Image Categorization Research Articles

Establishing an AI model and application for automated capsule endoscopy recognition based on convolutional neural networks (with video).

Although capsule endoscopy (CE) is a crucial tool for diagnosing small bowel diseases, the need to process a vast number of images imposes a significant workload on physicians, leading to a high risk of missed diagnoses. This study aims to develop an artificial intelligence (AI) model and application based on convolutional neural networks that can automatically recognize various lesions in small bowel capsule endoscopy. Three small bowel capsule endoscopy datasets were used for AI model training, validation, and testing, encompassing 12 categories of images. The model's performance was evaluated using metrics such as AUC, sensitivity, specificity, precision, accuracy, and F1 score to select the best model. A human-machine comparison experiment was conducted using the best model and endoscopists with varying levels of experience. Model interpretability was analyzed using Grad-CAM and SHAP techniques. Finally, a clinical application was developed based on the best model using PyQt5 technology. A total of 34,303 images were included in this study. The best model, MobileNetv3-large, achieved a weighted average sensitivity of 87.17%, specificity of 98.77%, and an AUC of 0.9897 across all categories. The application developed based on this model performed exceptionally well in comparison with endoscopists, achieving an accuracy of 87.17% and a processing speed of 75.04 frames per second, surpassing endoscopists of varying experience levels. The AI model and application developed based on convolutional neural networks can quickly and accurately identify 12 types of small bowel lesions. With its high sensitivity, this system can effectively assist physicians in interpreting small bowel capsule endoscopy images.Future studies will validate the AI system for video evaluations and real-world clinical integration.

O contracinema feminista de Agnès Varda: imagens do desnudamento na reinvenção do amor

The text aims to characterize the feminist counter-cinema of Agnès Varda in three fiction films, Cleo from 5 to 7 (1962), One sings, the other doesn’t (1976) and Vagabond (1985), based on an interpretative analysis that outlines three categories of images of nudity: literal, existential-metaphorical and cinematographic. The cine-pamphlet Women reply: our body, our sex (1975) summarizes the common proposal of the films and sheds light on their goal: the reinvention of love. This is an exercise in film analysis and philosophical interpretation, in dialogue with studies in history, theory and criticism of cinema, which seeks to characterize a particular form of feminist counter-cinema.

Explicit and Implicit Preference for Symmetry Across Object Categories

Symmetry affects aesthetic judgements, and it has been extensively studied at least for faces and abstract objects. We examined the role of bilateral symmetry on aesthetic judgements across different types of stimuli. It is important to test if symmetry is equally effective in the context of objects expected to be symmetrical, e.g., faces, and objects that are almost never symmetrical, e.g., landscapes. We used the following categories: angular shapes, smooth shapes, landscapes, flowers, female faces, and male faces. We selected these image categories considering their differing degrees of curvature, familiarity to the viewer, and tendency to be perceived as ensembles, as opposed to standalone objects. We also included blobs, manipulating landscapes into blurry tessellated patterns featuring patches of color, to remove familiarity while preserving the appearance of ensembles. For each item in these categories, images were modified to obtain perfect bilateral symmetry. We collected both explicit ratings and implicit measures of symmetry preference. For landscapes, there was a clear preference for the non-symmetrical (original) version. We observed a dissociation between explicit and implicit measures. Implicit measures demonstrated positive associations for all categories.

Enhanced Computer-Aided Digital Imaging Technique for Predictions in Breast Cancer

Background: Breast cancer (BRCA) is the most frequently diagnosed cancer in women, with a rise in occurrences and fatalities. The field of BRCA prediction and diagnosis has witnessed significant advancements in recent years, particularly emphasizing enhanced computer-aided digital imaging techniques, and has emerged as a powerful ally in the prediction of BRCA through histopathology image analysis. A number of approaches have been suggested in recent years for the categorization of histopathology BRCA images into benign and malignant as it examines the images at cellular level. The histopathology slides must be manually analysed which is time consuming and tiresome and is prone to human error. Additionally, different laboratories occasionally have different interpretation of these images. Methods: This paper focuses on implementing a framework for Computer-Aided digital imaging technique that can serve as a decision support. With recent advancements in computing power the analysis of BRCA histopathology image samples has become easier. Stain normalization (SN), segmentation, feature extraction and classification are the steps to categorize the cancer into benign and malignant. Nuclei segmentation is a crucial step that needs to be taken into account in order to establish malignancy. These are considered essential for early diagnosis of BRCA. A unique method proposed for BRCA prediction is put forward. To maximize the prediction accuracy, the suggested method is integrated with machine learning (ML) techniques and clinical data is used to evaluate the suggested approach. Results: This strategy is adaptable to many cancer types and imaging techniques. The suggested technique is applied to clinical data and is integrated with logistic regression and K-Nearest Neighbor resulting in accuracy of 92.10% and 86.89% respectively for BRCA histopathology images. Conclusion: The objective of this work is to validate the proposed model which takes input as feature pattern for a given label. For the collected clinical samples, the model is able to classify the input as benign or malignant. The proposed model worked efficiently for different BC datasets and performed classification task successfully. Integrating mathematical model (MM) with ML model for interpreting histopathology BRCA is a potential area of research in the field of digital pathology.

FACSNet: Forensics aided content selection network for heterogeneous image steganalysis

The main goal of image steganalysis, as a technique of confrontation with steganography, is to determine the presence or absence of secret information in conjunction with the specific statistical characteristics of the carrier. With the development of deep learning technology in recent years, the performance of steganography has been gradually enhanced. Especially for the complex reality environment, the image content is mixed and heterogeneous, which brings great challenges to the practical application of image steganalysis technology. In order to solve this problem, we design a forensics aided content selection network (FACSNet) for heterogeneous image steganalysis. Considering the heterogeneous situation of real images, a forensics aided module is introduced to pre-categorise the images to be tested, so that the network is able to detect different categories of images in a more targeted way. The complexity of the images is also further analysed and classified using the content selection module to train a more adapted steganalyser. By doing this, the network is allowed to achieve better performance in recognising and classifying the heterogeneous images for detection. Experimental results show that our designed FACSNet is able to achieve excellent detection performance in heterogeneous environments, improving the detection accuracy by up to 7.14% points, with certain robustness and practicality.

Cephalometric landmark annotation using transfer learning: Detectron2 and YOLOv8 baselines on a diverse cephalometric image dataset

BackgroundCephalometric landmark annotation is a key challenge in radiographic analysis, requiring automation due to its time-consuming process and inherent subjectivity. This study investigates the application of advanced transfer learning techniques to enhance the accuracy of anatomical landmarks in cephalometric images, which is a vital aspect of orthodontic diagnosis and treatment planning. MethodsWe assess the suitability of transfer learning methods by employing state-of-the-art pose estimation models. The first framework is Detectron2, with two baselines featuring different ResNet backbone architectures: rcnn_R_50_FPN_3x and rcnn_R_101_FPN_3x. The second framework is YOLOv8, with three variants reflecting different network sizes: YOLOv8s-pose, YOLOv8m-pose, and YOLOv8l-pose. These pose estimation models are adopted for the landmark annotation task. The models are trained and evaluated on the DiverseCEPH19 dataset, comprising 1692 radiographic images with 19 landmarks, and their performance is analyzed across various images categories within the dataset. Additionally, the study is extended to a benchmark dataset of 400 images to investigate how dataset size impacts the performance of these frameworks. ResultsDespite variations in objectives and evaluation metrics between pose estimation and landmark localization tasks, the results are promising. Detectron2's variant outperforms others with an accuracy of 85.89%, compared to 72.92% achieved by YOLOv8's variant on the DiverseCEPH19 dataset. This superior performance is also observed in the smaller benchmark dataset, where Detectron2 consistently maintains higher accuracy than YOLOv8. ConclusionThe noted enhancements in annotation precision suggest the suitability of Detectron2 for deployment in applications that require high precision while taking into account factors such as model size, inference time, and resource utilization, the evidence favors YOLOv8 baselines.

Machine Learning Algorithms for Image Classification: A Comparative Review

In the realm of computer vision, one of the most important challenges is image categorization. Its goal is to assign semantic labels to photographs based on a predetermined set of categories, and it does this via a process called semantic labeling. In attempt to find a solution to this issue, several distinct machine learning algorithms have been developed throughout the course of time; each strategy has its own unique mix of benefits and drawbacks. This article gives an in-depth review and comparison of a wide variety of well-known machine learning approaches for the classification of pictures. This review covers a wide range of algorithms, including more traditional approaches such as Support Vector Machines (SVMs), Convolutional Neural Networks (CNNs), and Transfer Learning using pretrained models such as VGG, Reset, and Inception.

Recent Progress and Current Status of Artificial Intelligence in Skin Cancer Diagnosis: A Systematic Review—Where do we Stand?

Introduction: Skin cancer is one of the most prevalent forms worldwide, with a significant increase in recent decades. Real-time and accurate detection can reduce the burdens of invasive treatments. The advent of Artificial Intelligence (AI) and Machine learning (ML) has introduced multiple tools to aid accurate and early detection, categorizing dermatological images and proving especially valuable in regions with a shortage of specialists. However, the adoption of these AI-based tools requires consideration of efficacy, safety, and ethical implications. Objective: The systematic review aims to evaluate existing research on the detection, categorization, and assessment of skin cancer images. Methods: The systematic literature review is conducted based on studies published from 2018 to 2023 in PubMed, Scopus, Embase, Web of Science, IEEE Xplore, ACM DL, and Ovid MEDLINE. Study selection, data extraction, and inclusion are carried out after a proper evaluation of the studies. Results are presented in tables and figures using a narrative synthesis. Results: The search identified 687 studies from the database. However, after three phases of identification, screening, and evaluation, only 16 studies were chosen, focusing on developing and validating AI tools to detect, diagnose, and categorize skin cancer. This systematic review covers the selected studies in multiple dimensions. Conclusion: The use of AI and ML in dermatology has revolutionized the early detection of cancer, but it is necessary to validate and collaborate with healthcare professionals to ensure efficacy, safety, and effectiveness.

Decoupling Deep Learning for Enhanced Image Recognition Interpretability

The quest for enhancing the interpretability of neural networks has become a prominent focus in recent research endeavors. Prototype-based neural networks have emerged as a promising avenue for imbuing models with interpretability by gauging the similarity between image components and category prototypes to inform decision-making. However, these networks face challenges as they share similarity activations during both the inference and explanation processes, creating a tradeoff between accuracy and interpretability. To address this issue and ensure that a network achieves high accuracy and robust interpretability in the classification process, this article introduces a groundbreaking prototype-based neural network termed the “Decoupling Prototypical Network” (DProtoNet). This novel architecture comprises encoder, inference, and interpretation modules. In the encoder module, we introduce decoupling feature masks to facilitate the generation of feature vectors and prototypes, enhancing the generalization capabilities of the model. The inference module leverages these feature vectors and prototypes to make predictions based on similarity comparisons, thereby preserving an interpretable inference structure. Meanwhile, the interpretation module advances the field by presenting a novel approach: a “multiple dynamic masks decoder” that replaces conventional upsampling similarity activations. This decoder operates by perturbing images with mask vectors of varying sizes and learning saliency maps through consistent activation. This methodology offers a precise and innovative means of interpreting prototype-based networks. DProtoNet effectively separates the inference and explanation components within prototype-based networks. By eliminating the constraints imposed by shared similarity activations during the inference and explanation phases, our approach concurrently elevates accuracy and interpretability. Experimental evaluations on diverse public natural datasets, including CUB-200-2011, Stanford Cars, and medical datasets like RSNA and iChallenge-PM, corroborate the substantial enhancements achieved by our method compared to previous state-of-the-art approaches. Furthermore, ablation studies are conducted to provide additional evidence of the effectiveness of our proposed components.

Low-Light Image Enhancement Technology Based on Image Categorization, Processing and Retinex Deep Network

Low-Light Image Enhancement Technology Based on Image Categorization, Processing and Retinex Deep Network

Adaptive classification of artistic images using multi-scale convolutional neural networks

The current art image classification methods have low recall and accuracy rate issues . To improve the classification performance of art images, a new adaptive classification method is designed employing multi-scale convolutional neural networks (CNNs). Firstly, the multi-scale Retinex algorithm with color recovery is used to complete the enhancement processing of art images. Then the extreme pixel ratio is utilized to evaluate the image quality and obtain the art image that can be analyzed. Afterward, edge detection technology is implemented to extract the key features in the image and use them as initial values of the item to be trained in the classification model. Finally, a multi-scale convolutional neural network (CNN) is constructed by using extended convolutions, and the characteristics of each level network are set. The decision fusion method based on maximum output probability is employed to calculate different subclassifies’ probabilities and determine the final category of an input image to realize the art image adaptive classification. The experimental results show that the proposed method can effectively improve the recall rate and precision rate of art images and obtain reliable image classification results.

Transformer based on multi-scale local feature for colon cancer histopathological image classification

Colon cancer histopathological image recognition is an important method in the early screening of colon cancer. At present, most whole slide images (WSIs) classification models only consider the features of a single patch, and do not consider the features of the WSIs region. To expand the receptive field of the patches and obtain its surrounding pathological information, this paper proposes a transformer based on multi-scale local feature for colon cancer histopathological image classification model. The model samples patches based on farthest point sampling (FPS). A multi-scale grouping scheme is also proposed to capture WSI local regions. Then the classification labels, feature information and local area information of sampled patches are embedded into the transformer encoder. In addition, the focal loss function is adopted to solve the problem of unbalanced categories of colon cancer histopathological images. Experimental results demonstrate that our model surpasses competing methods in performance on both hospital colon cancer datasets and The Cancer Genome Atlas(TCGA) colon cancer datasets.

Overcoming Dataset Bias: A Deep Learning Approach to Improve Cross-Cultural Image Classification

The difficulties and strategies concerning cross-ethnic image categorization are discussed throughout this report based on deep learning techniques for preventing model bias towards specific ethnic groups. In this part of the project, we continued our discussion of the theory and practice of bias in training datasets and how it impacts the model in the case of emotion recognition and facial analysis using simulations. Three real-time scenarios were explored: public security applications, health status evaluations, education performance, and awareness, all of which must include culturally sensitive data to maximize performance. Some of the issues we defined include the data bias problem, the problem that different cultures exhibit different levels of emotions, and technical concerns such as the limitations of machine learning algorithms, among others that we have described in the paper. Some solutions we provided include data augmentation, real-time learning, and ethical concerns such as using machine learning in making decisions. In doing so, we propose solutions that include building models that are not only precise but also culturally sensitive to avoid prejudice in applications, ranging from credit scoring to complaints handling.

Length of Stay and Destination Image: Insights from Social Media Content of Day Trippers and Tourists

ABSTRACT Social media platforms have a significant role in determining destination image. This study examines the impact of length of stay on destination image as reflected on visitors’ posts on social media through a comparative analysis of day trippers and tourists. Two text mining methods (Term Frequency-Inverse Document Frequency and Latent Dirichlet Allocation) and an image classification model (ResNet) were applied to Weibo data to identify day trippers’ and tourists’ online destination image. Differences were found between day trippers and tourists when examining keywords, topics, and visual scenes. The keyword-based image was predominantly utilitarian for day trippers and more recreational-oriented for tourists. Moreover, tourists shared a greater variety of topic-based image attributes (e.g. accommodation, catering, activity) than day trippers, and form an abundant holistic image. Both groups were highly consistent in the visual category of common images and top-10 visual scenes of unique features, though significant differences were recorded when considering gender.

Potential of multimodal large language models for data mining of medical images and free-text reports

Medical images and radiology reports are essential for physicians to diagnose medical conditions. However, the vast diversity and cross-source heterogeneity inherent in these data have posed significant challenges to the generalizability of current data-mining methods for clinical decision-making. Recently, multimodal large language models (MLLMs), especially Gemini-Vision-series (Gemini) and GPT-4-series (GPT-4) models, have revolutionized numerous domains, significantly impacting the medical field. In this study, we conducted a detailed evaluation of the performance of the Gemini series models (including Gemini-1.0-Pro-Vision, Gemini-1.5-Pro, and Gemini-1.5-Flash) and GPT series models (including GPT-4o, GPT-4-Turbo, and GPT-3.5-Turbo) across 14 medical datasets, covering 5 medical imaging categories (dermatology, radiology, dentistry, ophthalmology, and endoscopy) and 3 radiology report datasets. The investigated tasks encompass disease classification, lesion segmentation, anatomical localization, disease diagnosis, report generation, and lesion detection. Moreover, we also validated the performance of the Claude-3-Opus, Yi-Large, Yi-Large-Turbo, and LLaMA 3 models to gain a comprehensive understanding of the MLLM models in the medical field. Our experimental results demonstrated that Gemini-series models excelled in report generation and lesion detection but faces challenges in disease classification and anatomical localization. Conversely, GPT-series models exhibited proficiency in lesion segmentation and anatomical localization but encountered difficulties in disease diagnosis and lesion detection. Additionally, both the Gemini series and GPT series contain models that have demonstrated commendable generation efficiency. While both models hold promise in reducing physician workload, alleviating pressure on limited healthcare resources, and fostering collaboration between clinical practitioners and artificial intelligence technologies, substantial enhancements and comprehensive validations remain imperative before clinical deployment.

Optimizing magnetometers arrays and analysis pipelines for multivariate pattern analysis

BackgroundMultivariate pattern analysis (MVPA) has proven an excellent tool in cognitive neuroscience. It also holds a strong promise when applied to optically-pumped magnetometer-based magnetoencephalography. New methodTo optimize OPM-MEG systems for MVPA experiments this study examines data from a conventional MEG magnetometer array, focusing on appropriate noise reduction techniques for magnetometers. We determined the least required number of sensors needed for robust MVPA for image categorization experiments. ResultsWe found that the use of signal space separation (SSS) without a proper regularization significantly lowered the classification accuracy considering a sub-array of 102 magnetometers or a sub-array of 204 gradiometers. We also found that classification accuracy did not improve when going beyond 30 sensors irrespective of whether SSS has been applied. Comparison with existing methodsThe power spectra of data filtered with SSS has a substantially higher noise floor that data cleaned with SSP or HFC. Consequently, MVPA decoding results obtained from the SSS-filtered data are significantly lower compared to all other methods employed. ConclusionsWhen designing MEG system based on SQUID magnetometers optimized for multivariate analysis for image categorization experiments, about 30 magnetometers are sufficient. We advise against applying SSS filters without a proper regularization to data from MEG and OPM systems prior to performing MVPA as this method, albeit reducing low-frequency external noise contributions, also introduces an increase in broadband noise. We recommend employing noise reduction techniques that either decrease or maintain the noise floor of the data like signal-space projection, homogeneous field correction and gradient noise reduction.

Inhibition of return depends on image category

Inhibition of return depends on image category

Leukocyte classification using relative-relationship-guided contrastive learning

Hematologic diseases and blood disorders can be studied through microscopic examination of blood smear images or chemical assays. Many researchers are focused on utilizing deep learning (DL) to identify, quantify, and classify various types of blood cells, which is crucial for addressing theoretical and practical challenges in disease diagnosis and treatment planning. However, there is a significant deficiency in annotations for leukocyte classification, limiting the effectiveness of current DL methods. Contrastive learning (CL) facilitates the extraction of prior knowledge from unlabeled data, reducing the dependency on manual annotations. While CL demonstrates remarkable achievements in classifying natural images, the direct application to leukocyte classification presents certain defects. We observe that standard data augmentation techniques in CL exhibit varying sensitivity to different categories of white blood cell images. Employing a uniform augmentation strategy may lead the network into an optimization trap, acquiring inadequate representations from erroneous sample relationships. To address this issue, we propose a Relative-Relationship-Guided Contrastive Learning Representation (ReCLR) framework for the leukocyte classification. ReCLR mines positive and negative samples based on relative distance knowledge. Specifically, we provide adversarial guidance for the positive sample, restricting the distance between the positive sample and the original sample less than but as close as possible to the distance between the original sample and the farthest negative sample. Then, we utilize the entropy constraint to regulate the relative distance relationship between the negative and original samples. Finally, the guided positive and negative samples are employed for contrastive learning in leukocyte classification. The extensive experiments, including linear evaluation, domain transfer, and fine-tuning, demonstrate the effectiveness of the proposed method. Our ReCLR achieves accuracies of 92.07%, 65.36%, and 92.49% on three real-world leukocyte datasets, respectively, outperforming several state-of-the-art methods. The source code is released at https://github.com/AlchemyEmperor/ReCLR.

Optimizing Lung Condition Categorization through a Deep Learning Approach to Chest X-ray Image Analysis

Background: Evaluating chest X-rays is a complex and high-demand task due to the intrinsic challenges associated with diagnosing a wide range of pulmonary conditions. Therefore, advanced methodologies are required to categorize multiple conditions from chest X-ray images accurately. Methods: This study introduces an optimized deep learning approach designed for the multi-label categorization of chest X-ray images, covering a broad spectrum of conditions, including lung opacity, normative pulmonary states, COVID-19, bacterial pneumonia, viral pneumonia, and tuberculosis. An optimized deep learning model based on the modified VGG16 architecture with SE blocks was developed and applied to a large dataset of chest X-ray images. The model was evaluated against state-of-the-art techniques using metrics such as accuracy, F1-score, precision, recall, and area under the curve (AUC). Results: The modified VGG16-SE model demonstrated superior performance across all evaluated metrics. The model achieved an accuracy of 98.49%, an F1-score of 98.23%, a precision of 98.41%, a recall of 98.07% and an AUC of 98.86%. Conclusion: This study provides an effective deep learning approach for categorizing chest X-rays. The model’s high performance across various lung conditions suggests its potential for integration into clinical workflows, enhancing the accuracy and speed of pulmonary disease diagnosis.

Deep learning-based ultrasonographic classification of canine chronic kidney disease.

In veterinary medicine, attempts to apply artificial intelligence (AI) to ultrasonography have rarely been reported, and few studies have investigated the value of AI in ultrasonographic diagnosis. This study aimed to develop a deep learning-based model for classifying the status of canine chronic kidney disease (CKD) using renal ultrasonographic images and assess its diagnostic performance in comparison with that of veterinary imaging specialists, thereby verifying its clinical utility. In this study, 883 ultrasonograms were obtained from 198 dogs, including those diagnosed with CKD according to the International Renal Interest Society (IRIS) guidelines and healthy dogs. After preprocessing and labeling each image with its corresponding IRIS stage, the renal regions were extracted and classified based on the IRIS stage using the convolutional neural network-based object detection algorithm You Only Look Once. The training scenarios consisted of multi-class classification, categorization of images into IRIS stages, and four binary classifications based on specific IRIS stages. To prevent model overfitting, we balanced the dataset, implemented early stopping, used lightweight models, and applied dropout techniques. Model performance was assessed using accuracy, recall, precision, F1 score, and receiver operating characteristic curve and compared with the diagnostic accuracy of four specialists. Inter- and intra-observer variabilities among specialists were also evaluated. The developed model exhibited a low accuracy of 0.46 in multi-class classification. However, a significant performance improvement was observed in binary classifications, with the model designed to distinguish stage 3 or higher showing the highest accuracy of 0.85. In this classification, recall, precision, and F1 score values were all 0.85, and the area under the curve was 0.89. Compared with radiologists, whose accuracy ranged from 0.48 to 0.62 in this experimental scenario, the AI model exhibited superiority. Intra-observer reliability among radiologists was substantial, whereas inter-observer variability showed a moderate level of agreement. This study developed a deep-learning framework capable of reliably classifying CKD IRIS stages 3 and 4 in dogs using ultrasonograms. The developed framework demonstrated higher accuracy than veterinary imaging specialists and provided more objective and consistent interpretations. Therefore, deep-learning-based ultrasound diagnostics are potentially valuable tools for diagnosing CKD in dogs.