Image Analysis Research Articles

Short-Wave Infrared Hyperspectral Image-Based Quality Grading of Dried Laver (Pyropia spp.)

Laver (Pyropia spp.) is a major seaweed that is cultivated and consumed globally. Although quality standards for laver products have been established, traditional physicochemical analyses and sensory evaluations have notable drawbacks regarding rapid-quality inspection. Not all relevant physicochemical quality indices, such as texture, are typically evaluated. Therefore, in this study, we investigated the use of hyperspectral imaging to rapidly, accurately, and objectively determine the quality of dried laver. Hyperspectral images of 25 dried laver samples were captured in the short-wave infrared range from 980 to 2576 nm to assess their moisture, protein content, cutting stress, and other key quality indicators. Spectral signatures were analyzed using partial least-squares discriminant analysis (PLS-DA) to correlate the spectral data with three primary quality index values. The performance of PLS-DA was compared with that of the variable importance in projection score and nonlinear regression analysis methods. The comprehensive quality grading model demonstrated accuracies ranging from 96 to 100%, R2 values from 75 to 92%, and root-mean-square errors from 0.14 to 0.25. These results suggest that the PLS-DA regression model shows great potential for the multivariate analysis of hyperspectral images, serving as an effective quality grading system for dried laver.

Advances in colorectal cancer diagnosis using optimal deep feature fusion approach on biomedical images.

Colorectal cancer (CRC) is the second popular cancer in females and third in males, with an increased number of cases. Pathology diagnoses complemented with predictive and prognostic biomarker information is the first step for personalized treatment. Histopathological image (HI) analysis is the benchmark for pathologists to rank colorectal cancer of various kinds. However, pathologists' diagnoses are highly subjective and susceptible to inaccurate diagnoses. The improved diagnosis load in the pathology laboratory, incorporated with the reported intra- and inter-variability in the biomarker assessment, has prompted the quest for consistent machine-based techniques to be integrated into routine practice. In the healthcare field, artificial intelligence (AI) has achieved extraordinary achievements in healthcare applications. Lately, computer-aided diagnosis (CAD) based on HI has progressed rapidly with the increase of machine learning (ML) and deep learning (DL) based models. This study introduces a novel Colorectal Cancer Diagnosis using the Optimal Deep Feature Fusion Approach on Biomedical Images (CCD-ODFFBI) method. The primary objective of the CCD-ODFFBI technique is to examine the biomedical images to identify colorectal cancer (CRC). In the CCD-ODFFBI technique, the median filtering (MF) approach is initially utilized for noise elimination. The CCD-ODFFBI technique utilizes a fusion of three DL models, MobileNet, SqueezeNet, and SE-ResNet, for feature extraction. Moreover, the DL models' hyperparameter selection is performed using the Osprey optimization algorithm (OOA). Finally, the deep belief network (DBN) model is employed to classify CRC. A series of simulations is accomplished to highlight the significant results of the CCD-ODFFBI method under the Warwick-QU dataset. The comparison of the CCD-ODFFBI method showed a superior accuracy value of 99.39% over existing techniques.

Rheology of concentrated crystal suspensions: sucrose fondants as hard particles in soft matter

Hard particle dispersions are abundant in food as well as technical applications. In particular, the production of many candies like fondants, crystalline sugars or creamed honeys involves agitation of concentrated suspensions of microscopic crystals in saturated solutions. However, the complex rheological behavior of such non-colloidal suspensions with poly-disperse, irregular particles is not fully understood. This work investigates different sucrose suspensions with a particle volume fraction of about 50%. After detailed image analysis of the varying particle size distributions and shapes, the flow properties are investigated by oscillatory rheology. Amplitude sweeps, frequency sweeps and thixotropy tests show the dependency of rheological behavior on the microstructure of the suspensions. In particular, all samples show characteristic strain softening with subsequent strain hardening that indicates jamming at large strains. This is observed irrespective of specifics in the particle shape and material, suggesting universal behavior due to the high particle volume fraction. They also show significant time-dependent behavior. However, sedimentation rates are higher and structure rebuilding is lower for larger particle sizes and dispersity. The observed strain softening and structure rebuilding are explained by rearrangement of the crystals: Under moderate strain amplitudes, friction and collisions are minimized, with a larger optimization potential for larger dispersities. When oscillations are reduced again, mainly small particles re-arrange in an arbitrary order over time, leading to an increase in loss and storage modulus and thus thixotropic behavior. This time-dependent process needs to be taken into account when measuring or processing concentrated crystal suspensions. Our findings contribute to a better understanding of concentrated suspensions simple in composition, but complex in their flow properties. The observed behavior strongly depends on the particle-particle interactions. Thus, our findings can be transferred to other areas involving concentrated, non-Brownian frictional suspensions of compact hard particles, as they are often found in food, technical applications or geology.

3D visualization of human colon tissue using a modified CUBIC-based tissue-clearing technique

Background: Colorectal cancer represents one of the most common neoplastic diseases worldwide, making it a frequent focus in routine pathological analyses. Visualizing complex three-dimensional (3D) structures, such as nerves within tumors, requires thick tissue sections, which necessitates the use of optical tissue-clearing methods to achieve transparency. However, following tissue clearing, samples typically require advanced imaging techniques such as light-sheet and two-photon confocal microscopy, which are usually unavailable in standard histological laboratories. Objective: We aimed to demonstrate how a well-established tissue-clearing approach can be adapted for use in a routine histological laboratory, enabling a robust 3D visualization of nerve fibers in samples of both normal human colon and colon cancer tissues. Methods: We modified the “clear unobstructed brain/body imaging cocktails” method, originally developed for whole-brain imaging in mice, and applied it to human colon tissue samples measuring approximately 10 mm3, a standard size typically processed in pathological laboratories. Results: Our protocol, which integrates a tissue-clearing technique, enabled reliable immunofluorescent visualization of colonic nerve fibers labeled with anti-β3-tubulin antibodies. The labeled nerve fibers could be observed using a standard epifluorescence microscope, and high-quality 3D reconstructions were generated through a simple image analysis approach using the open-source software ilastik, which eliminates the need for confocal microscopy. Conclusion: The proposed steps provide a valuable method for researchers to visualize complex 3D structures, such as neural cells and processes, in both normal and tumor-transformed tissue settings.

Image registration for accurate electrode deformation analysis in operando microscopy of battery materials

Operando imaging techniques have become increasingly valuable in both battery research and manufacturing. However, the reliability of these methods can be compromised by instabilities in the imaging setup and operando cells, particularly when utilizing high-resolution imaging systems. The acquired imaging data often include features arising from both undesirable system vibrations and drift, as well as the scientifically relevant deformations occurring in the battery sample during cell operation. For meaningful analysis, it is crucial to distinguish and separately evaluate these two factors. To address these challenges, we employ a suite of advanced image-processing techniques. These include fast Fourier transform analysis in the frequency domain, power spectrum-based assessments for image quality, as well as rigid and non-rigid image-registration methods. These techniques allow us to identify and exclude blurred images, correct for displacements caused by motor vibrations and sample holder drift and, thus, prevent unwanted image artifacts from affecting subsequent analyses and interpretations. Additionally, we apply optical flow analysis to track the dynamic deformation of battery electrode materials during electrochemical cycling. This enables us to observe and quantify the evolving mechanical responses of the electrodes, offering deeper insights into battery degradation. Together, these methods ensure more accurate image analysis and enhance our understanding of the chemomechanical interplay in battery performance and longevity.

RL-Cervix.Net: A Hybrid Lightweight Model Integrating Reinforcement Learning for Cervical Cell Classification

Background: Reinforcement learning (RL) represents a significant advancement in artificial intelligence (AI), particularly for complex sequential decision-making challenges. Its capability to iteratively refine decisions makes it ideal for applications in medicine, such as the detection of cervical cancer; a major cause of mortality among women globally. The Pap smear test, a crucial diagnostic tool for cervical cancer, benefits from enhancements in AI, facilitating the development of automated diagnostic systems that improve screening effectiveness. This research introduces RL-Cervix.Net, a hybrid model integrating RL with convolutional neural network (CNN) technologies, aimed at elevating the precision and efficiency of cervical cancer screenings. Methods: RL-Cervix.Net combines the robust ResNet-50 architecture with a reinforcement learning module tailored for the unique challenges of cytological image analysis. The model was trained and validated using three extensive public datasets to ensure its effectiveness under realistic conditions. A novel application of RL for dynamic feature refinement and adjustment based on reward functions was employed to optimize the detection capabilities of the model. Results: The innovative integration of RL into the CNN framework allowed RL-Cervix.Net to achieve an unprecedented classification accuracy of 99.98% in identifying atypical cells indicative of cervical lesions. The model demonstrated superior accuracy and interpretability compared to existing methods, addressing variability and complexities inherent in cytological images. Conclusions: The RL-Cervix.Net model marks a significant breakthrough in the application of AI for medical diagnostics, particularly in the early detection of cervical cancer. By significantly improving diagnostic accuracy and efficiency, RL-Cervix.Net has the potential to enhance patient outcomes through earlier and more precise identification of the disease, ultimately contributing to reduced mortality rates and improved healthcare delivery.

FireVoxel: Interactive Software for Multi-Modality Analysis of Dynamic Medical Images.

This article provides an overview of the FireVoxel software for quantitative analysis of medical images and its applications in the field. We describe FireVoxel's user interface, multi-layer design, dynamic parametric models, and several turn-key workflows. Additionally, we discuss its application in recent imaging projects. We outline basic image analysis tools such as segmentation, non-uniformity correction, and coregistration through a pictorial overview, with a focus on deformable coregistration and motion correction. Several example workflows and image-based dynamic modeling are also highlighted. Furthermore, we analyze peer-reviewed studies that utilized FireVoxel for image processing, categorizing published papers based on body structures/organs, image processing methods, and imaging modalities. For comparison, we searched the Ovid MEDLINE database to assess the general use of medical image analysis software. FireVoxel is used by over 3000 users worldwide, with 528 articles, including 413 in English, published in the past 15years. MRI is the most commonly used imaging modality (78.2%), followed by CT (14.5%) and PET (7.3%). The most frequently used methods are dynamic modeling, segmentation, texture analysis, and coregistration. FireVoxel is commonly used in abdominal and genitourinary imaging studies, where it appears to fill a niche due to the lack of alternative software. The search of the Ovid MEDLINE suggests that quantitative medical imaging studies, on the other hand, focus on the brain and cardiovascular system. FireVoxel offers an effective set of quantitative tools, particularly for abdominal and genitourinary imaging, likely due to its ability to manage patient motion and correct for MR artifacts. The software is especially valuable for processing dynamic studies. The steady increase in publications utilizing FireVoxel reflects growing interest in this software and its relevance for image-based research.

Fractal Dimension and Entropy Analysis of Medical Images for KNN-Based Disease Classification

شهدت دراسة الكشف عن الأمراض المستندة إلى الصور الطبية زيادة ملحوظة في الاهتمام والنجاح باستخدام الأساليب الحسابية. يقترح هذا العمل إطارًا جديدًا للكشف عن الأمراض في مراحل مبكرة من الصور الطبية، باستخدام النمذجة الرياضية والتعلم الآلي. نقدم مقياسين كميين جديدين للكشف عن مرض كوفيد-19 وأمراض الأورام: عدم اليقين في الصورة بناءً على إنتروبيا شانون وتعقيد الصورة بناءً على البعد الكسري. أظهرت نتائجنا أنه في الصور الإيجابية لـCOVID-19 أظهرت توزيعًا منحرفًا للبكسل بسبب المناطق الضبابية مما أدى إلى انخفاض قيم الإنتروبيا للحالات المريضة مقارنة بالحالات السليمة. أما الكمية الثانية، وهي البعد الكسوري، فقد تم قياسها بطريقة العد المربع التي تحدد مدى تعقيد الصورة. تم تطبيق نتائج كلا التقنيتين على تصنيف الصور باستخدام نموذج التعلم الآلي (ML) k-NN (أقرب جار). يوفر هذا الإطار الكامل نهجًا جديدًا وفريدًا لتحديد وتصنيف أنواع مختلفة من الصور بدقة تصنيف تبلغ ≈ 90% لفيروس Covid و≈ 70% للورم. يُظهر عملنا أن الأنتروبيا والأبعاد الكسرية يمكن أن تميز بين كوفيد-19 والمرضى الأصحاء، مما يجعلها واعدة بالتشخيص المبكر. تقدم هذه المخطوطة منهجية جديدة وفعالة حسابياً وقابلة للتفسير لتصنيف الأمراض والتي توفر الكشف عن المرض في مرحلة مبكرة.

Advancements in Artificial Intelligence for Kidney Transplantology: A Comprehensive Review of Current Applications and Predictive Models

Background: Artificial intelligence is rapidly advancing within the domains of medicine and transplantology. In this comprehensive review, we provide an in-depth exploration of current AI methodologies, with a particular emphasis on machine learning and deep learning techniques, and their diverse subtypes. These technologies are revolutionizing how data are processed, analyzed, and applied in clinical decision making. Methods: A meticulous literature review was conducted with a focus on the application of artificial intelligence in kidney transplantation. Four research questions were formulated to establish the aim of the review. Results: We thoroughly examined the general applications of AI in the medical field, such as feature selection, dimensionality reduction, and clustering, which serve as foundational tools for complex data analysis. This includes the development of predictive models for transplant rejection, the optimization of personalized immunosuppressive therapies, the algorithmic matching of donors and recipients based on multidimensional criteria, and the sophisticated analysis of histopathological images to improve the diagnostic accuracy. Moreover, we present a detailed comparison of existing AI-based algorithms designed to predict kidney graft survival in transplant recipients. In this context, we focus on the variables incorporated into these predictive models, providing a critical analysis of their relative importance and contribution to model performance. Conclusions: This review highlights the significant advancements made possible through AI and underscores its potential to enhance both clinical outcomes and the precision of medical interventions in the field of transplantology.

Machine vision-based detection of key traits in shiitake mushroom caps

This study puts forward a machine vision-based prediction method to solve the problem regarding the measurement of traits in shiitake mushroom caps during the shiitake mushroom breeding process. It enables precise phenotyping through accurate image acquisition and analysis. In practical applications, this method improves the breeding process by rapidly and non-invasively assessing key traits such as the size and color of shiitake mushroom caps, which helps in efficiently screening strains and reducing human errors. Firstly, an edge detection model was established. This model is called KL-Dexined. It achieved an per-image best threshold (OIS) rate of 93.5%. Also, it reached an Optimal Dynamic Stabilization (ODS) rate of 96.3%. Moreover, its Average Precision (AP) was 97.1%. Secondly, the edge information detected by KL-Dexined was mapped onto the original image of shiitake mushroom caps, and using the OpenCV model,11 phenotypic key features including shiitake mushroom caps area, perimeter, and external rectangular length were obtained. Experimental results demonstrated that the R² between predicted values and true values was 0.97 with an RMSE as low as 0.049. After conducting correlation analysis between phenotypic features and shiitake mushroom caps weight, four most correlated phenotypic features were identified: Area, Perimeter, External rectangular width, and Long axis; they were divided into four groups based on their correlation rankings. Finally,M3 group using GWO_SVM algorithm achieved optimal performance among six mainstream machine learning models tested with an R²value of 0.97 and RMSE only at 0.038 when comparing predicted values with true values. Hence, this study provided guidance for predicting key traits in shiitake mushroom caps.

Prenatal Diagnostics Using Deep Learning: A Dual Approach to Plane Localization and Cerebellum Segmentation in Ultrasound Images.

The fetal ultrasound examination is the significant task of mid-term pregnancy inspection and the accurate localization as well as the segmentation of the cerebellum is crucial for clinical diagnosis. This research focuses on developing deep learning techniques for prenatal prediction of neurodevelopmental disorders using 5th-month ultrasound brain images. The study introduces two specialized convolutional neural network (CNN) architectures: the differential CNN for plane localization and the dual CNN for cerebellum segmentation which are critical for accurate diagnostics during prenatal care. The differential CNN incorporates six different convolutional operators to capture diverse features for precise localization of specific planes within images. The dual CNN architecture integrates both the original image and complementary information such as feature maps, to enhance segmentation accuracy for the cerebellum. The models are trained on annotated datasets of ultrasound images, validated, and tested on separate datasets. The effectiveness of the proposed CNN architectures is determined by performing the specific tasks of plane localization and cerebellum segmentation, respectively. The proposed models achieved high performances of 98.6% and 0.956% from accuracy and dice coefficient (DSC) compared to existing approaches in medical image analysis. The findings of this study have significant implications for the prenatal prediction of neurodevelopmental disorders, offering a promising advancement in prenatal care and early diagnostics. The custom CNN architectures tailored to the specific tasks of plane localization and cerebellum segmentation highlight the importance of task-specific model design in medical imaging. While the study acknowledges certain limitations and challenges, the power of deep learning is analyzed for marking the benefit of healthcare and neurodevelopmental disorder prediction during pregnancy.

A Refined Approach to Segmenting and Quantifying Inter-Fracture Spaces in Facial Bone CT Imaging

The human facial bone is made up of many complex structures, which makes it challenging to accurately analyze fractures. To address this, we developed advanced image analysis software which segments and quantifies spaces between fractured bones in facial CT images at the pixel level. This study used 3D CT scans from 1766 patients who had facial bone fractures at a university hospital between 2014 and 2020. Our solution included a segmentation model which focuses on identifying the gaps created by facial bone fractures. However, training this model required costly pixel-level annotations. To overcome this, we used a stepwise annotation approach. First, clinical specialists marked the bounding boxes of fracture areas. Next, trained specialists created the initial pixel-level unrefined ground truth by referencing the bounding boxes. Finally, we created a refined ground truth to correct human errors, which helped improve the segmentation accuracy. Radiomics feature analysis confirmed that the refined dataset had more consistent patterns compared with the unrefined dataset, showing improved reliability. The segmentation model showed significant improvement in the Dice similarity coefficient, increasing from 0.33 with the unrefined ground truth to 0.67 with the refined ground truth. This research introduced a new method for segmenting spaces between fractured bones, allowing for precise pixel-level identification of fracture regions. The model also helped with quantitative severity assessment and enabled the creation of 3D volume renderings, which can be used in clinical settings to develop more accurate treatment plans and improve outcomes for patients with facial bone fractures.

Transition to GPU-based reconstruction for clinical organ-targeted PET scanner.

This article explores a new Graphics Processing Unit (GPU)-based techniques for efficient image reconstruction in organ-targeted Positron Emission Tomography (PET) scanners with planar detectors .
Approach: GPU-based reconstruction is applied to the Radialis low-dose organ-targeted PET technology, developed to overcome the issues of high exposure and limited spatial resolution inherent in traditional whole-body PET/CT (Computed Tomography) scans. The Radialis planar detector technology is based on four-side tileable sensor modules that can be seamlessly combined into a sensing area of the needed size, optimizing the axial field-of-view (AFOV) for specific organs, and maximizing geometric sensitivity. The article explores the transition from Central Processing Unit (CPU)-based Maximum Likelihood Expectation Maximization (MLEM) algorithms to a GPU-based counterpart, demonstrating a tenfold overall speedup in image reconstruction with a hundredfold improvement in iteration speed.
Main Results: Through standardized PET performance tests and clinical image analysis, this work demonstrates that GPU-based image reconstruction maintains diagnostic image quality while significantly reducing reconstruction times. The application of this technology, particularly in breast imaging using the Radialis Low-Dose Positron Emission Mammography (LD-PEM), significantly reduces exam times thus improving patient comfort and throughput in clinical settings.
Significance: This study represents an important advancement in the clinical workflow of PET imaging, providing insights into optimizing reconstruction algorithms to effectively leverage the parallel processing capabilities of GPUs.&#xD.

Leveraging AI to automate detection and quantification of extrachromosomal DNA to decode drug responses

IntroductionTraditional drug discovery efforts primarily target rapid, reversible protein-mediated adaptations to counteract cancer cell resistance. However, cancer cells also utilize DNA-based strategies, often perceived as slow, irreversible changes like point mutations or drug-resistant clone selection. Extrachromosomal DNA (ecDNA), in contrast, represents a rapid, reversible, and predictable DNA alteration critical for cancer’s adaptive response.MethodsIn this study, we developed a novel post-processing pipeline for automated detection and quantification of ecDNA in metaphase Fluorescence in situ Hybridization (FISH) images, leveraging the Microscopy Image Analyzer (MIA) tool. This pipeline is tailored to monitor ecDNA dynamics during drug treatment.ResultsOur approach effectively quantified ecDNA changes, providing a robust framework for analyzing the adaptive responses of cancer cells under therapeutic pressure.DiscussionThe pipeline not only serves as a valuable resource for automating ecDNA detection in metaphase FISH images but also highlights the role of ecDNA in facilitating swift and reversible adaptation to epigenetic remodeling agents such as JQ1.

Radiomics analysis of ultrasound images to discriminate between benign and malignant adnexal masses with solid morphology on ultrasound.

The primary aim was to identify radiomics ultrasound features that can distinguish between benign and malignant adnexal masses with solid ultrasound morphology, and between primary malignant (including borderline and primary invasive) and metastatic solid ovarian masses, and to develop ultrasound-based machine learning models that include radiomics features to discriminate between benign and malignant solid adnexal masses. The secondary aim was to compare the discrimination performance of our newly developed radiomics models with that of the Assessment of Different NEoplasias in the adneXa (ADNEX) model and that of subjective assessment by an experienced ultrasound examiner. This was a retrospective, observational single-center study conducted at Fondazione Policlinico Universitario A. Gemelli IRCC, in Rome, Italy. Included were patients with a histological diagnosis of an adnexal tumor with solid morphology according to International Ovarian Tumor Analysis (IOTA) terminology at preoperative ultrasound examination performed in 2014-2020, who were managed with surgery. The patient cohort was split randomly into training and validation sets at a ratio of 70:30 and with the same proportion of benign and malignant tumors in the two subsets, with malignant tumors including borderline, primary invasive and metastatic tumors. We extracted 68 radiomics features, belonging to two different families: intensity-based statistical features and textural features. Models to predict malignancy were built based on a random forest classifier, fine-tuned using 5-fold cross-validation over the training set, and tested on the held-out validation set. The variables used in model-building were patient age and radiomics features that were statistically significantly different between benign and malignant adnexal masses and assessed as not redundant based on the Pearson correlation coefficient. We evaluated the discriminative ability of the models and compared it to that of the ADNEX model and that of subjective assessment by an experienced ultrasound examiner using the area under the receiver-operating-characteristics curve (AUC) and classification performance by calculating sensitivity and specificity. In total, 326 patients were included and 775 preoperative ultrasound images were analyzed. Of the 68 radiomics features extracted, 52 differed statistically significantly between benign and malignant tumors in the training set, and 18 uncorrelated features were selected for inclusion in model-building. The same 52 radiomics features differed significantly between benign, primary malignant and metastatic tumors. However, thevalues of the features manifested overlapped between primary malignant and metastatic tumors and did not differ significantly between them. In the validation set, 25/98 tumors (25.5%) were benign and 73/98 (74.5%) were malignant (6 borderline, 57 primary invasive, 10 metastatic). In the validation set, a model including only radiomics features had an AUC of 0.80, sensitivity of 0.78 and specificity of 0.76 at an optimal cut-off for risk of malignancy of 68%, based on Youden's index. The corresponding results for a model including age and radiomics features were AUC of 0.79, sensitivity of 0.86 and specificity of 0.56 (cut-off 60%, based on Youden's index), while those of the ADNEX model were AUC of 0.88, sensitivity of 0.99 and specificity of 0.64 (at a 20% risk-of-malignancy cut-off). Subjective assessment had a sensitivity of 0.99 and specificity of 0.72. Our radiomics model had moderate discriminative ability on internal validation and the addition of age to this model did not improve its performance. Even though our radiomics models had discriminative ability inferior to that of the ADNEX model, our results are sufficiently promising to justify continued development of radiomics analysis of ultrasound images of adnexal masses. © 2024 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

CelInsight:AI-Powered Web Solution for Cervical Cancer Classification

This paper introduces the system, a Python-based web platform developed for the secure management, processing, and intelligent analysis of medical images and video streams. The system leverages the great libraries and frameworks of Python, especially Flask, in building the backend.Through the emphasis on AI model integration of TensorFlow/PyTorch for better detection accuracy and precision.For the healthcare pro- fessionals.The report provides information about the architecture of the platform, the key features of the system, and how integrating AI transforms diagnostic workflows. Results indicate the system as a scalable, user-friendly, and secure tool for the management of medical images in health settings. It addresses the problem of cervical cancer as a health burden, with increased importance for low- and middle-income countries. Early and precise classification of cervical.Proper classification of cancer subtypes is crucial to guide the treatment decisions and to improve patient outcomes in those regions. In an attempt to solve this problem, the system develops a centralized imaging framework-based model intended for cervical cancer diagnosis classification. This framework is developed based on state-of-the- art imaging modalities and artificial intelligence. It improves the diagnostic workflow with greater efficiency and accuracy. The system presents hybrid models that are based on a combination of ideas of convolutional neural networks and Gradient-boosted machine learning classifiers are utilized for robust and reliable performance in the classification of various subtypes of cervical cancer. The system also ensures security and centralization of data; hence, the healthcare professionals get to work on scalable and accurate tools for the classification process. All these have been developed through Python-based technologies and incorporated into AI and secure infrastructure to make the system a pivotal innovation in modern diagnostics. Index Terms—Medical image processing, AI in healthcare, cervical cancer diagnosis, deep learning, convolutional neural net- works (CNN), Gradient-boosted machine learning, TensorFlow, PyTorch, Flask, diagnostic workflow, secure medical imaging, intelligent analysis, centralized imaging framework, healthcare technology, AI-driven classification, medical video stream analy- sis.

Combining transfer and ensemble learning models for image and text aspect-based sentiment analysis

Combining transfer and ensemble learning models for image and text aspect-based sentiment analysis

Utilization of Artificial Intelligence Coupled with a High-Throughput, High-Content Platform in the Exploration of Neurodevelopmental Toxicity of Individual and Combined PFAS

Per- and polyfluoroalkyl substances (PFAS) are synthetic chemicals used in various products, such as firefighting foams and non-stick cookware, due to their resistance to heat and degradation. However, these same properties make them persistent in the environment and human body, raising public health concerns. This study selected eleven PFAS commonly found in drinking water and exposed Caenorhabditis elegans to concentrations ranging from 0.1 to 200 µM to assess neurodevelopmental toxicity using a high-throughput, high-content screening (HTS) platform coupled with artificial intelligence for image analysis. Our findings showed that PFAS such as 6:2 FTS, HFPO-DA, PFBA, PFBS, PFHxA, and PFOS inhibited dopaminergic neuron activity, with fluorescence intensity reductions observed across concentrations from 0.1 to 100 µM. PFOS and PFBS also disrupted synaptic transmission, causing reduced motility and increased paralysis in aldicarb-induced assays, with the most pronounced effects at higher concentrations. These impairments in both neuron activity and synaptic function led to behavioral deficits. Notably, PFOS was one of the most toxic PFAS, affecting multiple neurodevelopmental endpoints. These results emphasize the developmental risks of PFAS exposure, highlighting the impact of both individual compounds and mixtures on neurodevelopment. This knowledge is essential for assessing PFAS-related health risks and informing mitigation strategies.

Accessible Non-Invasive Techniques for Museums: Extending Sustainability to Resource-Limited Institutions

This work provides a synthesis of an initial experience in the development of accessible imaging techniques and their implementation on a real case: the analysis of colonial Hispano-American paintings at the Complejo Museográfico Provincial “Enrique Udaondo” (Luján, Buenos Aires). It discusses different aspects related to the possibilities of obtaining, using, and reusing equipment and materials locally, as well as details of the ways of acquiring images for photography on site. It also provides information about the composition and conservation state of selected artworks, complementing image analysis with portable X-ray fluorescence (XRF) data, and reflects on articulated/collaborative work in situ as a methodology for transferring knowledge and skills. The project aims to contribute to strengthening Latin American sustainability by creating accessible non-invasive tools for heritage conservation institutions, highlighting the value of regional capacities to approach heritage studies from collaborative and ethical proposals that promote sovereignty and reduce dependence on external inputs.

Improved Pancreatic Cancer Diagnosis: Deep Learning Integration with U-Net for Segmented Histopathology Image Analysis

Pancreatic cancer remains one of the most lethal malignancies due to its asymptomatic early stages and rapid progression, leading to delayed diagnosis and limited treatment options. Accurate and early detection is critical for improving patient outcomes. This study introduces a robust deep learning approach integrating U-Net for image segmentation and four state-of-the-art Convolutional Neural Network (CNN) models—ResNet50, VGG16, MobileNetV2, and DenseNet121—for the classification of pancreatic cancer histopathology images. To address the challenges of data scarcity, various data augmentation techniques, including scaling, flipping, and random rotations, are employed to improve model generalizability. U-Net effectively isolates regions of interest, enabling precise segmentation, while transfer learning with CNNs ensures accurate classification of cancerous and non-cancerous tissues. Comparative analysis of the models reveals DenseNet121 as the most accurate model, achieving superior performance across all evaluation metrics, including accuracy, precision, recall, and F1-score. MobileNetV2, however, emerges as a viable candidate for real-time applications due to its lower computational overhead and efficient architecture. The proposed method demonstrates significant potential to enhance diagnostic accuracy, reduce time for diagnosis, and support clinical decision-making, paving the way for improved early detection of pancreatic cancer.