methodological support for subsequent sports technique analysis.

Identification of adulterated milk powder based on convolutional neural network and laser-induced breakdown spectroscopy

Freezing of gait (FOG) is one of the most debilitating motor symptoms experienced by patients with Parkinson's disease (PD). FOG detection is possible using acceleration data from wearable sensors, and a convolutional neural network (CNN) is often used to determine the presence of FOG epochs. We compared the performance of a standard CNN for the detection of FOG with two more complex networks, which are well suited for time series data, the MiniRocket and the InceptionTime. We combined acceleration data of people with PD across four studies. The final data set was split into a training (80%) and hold-out test (20%) set. A fifth study was included as an unseen test set. The data were windowed (2 s) and five-fold cross-validation was applied. The CNN, MiniRocket, and InceptionTime models were evaluated using a receiver operating characteristic (ROC) curve and its area under the curve (AUC). Multiple sensor configurations were evaluated for the best model. The geometric mean was subsequently calculated to select the optimal threshold. The selected model and threshold were evaluated on the hold-out and unseen test set. A total of 70 participants (23.7 h, 9% FOG) were included in this study for training and testing, and in addition, 10 participants provided an unseen test set (2.4 h, 11% FOG). The CNN performed best (AUC = 0.86) in comparison to the InceptionTime (AUC = 0.82) and MiniRocket (AUC = 0.76) models. For the CNN, we found a similar performance for a seven-sensor configuration (lumbar, upper and lower legs and feet; AUC = 0.86), six-sensor configuration (upper and lower legs and feet; AUC = 0.87), and two-sensor configuration (lower legs; AUC = 0.86). The optimal threshold of 0.45 resulted in a sensitivity of 77% and a specificity of 58% for the hold-out set (AUC = 0.72), and a sensitivity of 85% and a specificity of 68% for the unseen test set (AUC = 0.90). We confirmed that deep learning can be used to detect FOG in a large, heterogeneous dataset. The CNN model outperformed more complex networks. This model could be employed in future personalized interventions, with the ultimate goal of using automated FOG detection to trigger real-time cues to alleviate FOG in daily life.

Traditional machine learning methods like GLCM and ABCD rules have long been employed for image classification tasks. However, they come with inherent limitations, primarily the need for manual feature extraction. This manual feature extraction process is time-consuming and relies on expert domain knowledge, making it challenging for non-experts to use effectively. Deep learning methods, specifically Convolutional Neural Networks (CNN), have revolutionized image classification by automating the feature extraction. CNNs can learn hierarchical features directly from the raw pixel values, eliminating the need for manual feature engineering. Despite their powerful capabilities, CNNs have limitations, mainly when working with small image datasets. They may overfit the data or struggle to generalize effectively. In light of these considerations, this study adopts a hybrid approach that leverages the strengths of both deep learning and traditional machine learning. CNNs are automatic feature extractors, allowing the model to capture meaningful image patterns. These extracted features are then fed into a Support Vector Machine (SVM) classifier, known for its efficiency and effectiveness in handling small datasets. The results of this study are encouraging, with an accuracy of 0.94 and an AUC score of 0.94. Notably, these metrics outperform Abbas' previous research by a significant margin, underscoring the effectiveness of the hybrid CNN-SVM approach. This research reinforces that SVM classifiers are well-suited for tasks involving limited image data, yielding improved classification accuracy and highlighting the potential for broader applications in image analysis.