Automatic Image Classification Research Articles

Alzheimer's MRI Recognition Based on Convolutional Neural Networks

Alzheimer's disease (AD) is a progressively worsening neurodegenerative disorder, where early diagnosis is crucial for implementing effective disease management strategies. In multimodal diagnostic pathways, Magnetic Resonance Imaging (MRI) plays a pivotal role as a non-invasive imaging technique in disease identification and progression monitoring. Deep learning, particularly Convolutional Neural Networks (CNN), can extract key biomarkers from complex imaging data. By training CNN models to automatically interpret MRI scans, radiology experts can utilize these advanced analytical tools for more efficient and consistent pathological assessments, thereby enhancing clinical decision support systems. This study develops a deep learning-based method for the automatic classification of Alzheimer's brain MRI images, using convolutional neural networks to categorize MRI images into four stages: no dementia, very mild dementia, mild dementia, and moderate dementia. A CNN model is constructed, learning distinctive features of the images through multi-level feature extraction and performing feature map visualization. Early stopping is employed to prevent overfitting. The model is trained on a training set and evaluated on a test set, with performance metrics including confusion matrix, accuracy, precision, recall, F1 score, Kappa coefficient, Matthew’s coefficient, ROC curve with AUC value, and PQ curve with AP value. The results show that the proposed model effectively differentiates between various categories of MRI images, providing valuable tools for early diagnosis and condition monitoring.

Study on breast cancer image detection and classification based on residual connected convolutional neural network (CNN)

This paper presents a method for breast cancer image detection and classification based on convolutional neural networks. While traditional breast cancer detection methods carry the risk of subjectivity and misclassification, machine learning can improve the accuracy and efficiency of detection by training algorithms to automatically identify breast cancer lesions in patients. The dataset of this paper includes 7909 microscopic images of breast tumor tissues with different magnifications collected from 82 patients, which are divided into two categories: benign and malignant tumors. In this paper, residual connection is designed for convolutional neural networks, which is a cross-layer connection method that can effectively solve the gradient vanishing and gradient explosion problems in deep neural networks, and at the same time, improve the generalization ability and training speed of the model. In this paper, the dataset is divided into training set, validation set and test set according to the ratio of 6:2:2. Through training and validation, the prediction accuracy of the obtained model on the test set reaches 85.5%, which achieves good prediction results in breast cancer image detection and classification. Eventually, the model's loss converged at 0.53 and the AUC was 0.832. The research results in this paper are of great significance for the early diagnosis and treatment of breast cancer. Automatic identification and classification of breast cancer images by machine learning algorithms can reduce the subjective judgment of doctors, improve the accuracy and efficiency of detection, and provide important support for the early diagnosis and treatment of breast cancer. Meanwhile, the research method and results of this paper also provide reference and reference for image detection and classification of other malignant tumors.

Identifying urban built-up areas using CORONA imagery in the pre-Landsat era: a case study of Shanghai in 1965

ABSTRACT The Corona project (1959–1972) created a large number of high-resolution images that provided valuable historical research data before the advent of Landsat (1972) and even compensated for the lack of accuracy in early stages. In this study, we collected eight available Corona images to create a historical remote sensing image of Shanghai in the 1960 and developed an automatic image segmentation and classification methodology. In the experimental part, we verified its accuracy, and discussed the urbanization process in Shanghai. The results showed that 1) In 1965, the urban area of Shanghai was mainly distributed in Puxi, and the urbanization degree of the entire hinterland of Pudong was still very low. Built-up areas were highly concentrated in the main urban areas. 2) The overall accuracy was 91.5% and the kappa coefficient was 0.762. 3) We compared the built-up area in 1965 with the current urban area, which increased from 306.23 to 2,804.25 km2. Besides, historical imagery also captured the state of environmental pollution at that time. Overall, our method could inform the mapping and classification of remotely sensed land surfaces on a global scale in the 1960s, extending pre-Landsat era research to studies of urban history, archaeology and cultural heritage.

Explanation of the influence of geomorphometric variables on the landform classification based on selected areas in Poland

In recent years, automatic image classification methods have significantly progressed, notably black box algorithms such as machine learning and deep learning. Unfortunately, such efforts only focused on improving performance, rather than attempting to explain and interpret how classification models actually operate. This article compares three state-of-the-art algorithms incorporating random forests, gradient boosting and convolutional neural networks for geomorphological mapping. It also attempts to explain how the most effective classifier makes decisions by evaluating which of the geomorphometric variables are most important for automatic mapping and how they affect the classification results using one of the explainable artificial intelligence techniques, namely accumulated local effects (ALE). This method allows us to understand the relationship between predictors and the model’s outcome. For these purposes, eight sheets of the digital geomorphological map of Poland on the scale of 1:100,000 were used as the reference material. The classification results were validated using the holdout method and cross-validation for individual sheets representing different morphogenetic zones. The terrain elevation entropy, absolute elevation, aggregated median elevation and standard deviation of elevation had the greatest impact on the classification results among the 15 geomorphometric variables considered. The ALE analysis was conducted for the XGBoost classifier, which achieved the highest accuracy of 92.8%, ahead of Random Forests at 84% and LightGBM at 73.7% and U-Net at 59.8%. We conclude that automatic classification can support geomorphological mapping only if the geomorphological characteristics in the predicted area are similar to those in the training dataset. The ALE plots allow us to analyze the relationship between geomorphometric variables and landform membership, which helps clarify their role in the classification process.

An Empirical Evaluation of a Novel Ensemble Deep Neural Network Model and Explainable AI for Accurate Segmentation and Classification of Ovarian Tumors Using CT Images.

Ovarian cancer is one of the leading causes of death worldwide among the female population. Early diagnosis is crucial for patient treatment. In this work, our main objective is to accurately detect and classify ovarian cancer. To achieve this, two datasets are considered: CT scan images of patients with cancer and those without, and biomarker (clinical parameters) data from all patients. We propose an ensemble deep neural network model and an ensemble machine learning model for the automatic binary classification of ovarian CT scan images and biomarker data. The proposed model incorporates four convolutional neural network models: VGG16, ResNet 152, Inception V3, and DenseNet 101, with transformers applied for feature extraction. These extracted features are fed into our proposed ensemble multi-layer perceptron model for classification. Preprocessing and CNN tuning techniques such as hyperparameter optimization, data augmentation, and fine-tuning are utilized during model training. Our ensemble model outperforms single classifiers and machine learning algorithms, achieving a mean accuracy of 98.96%, a precision of 97.44%, and an F1-score of 98.7%. We compared these results with those obtained using features extracted by the UNet model, followed by classification with our ensemble model. The transformer demonstrated superior performance in feature extraction over the UNet, with a mean Dice score and mean Jaccard score of 0.98 and 0.97, respectively, and standard deviations of 0.04 and 0.06 for benign tumors and 0.99 and 0.98 with standard deviations of 0.01 for malignant tumors. For the biomarker data, the combination of five machine learning models-KNN, logistic regression, SVM, decision tree, and random forest-resulted in an improved accuracy of 92.8% compared to single classifiers.

Further exploration on deep learning in flower recognition

Flower recognition is an important research direction in the field of computer vision, and automatic classification of flower images through deep learning methods is of great significance for ecological environment monitoring and plant research. With this background, this study aims to further optimize the existing flower recognition system and improve its classification accuracy by adjusting key parameters. Based on the existing deep learning model and several rounds of training, this paper explores the tuning strategies for parameters such as different learning rates and weight decay to achieve higher recognition accuracy. In the experiments, this paper uses the classical flower dataset and enhances the diversity of the data through image preprocessing and data enhancement. Through a hundred rounds of training, the model in this paper achieves about 80% classification accuracy on the test set, which is significantly improved compared with the initial model. Further analysis of the results shows that by reasonably adjusting the learning rate and weight decay parameters, the model achieves certain improvements in different flower classes, demonstrating the impact of parameter tuning on the overall performance of the model.

An automatic online optics classification method used in the final optics recycling loop strategy

The final optics recycling loop used on large laser facility is an effcient and necessary strategy to maintain the optics in intervals between long-term physical experiments, In order to avoid cross-use between optics of different quality levels, we put forward the A/B recycling loop strategy of optics refer to the strategy from NIF, which arranges optics of the same quality level working in the same beamline, and optics of large quality difference loop independently to protect high-quality optics. Additionally, in order to improve the efficiency of recycling task and the stability of classification standard, we have searched for a proper intelligence technology applying on the loop process. To solve the small sample problem under each label, we use data augmentation method to manually increase samples. Furthermore, transfer learning method based on VGG16 is also used to extract features of the target. As a result the accuracy of the learning model reaches over 90 %. From now on, the integration and data interaction with the computer centralized control system have been completed. The realization of online image automatic classification can estimate the quality grades of optics, so as to provide reference for optics maintaining and optimize the efficiency of the optics recycling loop.

Automated Diagnosis of Bone Metastasis by Classifying Bone Scintigrams Using a Self-defined Deep Learning Model.

Patients with cancer can develop bone metastasis when a solid tumor invades the bone, which is the third most commonly affected site by metastatic cancer, after the lung and liver. The early detection of bone metastases is crucial for making appropriate treatment decisions and increasing survival rates. Deep learning, a mainstream branch of machine learning, has rapidly become an effective approach to analyzing medical images. To automatically diagnose bone metastasis with bone scintigraphy, in this work, we proposed to cast the bone metastasis diagnosis problem into automated image classification by developing a deep learning-based automated classification model. A self-defined convolutional neural network consisting of a feature extraction sub-network and feature classification sub-network was proposed to automatically detect lung cancer bone metastasis, with a feature extraction sub-network extracting hierarchal features from SPECT bone scintigrams and feature classification sub-network classifying high-level features into two categories (i.e., images with metastasis and without metastasis). Using clinical data of SPECT bone scintigrams, the proposed model was evaluated to examine its detection accuracy. The best performance was achieved if the two images (i.e., anterior and posterior scans) acquired from each patient were fused using pixel-wise addition operation on the bladder-excluded images, obtaining the best scores of 0.8038, 0.8051, 0.8039, 0.8039, 0.8036, and 0.8489 for accuracy, precision, recall, specificity, F-1 score, and AUC value, respectively. The proposed two-class classification network can predict whether an image contains lung cancer bone metastasis with the best performance as compared to existing classical deep learning models. The high accumulation of 99mTc MDP in the urinary bladder has a negative impact on automated diagnosis of bone metastasis. It is recommended to remove the urinary bladder before automated analysis.

Integrated Generative Adversarial Networks and Deep Convolutional Neural Networks for Image Data Classification: A Case Study for COVID-19

Convolutional Neural Networks (CNNs) have garnered significant utilisation within automated image classification systems. CNNs possess the ability to leverage the spatial and temporal correlations inherent in a dataset. This study delves into the use of cutting-edge deep learning for precise image data classification, focusing on overcoming the difficulties brought on by the COVID-19 pandemic. In order to improve the accuracy and robustness of COVID-19 image classification, the study introduces a novel methodology that combines the strength of Deep Convolutional Neural Networks (DCNNs) and Generative Adversarial Networks (GANs). This proposed study helps to mitigate the lack of labelled coronavirus (COVID-19) images, which has been a standard limitation in related research, and improves the model’s ability to distinguish between COVID-19-related patterns and healthy lung images. The study uses a thorough case study and uses a sizable dataset of chest X-ray images covering COVID-19 cases, other respiratory conditions, and healthy lung conditions. The integrated model outperforms conventional DCNN-based techniques in terms of classification accuracy after being trained on this dataset. To address the issues of an unbalanced dataset, GAN will produce synthetic pictures and extract deep features from every image. A thorough understanding of the model’s performance in real-world scenarios is also provided by the study’s meticulous evaluation of the model’s performance using a variety of metrics, including accuracy, precision, recall, and F1-score.

Unsupervised domain adaptation with local structure preservation for colon histopathological image classification

The histopathological image classification method, based on deep learning, can be used to assist pathologists in cancer recognition in colon histopathology. The popularization of automatic and accurate histopathological image classification methods in this way is of great significance. However, smaller medical institutions with limited medical resources may lack colon histopathology image training sets with reliable labeled information; thus they may be unable to meet the needs of deep learning for many labeled training samples. Therefore, in this paper, the colon histopathological image set with rich label information from a certain medical institution is taken as the source domain; the colon histopathological image set from a smaller medical institution with limited medical resources is taken as the target domain. Considering the potential differences between histopathological images obtained by different institutions, this paper proposes a classification learning framework, namely unsupervised domain adaptation with local structure preservation for colon histopathological image classification, which can learn an adaptive classifier by performing distribution alignment and preserving intra-domain local structure to predict the labels of the colon histopathological images from institutions with lower medical resources. Extensive experiments demonstrate that the proposed framework shows significant improvement in accuracy and specificity of colon histopathological images without reliable labeled information compared to models without unsupervised domain adaptation. Specifically, in an affiliated hospital in Fuyang City, Anhui Province, the classification accuracy of benign and malignant colon histopathological images reaches 96.21%. The results of comparative experiments also show promising classification performance of our method in comparison with other unsupervised domain adaptation methods.

Sub-alpine shrub classification using UAV images: Performance of human observers vs DL classifiers

In recent years, the automatic analysis of natural environment images acquired with unmanned aerial vehicles (UAV) has rapidly gained popularity. UAVs are specially important in mountainous forests where access is difficult and large areas need to be surveyed. In Zao mountains in northeastern Japan, regenerated fir saplings are competing with sub-alpine vegetation shrubs after a severe fir tree mortality caused by bark beetle infestation. A detailed survey of vegetation distribution is key to improve our understanding of species succession and the influence of climate change in that process. To that end, we evaluated the suitability of deep-learning-based automatic image classification of UAV images in order to map sub-alpine vegetation succession in large areas and the potential of fir regeneration.In order to assess the contribution of this technology in this research field, we first conducted an observer study to assess the difficulty for humans of the task of classifying vegetation from images. Afterwards, we compared the observers' accuracy to four state-of-the art deep learning networks for automatic image classification. The best observer accuracy of 55% demonstrates the limitations of species classification using only images. Furthermore, a detailed analysis of the sources of error showed that even though humans could differentiate between deciduous and evergreen species with an accuracy of 96%, identifying the correct species within each group proved much more challenging. In contrast, deep learning networks achieved accuracy values in the range of 70–80% for species classification, clearly demonstrating capabilities beyond human experts. Our experiments also indicated that the performance of these networks was significantly influenced by the similarity between the datasets used to fine-tune them and evaluate them. This fact highlights the importance of building publicly available images databases to further improve the results.Nevertheless, the results presented in this paper show that the analysis of UAV-acquired with deep learning networks can usher in a new type of large-scale study, spanning tenths or even hundreds of hectares with high spatial resolution (of a few cms per pixel), providing the ability to assess challenging vegetation dynamics problems that go beyond the ability of conventional fieldwork methodologies.

Research on breast cancer pathological image classification method based on wavelet transform and YOLOv8.

Breast cancer is one of the cancers with high morbidity and mortality in the world, which is a serious threat to the health of women. With the development of deep learning, the recognition about computer-aided diagnosis technology is getting higher and higher. And the traditional data feature extraction technology has been gradually replaced by the feature extraction technology based on convolutional neural network which helps to realize the automatic recognition and classification of pathological images. In this paper, a novel method based on deep learning and wavelet transform is proposed to classify the pathological images of breast cancer. Firstly, the image flip technique is used to expand the data set, then the two-level wavelet decomposition and reconfiguration technology is used to sharpen and enhance the pathological images. Secondly, the processed data set is divided into the training set and the test set according to 8:2 and 7:3, and the YOLOv8 network model is selected to perform the eight classification tasks of breast cancer pathological images. Finally, the classification accuracy of the proposed method is compared with the classification accuracy obtained by YOLOv8 for the original BreaKHis dataset, and it is found that the algorithm can improve the classification accuracy of images with different magnifications, which proves the effectiveness of combining two-level wavelet decomposition and reconfiguration with YOLOv8 network model.

On the nature of apparent transient sources on the National Geographic Society–Palomar Observatory Sky Survey glass copy plates

Abstract We examine critically recent claims for the presence of above-atmosphere optical transients in publicly available digitized scans of Schmidt telescope photographic plate material derived from the National Geographic Society–Palomar Observatory Sky Survey. We employ the publicly available SuperCOSMOS Sky Survey catalogues to examine statistically the morphology of the sources. We develop a simple, objective, and automated image classification scheme based on a random forest decision tree classifier. We find that the putative transients are likely to be spurious artefacts of the photographic emulsion. We suggest a possible cause of the appearance of these images as resulting from the copying procedure employed to disseminate glass copy survey atlas sets in the era before large-scale digitization programmes.

A Novel Decision Level Class-Wise Ensemble Method in Deep Learning for Automatic Multi-Class Classification of HER2 Breast Cancer Hematoxylin-Eosin Images

A Novel Decision Level Class-Wise Ensemble Method in Deep Learning for Automatic Multi-Class Classification of HER2 Breast Cancer Hematoxylin-Eosin Images

Deep learning-based automatic image classification of oral cancer cells acquiring chemoresistance in vitro.

Cell shape reflects the spatial configuration resulting from the equilibrium of cellular and environmental signals and is considered a highly relevant indicator of its function and biological properties. For cancer cells, various physiological and environmental challenges, including chemotherapy, cause a cell state transition, which is accompanied by a continuous morphological alteration that is often extremely difficult to recognize even by direct microscopic inspection. To determine whether deep learning-based image analysis enables the detection of cell shape reflecting a crucial cell state alteration, we used the oral cancer cell line resistant to chemotherapy but having cell morphology nearly indiscernible from its non-resistant parental cells. We then implemented the automatic approach via deep learning methods based on EfficienNet-B3 models, along with over- and down-sampling techniques to determine whether image analysis of the Convolutional Neural Network (CNN) can accomplish three-class classification of non-cancer cells vs. cancer cells with and without chemoresistance. We also examine the capability of CNN-based image analysis to approximate the composition of chemoresistant cancer cells within a population. We show that the classification model achieves at least 98.33% accuracy by the CNN model trained with over- and down-sampling techniques. For heterogeneous populations, the best model can approximate the true proportions of non-chemoresistant and chemoresistant cancer cells with Root Mean Square Error (RMSE) reduced to 0.16 by Ensemble Learning (EL). In conclusion, our study demonstrates the potential of CNN models to identify altered cell shapes that are visually challenging to recognize, thus supporting future applications with this automatic approach to image analysis.

Deep Learning Augmented Osteoarthritis Grading Standardization.

Manual grading of cartilage histology images for investigating the extent and severity of osteoarthritis (OA) involves critical examination of the cell characteristics, which makes this task tiresome, tedious, and error prone. This results in wide interobserver variation, causing ambiguities in OA grade prediction. Such drawbacks of manual assessment can be overcome by implementing artificial intelligence-based automated image classification techniques such as deep learning (DL). Hence, we present the feasibility of training a deep neural network with cartilage histology images, which can grade the extent and severity of knee OA based on modified Mankin scoring system. The grading system used here for automating OA grading was simplified and modified based on the microscopic observations from the histology images, where three parameters (Safranin-O staining intensity, chondrocyte distribution and arrangement, and morphology) were considered for evaluating the OA progression. The histology images were tiled, labeled, and grouped together based on the developed grading system (Grade 0-3). Four different DL architectures were tried for image classification and the best performing model was selected by fivefold validation method. With a validation accuracy of ∼84%, 0.632 Cohen's kappa score, and an excellent receiver operating characteristic (ROC)-area under the ROC curve ranging between 0.89 and 0.99, DenseNet121 was selected among the four models as the best performing model, and was used for inferencing on new data. Final grades obtained from the models were in accordance with the grades provided by the medical experts. We hereby demonstrate that a DL architecture can be taught to interpret the degree of cartilage degradation, with excellent discriminatory ability across all four classes of OA severity. Unlike other works where radiographic images have been considered for grading of OA, we have considered histology images, which is a fundamental approach for grading OA extent and severity. This would bring a paradigm shift in histology-based assessment of OA, making this automated approach to be explored as an option for OA grading standardization. Ethical approval number-IAH-BMR-018/10-19.

Skin cancer classifier based on convolution residual neural network

Accurate automatic classification of skin lesion images is a great challenge as the image features are very close in these images. Convolution neural networks (CNN) promise to provide a potential classifier for skin lesions. This work will present dermatologist-level classification of skin cancer by using residual network (ResNet-50) as a deep learning convolutional neural network (DLCNN) that maps images to class labels. It presents a classifier with a single CNN to automatically recognize benign and malignant skin images. The network inputs are only disease labels and image pixels. About 320 clinical images of the different diseases have been used to train CNN. The model performance has been tested with untrained images from the two labels. This model identifies the most common skin cancers and can be updated with a new unlimited number of images. The DLCNN trained by the ResNet-50 model showed good classification of the benign and malignant skin categories. The ResNet-50 as a DLCNN has verified a significant recognition rate of more than 97% on the testing images, which proves that the benign and malignant lesion skin images are properly classified.

Automatic classification of kidney CT images with relief based novel hybrid deep model

One of the most crucial organs in the human body is the kidney. Usually, the patient does not realize the serious problems that arise in the kidneys in the early stages of the disease. Many kidney diseases can be detected and diagnosed by specialists with the help of routine computer tomography (CT) images. Early detection of kidney diseases is extremely important for the success of the treatment of the disease and for the prevention of other serious diseases. In this study, CT images of kidneys containing stones, tumors, and cysts were classified using the proposed hybrid model. Results were also obtained using pre-trained models that had been acknowledged in the literature to evaluate the effectiveness of the suggested model. The proposed model consists of 29 layers. While classifying kidney CT images, feature maps were obtained from the convolution 6 and convolution 7 layers of the proposed model, and these feature maps were combined after optimizing with the Relief method. The wide neural network classifier then classifies the optimized feature map. While the highest accuracy value obtained in eight different pre-trained models was 87.75%, this accuracy value was 99.37% in the proposed model. In addition, different performance evaluation metrics were used to measure the performance of the model. These values show that the proposed model has reached high-performance values. Therefore, the proposed approach seems promising in order to automatically and effectively classify kidney CT images.

Comparison of the Performance of Convolutional Neural Networks and Vision Transformer-Based Systems for Automated Glaucoma Detection with Eye Fundus Images

Glaucoma, a disease that damages the optic nerve, is the leading cause of irreversible blindness worldwide. The early detection of glaucoma is a challenge, which in recent years has driven the study and application of Deep Learning (DL) techniques in the automatic classification of eye fundus images. Among these intelligent systems, Convolutional Neural Networks (CNNs) stand out, although alternatives have recently appeared, such as Vision Transformers (ViTs) or hybrid systems, which are also highly efficient in image processing. The question that arises in the face of so many emerging methods is whether all these new techniques are really more efficient for the problem of glaucoma diagnosis than the CNNs that have been used so far. In this article, we present a comprehensive comparative study of all these DL models in glaucoma detection, with the aim of elucidating which strategies are significantly better. Our main conclusion is that there are no significant differences between the efficiency of both DL strategies for the medical diagnostic problem addressed.

Automatic classification of parasitized fruit fly pupae from X-ray images by convolutional neural networks

The parasitoid wasp Diachasmimorpha longicaudata (Hymenoptera: Braconidae) has been used for the biological control of fruit fly larvae in many countries. Due to the large scale of production, quality control systems must be utilized to assess insect quality to optimize prerelease activities. However, the parasitism rate, and the unparasitized puparia, which become waste pupae, can only be known after waiting for the emergence of the adults from sampled pupae (ca. 16 days at 25 °C). This waiting time can result in resources being wasted. A way to speed up the quality control of pupal batches and increase the accuracy of the production process would be to combine digital radiography of the parasitized pupae and deep learning methods for the automatic classification of images. Therefore, the purpose of this work was to discriminate parasitized from waste pupae through X-ray images and to test the suitability of 7 Convolutional Neural Networks to classify the pupal images. Radiographic images from 11-day-old pupae allowed the in vivo identification of immature stages of the parasitoid, preserving the viability of the wasp. A positive correlation was found between the number of emerged parasitoids and the ones identified in the X-ray images. In terms of performance metrics, the accuracies achieved by all CNN-based neural architectures were higher than 97%, indicating a high predictive classification power. At least three of the CNNs tested showed great potential as classifiers of X-ray images of parasitized pupae and can be indicated for practical applications in quality control programs.