Inception V3 Model Research Articles

Deep learning based classification for alzheimer's disease detection using MRI images

Alzheimer's disease is a common type of dementia that can cause serious problems in cognitive functions and activities of daily living. Although there is no definitive cure for Alzheimer's disease today, early diagnosis is important to slow down the adverse conditions that may arise and to improve the quality of life. As a result of the development of artificial intelligence technologies and their consistent application in different fields, machine learning techniques have the potential to play an important role in the detection of Alzheimer's disease. In particular, deep learning-based methods, which have the ability to automatically extract patterns from complex patterns, are promising in this field. Recent studies show that the use of deep learning models for Alzheimer's detection on images is becoming widespread. In addition to contributing to the early diagnosis of the disease, these models also show potential in detecting different stages of the disease by analyzing the symptoms in magnetic resonance images. These developments enable the development of more effective treatment methods for patients. However, more studies are needed to evaluate the efficacy and safety of these technologies in clinical applications. In this study, classification studies were performed using MobileNetV2, InceptionV3, Xception, Vgg16 and Vgg19 models for the diagnosis of the disease on a publicly shared Alzheimer's dataset consisting of 6400 different samples and 4 different classes. An accuracy of 99.92% was calculated for the MobileNetV2 model. The performances of the models used in this study were compared with similar studies in the literature and their performances were reported in terms of different metrics. Among the five different models used, the highest accuracy value of 99.92% was obtained with MobileNetV2. It was concluded that the architectures used in the experimental studies produced generally better results than similar studies in the literature.

Tropical Cyclone Wind Direction Retrieval Based on Wind Streaks and Rain Bands in SAR Images

Tropical cyclones (TCs) are associated with severe weather phenomena, making accurate wind field retrieval crucial for TC monitoring. SAR’s high-resolution imaging capability provides detailed information for TC observation, and wind speed calculations require wind direction as prior information. Therefore, utilizing SAR images to retrieve TC wind fields is of significant importance. This study introduces a novel approach for retrieving wind direction from SAR images of TCs through the classification of TC sub-images. The method utilizes a transfer learning-based Inception V3 model to identify wind streaks (WSs) and rain bands in SAR images under TC conditions. For sub-images containing WSs, the Mexican-hat wavelet transform is applied, while for sub-images containing rain bands, an edge detection technique is used to locate the center of the TC eye and subsequently the tangent to the spiral rain bands is employed to determine the wind direction associated with the rain bands. Wind direction retrieval from 10 SAR TC images showed an RMSD of 19.52° and a correlation coefficient of 0.96 when compared with ECMWF and HRD observation wind directions, demonstrating satisfactory consistency and providing highly accurate TC wind directions. These results confirm the method’s potential applications in TC wind direction retrieval.

Performance Analysis of Transfer Learning Models for Identifying AI-Generated and Real Images

This study aims to analyze and compare the performance of three transfer learning methods, namely InceptionV3, VGG16, and DenseNet121, in detecting AI-generated and real images. The background of this research is the unknown performance of transfer learning methods for detecting AI-generated and real images. This study introduces innovation by conducting 54 experiments involving three types of transfer learning, three dataset split ratios (60:40, 70:30, and 80:20), three optimizers (Adam, SGD, and RMSprop), two numbers of epochs (20 and 50), and the addition of dense and flatten layers during fine tuning. Performance evaluation was conducted using binary cross entropy loss and confusion matrix. This research provides significant benefits in determining the most effective transfer learning model for detecting AI-generated and real images and offers practical guidance for further development. The results show that the InceptionV3 model with the Adam optimizer, an 80:20 split ratio, and 20 epochs achieved the highest accuracy of 84.26%, with a loss of 39.54%, precision of 81.33%, recall of 82.43%, and an F1-Score of 81.88%.

Atmospheric Gravity Wave Detection in Low-Light Images: A Transfer Learning Approach

Atmospheric gravity waves, as a key fluctuation in the atmosphere, have a significant impact on climate change and weather processes. Traditional observation methods rely on manually identifying and analyzing gravity wave stripe features from satellite images, resulting in a limited number of gravity wave events for parameter analysis and excitation mechanism studies, which restricts further related research. In this study, we focus on the gravity wave events in the South China Sea region and utilize a one-year low-light satellite dataset processed with wavelet transform noise reduction and light pixel replacement. Furthermore, transfer learning is employed to adapt the Inception V3 model to the classification task of a small-sample dataset, performing the automatic identification of gravity waves in low-light images. By employing sliding window cutting and data enhancement techniques, we further expand the dataset and enhance the generalization ability of the model. We compare the results of transfer learning detection based on the Inception V3 model with the YOLO v10 model, showing that the results of the Inception V3 model are greatly superior to those of the YOLO v10 model. The accuracy on the test dataset is 88.2%.

Empowering Brain Tumor Diagnosis through Explainable Deep Learning

Brain tumors are among the most lethal diseases, and early detection is crucial for improving patient outcomes. Currently, magnetic resonance imaging (MRI) is the most effective method for early brain tumor detection due to its superior imaging quality for soft tissues. However, manual analysis of brain MRI scans is prone to errors, largely influenced by the radiologists’ experience and fatigue. To address these challenges, computer-aided diagnosis (CAD) systems are more significant. These advanced computer vision techniques such as deep learning provide accurate predictions based on medical images, enhancing diagnostic precision and reliability. This paper presents a novel CAD framework for multi-class brain tumor classification. The framework employs six pre-trained deep learning models as the base and incorporates comprehensive data preprocessing and augmentation strategies to enhance computational efficiency. To address issues related to transparency and interpretability in deep learning models, Gradient-weighted Class Activation Mapping (Grad-CAM) is utilized to visualize the decision-making processes involved in tumor classification from MRI scans. Additionally, a user-friendly Brain Tumor Detection System has been developed using Streamlit, demonstrating its practical applicability in real-world settings and providing a valuable tool for clinicians. All simulation results are derived from a public benchmark dataset, showing that the proposed framework achieves state-of-the-art performance, with accuracy approaching 99% in ResNet-50, Xception, and InceptionV3 models.

Deep Learning for Automatic Knee Osteoarthritis Severity Grading and Classification.

Knee osteoarthritis (OA) is a prevalent condition that significantly impacts the quality of life, often leading to the need for knee replacement surgery. Accurate and timely identification of knee degeneration is crucial for effective treatment and management. Traditional methods of diagnosing OA rely heavily on radiological assessments, which can be time-consuming and subjective. This study aims to address these challenges by developing a deep learning-based method to predict the likelihood of knee replacement and the Kellgren-Lawrence (KL) grade of knee OA from X-ray images. We employed the Osteoarthritis Initiative (OAI) dataset and utilized a transfer learning approach with the Inception V3 architecture to enhance the accuracy of OA detection. Our approach involved training 14 different models-Xception, VGG16, VGG19, ResNet50, ResNet101, ResNet152, ResNet50V2, ResNet101V2, ResNet152V2, Inception V3, Inception, ResNetV2, DenseNet121, DenseNet169, DenseNet201-and comparing their performance. The study incorporated pixel ratio computation and picture pre-processing, alongside a decision tree model for prediction. Our experiments revealed that the Inception V3 model achieved the highest training accuracy of 91% and testing accuracy of 67%, with notable performance in both training and validation phases. This model effectively identified the presence and severity of OA, correlating with the Kellgren-Lawrence scale and facilitating the assessment of knee replacement needs. By integrating advanced deep learning techniques with radiological diagnostics, our methodology supports radiologists in making more accurate and prompt decisions regarding knee degeneration. The Inception V3 model stands out as the optimal choice for knee X-ray analysis, contributing to more efficient and timely healthcare delivery for patients with knee osteoarthritis.

Advanced Fingerprint Alteration Detection: A Comparative Analysis of Real and Synthetic Modifications Using InceptionV3 on the SOCOFing Dataset

This study investigates the efficacy of fingerprint alteration detection using Advanced Deep Learning techniques, specifically focusing on real and synthetically altered fingerprint images. Utilizing the Sokoto Coventry Fingerprint Dataset (SOCOFing), which comprises over 55,000 fingerprint images from 600 African subjects, we employed the Google InceptionV3 model to classify real and altered images under varying degrees of alteration. Our experimental results demonstrate a robust performance of the model, achieving an accuracy of 91.04% for detecting alterations with easy alteration parameter settings, 98.07% for medium alteration parameter settings, and 96.47% for hard alteration parameter settings. The findings highlight the potential of deep learning frameworks like InceptionV3 in enhancing the reliability of biometric systems by effectively distinguishing between real and altered fingerprints.

Enhancing natural disaster image classification: an ensemble learning approach with inception and CNN models

The core problem of this research is the rapid and accurate classification of natural disasters, which is essential for effective response and mitigation strategies. Existing detection methods are often time-consuming and costly. The purpose of this research is to introduce an innovative approach to the multi-class classification of natural disasters using image data from a Kaggle dataset encompassing Cyclone, Wildfire, Flood, and Earthquake incidents. The method used is an ensemble learning model that combines the strengths of the InceptionV3 model and a custom Convolutional Neural Network (CNN). The result of this study is an ensemble model that achieves a commendable accuracy of 92.79%, surpassing individual models and demonstrating the efficacy of combining diverse features extracted by InceptionV3 and CNN architectures. Additionally, a standalone CNN model is implemented, achieving an accuracy of 88.76%. The research concludes that the ensemble model’s superior performance makes it a valuable tool for the multi-class classification of natural disaster images.

Utilizing deep learning models in an intelligent spiral drawing classification system for Parkinson's disease classification.

Parkinson's disease (PD) is a neurodegenerative illness that impairs normal human movement. The primary cause of PD is the deficiency of dopamine in the human brain. PD also leads to several other challenges, including insomnia, eating disturbances, excessive sleepiness, fluctuations in blood pressure, sexual dysfunction, and other issues. The suggested system is an extremely promising technological strategy that may help medical professionals provide accurate and unbiased disease diagnoses. This is accomplished by utilizing significant and unique traits taken from spiral drawings connected to Parkinson's disease. While PD cannot be cured, early administration of drugs may significantly improve the condition of a patient with PD. An expeditious and accurate clinical classification of PD ensures that efficacious therapeutic interventions can commence promptly, potentially impeding the advancement of the disease and enhancing the quality of life for both patients and their caregivers. Transfer learning models have been applied to diagnose PD by analyzing important and distinctive characteristics extracted from hand-drawn spirals. The studies were carried out in conjunction with a comparison analysis employing 102 spiral drawings. This work enhances current research by analyzing the effectiveness of transfer learning models, including VGG19, InceptionV3, ResNet50v2, and DenseNet169, for identifying PD using hand-drawn spirals. Transfer machine learning models demonstrate highly encouraging outcomes in providing a precise and reliable classification of PD. Actual results demonstrate that the InceptionV3 model achieved a high accuracy of 89% when learning from spiral drawing images and had a superior receiver operating characteristic (ROC) curve value of 95%. The comparison results suggest that PD identification using these models is currently at the forefront of PD research. The dataset will be enlarged, transfer learning strategies will be investigated, and the system's integration into a comprehensive Parkinson's monitoring and evaluation platform will be looked into as future research areas. The results of this study could lead to a better quality of life for Parkinson's sufferers, individualized treatment, and an early classification.

Deep learning with ensemble approach for early pile fire detection using aerial images

Wildfires rank among the world’s most devastating and expensive natural disasters, destroying vast forest resources and endangering lives. Traditional firefighting methods, reliant on ground crew inspections, have notable limitations and pose significant risks to firefighters. Consequently, drone-based aerial imaging technologies have emerged as a highly sought-after solution for combating wildfires. Recently, there has been growing research interest in autonomous wildfire detection using drone-captured images and deep-learning algorithms. This paper introduces a novel deep-learning-based method, distinct in its integration of infrared thermal, white, and night vision imaging to enhance early pile fire detection, thereby addressing the limitations of existing methods. The study evaluates the performance of machine learning algorithms such as random forest (RF) and support vector machines (SVM), alongside pre-trained deep learning models including AlexNet, Inception ResNetV2, InceptionV3, VGG16, and ResNet50V2 on thermal-hot, green-hot, and white-green-hot color images. The proposed approach, particularly the ensemble of ResNet50V2 and InceptionV3 models, achieved over 97% accuracy and over 99% precision in early pile fire detection on the FLAME dataset. Among the tested models, ResNet50V2 excelled with the thermal-fusion palette, InceptionV3 with the white-hot and green-hot fusion palettes, and VGG16 with a voting classifier on the normal spectrum palette dataset. Future work aims to enhance the detection and localization of pile fires to aid firefighters in rescue operations.

Promoting Sustainable Development of Coal Mines: CNN Model Optimization for Identification of Microseismic Signals Induced by Hydraulic Fracturing in Coal Seams

Borehole hydraulic fracturing in coal seams can prevent dynamic coal mine disasters and promote the sustainability of the mining industry, and microseismic signal recognition is a prerequisite and foundation for microseismic monitoring technology that evaluates the effectiveness of hydraulic fracturing. This study constructed ultra-lightweight CNN models specifically designed to identify microseismic waveforms induced by borehole hydraulic fracturing in coal seams, namely Ul-Inception28, Ul-ResNet12, Ul-MobileNet17, and Ul-TripleConv8. The three best-performing models were selected to create both a probability averaging ensemble CNN model and a voting ensemble CNN model. Additionally, an automatic threshold adjustment strategy for CNN identification was introduced. The relationships between feature map entropy, training data volume, and model performance were also analyzed. The results indicated that our in-house models surpassed the performance of the InceptionV3, ResNet50, and MobileNetV3 models from the TensorFlow Keras library. Notably, the voting ensemble CNN model achieved an improvement of at least 0.0452 in the F1 score compared to individual models. The automatic threshold adjustment strategy enhanced the identification threshold’s precision to 26 decimal places. However, a continuous zero-entropy value in the feature maps of various channels was found to detract from the model’s generalization performance. Moreover, the expanded training dataset, derived from thousands of waveforms, proved more compatible with CNN models comprising hundreds of thousands of parameters. The findings of this research significantly contribute to the prevention of dynamic coal mine disasters, potentially reducing casualties, economic losses, and promoting the sustainable progress of the coal mining industry.

RetNet30: A Novel Stacked Convolution Neural Network Model for Automated Retinal Disease Diagnosis

ABSTRACTAutomated diagnosis of retinal diseases holds significant promise in enhancing healthcare efficiency and patient outcomes. However, existing methods often lack the accuracy and efficiency required for timely disease detection. To address this gap, we introduce RetNet30, a novel stacked convolutional neural network (CNN) designed to revolutionize automated retinal disease diagnosis. RetNet30 combines a custom‐built 30‐layer CNN with a fine‐tuned Inception V3 model, integrating these sub‐models through logistic regression to achieve superior classification performance. Extensive evaluations on retinal image datasets such as DRIVE, STARE, CHASE_DB1, and HRF demonstrate significant improvements in accuracy, sensitivity, specificity, and area under the ROC curve (AUROC) when compared to conventional approaches. By leveraging advanced deep learning architectures, RetNet30 not only enhances diagnostic precision but also generalizes effectively across diverse datasets, establishing a new benchmark in retinal disease classification. This novel approach offers a highly efficient and reliable solution for early disease detection and patient management, addressing the limitations of manual examination methods. Through rigorous quantitative and qualitative assessments, our proposed method demonstrates its potential to significantly impact medical image analysis and improve healthcare outcomes. RetNet30 marks a major step forward in automated retinal disease diagnosis, showcasing the future of AI‐driven advancements in ophthalmology.

Enhancing Diabetic Retinopathy Detection Accuracy with Convolutional Neural Networks

Diabetic Retinopathy (DR) has emerged as a major illness that makes diabetic patients blind worldwide. If this disease is not treated promptly, it can progress to permanent blindness. Having the ability to identify people with DR rapidly will be beneficial for both medical professionals and researchers. In the current situation, manually analysing each minute nerve cell from fundus pictures is extremely time-consuming for clinicians. This paper not only concentrates on diabetic retinopathy detection but also on the analysis of DR progression in the given fundus image, which is performed with the help of data augmentation, Convolutional Neural network and transfer learning algorithms. Deep learning models DenseNet121, DenseNet169, DenseNet201, Resnet50, and InceptionV3 models are used on the Diabetic Retinopathy dataset in Kaggle and APTOS. Five DR stages, which are no DR, mild DR, moderate DR, severe DR and proliferate DR, are handled in this work. The fundus images of the eye are used as input to the model. The most robust model in the evaluations, DenseNet201, achieved an accuracy of approximately 98.56% for the APTOS dataset and 97.14% for the Diabetic Retinopathy dataset in Kaggle. These results were obtained using 5-fold stratified cross-validation and hyperparameter tuning, for detecting retinopathy and assessing its stage.

Deep Learning Based Offline Handwritten Signature Recognition

In our digitalized world, the need for reliable authentication methods is steadily increasing. Biometric authentication methods are divided into two main categories: physiological and behavioral. While physiological biometrics include features such as face, iris, and fingerprint, behavioral biometrics encompass dynamics such as gait, speech, and signature. Most of these methods require specialized equipment, whereas signatures can be easily obtained without additional tools, making them ideal for verifying the legality of documents. Although manual signature recognition is effective, it is resource-intensive, slow, and susceptible to errors. With advancements in technology, the need to automate the signature recognition process to enhance accuracy and efficiency has become increasingly important. Based on this need, in this study, five different DL techniques (GoogLeNet, MobileNet-V3 Large, Inception-V3, ResNet50 and EfficientNet-B0) are used to classify signature images with detailed analyses. DL methods have outperformed traditional techniques by leveraging the power of CNNs to automatically learn and extract complex features from signature data. The dataset used consists of a total of 12,600 images belonging to 420 individuals, each contributing 30 original signatures. The dataset is divided into training, validation, and test sets in different proportions to analyze classification performance. The pre-trained DL models were fine-tuned to optimize their parameters for the signature dataset. The results demonstrate that DL models achieve high accuracy in signature classification, with the GoogLeNet and Inception-V3 models reaching an accuracy of 98.77% at a 20% test rate. The study also highlights the impact of different test rates on model performance.

Computer-Aided Diagnosis of Diabetic Retinopathy Lesions Based on Knowledge Distillation in Fundus Images

At present, the early diagnosis of diabetic retinopathy (DR), a possible complication of diabetes due to elevated glucose concentrations in the blood, is usually performed by specialists using a manual inspection of high-resolution fundus images based on lesion screening, leading to problems such as high work-intensity and accessibility only in specialized health centers. To support the diagnosis of DR, we propose a deep learning-based (DL) DR lesion classification method through a knowledge distillation (KD) strategy. First, we use the pre-trained DL architecture, Inception-v3, as a teacher model to distill the dataset. Then, a student model, also using the Inception-v3 model, is trained on the distilled dataset to match the performance of the teacher model. In addition, a new combination of Kullback–Leibler (KL) divergence and categorical cross-entropy (CCE) loss is used to measure the difference between the teacher and student models. This combined metric encourages the student model to mimic the predictions of the teacher model. Finally, the trained student model is evaluated on a validation dataset to assess its performance and compare it with both the teacher model and another competitive DL model. Experiments are conducted on the two datasets, corresponding to an imbalanced and a balanced dataset. Two baseline models (Inception-v3 and YOLOv8) are evaluated for reference, obtaining a maximum training accuracy of 66.75% and 90.90%, respectively, and a maximum validation accuracy of 35.94% and 81.52%, both for the imbalanced dataset. On the other hand, the proposed DR classification model achieves an average training accuracy of 99.01% and an average validation accuracy of 97.30%, overcoming the baseline models and other state-of-the-art works. Experimental results show that the proposed model achieves competitive results in DR lesion detection and classification tasks, assisting in the early diagnosis of diabetic retinopathy.

A novel CatractNetDetect deep learning model for effective cataract classification through data fusion of fundus images

Cataracts are common eye disorders characterized by the clouding of the lens, preventing light from passing through and impairing vision. Various factors, including changes in the lens’s hydration or alterations in its proteins, may contribute to their development. Regular eye examinations conducted by an ophthalmologist or optometrist are imperative for detecting cataracts and other ocular conditions early on. Manual checks by caregivers pose several problems, including subjectivity, human error, and a lack of expertise. Biomedical fusion involves combining or linking various characteristics specific to certain diseases from different medical imaging resources. The primary objectives of this approach in disease classification are to reduce the error rate and increase the number of retrieved features. The aim of this study is to evaluate the outcomes associated with fusing visual features related to left and right eye cataract characteristics. Additionally, we investigate the impact of limited variability in deep learning models, specifically in the classification of cataract fundus versus normal fundus images. To address this issue, this study introduces CataractNetDetect, an innovative multi-label deep learning classification system that fuses feature representations from pairs of fundus images (e.g., left and right eyes) for the automatic diagnosis of various ocular disorders. Our focus is on achieving improved performance by stacking discriminative deep feature representations to combine two fundus images into a unified feature representation. Several deep learning architectures are utilized as feature descriptors, including ResNet-50, DenseNet-121, and Inception-V3, enhancing the resilience and quality of representations. Fine-tuning of these DL architectures is conducted using the ImageNet dataset, followed by an integrated stacking approach combining ResNet-50, DenseNet-121, and Inception-V3 models. The model is trained on the publicly available ODIR-5k dataset, which includes 5000 left/right eye images depicting eight different ocular conditions, ranging from healthy states to uncommon ailments such as cataracts, glaucoma, age-related macular degeneration (AMD), diabetes, hypertension, and myopia abnormalities. Moreover, extensive preprocessing of the images is performed, including data augmentation, noise reduction, contrast enhancement, scaling, and circular border cropping. The CataractNetDetect system demonstrates F1-scores, AUC, and maximum validation scores of 98.0%, 97.9%, and 100%, respectively. This ensemble-based model distinguishes itself by surpassing the performance of conventional established methodologies, including ResNet-50, DenseNet-121, and Inception-V3, thereby underscoring its efficacy in diagnostic applications.

Automated Analysis of Tooth Anatomy and Pathological Conditions from Orthopantomogram using Deep Neural Networks

This research project aims to automate the identification, labeling, and counting of teeth, as well as the classification of abnormalities and detection of caries in dental X-rays, specifically orthopantomograms (OPGs). It involves several deep neural networks and learning algorithms. The first module uses semantic segmentation with a U-net model to create masks for tooth detection, which are then refined with the YOLOv3 detector, achieving 80% accuracy. Canonical correlation analysis (CCA) helps find tooth midpoints and count the total number of teeth. The second module classifies abnormalities and pathologies using transfer learning with the Inceptionv3 model, yielding moderate accuracy. Caries detection is performed with thresholding and segmentation. The third module detects three treated pathologies—root canal treatments, crowns, and implants—using Faster RCNN and Inceptionv3, showing fair accuracy. Overall, the automated approach demonstrates promising results for enhancing X-ray image interpretation and diagnosing oral diseases.

Improved inception-V3 model for apple leaf disease classification

Apple, a nutrient-rich fruit belonging to the genus Malus, is recognized for its fiber, vitamins, and antioxidants, giving health benefits such as improved digestion and reduced cardiovascular disease risk. In Indonesia, the soil and climate create favorable conditions for apple cultivation. However, it is essential to prioritize the health of the plant. Biotic factors, such as fungal infections like apple scabs and pests, alongside abiotic factors like temperature and soil moisture, impact the health of apple plants. Computer vision, specifically convolution neural network (CNN) inception-V3, proves effective in aiding farmers in identifying these diseases. The output layer in inception-V3 is essential, generating predictions based on input data. For this reason, in this paper, we add an output layer in inception-V3 architecture to increase the accuracy of apple leaf disease classification. The added output layers are dense, dropout, and batch normalization. Adding a dense layer after flattening typically consolidates the extracted features into a more compact representation. Dropout can help prevent overfitting by randomly deactivating some units during training. Batch normalization helps normalize activations across batches, speeding up training and providing stability to the model. Test results show that the proposed method produced an accuracy of 99.27% and can increase accuracy by 1.85% compared to inception-V3. These enhancements showcase the potential of leveraging computer vision for precise disease diagnosis in apple crops.

Water Sustainability Enhancement with UAV and AIoT: An Integrated Technology for Water Quality and Flood Hazard Monitoring using the Internet of Drones

Globally, there are challenges in minimizing the effects of water pollution and global warming everywhere. We want to apply a sensor network connected to an Esp32 and Tensorflow lite integrated system to map the flood conditions for drone-based water surface waste collection. Finally, a GSM sim 800L Module is incorporated to notify the user about the monitored conditions, such as trash level and other data. An ultrasonic sensor is utilized to detect the water level. The outcome shows a high chance of tracking water levels and monitoring floods. This innovative technology allows users to receive warnings and be warned remotely. The Inception-v3 model on clean and unclean water images obtained 97% accuracy on testing USING Inception-v3, and using the proposed circuit diagram, a prototype is developed for possible deployment in such water resource region for possible operation and application is presented in the paper.

Identifying Acute Aortic Syndrome and Thoracic Aortic Aneurysm from Chest Radiography in the Emergency Department Using Convolutional Neural Network Models.

(1) Background: Identifying acute aortic syndrome (AAS) and thoracic aortic aneurysm (TAA) in busy emergency departments (EDs) is crucial due to their life-threatening nature, necessitating timely and accurate diagnosis. (2) Methods: This retrospective case-control study was conducted in the ED of three hospitals. Adult patients visiting the ED between 1 January 2010 and 1 January 2020 with a chief complaint of chest or back pain were enrolled in the study. The collected chest radiography (CXRs) data were divided into training (80%) and testing (20%) datasets. The training dataset was trained by four different convolutional neural network (CNN) models. (3) Results: A total of 1625 patients were enrolled in this study. The InceptionV3 model achieved the highest F1 score of 0.76. (4) Conclusions: Analysis of CXRs using a CNN-based model provides a novel tool for clinicians to interpret ED patients with chest pain and suspected AAS and TAA. The integration of such imaging tools into ED could be considered in the future to enhance the diagnostic workflow for clinically fatal diseases.