Image Analysis Techniques Research Articles

Coastal spatial planning using object-based image analysis and image classification techniques

Coastal spatial planning using object-based image analysis and image classification techniques

Automation of Ultrasonographic Optic Nerve Sheath Diameter Measurement: A Scoping Review.

Intracranial pressure (ICP) monitoring is a cornerstone of neurocritical care in managing severe brain injury. However, current invasive ICP monitoring methods carry significant risks, including infection and intracranial hemorrhage, and are contraindicated in certain clinical situations. Additionally, these methods are not universally available. Optic nerve sheath diameter (ONSD) measurement presents a promising noninvasive alternative for ICP monitoring, though its clinical adoption has been limited due to its operator dependence and inconsistencies in imaging acquisition and measurement techniques. Automating both ONSD image acquisition and measurement could enhance accuracy and reliability, thereby improving its utility as a noninvasive ICP estimation tool. A range of image analysis and machine learning (ML) techniques have been applied to address these challenges. In this paper, we provide a narrative review of the current literature on ONSD automation, examining the strengths and limitations of classical image analysis and ML models in improving ONSD-based ICP assessment.

Quantification of morphological characteristics and filamentous bacteria in activated-sludge flocs through quantitative image-analysis techniques incorporating image-processing software and U-Net deep-learning framework

Quantification of morphological characteristics and filamentous bacteria in activated-sludge flocs through quantitative image-analysis techniques incorporating image-processing software and U-Net deep-learning framework

In-situ quality monitoring during embedded bioprinting using integrated microscopy and classical computer vision

Despite significant advances in bioprinting technology, current hardware platforms lack the capability for process monitoring and quality control. This limitation hampers the translation of the technology into industrial GMP-compliant manufacturing settings. As a key step towards a solution, we developed a novel bioprinting platform integrating a high-resolution camera forin-situmonitoring of extrusion outcomes during embedded bioprinting. Leveraging classical computer vision and image analysis techniques, we then created a custom software module for assessing print quality. This module enables quantitative comparison of printer outputs to input points of the computer-aided design model's 2D projections, measuring area and positional accuracy. To showcase the platform's capabilities, we then investigated compatibility with various bioinks, dyes, and support bath materials for both 2D and 3D print path trajectories. In addition, we performed a detailed study on how the rheological properties of granular support hydrogels impact print quality during embedded bioprinting, illustrating a practical application of the platform. Our results demonstrated that lower viscosity, faster thixotropy recovery, and smaller particle sizes significantly enhance print fidelity. This novel bioprinting platform, equipped with integrated process monitoring, holds great potential for establishing auditable and more reproducible biofabrication processes for industrial applications.

Advancing cancer diagnosis and treatment: integrating image analysis and AI algorithms for enhanced clinical practice

Cancer screening and diagnosis with the utilization of innovative Artificial Intelligence tools improved the treatment strategies and patients’ survival. With the rapid development of imaging technologies and the rise of artificial intelligence (AI), there is a significant opportunity to improve cancer diagnostics through the combination of image analysis and AI algorithms. This article provides a comprehensive review of studies that have investigated the application of AI-assisted image processing in cancer diagnosis. We searched the Web of Science and Scopus databases to identify relevant studies published between 2014 and January 2024. The search strategy utilized targeted keywords such as cancer diagnostics, image analysis, artificial intelligence, and advanced imaging techniques. We limited the review to articles written in English and using AI-assisted image processing in cancer diagnosis. The results show that by leveraging machine learning algorithms, including deep learning, computer-aided diagnosis systems have been developed that are efficient in detecting tumors, thereby facilitating early cancer detection. Additionally, various authors have explored the integration of personalized treatment approaches and precision medicine, allowing for the development of treatment plans tailored to individual patient characteristics and needs. The review emphasizes the potential of AI-assisted image processing in revolutionizing cancer diagnostics. The insights gained from this study contribute to the current understanding of the field and pave the way for future research and development aimed at advancing cancer diagnostics using image analysis and artificial intelligence.

Mechanism of Crack Development and Strength Deterioration in Controlled Low-Strength Material in Dry Environment

The continuous expansion at the urban scale has produced a lot of construction waste, which has created increasingly serious problems in the environmental, social, and economic realms. Reuse of this waste can address these problems and is critical for sustainable development. In recent years, construction waste has been extensively recycled and transformed into highly sustainable construction materials called controlled low-strength materials (CLSMs) in backfilling projects, pile foundation treatment, roadbed cushion layers, and other applications. However, CLSMs often experience shrinkage and cracking due to water loss influenced by climatic temperature factors, which can pose safety and stability risks in various infrastructures. The purpose of this paper was to study the mechanism of crack formation and strength degradation in a CLSM in a dry environment and to analyze the deterioration process of the CLSM at the macro- and micro-scales by using image analysis techniques and scanning electron microscopy (SEM). The test results show that with the drying time, the CLSM samples had different degrees of cracks and unconfined compressive strength (UCS) decreases, and increasing the content of ordinary Portland cement (OPC) reduced the number of cracks. The addition of bentonite with the same OPC content also slowed down the crack development and reduced the loss of UCS. The development of macroscopic cracks and UCS is caused by the microscopic scale, and the weak areas are formed due to water loss in dry environments and the decomposition of gel products, and the integrity of the microstructure is weakened, which is manifested as strength deterioration. This research provides a novel methodology for the reuse of construction waste, thereby offering a novel trajectory for the sustainable progression of construction projects.

Regulated Power Supply with High Power Factor for Hyperspectral Imaging Applications

Illumination is a crucial factor in hyperspectral imaging systems. In this respect, this work is focused on analyzing the influence of the light power source in acquiring hyperspectral images. To this end, a custom regulated power supply was designed and developed. This power supply was then integrated into a hyperspectral acquisition system, and several light stability measurements were conducted. Finally, several parameters related to the stability of the light produced by those systems were extracted using image analysis techniques, and a statistical comparison among the different power supplies was performed. Two commercial power supplies were also analyzed under the same experimental conditions and compared with the proposed power supply. The hyperspectral measurements were conducted using light transmission and reflectance. The results indicate that the proposed power supply performs better than or at least as well as commercial power supplies in terms of light stability. Additionally, this study shows the impact of power supply design on the stability and quality of hyperspectral illumination, especially concerning the signal-to-noise ratio (SNR) across different spectral bands. It is shown that optimizing the design of the power supply could improve light stability in hyperspectral imaging applications.

Chemical and temporal manipulation of early steps in protein assembly tunes the structure and intermolecular interactions of protein-based materials.

The Drosophila intrinsically disordered protein Ultrabithorax (Ubx) undergoes a series of phase transitions, beginning with noncovalent interactions between apparently randomly organized monomers, and evolving over time to form increasingly ordered coacervates. This assembly process ends when specific dityrosine covalent bonds lock the monomers in place, forming macroscale materials. Inspired by this hierarchical, multistep assembly process, we analyzed the impact of protein concentration, assembly time, and subphase composition on the early, noncovalent stages of Ubx assembly, which are extremely sensitive to their environment. We discovered that in low salt buffers, we can generate a new type of Ubx material from early coacervates using 5-fold less protein, and 100-fold less assembly time. Comparison of the new materials with standard Ubx fibers also revealed differences in the extent of wrinkling on the fiber surface. A new image analysis technique based on autocorrelation of scanning electron microscopy (SEM) images was developed to quantify these structural differences. These differences extend to the molecular level: new materials form more dityrosine covalent cross-links per monomer, but without requiring the specific tyrosine residues necessary for crosslinking previously established materials. We conclude that varying the assembly conditions represents a facile and inexpensive process for creating new materials. Most new biopolymers are created by changing the composition of the monomers or the method used to drive assembly. In contrast, in this study we used the same monomers and assembly approach, but altered the assembly time and chemical environment to create a new material with unique properties.

Classification of Molecular Subtypes of Breast Cancer Using Radiomic Features of Preoperative Ultrasound Images.

Radiomics has been used as a non-invasive medical image analysis technique for diagnosis and prognosis prediction of breast cancer. This study intended to use radiomics based on preoperative Doppler ultrasound images to classify four molecular subtypes of breast cancer. A total of 565 female breast cancer patients diagnosed by postoperative pathology in a hospital between 2014 and 2022 were included in this study. Radiomic features extracted from preoperative ultrasound images and clinical features were used to construct models for the classification of molecular subtypes of breast cancer. The least absolute shrinkage and selection operator (LASSO) regression was applied for the final screening of radiomic features and clinical features. Three classifiers including Logistic regression, support vector machine (SVM), and XGBoost were utilized to construct model. Model performance was assessed primarily by the area under the receiver operating characteristic curve (AUC) and 95% confidence interval (CI). The mean age of these patients was 54.58 (± 11.27) years. Of these 565 patients, 130 (23.01%) were Luminal A subtype, 329 (58.23%) were Luminal B subtype, 65 (11.50%) were human epidermal growth factor receptor-2 (HER-2) subtype, and 41 (7.26%) were triple negative (TN) subtype. A total of 12 clinical features and 8 radiomic features were selected for model construction. The AUC of the SVM model [0.826 (95%CI 0.808-0.845)] was higher than that of the Logistic regression model [0.776 (95%CI 0.756-0.796)] and the XGB model [0.800 (95%CI 0.779-0.821)] in the multiple classification of breast cancer. For the single classification of breast cancer, the AUC of the SVM model was 0.710 (95%CI 0.660-0.760) for Luminal A subtype, 0.639 (95%CI 0.592-0.685) for Luminal B subtype, 0.754 (95%CI 0.695-0.813) for HER-2 subtype, and 0.832 (95%CI 0.771-0.892) for TN subtype. The SVM model with radiomic features combined with clinical features shows good performance in classifying four molecular subtypes of breast cancer.

Gender Classification With Hand-Wrist Radiographs Using the Deep Learning Method

Objective: Before dental procedures, hand-wrist radiographs are used to plan treatment time and determine skeletal maturity. This study aims to determine gender from hand-wrist radiographs using different deep-learning methods. Material and methods: The left hand-wrist radiographs of 1044 individuals (534 males and 510 females) were pre-processed to clarify the image and adjust the contrast. In the gender classification problem, AlexNet, VGG16 and VGG19 transfer learning methods were both used as separate classifiers, and the features taken from these methods were combined and given to the support vector machine (SVM) classifier. Results: The results revealed that image analysis and deep learning techniques provided 91.1% accuracy in gender determination. Conclusion: Hand-wrist radiographs exhibited sexual dimorphism and could be used in gender prediction. Keywords: deep learning, image analysis,; hand-wrist radiographs, gender determination

Compensating the Meniscus Effect in Phase Contrast Microscopy Using an LCD for Adaptive Condenser Annulus Shifting.

The meniscus effect in cell culture vessels limits the observable areas with phase contrast microscopy. For meniscus effect compensation in microtiter plates (MTPs), we present a method using an LCD to replace the fixed condenser annulus, which enables adaptive annulus shifting based on image analysis. This approach led to an increase in phase contrast area by a factor of 8.3. Utilizing a standard phase contrast microscope, we substituted the static condenser annulus with a transparent LCD that displays an adaptive annulus, which can be repositioned to counteract meniscus-induced refraction across an entire MTP-24 well. We developed image analysis using Bertrand lens images to determine the misalignment between annulus center and phase ring, enabling the calculation of the required annulus shift. Experiments demonstrate the effectiveness of this image analysis technique. The detected shift was translated into new LCD settings through a linear regression model to ensure proper alignment for the following image. We proved that an algorithm based on background brightness yields a reliable metric for assessing phase contrast conditions within well-plates. The proposed approach substantially increased the phase contrast area in 24-well MTPs at 10× magnification from 5.0% with conventional microscopy to 41.9%, thereby restoring phase contrast conditions throughout the well, except near the edges.

Microstructural analysis and compressive strength evaluation of interlocking concrete paving blocks incorporating crumb rubber

Imaging Analysis Techniques (IATs) have become instrumental in civil engineering materials research, providing critical insights into the microstructural characteristics of mixtures and enabling associations between these features, numerical parameters, and laboratory-derived mechanical performance data. However, using IATs specifically for Concrete Paving Blocks (CPBs), particularly when modified with crumb rubber (CR), remains underexplored. In this study, two numerical parameters derived from IATs—interlocking parameter (PINT) and interlocking rate (IR)—were investigated for their correlations with the estimated compressive strength (fpk,est) of CPBs after a 28-day curing period. CPBs were prepared with CR at 5, 10, 15, and 20% by mass, with a reference concrete mixture designed per American standards for no-slump concrete and a target fpk,est of 50 MPa. PINT and IR were calculated using custom Python-based software developed by the authors. Consistent with prior findings, increasing CR content resulted in a decrease in fpk,est, a trend that was well-represented by linear and power regression models. Both IR and PINT showed potential for explaining the reductions in fpk,est, with IR demonstrating stronger predictive capabilities. Consequently, IR proves to be a promising parameter for describing the microstructural characteristics of CPBs, whether containing CR or not, due to its consistently good correlations with both fpk,est, and CR content.

Evaluation of the Zirconium Hydride Morphology at the Flaws in the CANDU Pressure Tube Using a Novel Metric

The Zr-2.5%Nb alloy used to manufacture the pressure tubes for the CANDU 600 power plant experiences continual corrosion when the reactor’s fuel channels are functioning normally. Analysis of the hydrogen accumulation circumstances, the creation of zirconium hydride platelets, evaluation of the platelets’ reorientation in the thermo–mechanical field at volumetric flaws, and determination of the hydrogen morphology are therefore significant goals of the worldwide research being conducted in this field. In this paper, pressure tube alloy samples with artificial V flaws were hydrided by the technique of electrolytic deposition of a hydrogen film layer, followed by a specific thermal treatment. Micrographs of the Zr-2.5%Nb alloy samples in the radial cross-section were taken to examine the hydride reorientation phenomenon that occurred when the samples were heated under mechanical stress. The complex stress field around a tip flaw promoted the formation of some circles from hydride filaments. To characterize the zirconium hydride morphology in the reorientation zone at the volumetric flaw tip, image analysis and processing techniques were applied. To better characterize the reorientation zone from the point of view of embrittlement and mechanical behavior, this paper proposes a novel metric for the morphology of hydrides located in the reorientation zone. This work’s findings are beneficial for the investigation of CANDU fuel channels’ structural integrity.

Label credibility correction based on cell morphological differences for cervical cells classification

Cervical cancer is one of the deadliest cancers that pose a significant threat to women’s health. Early detection and treatment are commonly used methods to prevent cervical cancer. The use of pathological image analysis techniques for the automatic interpretation of cervical cells in pathological slides is a prominent area of research in the field of digital medicine. According to The Bethesda System, cervical cytology necessitates further classification of precancerous lesions based on positive interpretations. However, clinical definitions among different categories of lesion are complex and often characterized by fuzzy boundaries. In addition, pathologists can deduce different criteria for judgment based on The Bethesda System, leading to potential confusion during data labeling. Noisy labels due to this reason are a great challenge for supervised learning. To address the problem caused by noisy labels, we propose a method based on label credibility correction for cervical cell images classification network. Firstly, a contrastive learning network is used to extract discriminative features from cell images to obtain more similar intra-class sample features. Subsequently, these features are fed into an unsupervised method for clustering, resulting in unsupervised class labels. Then unsupervised labels are corresponded to the true labels to separate confusable and typical samples. Through a similarity comparison between the cluster samples and the statistical feature centers of each class, the label credibility analysis is carried out to group labels. Finally, a cervical cell images multi-class network is trained using synergistic grouping method. In order to enhance the stability of the classification model, momentum is incorporated into the synergistic grouping loss. Experimental validation is conducted on a dataset comprising approximately 60,000 cells from multiple hospitals, showcasing the effectiveness of our proposed approach. The method achieves 2-class task accuracy of 0.9241 and 5-class task accuracy of 0.8598. Our proposed method achieves better performance than existing classification networks on cervical cancer.

Expert System to Diagnose and Treat Renal Disease using Medical Imaging Analysis and Generative AI Techniques

Expert System to Diagnose and Treat Renal Disease using Medical Imaging Analysis and Generative AI Techniques

Expression evaluated by digital image analysis techniques of PRAME more than MCM6 is associated with poor prognosis in neuroblastoma: A pilot study with 84 cases.

Neuroblastoma is a common childhood tumor originating from neural crest progenitors with variable clinical behavior. Despite improved overall survival, factors such as stage, histoprognosis, MYCN status, and age still influence outcome. MCM6 regulates DNA replication and contributes to cancer progression. PRAME, first identified in melanoma, also acts on cell replication, epithelial-mesenchymal transition, and cell migration and has been associated with poor outcomes in several cancers, including neuroblastoma, using molecular biology techniques. The study aims to investigate MCM6 and PRAME expression and prognostic roles in neuroblastoma. A retrospective study was conducted, which included data of 84 patients with neuroblastoma diagnosed between 2000 and 2022, sourced from the pediatric tumor registry. Patient's characteristics and prognostic tumor factors were collected. Expression of MCM6 and PRAME proteins was evaluated using digital image analysis techniques. Univariate and multivariate analyses were performed using Cox regression to assess the impact of protein expression on survival and their associations with these prognostic factors. A total of 84 children diagnosed with neuroblastoma were included. MCM6 and PRAME were associated with unfavorable histologies (p=0.03). PRAME was associated with bone marrow metastases (p<0.01), high mitotic-karyorrhectic index (p=0.04), and poor histoprognosis (p<0.01). PRAME and MCM6 expression was correlated with several neuroblastoma prognostic factors. PRAME was significantly (p=0.05) associated with poor event-free survival (EFS) and not significantly (p=0.08) associated with overall survival (OS). Although statistical significance was not reached in multivariate analysis, the trends strongly suggested that the overexpression of MCM6 and PRAME was correlated with decreased survival.

Image quantification analysis of cytoplasmic mucin and interpretation of mucin color in lobular endocervical glandular hyperplasia.

Although the widespread use of screening tests and HPV vaccines for squamous cell carcinoma has led to early detection and treatment, effectiveness is limited for cervical adenocarcinoma. Lobular endocervical glandular hyperplasia (LEGH) corresponds to gastric metaplasia, but is regarded as a pathological condition with subtle morphological abnormalities. LEGH is a benign lesion and a precursor to gastric-type adenocarcinoma. We herein developed an objective and quantitative method by applying an image analysis technique to overcome the difficulties associated with the differential diagnosis of LEGH in uterine cervical cytology. This approach is expected to enable the early detection and accurate diagnosis of LEGH. We extracted signal values for the nucleus and cytoplasm from microscopic images of cytological specimens of normal endocervical (EC) and LEGH cells. These values were then converted into CIELAB and sRGB values to create color distribution maps, and color unmixing techniques were applied to assess the spectral absorbance of each pigment. The CIELAB signal values extracted from the nuclear images of LEGH cells exhibited lower values than those of EC cells. Furthermore, based on color distribution maps, the cytoplasm of EC cells exhibited shades from purple to pink, while LEGH cells showed a distribution towards yellow. This study reveals that, compared to EC cells, LEGH cells exhibit lower nuclear signal values and increased nuclear chromatin content. Thus, assessing the relative difference in cytoplasmic color tones between them may become an effective indicator for distinguishing between EC and LEGH cells.

Leveraging transfer learning-driven convolutional neural network-based semantic segmentation model for medical image analysis using MRI images

Recognition and segmentation of brain tumours (BT) using MR images are valuable and tedious processes in the healthcare industry. Earlier diagnosis and localization of BT provide timely options to select effective treatment plans for the doctors and can save lives. BT segmentation from Magnetic Resonance Images (MRI) is considered a big challenge owing to the difficulty of BT tissues, and segmenting them from the healthier tissue is challenging when manual segmentation is done through radiologists. Among the recent proposals for the brain segmentation method, the BT segmentation method based on machine learning (ML) and image processing could be better. Thus, the DL-based brain segmentation method is extensively applied, and the convolutional network has better brain segmentation effects. The deep convolutional network model has the problem of a large loss of information and a large number of parameters in the encoding and decoding processes. With this motivation, this article presents a new Deep Transfer Learning with Semantic Segmentation based Medical Image Analysis (DTLSS-MIA) technique on MRI images. The DTLSS-MIA technique aims to segment the affected BT area in the MRI images. At first, the presented method utilizes a Median filtering (MF) approach to optimize the quality of MRI images and remove the noise. For the semantic segmentation method, the DTLSS-MIA method follows DeepLabv3 + with a backbone of the EfficientNet model for determining the affected brain region. Moreover, the CapsNet architecture is employed for the feature extraction process. Lastly, the crayfish optimization (CFO) technique with diffusion variational autoencoder (D-VAE) architecture is used as a classification mechanism, and the CFO technique effectively tunes the D-VAE hyperparameter. The simulation analysis of the DTLSS-MIA technique is validated on a benchmark dataset. The performance validation of the DTLSS-MIA technique exhibited a superior accuracy value of 99.53% over other methods.

Development of an Autonomous Drone-Based Irrigation Decision Support System Utilizing Image Processing and Machine Learning Techniques

Efficient management of water resources is essential for sustaining the global food supply amidst growing populations and climate change. Traditional irrigation methods are often plagued by inefficiencies, leading to significant water wastage. This paper presents the development and validation of an autonomous drone-based irrigation system that leverages advanced image processing and machine learning techniques to optimize water usage in agriculture. The system employs standard low-cost cameras to capture high-resolution aerial images, which are processed to accurately predict the water needs of the plants and inform irrigation decisions in real-time also it can do autonomous watering by controlling the electrical water valve in the specified irrigation areas. Comprehensive field tests conducted on pepper crops demonstrate the system's ability to enhance water use efficiency and improve crop yields. By integrating state-of-the-art technologies such as TensorFlow techniques for machine lear-nig, image analysis and autonomous navigation capabilities, the proposed solution represents a significant advancement in precision agriculture. The results indicate that the autonomous drone-based irrigation system can substantially reduce water consumption while maintaining or enhancing crop productivity, thereby promoting sustainable agricultural practices.

Role of Imaging in Multiple Myeloma: A Potential Opportunity for Quantitative Imaging and Radiomics?

Multiple myeloma (MM) is the second most prevalent hematologic malignancy, particularly affecting the elderly. The disease often begins with a premalignant phase known as monoclonal gammopathy of undetermined significance (MGUS), solitary plasmacytoma (SP) and smoldering multiple myeloma (SMM). Multiple imaging modalities are employed throughout the disease continuum to assess bone lesions, prevent complications, detect intra- and extramedullary disease, and evaluate the risk of neurological complications. The implementation of advanced imaging analysis techniques, including artificial intelligence (AI) and radiomics, holds great promise for enhancing our understanding of MM. The integration of advanced image analysis techniques which extract features from magnetic resonance imaging (MRI), computed tomography (CT), or positron emission tomography (PET) images has the potential to enhance the diagnostic accuracy for MM. This innovative approach may lead to the identification of imaging biomarkers that can predict disease prognosis and treatment outcomes. Further research and standardized evaluations are needed to define the role of radiomics in everyday clinical practice for patients with MM.