Image Classification Framework Research Articles

A Robust Automated Framework for Classification of CT Covid-19 Images Using MSI-ResNet

Nowadays, the COVID-19 virus disease is spreading rampantly. There are some testing tools and kits available for diagnosing the virus, but it is in a limited count. To diagnose the presence of disease from radiological images, automated COVID-19 diagnosis techniques are needed. The enhancement of AI (Artificial Intelligence) has been focused in previous research, which uses X-ray images for detecting COVID-19. The most common symptoms of COVID-19 are fever, dry cough and sore throat. These symptoms may lead to an increase in the rigorous type of pneumonia with a severe barrier. Since medical imaging is not suggested recently in Canada for critical COVID-19 diagnosis, computer-aided systems are implemented for the early identification of COVID-19, which aids in noticing the disease progression and thus decreases the death rate. Here, a deep learning-based automated method for the extraction of features and classification is enhanced for the detection of COVID-19 from the images of computer tomography (CT). The suggested method functions on the basis of three main processes: data preprocessing, the extraction of features and classification. This approach integrates the union of deep features with the help of Inception 14 and VGG-16 models. At last, a classifier of Multi-scale Improved ResNet (MSI-ResNet) is developed to detect and classify the CT images into unique labels of class. With the support of available open-source COVID-CT datasets that consists of 760 CT pictures, the investigational validation of the suggested method is estimated. The experimental results reveal that the proposed approach offers greater performance with high specificity, accuracy and sensitivity.

A Regional-Attentive Multi-Task Learning Framework for Breast Ultrasound Image Segmentation and Classification

Breast ultrasound (BUS) imaging is commonly used in the early detection of breast cancer as a portable, valuable, and widely available diagnosis tool. Automated BUS image classification and segmentation can assist radiologists in making accurate and fast decisions. Recent studies illustrate that tumor, peritumoral, and background regions of BUS images provide valuable information for BUS image segmentation or classification. However, few studies have investigated the influence of these three regions on multi-task learning. In this study, we propose an RMTL-Net to simultaneously segment tumor regions and classify tumors in BUS images into benign or malignant categories. To improve both segmentation and classification performance, we design a regional attention (RA) module that employs the predicted probability maps to automatically guide the classifier to learn important category-sensitive information in the tumor, peritumoral, and background regions and seamlessly fuse them to obtain a better feature representation. We conduct detailed ablation experiments of the proposed RA module and comparative experiments with four recent state-of-the-art peer multi-task learning methods, three single-task segmentation methods, and four single-task classification methods on two public BUS datasets. Experimental results show that the proposed RMTL-Net achieves the best overall segmentation and classification accuracy in terms of five segmentation metrics and six classification metrics.

Graph Guided Transformer: An Image-Based Global Learning Framework for Hyperspectral Image Classification

Graph Guided Transformer: An Image-Based Global Learning Framework for Hyperspectral Image Classification

A Novel Framework for Semi-supervised Multiple-label Image Classification using Multi-stage CNN and Visual Attention Mechanism

To train deep neural networks effectively, a lot of labeled data is typically needed. However, real-time applications make it difficult and expensive to acquire high-quality labels for the data because it takes skill and knowledge to accurately annotate multiple label images. In order to enhance classification performance, it is also crucial to extract image features from all potential objects of various sizes as well as the relationships between labels of numerous label images. The current approaches fall short in their ability to map the label dependencies and effectively classify the labels. They also perform poor to label the unlabeled images when small amount of labeled images available for classification. In order to solve these issues, we suggest a new framework for semi-supervised multiple object label classification using multi-stage Convolutional neural networks with visual attention (MSCNN)and GCN for label co-occurrence embedding(LCE) (MSCNN-LCE-MIC), which combines GCN and attention mechanism to concurrently capture local and global label dependencies throughout the entire image classification process. Four main modules make up MSCNN-LCE-MIC: (1) improved multi-label propagation method for labeling largely available unlabeled image; (2) a feature extraction module using multi-stage CNN with visual attention mechanism that focuses on the connections between labels and target regions to extract accurate features from each input image; (3) a label co-existence learning that applies GCN to discover the associations between different items to create embeddings of label co-occurrence; and (4) an integrated multi-modal fusion module. Numerous tests on MS-COCO and PASCAL VOC2007 show that MSCNN-LCE-MIC significantly improves classification efficiency on mAP 84.3% and 95.8% respectively when compared to the most recent existing methods.

SpectralDiff: A Generative Framework for Hyperspectral Image Classification With Diffusion Models

SpectralDiff: A Generative Framework for Hyperspectral Image Classification With Diffusion Models

Privacy-Preserving Federated Learning of Remote Sensing Image Classification With Dishonest Majority

The classification of remote sensing images can give valuable data for various practical applications for smart cities, including urban planning, construction, and water resource management. The federated learning (FL) solution is often adopted to resolve the problems of limited resources and the confidentiality of data in remote sensing image classification. Privacy-preserving federated learning (PPFL) is a state-of-art FL scheme tailored for the privacy-constrained situation. It is required to address safeguarding data privacy and optimizing model accuracy effectively. However, existing PPFL methods usually suffer from model poisoning attacks, especially in the case of dishonest-majority scenarios. To address this challenge, in this work, we propose a blockchain-empowered PPFL for remote sensing image classification framework with the poisonous dishonest majority, which is able to defend against encrypted model poisoning attacks without compromising users' privacy. Specifically, we first propose the method of proof of accuracy (PoA) aiming to evaluate the encrypted models in an authentic way. Then, we design the secure aggregation framework using PoA, which can achieve robustness in a majority proportion of adversary settings. The experimental results show that our scheme can reach 92.5%, 90.61%, 87.48%, and 81.84% accuracy when the attacker accounts for 20%, 40%, 60%, and 80%, respectively. This is consistent with the FedAvg accuracy when only benign clients own the corresponding proportion of data. The experiment results demonstrate the proposed scheme's superiority in defending against model poisoning attacks.

2SRS: Two-Stream Residual Separable Convolution Neural Network for Hyperspectral Image Classification

Typically, hyperspectral image suffers from redundant information, data scarcity, and class imbalance problems. This letter proposes a hyperspectral image classification framework named as Two-Stream Residual Separable Convolution (2SRS) network that aims to mitigate these problems. Principal Component Analysis (PCA) is first employed to reduce the spectral dimension of the hyperspectral image. Subsequently, the data scarcity and class imbalance problems are overcome via spatial and spectral data augmentations. A novel spectral data creation from image patches is proposed. The augmented samples are fed into the proposed 2SRS network for hyperspectral image classification. We evaluated the proposed method on three benchmark datasets, namely (1) Indian Pines, (2) Pavia University, and (3) Salinas Scene. The proposed method achieved state-of-the-art performance in terms of Overall Accuracy (OA), Average Accuracy (AA), and Kappa Coefficient (Kappa) for both 30% and 10% training set ratio.

Multi-feature based Hazy Image Classification for Vision Enhancement

Deteriorating contrast, low glow, restricted dynamic range, poor resolution details, non-bright natural landscape colours, and reduced saturation of an image are subjected to various degrees of influence and deterioration in hazy weather conditions. Dehazing haze degraded images becomes challenging if they are not classified as hazy or clear, given that image dehazing techniques can only be used with hazy images. The competence to differentiate between hazy and clear images can not be left to human perception; hence a robust model is needed that classifies the input image into hazy and clear. Thus, we propose a nine unique features-based image classification framework based on K-Nearest Neighbour (KNN), which can accurately classify hazy and clear images. Experimental results demonstrate that the proposed method can efficiently classify the hazy and clear images, with an accuracy of 92%, a precision of 0.90, recall of 0.96, and F1 score of 0.93 for a benchmark dataset, which has both theoretical and practical implications.

Dynamic Ensemble Learning with Evolutionary Programming and Swarm Intelligence for Image Classification

Image classification is a fundamental and pervasive task in the field of computer vision, with profound implications across a wide array of applications. From the autonomous vehicles navigating complex urban environments to the critical diagnosis of diseases through medical image analysis, the accurate categorization of images plays a pivotal role in modern technology and society. As the world becomes increasingly digitized, the volume of image data generated daily continues to soar. This exponential growth necessitates the development of robust and adaptive image classification techniques capable of handling the complexity and diversity of this data.In response to these evolving demands, this work introduces a pioneering approach known as Dynamic Ensemble Learning with Evolutionary Programming and Swarm Intelligence (DEL-EPSI). DEL-EPSI represents a transformative paradigm shift in the realm of image classification, offering a multifaceted solution to address the multifarious challenges posed by this critical task. At its core, DEL-EPSI combines the strengths of dynamic ensemble learning, evolutionary programming, and swarm intelligence to provide a holistic, adaptive, and highly accurate image classification framework. In this study, the principles, capabilities, and implications of DEL-EPSI are studied and investigated.

A CNN with noise inclined module and denoise framework for hyperspectral image classification

AbstractDeep Neural Networks have been successfully applied in hyperspectral image classification. However, most of prior works adopt general deep architectures while ignore the intrinsic structure of the hyperspectral image, such as the physical noise generation. This would make these deep models unable to generate discriminative features and provide impressive classification performance. To leverage such intrinsic information, this work develops a novel deep learning framework with the noise inclined module and denoise framework for hyperspectral image classification. First, the spectral signature of hyperspectral image is modeled with the physical noise model to describe the high intra‐class variance of each class and great overlapping between different classes in the image. Then, a noise inclined module is developed to capture the physical noise within each object and a denoise framework is then followed to remove such noise from the object. Finally, the CNN with noise inclined module and the denoise framework is developed to obtain discriminative features and provides good classification performance of hyperspectral image. Experiments are conducted over two commonly used real‐world datasets and the experimental results show the effectiveness of the proposed method. The implementation of the proposed method and other compared methods could be accessed at https://github.com/shendu‐sw/noise‐physical‐framework.

Improving quality control in the routine practice for histopathological interpretation of gastrointestinal endoscopic biopsies using artificial intelligence.

Colorectal and gastric cancer are major causes of cancer-related deaths. In Korea, gastrointestinal (GI) endoscopic biopsy specimens account for a high percentage of histopathologic examinations. Lack of a sufficient pathologist workforce can cause an increase in human errors, threatening patient safety. Therefore, we developed a digital pathology total solution combining artificial intelligence (AI) classifier models and pathology laboratory information system for GI endoscopic biopsy specimens to establish a post-analytic daily fast quality control (QC) system, which was applied in clinical practice for a 3-month trial run by four pathologists. Our whole slide image (WSI) classification framework comprised patch-generator, patch-level classifier, and WSI-level classifier. The classifiers were both based on DenseNet (Dense Convolutional Network). In laboratory tests, the WSI classifier achieved accuracy rates of 95.8% and 96.0% in classifying histopathological WSIs of colorectal and gastric endoscopic biopsy specimens, respectively, into three classes (Negative for dysplasia, Dysplasia, and Malignant). Classification by pathologic diagnosis and AI prediction were compared and daily reviews were conducted, focusing on discordant cases for early detection of potential human errors by the pathologists, allowing immediate correction, before the pathology report error is conveyed to the patients. During the 3-month AI-assisted daily QC trial run period, approximately 7-10 times the number of slides compared to that in the conventional monthly QC (33 months) were reviewed by pathologists; nearly 100% of GI endoscopy biopsy slides were double-checked by the AI models. Further, approximately 17-30 times the number of potential human errors were detected within an average of 1.2 days. The AI-assisted daily QC system that we developed and established demonstrated notable improvements in QC, in quantitative, qualitative, and time utility aspects. Ultimately, we developed an independent AI-assisted post-analytic daily fast QC system that was clinically applicable and influential, which could enhance patient safety.

Deep ensemble transfer learning-based framework for mammographic image classification

Deep ensemble transfer learning-based framework for mammographic image classification

PulDi-COVID: Chronic obstructive pulmonary (lung) diseases with COVID-19 classification using ensemble deep convolutional neural network from chest X-ray images to minimize severity and mortality rates

Background and ObjectiveIn the current COVID-19 outbreak, efficient testing of COVID-19 individuals has proven vital to limiting and arresting the disease's accelerated spread globally. It has been observed that the severity and mortality ratio of COVID-19 affected patients is at greater risk because of chronic pulmonary diseases. This study looks at radiographic examinations exploiting chest X-ray images (CXI), which have become one of the utmost feasible assessment approaches for pulmonary disorders, including COVID-19. Deep Learning(DL) remains an excellent image classification method and framework; research has been conducted to predict pulmonary diseases with COVID-19 instances by developing DL classifiers with nine class CXI. However, a few claim to have strong prediction results; because of noisy and small data, their recommended DL strategies may suffer from significant deviation and generality failures. MethodsTherefore, a unique CNN model(PulDi-COVID) for detecting nine diseases (atelectasis, bacterial-pneumonia, cardiomegaly, covid19, effusion, infiltration, no-finding, pneumothorax, viral-Pneumonia) using CXI has been proposed using the SSE algorithm. Several transfer-learning models: VGG16, ResNet50, VGG19, DenseNet201, MobileNetV2, NASNetMobile, ResNet152V2, DenseNet169 are trained on CXI of chronic lung diseases and COVID-19 instances. Given that the proposed thirteen SSE ensemble models solved DL's constraints by making predictions with different classifiers rather than a single, we present PulDi-COVID, an ensemble DL model that combines DL with ensemble learning. The PulDi-COVID framework is created by incorporating various snapshots of DLmodels, which have spearheaded chronic lung diseases with COVID-19 cases identification process with a deep neural network produced CXI by applying a suggested SSE method.That is familiar with the idea of various DL perceptions on different classes. ResultsPulDi-COVID findings were compared to thirteen existing studies for nine-class classification using COVID-19. Test results reveal that PulDi-COVID offers impressive outcomes for chronic diseases with COVID-19 identification with a 99.70% accuracy, 98.68% precision, 98.67% recall, 98.67% F1 score, lowest 12 CXIs zero-one loss, 99.24% AUC-ROC score, and lowest 1.33% error rate. Overall test results are superior to the existing Convolutional Neural Network(CNN). To thebest of our knowledge, the observed results for nine-class classification are significantly superior to the state-of-the-art approaches employed for COVID-19 detection. Furthermore, the CXIthat we usedto assess our algorithm is one of the larger datasets for COVID detection with pulmonary diseases. ConclusionThe empirical findings of our suggested approach PulDi-COVIDshow that it outperforms previously developed methods. The suggested SSE method with PulDi-COVID can effectively fulfill the COVID-19 speedy detection needs with different lung diseases for physicians to minimize patient severity and mortality.

DeepTumor: Framework for Brain MR Image Classification, Segmentation and Tumor Detection.

The proper segmentation of the brain tumor from the image is important for both patients and medical personnel due to the sensitivity of the human brain. Operation intervention would require doctors to be extremely cautious and precise to target the brain's required portion. Furthermore, the segmentation process is also important for multi-class tumor classification. This work primarily concentrated on making a contribution in three main areas of brain MR Image processing for classification and segmentation which are: Brain MR image classification, tumor region segmentation and tumor classification. A framework named DeepTumor is presented for the multistage-multiclass Glioma Tumor classification into four classes; Edema, Necrosis, Enhancing and Non-enhancing. For the brain MR image binary classification (Tumorous and Non-tumorous), two deep Convolutional Neural Network) CNN models were proposed for brain MR image classification; 9-layer model with a total of 217,954 trainable parameters and an improved 10-layer model with a total of 80,243 trainable parameters. In the second stage, an enhanced Fuzzy C-means (FCM) based technique is proposed for the tumor segmentation in brain MR images. In the final stage, an enhanced CNN model 3 with 11 hidden layers and a total of 241,624 trainable parameters was proposed for the classification of the segmented tumor region into four Glioma Tumor classes. The experiments are performed using the BraTS MRI dataset. The experimental results of the proposed CNN models for binary classification and multiclass tumor classification are compared with the existing CNN models such as LeNet, AlexNet and GoogleNet as well as with the latest literature.

A Federated Learning Framework for Breast Cancer Histopathological Image Classification

Quantities and diversities of datasets are vital to model training in a variety of medical image diagnosis applications. However, there are the following problems in real scenes: the required data may not be available in a single institution due to the number of patients or the type of pathology, and it is often not feasible to share patient data due to medical data privacy regulations. This means keeping private data safe is required and has become an obstacle in fusing data from multi-party to train a medical model. To solve the problems, we propose a federated learning framework, which allows knowledge fusion achieved by sharing the model parameters of each client through federated training rather than sharing data. Based on breast cancer histopathological dataset (BreakHis), our federated learning experiments achieve the expected results which are similar to the performances of the centralized learning and verify the feasibility and efficiency of the proposed framework.

A dual-branch multi-feature deep fusion network framework for hyperspectral image classification

Recent research has proven that deep learning models are effective at mining the rich spectral-spatial information of hyperspectral images and attaining high classification performance. In this study, an end-to-end two-branch multi-feature deep fusion network framework (MFDFN) is proposed, combining object-oriented features of hyperspectral images after multi-scale super-pixel segmentation and original image point-image element neighbourhood block features, and designing different network modules in the upper and lower branches for different features in order to extract more distinguishable and advantageous features for classification. For the second part, a series spectral-spatial feature learning modules and augmentation modules for spatial feature learning are being developed to learn these features in a continuous manner while also effectively fusing features from various depth layers. It also uses a variety of techniques (BN, Dropout, residual join, etc.) to speed up the model’s convergence, avoid overfitting, and improve the model’s generalization performance. In addition, experiment results on the Indian Pines, University of Pavia, Tea, and Salinas datasets reveal that the proposed MFDFN framework outperforms current deep-learning-based methods in terms of comprehensive classification effectiveness evaluation.

A Scalable Graph-Based Framework for Multi-Organ Histology Image Classification

Graph-based approaches are successful for histology image classification tasks but still face many challenges, such as: 1) the lack of nuclei-level labels and the significant variations between histology images make it extremely difficult to extract discriminative high-level nuclei features like nuclei type, texture and micro-environment; 2) graph-based approaches cannot handle large-scale cell graph nodes typically contained in histology images; and 3) graph neural networks (GNNs) struggle to learn the long-range dependency of cell graphs. To address the above challenges, we propose a scalable graph-based framework for multi-organ histology image classification. We develop a two-step masked nuclei patches supervised training approach to extract discriminative high-level nuclei features for histology images without nuclei-level labels. Additionally, we introduce a nuclei sampling strategy to make our graph-based framework scalable for large-scale cell graphs. Furthermore, we propose <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>H</b></u> ier <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>A</b></u> rchical <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>T</b></u> ransformer Graph Neural <underline xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><b>Net</b></u> work (HAT-Net+) for cell graph classi- fications. HAT-Net+ adopts Transformer to model the long-range dependency of cell graphs and a parameter-free approach to adaptively fuse different hierarchical graph representations of each layer. We achieved the state-of-the-art results on four public histology image classification datasets: CRC dataset (100%), Extended CRC dataset (98%), UZH dataset (96.9%) and BACH dataset (88%). Unlike other methods, our approach can be used in various histology image classification tasks, even for images without nuclei-level labels, indicating its potential in cancer diagnosis. The code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/suyouooooo/HAT-Net</uri> .

A Spectral-Spatial-Dependent Global Learning Framework for Insufficient and Imbalanced Hyperspectral Image Classification.

Deep learning techniques have been widely applied to hyperspectral image (HSI) classification and have achieved great success. However, the deep neural network model has a large parameter space and requires a large number of labeled data. Deep learning methods for HSI classification usually follow a patchwise learning framework. Recently, a fast patch-free global learning (FPGA) architecture was proposed for HSI classification according to global spatial context information. However, FPGA has difficulty in extracting the most discriminative features when the sample data are imbalanced. In this article, a spectral-spatial-dependent global learning (SSDGL) framework based on the global convolutional long short-term memory (GCL) and global joint attention mechanism (GJAM) is proposed for insufficient and imbalanced HSI classification. In SSDGL, the hierarchically balanced (H-B) sampling strategy and the weighted softmax loss are proposed to address the imbalanced sample problem. To effectively distinguish similar spectral characteristics of land cover types, the GCL module is introduced to extract the long short-term dependency of spectral features. To learn the most discriminative feature representations, the GJAM module is proposed to extract attention areas. The experimental results obtained with three public HSI datasets show that the SSDGL has powerful performance in insufficient and imbalanced sample problems and is superior to other state-of-the-art methods.

MF-OMKT: Model fusion based on online mutual knowledge transfer for breast cancer histopathological image classification

Pathological diagnosis is considered as the benchmark for the detection of breast cancer. With the increasing number of patients, computer-aided histopathological image classification can assist pathologists in improving breast cancer diagnosis accuracy and working efficiency. However, a single model is insufficient for effective diagnosis, and this also does not accord with the principle of centralized decision-making. Starting from the real pathological diagnosis scenario, we propose a novel model fusion framework based on online mutual knowledge transfer (MF-OMKT) for breast cancer histopathological image classification. The OMKT part based on deep mutual learning (DML) imitates the mutual communication and learning between multiple experienced pathologists, which can break the isolation of single models and provides sufficient complementarity among heterogeneous networks for MF. The MF part based on adaptive feature fusion uses the complementarity to train a powerful fusion classifier. MF imitates the centralized decision-making process of these pathologists. We used the MF-OMKT model to classify breast cancer histopathological images (BreakHis dataset) into benign and malignant as well as eight subtypes. The accuracy of our model reaches the range of [99.27 %, 99.84 %] for binary classification. And that for multi-class classification reaches the range of [96.14 %, 97.53 %]. Additionally, MF-OMKT is applied to the classification of skin cancer images (ISIC 2018 dataset) and achieves an accuracy of 94.90 %. MF-OMKT is an effective and versatile framework for medical image classification.

IDT: An incremental deep tree framework for biological image classification

Nowadays, breast and cervical cancers are respectively the first and fourth most common causes of cancer death in females. It is believed that, automated systems based on artificial intelligence would allow the early diagnostic which increases significantly the chances of proper treatment and survival. Although Convolutional Neural Networks (CNNs) have achieved human-level performance in object classification tasks, the regular growing of the amount of medical data and the continuous increase of the number of classes make them difficult to learn new tasks without being re-trained from scratch. Nevertheless, fine tuning and transfer learning in deep models are techniques that lead to the well-known catastrophic forgetting problem. In this paper, an Incremental Deep Tree (IDT) framework for biological image classification is proposed to address the catastrophic forgetting of CNNs allowing them to learn new classes while maintaining acceptable accuracies on the previously learnt ones. To evaluate the performance of our approach, the IDT framework is compared against with three popular incremental methods, namely iCaRL, LwF and SupportNet. The experimental results on MNIST dataset achieved 87 % of accuracy and the obtained values on the BreakHis, the LBC and the SIPaKMeD datasets are promising with 92 %, 98 % and 93 % respectively.