Inception V3 Model Research Articles

VGG and InceptionV3 model based on CIFAR data contrast analysis

VGG and InceptionV3 model based on CIFAR data contrast analysis

Comparative Analysis of Image Classification Methods on Cat Breeds and Behavior using Machine Learning Techniques

This research investigates image classification techniques applied to two distinct datasets related to cats. The primary focus is on addressing the problem of accurately classifying cat breeds and cat behavior. This research focuses on the comparative analysis of both deep learning and machine learning techniques. The techniques are categorized as use of Transfer learning on deep learning models, Transfer learning on machine learning algorithms, and Teachable machine pre-trained model. Transfer learning has gained popularity as one of the employed techniques, in inception V3 for classifying images. It requires re-utilizing an existing model, for a new model by applying a small-scale dataset to pace up training and enhance overall performance. Five different methodologies are explored: Convolutional Neural Networks using Google Inception-V3 model, Convolutional Neural Networks on top of Google Inception-V3 model with K-fold cross-validation, Random Forest on Inception V3 features, Support Vector Machine on Inception V3 features, and Teachable Machine model. The study aims to compare the performance of these methodologies in terms of accuracy, F1 score, and ROC-AUC score. The research results show that each approach has levels of effectiveness with various algorithms and models showing accuracy and F1 scores in classifying both cat breeds and behaviors. These findings offer information, on image classification, in datasets related to cats helping to improve the precision of identifying cat breeds and behaviors.

Ensemble transfer learning using MaizeSet: A dataset for weed and maize crop recognition at different growth stages

Maize holds significant importance as a staple food source globally. Increasing maize yield requires the effective removal of weeds from maize fields, as they pose a detrimental threat to the growth of maize plants. In recent years, there has been a drive towards Precision Agriculture (PA), involving the integration of farming methods with artificial intelligence and advanced automation techniques. In the realm of PA, deep learning techniques present a promising solution for addressing the complex challenge of classifying maize plants and weeds. In this work, a deep learning method based on transfer learning and ensemble techniques is developed. The proposed method is implementable on any number of existing CNN models irrespective of their architecture and complexity. The developed ensemble model is trained and tested on our custom-built dataset, namely MaizeSet, comprising 3330 images of maize plants and weeds under varying environmental conditions. The performance of the ensemble model is compared against individual pre-trained VGG16 and InceptionV3 models using two experiments: the identification of weeds and maize plants, and the identification of the various vegetative growth stages of maize plants. VGG16 attained an accuracy of 83% in Experiment 1 and 71% in Experiment 2, while InceptionV3 showcased improved performance, boasting an accuracy of 98% in Experiment 1 and 81% in Experiment 2. With the proposed ensemble approach, VGG16 when combined with InceptionV3, achieved an accuracy of 90% for Experiment 1 and 80% for Experiment 2. The findings demonstrate that integrating a sub-optimal pre-defined classifier, specifically VGG16, with a more proficient model like InceptionV3, yields enhanced performance across various analytical metrics. This underscores the efficacy of ensemble techniques in the context of maize classification and analogous applications within the agricultural domain.

COVID-19 Identification System from X-Ray Images of Chest using Deep Neural Network with Transfer Learning

Recently, the impact of COVID-19 has significantly diminished; however, it has not been completely eradicated. There are still instances where individuals are experiencing suffering due to this life-threatening virus which has a significant impact on health care as well as lifestyles throughout the world. So, early discovery is important to controlling case extension and the death rate. The RT-PCR is known as the true leading diagnosis test; nevertheless, the expense and result times of these tests are long, thus additional quick and accessible diagnostic techniques are required. However, most countries are suffering due to limited testing resources and kits. The unavailability of testing resources, kits, and a rising amount of regular occurrences, caused us to develop a model on Deep Learning which may benefit radiologists as well as doctors for detecting COVID-19 instances using images of chest X-rays. For developing a representation of modality-specific features, a convolutions neural network and a variety of ImageNet pre-trained models are trained and evaluated at the patient level by using different available CXR datasets. We choose 5000 images in total from the dataset collected from Kaggle where we kept 4000 images in case of training and validation, and the remaining 1000 in case of testing. We use four Pre-train Deep CNN Models which are very popular for image calcification. VVG16, VGG19, InceptionV3, and Resnet50 CNN Models we choose to analyze the performance and find the best one among them. In our testing, we get 88.5% testing accuracy on ResNet and 95.10% on InceptionV3 models while VGG19 gives 90.22% accuracy and VGG16 gives the highest 96.10% accuracy. To increase performance accuracy, Transfer Learning knowledge is transmitted and fine-tuned. After applying Transfer Learning in the modified VGG16 we got an accuracy of 97% which is clearly an improvement over the previous VGG16 model. GUB JOURNAL OF SCIENCE AND ENGINEERING, Vol 10(1), 2023 P 53-67

Ensemble approach of transfer learning and vision transformer leveraging explainable AI for disease diagnosis: An advancement towards smart healthcare 5.0

Smart healthcare has advanced the medical industry with the integration of data-driven approaches. Artificial intelligence and machine learning provided remarkable progress, but there is a lack of transparency and interpretability in such applications. To overcome such limitations, explainable AI (EXAI) provided a promising result. This paper applied the EXAI for disease diagnosis in the advancement of smart healthcare. The paper combined the approach of transfer learning, vision transformer, and explainable AI and designed an ensemble approach for prediction of disease and its severity. The result is evaluated on a dataset of Alzheimer's disease. The result analysis compared the performance of transfer learning models with the ensemble model of transfer learning and vision transformer. For training, InceptionV3, VGG19, Resnet50, and Densenet121 transfer learning models were selected for ensembling with vision transformer. The result compares the performance of two models: a transfer learning (TL) model and an ensemble transfer learning (Ensemble TL) model combined with vision transformer (ViT) on ADNI dataset. For the TL model, the accuracy is 58 %, precision is 52 %, recall is 42 %, and the F1-score is 44 %. Whereas, the Ensemble TL model with ViT shows significantly improved performance i.e., 96 % of accuracy, 94 % of precision, 90 % of recall and 92 % of F1-score on ADNI dataset. This shows the efficacy of the ensemble model over transfer learning models.

Classification of physiotherapy exercise of stroke patients using deep transfer learning and fuzzy logic: A novel approach

According to the world health organization (WHO), stroke stands as a significant contributor to mortality and adult disability, causing motor function impairment, paralysis, and intense back pain. In aiding stroke patients' mobility recovery, physiotherapists employ diverse therapeutic techniques. This research introduces an automated method for identifying distinct therapeutic exercises performed by stroke patients during their rehabilitation process. For detecting rehabilitation exercises, leveraging pre-trained neural networks like GoogLeNet, InceptionV3, ResNet-101, DenseNet-201, Xception, InceptionResNetV2, and DarkNet-53, all potent models trained on extensive datasets. The proposed models were trained on a dataset of 2250 diverse RGB images to classify eight rehabilitation exercises: Elbow Extension, Knee Flexion, Neck Exercise, Planter Flexion of Foot, Trunk Extension, Trunk Flexion, Wrist Extension, and Wrist Flexion. The resulting average validation accuracies are as follows: InceptionV3 (97.4%), Xception (97.3%), ResNet101 (97.3%), DarkNet53 (96.7%), GoogLeNet (95.9%), DenseNet201 (94.3%), and InceptionResNetV2 (93.4%). Fuzzy EDAS is then employed to rank the models. This ranking suggests that the inception-v3 model has high rank for most of the classes and is highly recommended for physiotherapy exercises classification.

A comparative study of deep learning models and classification algorithms for chemical compound identification and Tox21 prediction

Chemical compound classification, toxicity prediction, and environmental risk assessments are critically important in various applications within the field of chemistry. Deep learning models provide highly effective tools for extracting features from complex large datasets and performing classification tasks. Four different deep learning models, namely ResNet50V2, VGG19, InceptionV3, and MobileNetV2, have been compared with the random forest (RF) and k-nearest neighbors (KNN) algorithms. The results obtained from experiments conducted using QRCODE images of the Tox21SMILES dataset demonstrate the effectiveness of deep learning models for classifying chemical compounds and showcase the performance of different classification algorithms. The findings of the study thoroughly evaluate the performance of deep learning models and classification algorithms in the task of chemical classification. While ResNet50V2 and VGG19 models achieve high accuracy and precision, InceptionV3 and MobileNetV2 models provide more balanced results. Additionally, in terms of classification algorithms, the k-nearest neighbors (KNN) algorithm generally outperforms the Random Forest (RF) algorithm. Although the RF algorithm achieves good accuracy, the KNN algorithm proves to be more effective in terms of sensitivity and F1 score. These results emphasize the factors to consider when choosing which deep learning model or classification algorithm to use in chemical classification tasks. In conclusion, this study presents a comprehensive analysis comparing the performance of deep learning models and classification algorithms in chemical classification tasks. The selection of the most suitable model and algorithm for a specific task supports achieving better results in the classification of chemical compounds and related applications.

Transfer learning: classifying balanced and imbalanced fungus images using inceptionV3

Identifying the genus of fungi is known to facilitate the discovery of new medicinal compounds. Currently, the isolation and identification process is predominantly conducted in the laboratory using molecular samples. However, mastering this process requires specific skills, making it a challenging task. Apart from that, the rapid and highly accurate identification of fungus microbes remains a persistent challenge. Here, we employ a deep learning technique to classify fungus images for both balanced and imbalanced datasets. This research used transfer learning to classify fungus from the genera Aspergillus, Cladosporium, and Fusarium using InceptionV3 model. Two experiments were run using the balanced dataset and the imbalanced dataset, respectively. Thorough experiments were conducted and model effectiveness was evaluated with standard metrics such as accuracy, precision, recall, and F1 score. Using the trendline of deviation knew the optimum result of the epoch in each experimental model. The evaluation results show that both experiments have good accuracy, precision, recall, and F1 score. A range of epochs in the accuracy and loss trendline curve can be found through the experiment with the balanced, even though the imbalanced dataset experiment could not. However, the validation results are still quite accurate even close to the balanced dataset accuracy.

Transfer learning: classifying balanced and imbalanced fungus images using inceptionV3

Identifying the genus of fungi is known to facilitate the discovery of new medicinal compounds. Currently, the isolation and identification process is predominantly conducted in the laboratory using molecular samples. However, mastering this process requires specific skills, making it a challenging task. Apart from that, the rapid and highly accurate identification of fungus microbes remains a persistent challenge. Here, we employ a deep learning technique to classify fungus images for both balanced and imbalanced datasets. This research used transfer learning to classify fungus from the genera Aspergillus, Cladosporium, and Fusarium using InceptionV3 model. Two experiments were run using the balanced dataset and the imbalanced dataset, respectively. Thorough experiments were conducted and model effectiveness was evaluated with standard metrics such as accuracy, precision, recall, and F1 score. Using the trendline of deviation knew the optimum result of the epoch in each experimental model. The evaluation results show that both experiments have good accuracy, precision, recall, and F1 score. A range of epochs in the accuracy and loss trendline curve can be found through the experiment with the balanced, even though the imbalanced dataset experiment could not. However, the validation results are still quite accurate even close to the balanced dataset accuracy.

Classification of Plant Disease using a State-of-the Art Deep learning Algorithm on a Tesla GPU

This paper proposes a study conducted on various techniques that can be employed for the early detection of plant diseases. With exponential growth in the global population, there is a dire need for the detection and prevention of various types of plant diseases such as Mosaic virus in Solanum Lycopersicon (tomato), bacterial spot in Fragaria Ananassa (strawberry), late and early blight in Solanum Tuberosum (potato), huanglongbing in Citrus sinensis (orange), and Isariopsis leaf spot in Vitis vinifera (grapes). These diseases generally lead to lower yields and hence less profit. In the last two decades, there has been rapid development in the fields of image processing and deep learning. Various models of deep learning can be used for plant disease detection. The main objective is that as soon as plant leaf disease appears, there should be one device to monitor the symptoms and detect them over a large field with as much accuracy as possible. This study compares the deep learning models Resnet, MobileNet, and inceptionV3 that are implemented on a large dataset taken from the Kaggle repository. We implemented the models using Google Colaboratory tools, which provide us with Python’s Jupyter notebook that runs on the Google cloud server. The GPU “Tesla T4” and CPU “Intel Xenon” were used during training, validation, and testing respectively. The training and validation accuracy of the InceptionV3 model was 98.78% and 93.94%, respectively. MobileNet classified various plant diseases with training and validation accuracies of 99.57% and 97.31. Similarly, for ResNet, the training accuracy was found to be around 99.62% and the validation accuracy was 97.16%. We hope that this work will provide a helpful resource for other researchers working in the field of agriculture to detect various types of crop diseases. Future work and some challenges still faced are also discussed in this study.

Classification of Plant Disease using a State-of-the Art Deep learning Algorithm on a Tesla GPU

This paper proposes a study conducted on various techniques that can be employed for the early detection of plant diseases. With exponential growth in the global population, there is a dire need for the detection and prevention of various types of plant diseases such as Mosaic virus in Solanum Lycopersicon (tomato), bacterial spot in Fragaria Ananassa (strawberry), late and early blight in Solanum Tuberosum (potato), huanglongbing in Citrus sinensis (orange), and Isariopsis leaf spot in Vitis vinifera (grapes). These diseases generally lead to lower yields and hence less profit. In the last two decades, there has been rapid development in the fields of image processing and deep learning. Various models of deep learning can be used for plant disease detection. The main objective is that as soon as plant leaf disease appears, there should be one device to monitor the symptoms and detect them over a large field with as much accuracy as possible. This study compares the deep learning models Resnet, MobileNet, and inceptionV3 that are implemented on a large dataset taken from the Kaggle repository. We implemented the models using Google Colaboratory tools, which provide us with Python’s Jupyter notebook that runs on the Google cloud server. The GPU “Tesla T4” and CPU “Intel Xenon” were used during training, validation, and testing respectively. The training and validation accuracy of the InceptionV3 model was 98.78% and 93.94%, respectively. MobileNet classified various plant diseases with training and validation accuracies of 99.57% and 97.31. Similarly, for ResNet, the training accuracy was found to be around 99.62% and the validation accuracy was 97.16%. We hope that this work will provide a helpful resource for other researchers working in the field of agriculture to detect various types of crop diseases. Future work and some challenges still faced are also discussed in this study.

INCEPTION SH: A NEW CNN MODEL BASED ON INCEPTION MODULE FOR CLASSIFYING SCENE IMAGES

In this study, a light-weight model with an optimum block structure that can be used in autonomous unmanned aerial vehicles (UAVs) was designed. The Inception SH model, which was developed based on the Inception V3 model, was compared on "Intel Image Dataset", a publicly available dataset in the literature. As a result of the comparison, values of 0.882, 0.883, 0.882 and 0.882 were obtained for the accuracy, precision, recall, and F1 score metrics for the Inception V3 model, respectively. In the Inception SH model, values of 0.958, 0.957, 0.974 and 0.967 were obtained for accuracy, precision, recall and F1 score metrics, respectively. As can be seen from these values, the proposed Inception SH model offers higher performance values than the underlying Inception V3 model. The Inception SH model was compared with different models in the literature using the same data set and was superior in accuracy, precision, recall and F1 score metrics compared to the compared models. According to the results obtained, it is predicted that the Inception SH model can be used as a lightweight model in various IoT devices, considering the popularity of autonomous UAVs.

Deep learning-based rock type identification using drill vibration frequency spectrum images

ABSTRACT Rock identification is crucial in the mining industry. It provides useful information regarding the geological characteristics of an area, which can be applied to drill-bit selection, optimisation of drilling parameters, and selection of blasting materials. Common methods for this purpose are core drilling and core analysis. Although these methods are dependable, they lag and are expensive. Recent studies have highlighted a need for an automatic and reliable system for rock identification during the drilling process. Hence, this study establishes a new and reliable method for automatically identifying rocks using drill vibrations and deep-learning algorithms. The sample rocks were drilled using a rotary percussion rock drifter with accelerometers mounted on a guide cell. The fast Fourier transform algorithm was used to convert the drill vibration signals into frequency spectrum images, which were subsequently used as inputs to the deep-learning algorithms. Study rock-identification models were constructed using three convolutional neural networks: ResNet-50, Inception-v3, and DenseNet-201. The classification accuracy was used as a metric to assess the performance of the models. Subsequently, a Gradient-weighted Class Activation Mapping (Grad-CAM) algorithm was used to identify noteworthy frequencies responsible for rock predictions. With the help of deep-learning algorithms, drill vibrations could be used to identify different rocks during the drilling process. The Inception-v3 model exhibited optimum performance, with a classification accuracy of 99.0%. Grad-CAM indicated that frequencies from 0 to 8000 Hz are important for rock classification. This approach offers an automatic, low-latency, and dependable rock-identification system.

An improved method for diagnosis of Parkinson’s disease using deep learning models enhanced with metaheuristic algorithm

Parkinson's disease (PD) is challenging for clinicians to accurately diagnose in the early stages. Quantitative measures of brain health can be obtained safely and non-invasively using medical imaging techniques like magnetic resonance imaging (MRI) and single photon emission computed tomography (SPECT). For accurate diagnosis of PD, powerful machine learning and deep learning models as well as the effectiveness of medical imaging tools for assessing neurological health are required. This study proposes four deep learning models with a hybrid model for the early detection of PD. For the simulation study, two standard datasets are chosen. Further to improve the performance of the models, grey wolf optimization (GWO) is used to automatically fine-tune the hyperparameters of the models. The GWO-VGG16, GWO-DenseNet, GWO-DenseNet + LSTM, GWO-InceptionV3 and GWO-VGG16 + InceptionV3 are applied to the T1,T2-weighted and SPECT DaTscan datasets. All the models performed well and obtained near or above 99% accuracy. The highest accuracy of 99.94% and AUC of 99.99% is achieved by the hybrid model (GWO-VGG16 + InceptionV3) for T1,T2-weighted dataset and 100% accuracy and 99.92% AUC is recorded for GWO-VGG16 + InceptionV3 models using SPECT DaTscan dataset.

Efficient Method of Road Outlier Recognition Using Deep Learning Coupled with Data Augmentation Approach

In recent years, Closed-circuit Television (CCTV) cameras have been playing a vital role in the surveillance of both public and private areas. The primary objective of surveillance is to monitor human behavior and road conditions. In the real-world situation, detecting, and recognizing abnormal activities poses significant challenges due to the densely crowded environment and the complex nature of transportation systems. These factors make it difficult to automatically identify various anomalies that occur while traveling, leading to emergencies, and endangering human life and property. In response to these challenges, contemporary Road Outlier Recognition Surveillance Systems (RORSS) have been deployed to monitor and mitigate abnormalities on streets, highways, and roads. This research specifically investigated conventional as well as human-centered road anomalies encompassing snatching, accidents, fighting, and car fires. The proposed Real-time Road Outlier Recognition methodology is formulated as a classification task, involving the analysis and processing of real-time CCTV videos. The proposed study investigated different types of Convolutional Neural Network (CNN) pre-trained models with the Data Augmentation (DA) approach to address the frame variance problem in real-time videos. Furthermore, we introduced a benchmark real-world Road Outlier Dataset (ROD) containing roads, streets, and highways videos and images that presented different road anomalies performed by vehicles and humans. Experimentation using different pre-trained CNN models i.e., VGG19, InceptionV3, ResNet50, and DenseNet201 with a data augmentation approach has been performed on the ROD dataset. The experimental results demonstrated that the InceptionV3 model performed best with the augmentation approach as compared to other deep learning models that achieved the best accuracy of 98.80% in recognizing road anomalies

Automated interpretation of retinal vein occlusion based on fundus fluorescein angiography images using deep learning: A retrospective, multi-center study

PurposeFundus fluorescein angiography (FFA) is the gold standard for retinal vein occlusion (RVO) diagnosis. This study aims to develop a deep learning-based system to diagnose and classify RVO using FFA images, addressing the challenges of time-consuming and variable interpretations by ophthalmologists. Methods4028 FFA images of 467 eyes from 463 patients were collected and annotated. Three convolutional neural networks (CNN) models (ResNet50, VGG19, InceptionV3) were trained to generate the label of image quality, eye, location, phase, lesions, diagnosis, and macular involvement. The performance of the models was evaluated by accuracy, precision, recall, F-1 score, the area under the curve, confusion matrix, human-machine comparison, and Clinical validation on three external data sets. ResultsThe InceptionV3 model outperformed ResNet50 and VGG19 in labeling and interpreting FFA images for RVO diagnosis, achieving 77.63%–96.45% accuracy for basic information labels and 81.72%–96.45% for RVO-relevant labels. The comparison between the best CNN and ophthalmologists showed up to 19% accuracy improvement with the inceptionV3. ConclusionThis study developed a deep learning model capable of automatically multi-label and multi-classification of FFA images for RVO diagnosis. The proposed system is anticipated to serve as a new tool for diagnosing RVO in places short of medical resources.

Enhancing Agricultural Efficiency: Deep Learning-Based Soil Crack Detection for Water Irrigation

The escalating demand for agricultural precision and environmental monitoring underscores the necessity for effective soil crack detection methods. This study explores the feasibility of employing a Raspberry Pi-powered camera system and deep learning image recognition to detect soil cracks and control agricultural irrigation. The purpose is to develop a soil crack detection system using deep learning techniques, sustain plant growth process, increase productivity, and optimize water irrigation practice. Our approach leverages TensorFlow to craft a convolutional neural network tailored specifically for execution on a Raspberry Pi 3B+. A dataset comprises manually captured images and is trained with the InceptionV3 model categorized into crack or nocrack classes. The accuracy is achieved ranging from 97% to 99%. These results underscore deep learning image recognition models on Raspberry Pi for cost-effective soil crack monitoring and controlling the plants watering system.

AUTOMATED CLASSIFICATION OF EMPHYSEMA USING CONVOLUTIONAL NEURAL NETWORKS

The analysis of CT scans for emphysema diagnosis can be formulated as a computer vision problem, where predefined patterns are used to automatically classify the images. This paper investigates a method for classifying emphysema subtypes in High-Resolution Computed Tomography (HRCT) scans using convolutional neural networks (CNNs). This classification is crucial for accurate diagnosis and management of emphysema, a chronic lung disease causing shortness of breath. Our approach leverages transfer learning to extract informative features from HRCT images labeled as centrilobular (CLE), paraseptal (PLE), panlobular (PSE), and non-emphysematous (NT). We evaluate various CNN architectures, with InceptionV3 demonstrating exceptional performance, achieving an accuracy of 98% while effectively distinguishing between all subtypes. The trained InceptionV3 model is then integrated into a user-friendly front-end application developed using Streamlit and ngrok. This application allows real-time emphysema classification from HRCT scans, potentially aiding clinicians in diagnosis and treatment decisions. Keywords:- Emphysema classification ,Transfer Learning,CNN,InceptionV3,Streamlit , Ngrok

Classification of Apple Plant Leaf Diseases Using Deep Convolutional Neural Network

Food production is one of the main sources of income and livelihood in the world. Various agricultural products are grown as essential food in the largest areas of World. According to various research, many agriculture sectors face loss due to crop diseases Plant anthologists find new methods for diagnosing plant diseases perfectly and reliably. Classification of crop diseases is done by using machine learning techniques. Now a day largest no of plant diseases is identified by using deep learning methods. In this work, we use an effective approach that is based on Otsu's thresholding method in preprocessing whereas plant diseases classify by using deep CNN. In this research, we use a benchmark dataset of apple leafs from Kaggle. The method that we use in this research is not applied to apple plants in previous studies. The dataset contains three classes first we apply preprocessing on the dataset which applies three models on these images named 19 layer CNN, AlexNet, and Inception V3 model. Apple dataset preprocesses by applying to resize, background removal, and cropping functions. In the first experiment, we did not preprocess the dataset and directly apply deep CNN on original images and show the behavior of this method on the unclean dataset. On the other hand, in the second experiment first, preprocess datasets and then apply deep CNN for the classification of these diseases. apple leaf diseases are also classified by using AlexNet and the inception V3 model lastly 19 layer CNN is compared with two other models named Alexnet and Inception V3 model both are transfer learning models Results of the AlexNet model is quietly better than the CNN and Inception V3 model is not perform well as compare to both algorithms.

Deep Learning Model for Automatic Identification and Classification of Distal Radius Fracture.

Distal radius fracture (DRF) is one of the most common types of wrist fractures. We aimed to construct a model for the automatic segmentation of wrist radiographs using a deep learning approach and further perform automatic identification and classification of DRF. A total of 2240 participants with anteroposterior wrist radiographs from one hospital between January 2015 and October 2021 were included. The outcomes were automatic segmentation of wrist radiographs, identification of DRF, and classification of DRF (type A, type B, type C). The Unet model and Fast-RCNN model were used for automatic segmentation. The DenseNet121 model and ResNet50 model were applied to DRF identification of DRF. The DenseNet121 model, ResNet50 model, VGG-19 model, and InceptionV3 model were used for DRF classification. The area under the curve (AUC) with 95% confidence interval (CI), accuracy, precision, and F1-score was utilized to assess the effectiveness of the identification and classification models. Of these 2240 participants, 1440 (64.3%) had DRF, of which 701 (48.7%) were type A, 278 (19.3%) were type B, and 461 (32.0%) were type C. Both the Unet model and the Fast-RCNN model showed good segmentation of wrist radiographs. For DRF identification, the AUCs of the DenseNet121 model and the ResNet50 model in the testing set were 0.941 (95%CI: 0.926-0.965) and 0.936 (95%CI: 0.913-0.955), respectively. The AUCs of the DenseNet121 model (testing set) for classification type A, type B, and type C were 0.96, 0.96, and 0.96, respectively. The DenseNet121 model may provide clinicians with a tool for interpreting wrist radiographs.