Set Of Images Research Articles

EARLY STAGES OF COLORECTAL CANCER CHARACTERIZATION BY AUTOFLUORESCENCE 3D MICROSCOPY: A PRELIMINARY STUDY.

Colorectal cancer is one of the most prevalent pathologies worldwide whose prognosis is linked to early detection. Colonoscopy is the gold standard for screening, and diagnosis is usually made histologically from biopsies. Aiming to reduce the inspection and diagnostic time as well as the biopsies and resources involved, other techniques are being promoted to conduct accurate in vivo colonoscopy assessments. Optical biopsy aims to detect normal and neoplastic tissues analysing the autofluorescence spectrum based on the changes in the distribution and concentration of autofluorescent molecules caused by colorectal cancer. Therefore, the autofluorescence contribution analysed by image processing techniques could be an approach to a faster characterization of the target tissue. Quantify intensity parameters through digital processing of two data sets of three-dimensional widefield autofluorescence microscopy images, acquired by fresh colon tissue samples from a colorectal cancer murine model. Additionally, analyse the autofluorescence data to provide a characterization over a volume of approximately 50 µm of the colon mucosa for each image, at second (2nd), fourth (4th) and eighth (8th) weeks after colorectal cancer induction. Development of a colorectal cancer murine model using azoxymethane/dextran sodium sulphate induction, and data sets acquisition of Z-stack images by widefield autofluorescence microscopy, from control and colorectal cancer induced animals. Pre-processing steps of intensity value adjustments followed by quantification and characterization procedures using image processing workflow automation by Fiji's macros, and statistical data analysis. The effectiveness of the colorectal cancer induction model was corroborated by a histological assessment to correlate and validate the link between histological and autofluorescence changes. The image digital processing methodology proposed was then performed on the three-dimensional images from control mice and from the 2nd, 4th, and 8th weeks after colorectal cancer chemical induction, for each data set. Statistical analyses found significant differences in the mean, standard deviation, and minimum parameters between control samples and those of the 2nd week after induction with respect to the 4th week of the first experimental study. This suggests that the characteristics of colorectal cancer can be detected after the 2nd week post-induction. The use of autofluorescence still exhibits levels of variability that prevent greater systematization of the data obtained during the progression of colorectal cancer. However, these preliminary outcomes could be considered an approach to the three-dimensional characterization of the autofluorescence of colorectal tissue, describing the autofluorescence features of samples coming from dysplasia to colorectal cancer. • A new digital image processing method was developed to measure intensity in 3D autofluorescence images of colorectal samples using a CRC mouse model. • This method showed that autofluorescence intensity in colon mucosa is similar in healthy tissue but changes significantly in tumor development. • Statistical analysis revealed CRC traits detectable from the second week post-induction, aiding in early CRC detection. • The study provides a basis for 3D autofluorescence characterization in colorectal tissue from dysplasia to cancer, although variability in autofluorescence limits data systematization during cancer progression.

Structural and functional features of asthma participants with fixed airway obstruction using CT imaging and 1D computational fluid dynamics: A feasibility study.

Asthma with fixed airway obstruction (FAO) is associated with significant morbidity and rapid decline in lung function, making its treatment challenging. Quantitative computed tomography (QCT) along with data postprocessing is a useful tool to obtain detailed information on airway structure, parenchymal function, and computational flow features. In this study, we aim to identify the structural and functional differences between asthma with and without FAO. The FAO group was defined by a ratio of forced expiratory volume in 1 s (FEV1 ) to forced vital capacity (FVC), FEV1 /FVC <0.7. Accordingly, we obtained two sets of QCT images at inspiration and expiration of asthma subjects without (N = 24) and with FAO (N = 12). Structural and functional QCT-derived airway variables were extracted, including normalized hydraulic diameter, normalized airway wall thickness, functional small airway disease, and emphysema percentage. A one-dimensional (1D) computational fluid dynamics (CFD) model considering airway deformation was used to compare the pressure distribution between the two groups. The computational pressures showed strong correlations with the pulmonary function test (PFT)-based metrics. In conclusion, asthma participants with FAO had worse lung functions and higher-pressure drops than those without FAO.

ViComp: Video Compensation for Projector-Camera Systems.

Projector video compensation aims to cancel the geometric and photometric distortions caused by non-ideal projection surfaces and environments when projecting videos. Most existing projector compensation methods start by projecting and capturing a set of sampling images, followed by an offline compensation model training step. Thus, abundant user effort is required before the users can watch the video. Moreover, the sampling images have little prior knowledge of the video content and may lead to suboptimal results. To address these issues, this paper builds a video compensation system that can online adapt the compensation parameters. Our approach consists of five threads and can perform compensation, projection, capturing, and short-term and long-term model updates in parallel. Due to the parallel mechanism, rather than projecting and capturing hundreds of sampling images and training the model offline, we can directly use the projected and captured video frames for model updates on the fly. To quickly apply to the new environment, we introduce a deep learning-based compensation model that integrates a fixed transformer-based method and a novel CNN-based network. Moreover, for fast convergence and to reduce error accumulation during fine-tuning, we present a strategy that cooperates with short-term and long-term memory model updates. Experiments show that it significantly outperforms state-of-the-art baselines.

From prediction to measurement, an efficient method for digital human model obtainment

Digital human has been increasingly used in industry, for example in Metaverse which has been a popular topic in recent years. The existing method of obtaining digital human models are either expensive or lack of accuracy. In this paper, we discuss a novel method to reconstruct a 3D human model from 2D images captured by a monocular camera. The input of our method only requires a set of rotated human body images that can accept slight movement. First, we apply a deep learning method to predict an initial 3D human body model from multi-view human body images. Then the total detailed digital human model will be computed and optimized. The typical method requires the human body and cameras fixed to obtain a visual hull from a significant number of camera images. This could be extremely expensive and inconvenient when such an application is developed for online users. Compared to the structural lighting measurement system, our predict-optimized framework only requires several input images captured by personal equipment to provide enough accuracy and online use resolution results.

Global strategy for robust air‐light estimation in dehazing

AbstractThis letter proposes a novel approach to enhance the robustness of air‐light estimation for dehazing. Unlike most existing methods, it employs a global strategy, considering all pixels instead of specific individual ones, for recovering air‐light. Through an iterative algorithm via the Gray World (GW), the authors extract the air‐light orientation from the entire image. Next, a global detail‐preserving algorithm is designed to determine the optimal magnitude of air‐light. Experimental results on a diverse set of hazy images reveal that the authors’ method outperforms other state‐of‐the‐art alternatives, highlighting the advantage of air‐light estimation using the entire image information.

Generalized super-resolution 4D Flow MRI - using ensemble learning to extend across the cardiovascular system.

4D Flow Magnetic Resonance Imaging (4D Flow MRI) is a non-invasive measurement technique capable of quantifying blood flow across the cardiovascular system. While practical use is limited by spatial resolution and image noise, incorporation of trained super-resolution (SR) networks has potential to enhance image quality post-scan. However, these efforts have predominantly been restricted to narrowly defined cardiovascular domains, with limited exploration of how SR performance extends across the cardiovascular system; a task aggravated by contrasting hemodynamic conditions apparent across the cardiovasculature. The aim of our study was therefore to explore the generalizability of SR 4D Flow MRI using a combination of existing super-resolution base models, novel heterogeneous training sets, and dedicated ensemble learning techniques; the latter-most being effectively used for improved domain adaption in other domains or modalities, however, with no previous exploration in the setting of 4D Flow MRI. With synthetic training data generated across three disparate domains (cardiac, aortic, cerebrovascular), varying convolutional base and ensemble learners were evaluated as a function of domain and architecture, quantifying performance on both in-silico and acquired in-vivo data from the same three domains. Results show that both bagging and stacking ensembling enhance SR performance across domains, accurately predicting high-resolution velocities from low-resolution input data in-silico. Likewise, optimized networks successfully recover native resolution velocities from downsampled in-vivo data, as well as show qualitative potential in generating denoised SR-images from clinicallevel input data. In conclusion, our work presents a viable approach for generalized SR 4D Flow MRI, with the novel use of ensemble learning in the setting of advanced fullfield flow imaging extending utility across various clinical areas of interest.

A New 6D Hyperchaos-Based Medical Image Encryption Scheme Using k-Fibonacci Numbers

In the era of information technology, hospitals, medical centers, doctors and health specialists share millions of images. Securing these images is essential to maintaining patients’ privacy. Several cryptographic algorithms are implemented to meet the increasing demands of transmission systems. As a contribution to securing these data, we propose a novel robust and efficient algorithm. We randomly generate numbers from a six-dimensional hyperchaotic system and Arnold’s cat map to confuse the original images. The confused images are then diffused using a k-Fibonacci matrix. The performance of the proposed algorithm was evaluated using several parameters tested on a set of reference images of different sizes and modalities. The obtained results are conclusive and the performances are excellent, sometimes exceeding those found by other recent algorithms proposed in the literature.

Co-creating art with generative artificial intelligence: Implications for artworks and artists

Synthetic visual art is becoming a commodity due to generative artificial intelligence (AI). The trend of using AI for co-creation will not spare artists’ creative processes, and it is important to understand how the use of generative AI at different stages of the creative process affects both the evaluation of the artist and the result of the human-machine collaboration (i.e., the visual artifact). In three experiments (N = 560), this research explores how the evaluation of artworks is transformed by the revelation that the artist collaborated with AI at different stages of the creative process. The results show that co-created art is less liked and recognized, especially when AI was used in the implementation stage. While co-created art is perceived as more novel, it lacks creative authenticity, which exerts a dominant influence. The results also show that artists’ perceptions suffer from the co-creation process, and that artists who co-create are less admired because they are perceived as less authentic. Two boundary conditions are identified. The negative effect can be mitigated by disclosing the level of artist involvement in co-creation with AI (e.g., by training the algorithm on a curated set of images vs. simply prompting an off-the-shelf AI image generator). In the context of art that is perceived as commercially motivated (e.g., stock images), the effect is also diminished. This research has important implications for the literature on human-AI-collaboration, research on authenticity, and the ongoing policy debate regarding the transparency of algorithmic presence.

Exploring Frequency Band-Based Biomarkers of EEG Signals for Mild Cognitive Impairment Detection.

Mild Cognitive Impairment (MCI) is often considered a precursor to Alzheimer's disease (AD), with a high likelihood of progression. Accurate and timely diagnosis of MCI is essential for halting the progression of AD and other forms of dementia. Electroencephalography (EEG) is the prevalent method for identifying MCI biomarkers. Frequency band-based EEG biomarkers are crucial for identifying MCI as they capture neuronal activities and connectivity patterns linked to cognitive functions. However, traditional approaches struggle to identify precise frequency band-based biomarkers for MCI diagnosis. To address this challenge, a novel framework has been developed for identifying important frequency sub-bands within EEG signals for MCI detection. In the proposed scheme, the signals are first denoised using a stationary wavelet transformation and segmented into small time frames. Then, four frequency sub-bands are extracted from each segment, and spectrogram images are generated for each sub-band as well as for the full filtered frequency band signal segments. This process produces five different sets of images for five separate frequency bands. Afterwards, a convolutional neural network is used individually on those image sets to perform the classification task. Finally, the obtained results for the tested four sub-bands are compared with the results obtained using the full bandwidth. Our proposed framework was tested on two MCI datasets, and the results indicate that the 16-32 Hz sub-band range has the greatest impact on MCI detection, followed by 4-8 Hz. Furthermore, our framework, utilizing the full frequency band, outperformed existing state-of-the-art methods, indicating its potential for developing diagnostic tools for MCI detection.

Label-free cell classification in holographic flow cytometry through an unbiased learning strategy.

Nowadays, label-free imaging flow cytometry at the single-cell level is considered the stepforward lab-on-a-chip technology to address challenges in clinical diagnostics, biology, life sciences and healthcare. In this framework, digital holography in microscopy promises to be a powerful imaging modality thanks to its multi-refocusing and label-free quantitative phase imaging capabilities, along with the encoding of the highest information content within the imaged samples. Moreover, the recent achievements of new data analysis tools for cell classification based on deep/machine learning, combined with holographic imaging, are urging these systems toward the effective implementation of point of care devices. However, the generalization capabilities of learning-based models may be limited from biases caused by data obtained from other holographic imaging settings and/or different processing approaches. In this paper, we propose a combination of a Mask R-CNN to detect the cells, a convolutional auto-encoder, used to the image feature extraction and operating on unlabelled data, thus overcoming the bias due to data coming from different experimental settings, and a feedforward neural network for single cell classification, that operates on the above extracted features. We demonstrate the proposed approach in the challenging classification task related to the identification of drug-resistant endometrial cancer cells.

Transferring U-Net between low-dose CT denoising tasks: a validation study with varied spatial resolutions.

Recently, deep learning techniques have been widely used in low-dose computed tomography (LDCT) imaging applications for quickly generating high quality computed tomography (CT) images at lower radiation dose levels. The purpose of this study is to validate the reproducibility of the denoising performance of a given network that has been trained in advance across varied LDCT image datasets that are acquired from different imaging systems with different spatial resolutions. Specifically, LDCT images with comparable noise levels but having different spatial resolutions were prepared to train the U-Net. The number of CT images used for the network training, validation and test was 2,400, 300 and 300, respectively. Afterwards, self- and cross-validations among six selected spatial resolutions (62.5, 125, 250, 375, 500, 625 µm) were studied and compared side by side. The residual variance, peak signal to noise ratio (PSNR), normalized root mean square error (NRMSE) and structural similarity (SSIM) were measured and compared. In addition, network retraining on a small number of image set was performed to fine tune the performance of transfer learning among LDCT tasks with varied spatial resolutions. Results demonstrated that the U-Net trained upon LDCT images having a certain spatial resolution can effectively reduce the noise of the other LDCT images having different spatial resolutions. Regardless, results showed that image artifacts would be generated during the above cross validations. For instance, noticeable residual artifacts were presented at the margin and central areas of the object as the resolution inconsistency increased. The retraining results showed that the artifacts caused by the resolution mismatch can be greatly reduced by utilizing about only 20% of the original training data size. This quantitative improvement led to a reduction in the NRMSE from 0.1898 to 0.1263 and an increase in the SSIM from 0.7558 to 0.8036. In conclusion, artifacts would be generated when transferring the U-Net to a LDCT denoising task with different spatial resolution. To maintain the denoising performance, it is recommended to retrain the U-Net with a small amount of datasets having the same target spatial resolution.

Quantitative Analysis of Whole-Mount Fluorescence-Stained Tumor Spheroids in Phenotypic Drug Screens.

Three-dimensional cell cultures, such as spheroids or organoids, serve as important models for drug screening purposes. Optical tissue clearing (OTC) enhances the visualization of fluorescence stainings and enables in toto microscopy of 3D cell culture models. Furthermore, subsequent automated image analysis tools convert qualitative confocal image sets into quantitative data. In this chapter, we describe a detailed protocol for preparation of HT29 cancer spheroids, 3D in toto immunostaining, glycerol-based OTC, whole-mount imaging, and semi-automated downstream image processing and segmentation for nuclear image analysis using open-source software.

Image Insertion Using Depth- and Topology- Constrained Minimum Spanning Tree for Compressed Image Sets

Image Insertion Using Depth- and Topology- Constrained Minimum Spanning Tree for Compressed Image Sets

РАСПОЗНАВАНИЕ АКТИВНОСТИ СТУДЕНТОВ В АУДИТОРИИ МЕТОДАМИ ГЛУБОКОГО ОБУЧЕНИЯ

Human activity recognition is one of the actively developing areas of artificial intelligence that can be implemented in learning environments to improve safety, efficiency and quality of education. Deep learning transfer is a widespread method of training neural networks and has proven its effectiveness in such complex tasks as digital image and video processing. In this paper, we propose a model for recognizing different student activities using pretrained models including VGG16, ResNet50, DenseNet201, EfficientNetB0 and Xception, which are then trained using the method proposed in the paper on a Class box image set created by the authors. The EfficientNetB0 model showed the maximum performance among the considered models and achieved an accuracy of 94,25%. The system proposed in this study aims to create a safer and more productive learning environment for students and teachers.

Non-numerical features fail to predict numerical performance in real-world stimuli

It has been proposed that humans use non-numerical features (such as convex hull and surface area) to estimate the number of objects in a scene. This would be an evolutionarily advantageous strategy if such features truly patterned with number in the world, but this has never been empirically tested. Here, we quantify the strength of the relationship between number and non-numerical features in two relevant image sets: the illustrations from children’s counting books, and real-world photographs. We find that non-numerical features are much less predictive of the number of objects in counting books than in photographs, despite the former being specifically designed for use in teaching children about numbers. Then, across three behavioral experiments, we ask whether the stronger relationship in photographs predicts better number estimation performance in adults (N = 120) and in children (N = 94; M age = 7;2 years). Our experiments reveal that number estimation is easier from the counting books than the photographs, even though non-numerical features are less predictive of number in books. This analysis uses real-world stimuli and draws into question the claim that non-numerical features are intrinsically involved in number extraction.

Domain Incremental Object Detection Based on Feature Space Topology Preserving Strategy

Object detection with the capacity to incrementally adapt to new domains is a crucial yet relatively under-explored research topic. The <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">catastrophic forgetting</i> problem presents a significant challenge to achieve this goal, where the model’s performance improves quickly in new conditions but deteriorates sharply in old ones after several incremental learning sessions. Drawing on recent discoveries in visual memories of the human brain, we introduce the Topology-Preserving Domain Incremental Object Detection (TP-DIOD) approach, which aims to address the catastrophic forgetting problem by extracting the topological structure of the feature space learned by the Convolutional Neural Network (CNN) model and preserving this topology during the subsequent incremental learning sessions. Specifically, we model the feature space topology using the self-organizing map (SOM) and construct an anchor image set based on the centroid vectors of the SOM nodes to memorize the feature space topology. We then develop the anchor loss function to penalize the topological changes of the feature space during the subsequent incremental learning sessions. Experimental evaluations on two sets of datasets demonstrate the effectiveness of the proposed TP-DIOD method in mitigating the catastrophic forgetting problem and achieving high accuracy on both old and new domain datasets.

Accelerating Image Classification based on a Model for Estimating Descriptor-to-Class Distance

The article describes a method of image classification based on the estimation of the distance to the etalon class. The implementation of estimates gives a significant gain in classification speed compared to linear search while maintaining a decent level of accuracy. The methodology is based on the use of the triangle inequality for images given by a set of binary vectors as descriptors of the image key points. The evaluation is applied to the "object descriptor – etalon" classification method, which is based on the descriptor voting procedure. An analysis of evaluation options is carried out using the parameters of the etalon sets in the form of a medoid and the closest or farthest points from it. The gain in classification time compared to the traditional method proportionally depends on the number of descriptors in the etalon description. Software simulation of classifiers with the implementation of evaluation shows a gain in speed of 350-450 times for the description of 500 descriptors while maintaining one hundred percent classification accuracy on the training set of similar NFT images. A control sample experiment shows that the classifier with estimation can respond better to image details compared to the traditional method.

External Defects and Soil Deposits Identification on Potato Tubers using 2CCD Camera and Principal Component Images

Precise recognition of potato external defects and the ability to identify defects and non-defect areas are in demand. Common scab represents a significant issue that requires detection, yet identifying the extent of common scab infection remains challenging when using a standard RGB camera. In this research, a 2CCD camera system that could obtain a set of RGB and near-infrared images, which could enhance defect detection, has been used. Image segmentation strategies based on a single principal component image and the principal component pseudo-colored image have been proposed to identify external potato defects while excluding soil deposits on the potato surface, often recognized as defects by the normal color machine vision system. Performance metrics calculation results show relatively good results, with segmentation true accuracy around 64% for both methods. Principal component pseudo-colored images were able to discriminate defects area and soil deposits in a single image. The methods presented in this paper could be used as the basis to develop further classification and grading algorithms.

AntiHalluciNet: A Potential Auditing Tool of the Behavior of Deep Learning Denoising Models in Low-Dose Computed Tomography.

Gaining the ability to audit the behavior of deep learning (DL) denoising models is of crucial importance to prevent potential hallucinations and adversarial clinical consequences. We present a preliminary version of AntiHalluciNet, which is designed to predict spurious structural components embedded in the residual noise from DL denoising models in low-dose CT and assess its feasibility for auditing the behavior of DL denoising models. We created a paired set of structure-embedded and pure noise images and trained AntiHalluciNet to predict spurious structures in the structure-embedded noise images. The performance of AntiHalluciNet was evaluated by using a newly devised residual structure index (RSI), which represents the prediction confidence based on the presence of structural components in the residual noise image. We also evaluated whether AntiHalluciNet could assess the image fidelity of a denoised image by using only a noise component instead of measuring the SSIM, which requires both reference and test images. Then, we explored the potential of AntiHalluciNet for auditing the behavior of DL denoising models. AntiHalluciNet was applied to three DL denoising models (two pre-trained models, RED-CNN and CTformer, and a commercial software, ClariCT.AI [version 1.2.3]), and whether AntiHalluciNet could discriminate between the noise purity performances of DL denoising models was assessed. AntiHalluciNet demonstrated an excellent performance in predicting the presence of structural components. The RSI values for the structural-embedded and pure noise images measured using the 50% low-dose dataset were 0.57 ± 31 and 0.02 ± 0.02, respectively, showing a substantial difference with a p-value < 0.0001. The AntiHalluciNet-derived RSI could differentiate between the quality of the degraded denoised images, with measurement values of 0.27, 0.41, 0.48, and 0.52 for the 25%, 50%, 75%, and 100% mixing rates of the degradation component, which showed a higher differentiation potential compared with the SSIM values of 0.9603, 0.9579, 0.9490, and 0.9333. The RSI measurements from the residual images of the three DL denoising models showed a distinct distribution, being 0.28 ± 0.06, 0.21 ± 0.06, and 0.15 ± 0.03 for RED-CNN, CTformer, and ClariCT.AI, respectively. AntiHalluciNet has the potential to predict the structural components embedded in the residual noise from DL denoising models in low-dose CT. With AntiHalluciNet, it is feasible to audit the performance and behavior of DL denoising models in clinical environments where only residual noise images are available.

An Analysis of Visual Preference and Characteristics through a Woodland Garden Perception Survey

Background and objective: Woodland gardens, or gardens designed to emulate the aesthetic and environmental characteristics of forest vegetation, can assist in resolving various environmental and societal problems. However, research regarding woodland gardens in a Korean context has been insufficient, as the concept has only recently been introduced to Korea. This study was conducted to investigate the Korean public's perceptions of two types of woodland gardens and to suggest future directions for the popularization of woodland gardens in Korea.Methods: This study was carried out based on a survey. The respondents were provided with a questionnaire on three sets of images representing two types of woodland garden (naturalistic and urban) and a typical formal garden. The questionnaire was designed based on the semantic differential method to gather information on the general public's recognition of the concept of woodland gardens, and their preference and perception of each type of garden. The collected data were analyzed using SPSS Statistics 29.Results: The results suggest that the majority of the respondents were familiar with the term "woodland garden." Of the types of gardens, preference for naturalistic woodland gardens (NWGs) was the highest. Landscape adjectives associated with each type of garden were natural, harmonious, comfortable and simple for NWGs, and organized, artificial, simple, poor, and comfortable for urban woodland gardens (UWGs). A factor analysis on the adjectives identified four factors for each type. Of the identified factors, comfort and stability were found to have particularly greater effects on preference.Conclusion: Preference for NWGs was greater than UWGs, due to the perception that they provided greater comfort and stability. It is expected that designing woodland gardens based on the finding of this study would aid in the popularization of woodland gardens, and the advancement of garden culture in Korea.