Image Pattern Research Articles

Classification of diabetic retinopathy grades using CNN feature extraction to segment the lesion

Diabetes's microvascular aftereffect, diabetic retinopathy (DR), is the primary cause of eyesight loss in the globe. In order to prevent vision impairment and to intervene promptly, early detection and precise classification of DR severity are essential. Using standard methods for diagnosing DR requires ophthalmologists to grade cases by hand, a process that can be laborious, subjective, and subject to observer error. In supervised learning task of classification, data instances are classified into predefined classes based on features. The relation between the traits and the classes can be found from the labelled data. After the training is completed, the classes of the unseen data. The frequent reason found for the loss of vision in diabetic retinopathy (DR) is found to be diabetes. Visual damage can be prevented by identifying the degree of DR at right time. For the grading of the DR, deep learning techniques are found to be very effective with maximum possible accuracy. The proposed model is useful in accurately classifying the DR images using the feature extraction with lesion segmentation, by implementing the patterns in the DR images. ReLU activation function is used in the proposed model. CNN feature extraction is used for the important feature extraction by applying the Convolution layers, and edges, textures, and forms are identified. As the model proceeds layer by layer, complicated patterns in the photos can be learned by the model, and can be analysed better. The features of the photos were extracted and found useful in segmentation and classification. ReLU is helpful in improving the convergence and also found useful in learning the patterns. Among the other activation functions, ReLU has higher computational efficiency and therefore is used in the model, which suits well for the DR application. A strong framework is proposed for the classification of the DR grade, for the lesion segmentation and CNN feature extraction. DR categorization using the proposed model is evaluated by data visualization of the important calculated metrics and found to be very effective.

Surface plasmon resonance to trace and measure cancer cell apoptosis using morphological and refractive index changes

Morphological changes of cancer cells are often used as an important indicator within efficiency studies of anticancer drugs. Morphological cell analysis on cell size and shape distribution is typically performed using microscopic methods, which are time consuming and require skilled personnel. Recently, more advanced image processing and pattern recognition have enabled identification and quantitative analysis of the cell’s abnormality and classification in an automated way. However, these methods usually involve multiple staining steps. In addition to computational complexity, the processes greatly compromise real-time applications of the system. Therefore, a non-invasive, real-time method allowing for assessment of living cells’ reactions to a death inducer is very much needed. Here, we present an SPR biosensor that measures the changes in cancer cells’ size and detachment, relating the cell confluency with the changes of the refractive index on the cell-substrate interface. As a proof-of-concept, we chose HeLa cell and hydrogen peroxide (H2O2) induced apoptosis as the model system to study the morphological changes of the cell. The results show that the SPR response to cell apoptosis agreed with the cellular morphological changes observed via microscopy. Interestingly, we observed simultaneous apoptosis and necrosis at high H2O2 concentrations. This simultaneous occurrence was verified using a mathematical model which incorporated other important factors such as cell thickness and intercellular refractive index. This model helped resolve the disagreement between SPR signal and cell confluency at high H2O2 concentrations. Our results show the potential of SPR as a label free and real time monitoring method for morphological changes and surface detachment of cancer cells. This method can be fully expanded to other cell-based sensing applications.

MR perfusion characteristics of pseudoprogression in brain tumors treated with immunotherapy - a comparative study with chemo-radiation induced pseudoprogression and radiation necrosis.

Pseudoprogression is an atypical imaging pattern of response to immunotherapy in patients with brain tumors. MR perfusion studies in this field are limited. The purpose of our study is to compare the perfusion features between pseudoprogression lesions in malignant gliomas and brain metastases treated with immunotherapy (iPsP) and the pseudoprogression after chemo-radiation therapy and radiation necrosis after radiation treatment (ChR-PsP & RN). We retrospectively reviewed 25 iPsP lesions in 16 brain tumor patients and 48 ChR-PsP & RN lesions in 35 patients. The cerebral blood volume (CBV) of MR dynamic susceptibility contrast (DSC) perfusion weighted imaging (PWI) was analyzed, and the mean and maximal values of the ratio of CBV (rCBVmean and rCBVmax) of iPsPs and ChR-PsP & RNs were calculated and compared between these two groups using the Mann-Whitney U test. A receiver operating characteristic curve analysis was conducted, and the optimal cutoff of perfusion parameters were determined using the area under the curve, sensitivity, and specificity. The medians of rCBVmean and rCBVmax in iPsP group were significantly higher (0.94 and 1.39 respectively) than ChR-PsP & RN group (0.67, p < 0.01 and 1.1, p = 0.01 respectively). The rCBVmean value of 0.69 can differentiate the iPsP from ChR-PsP & RN with the area under the curve of 0.71, sensitivity of 0.72, and specificity of 0.56. These findings may suggest immunotherapy-induced higher perfusion in the iPsP lesions compared to ChR-PsP & RN lesions in primary and metastatic brain tumors.

Differentiating Glioma Recurrence and Pseudoprogression by APTw CEST MRI.

Recurrent glioma is highly treatment resistant due to its metabolic, cellular, and molecular heterogeneity and invasiveness. Tumor monitoring by conventional MRI has shortcomings to assess these key glioma characteristics. Recent studies introduced chemical exchange saturation transfer for metabolic imaging in oncology and assessed its diagnostic value for newly diagnosed glioma. This prospective study investigates amide proton transfer-weighted (APTw) MRI at 3 T as an imaging biomarker to elucidate the molecular heterogeneity and invasion patterns of recurrent glioma in comparison to pseudoprogression (PsPD). We performed a monocenter, prospective trial and screened 371 glioma patients who received tumor monitoring between August 2021 and March 2024 at our institution. The study included IDH wildtype astrocytoma and IDH mutant astrocytoma and oligodendroglioma, graded according to the WHO 2021 classification. Patients had received clinical standard of care treatment including surgical resection and radiochemotherapy prior to study inclusion. Patients were monitored by 3 monthly MRI follow-up imaging, and response assessment was performed according to the RANO criteria. Within this cohort, we identified 30 patients who presented with recurrent glioma and 12 patients with PsPD. In addition to standard anatomical sequences (FLAIR and T1-w Gd-enhanced sequences), MRI included APTw imaging. After sequence co-registration, semiautomated segmentation was performed of the FLAIR lesion, CE lesion, resection cavity, and the contralateral normal-appearing white matter, and APTw signals were quantified in these regions of interest. APTw values were highest in solid, Gd-enhancing tumor parts as compared with the nonenhancing FLAIR lesion (APTw: 1.99% vs 1.36%, P = 0.001), whereas there were no detectable APTw alterations in the normal-appearing white matter (APTw: 0.005%, P < 0.001 compared with FLAIR). Patients with progressive disease had higher APTw levels compared with patients with PsPD (APTw: 1.99% vs 1.26%, P = 0.008). Chemical exchange saturation transfer identified heterogeneity within the FLAIR lesion that was not detectable by conventional sequences. There were also focal APTw signal peaks within contrast enhancing lesions as putative metabolic hotspots within recurrent glioma. The resection cavity developed an APTw increase at recurrence that was not detectable prior to recurrence nor in patients with PsPD (APTw before recurrence: 0.6% vs 2.68% at recurrence, P = 0.03). Our study shows that APTw imaging can differentiate PD and PsPD. We identify previously undetectable imaging patterns during glioma recurrence, which include alterations within resection cavity associated with disease progression. Our work highlights the clinical potential of APTw imaging for glioma monitoring and further establishes it as an imaging biomarker in neuro-oncology.

Neurological involvement in patients with systemic autoimmune rheumatic diseases: a descriptive study in an Egyptian cohort

BackgroundNeurologic manifestations in the systemic autoimmune rheumatic diseases (SARDs) are protean. They add to the disease burden and could contribute to mortality. Increasing awareness about the neuro-rheumatologic syndromes might help with early diagnosis and effective therapy. Our aim is to survey the clinical and imaging patterns of neurological involvement in Egyptian patients with SARDs.ResultsNeurological involvement is common in Behçet’s disease (BD) (12.7%) and systemic lupus erythematosus (SLE) (6.4%) patients compared with other SARDs. Compared with SLE, neurological involvement in BD tends to develop at an older age (31 ± 7.1 versus 28.3 ± 9.6 years = 0.022) with a greater progression risk (13.8% versus 2.6%, P = 0.003). A higher proportion of SLE patients had abnormal neuroimaging without neurological symptoms (15.7% versus 4.3%, P = 0.026, OR = 4.9, 95%CI 1.1–22.4). SLE patients had a higher frequency of seizures (31.3% versus 6.4%, P < 0.001, OR = 6.7, 95%CI 2.7–16.7) and benign intracranial hypertension (9.6% versus 1.1%, P = 0.009, OR = 9.8, 95%CI 1.2–77.7) but a lower prevalence of quadriplegia due to brain insult (1.7% versus 3.2%, P = 0.045, OR = 0.2, 95%CI 0.04–0.9), dural sinus thrombosis (13% versus 33%, P = 0.001, OR = 0.3, 95%CI 0.2–0.6), brainstem syndrome (0.9% versus 6.4%, P = 0.047, OR = 0.1, 95%CI 0–1.1) and cranial neuropathies (9.6% versus 31.9%, P < 0.001, OR = 0.2, 95%CI 0.1–0.5). Concerning neuroimaging, brain atrophic changes were more common (27.4% versus 9.5%, P = 0.002, OR = 3.6, 95%CI 1.6–8.3) while thrombosis was less prevalent (36.3% versus 53.6%, P = 0.016, OR 0.5, 95%CI = 0.3–0.9) in lupus patients. The cerebral cortex was more commonly affected (20.4 versus 4.8%, P = 0.002, OR = 5.1, 95%CI 1.7–15.4) while dural sinuses (14.2% versus 40.5%, P < 0.001, OR = 0.2, 95%CI 0.1–0.5), basal ganglia (1.8% versus 10.7%, P = 0.010, OR = 0.2, 95%CI 0–0.7), diencephalon (0% versus 13.1%, P < 0.001) and brainstem (1.8% versus 22.6%, P < 0.001, OR = 0.1, 95%CI 0–0.3) were less frequently involved in SLE patients. Concerning other SARDs, cranial neuropathies were the most common neurological presentations. Abnormalities in neuroimaging did not correlate with the patients’ clinical presentations.ConclusionsNeurological presentations associated with SARDs are protean. Neuroimaging abnormalities should be interpreted within the context of the clinical picture and the results of other investigations.

Comparison of Accuracy between Random Forest Method and K-Nearest Neighbors Method for Recognizing Solar Panel Energy Conversion Temperature

This study analyzes the classification of temperature image pattern recognition on solar panels to improve the accuracy of energy conversion performance affected by weather changes. The process begins by capturing the surface temperature image of the panel as primary data, which is then processed through the pattern recognition stage. The pattern recognition method is chosen to detect and understand patterns in temperature images that will be used as datasets. This study also compares the results of pattern recognition using the Random Forest classification method with the K-Nearest Neighbors (KNN) method, in order to build an effective model in analyzing images based on weather temperature in Medan City. The results of the study obtained that the solar panel produced a maximum output of 15.74 Wp at 12:00 pm, when the temperature tends to be higher and sunlight is optimal. Then the results of the random forest method showed good performance with an accuracy of 84% and the K-Nearest Neighbors method had an accuracy of 78%.

Revealing the Dark Side of Non-Local Attention in Single Image Super-Resolution.

Single Image Super-Resolution (SISR) aims to reconstruct a high-resolution image from its corresponding low-resolution input. A common technique to enhance the reconstruction quality is Non-Local Attention (NLA), which leverages self-similar texture patterns in images. However, we have made a novel finding that challenges the prevailing wisdom. Our research reveals that NLA can be detrimental to SISR and even produce severely distorted textures. For example, when dealing with severely degrade textures, NLA may generate unrealistic results due to the inconsistency of non-local texture patterns. This problem is overlooked by existing works, which only measure the average reconstruction quality of the whole image, without considering the potential risks of using NLA. To address this issue, we propose a new perspective for evaluating the reconstruction quality of NLA, by focusing on the sub-pixel level that matches the pixel-wise fusion manner of NLA. From this perspective, we provide the approximate reconstruction performance upper bound of NLA, which guides us to design a concise yet effective Texture-Fidelity Strategy (TFS) to mitigate the degradation caused by NLA. Moreover, the proposed TFS can be conveniently integrated into existing NLA-based SISR models as a general building block. Based on the TFS, we develop a Deep Texture-Fidelity Network (DTFN), which achieves state-of-the-art performance for SISR. Our code and a pre-trained DTFN are available on GitHub† for verification.

Diabetic Retinopathy Detection Model using Hybrid of U-Net and Vision Transformer Algorithms

Diabetic retinopathy is one of the leading causes of vision impairment noticed among individuals with prolonged diabetes. Early-stage detection is very crucial for its treatment. Now, we present a hybrid model which is a combination of U-Net algorithm used for image segmentation and Vision Transformer for classification. The total integration offers a robust model which helps in detecting various stages of diabetic retinopathy. We leverage the use of U-Net algorithm in image segmentation process to delineate the regions of interest in retinal images. Further, the outputs which are segmented are passed into Vision Transformer, which is enhanced by Efficient Net, which is used across various severity levels involved in Diabetic Retinopathy. The usage of transformer architecture helps improve feature extraction and classification performance which ensures that our model captures all patterns in retinal images. We have evaluated our model on APTOS Blindness detection dataset in which our model outperforms traditional convolutional neural networks-based models. Hence, the hybrid approach consisting of combination of both the algorithms demonstrates excellent robustness and generalization which offers a promising application for diabetic retinopathy screening, involving the potential to revolutionize early diagnosis in clinical settings.

ProtoMed: Prototypical networks with auxiliary regularization for few-shot medical image classification

Although deep learning has shown impressive results in computer vision, the scarcity of annotated medical images poses a significant challenge for its effective integration into Computer-Aided Diagnosis (CAD) systems. Few-Shot Learning (FSL) opens promising perspectives for image recognition in low-data scenarios. However, applying FSL for medical image diagnosis presents significant challenges, particularly in learning disease-specific and clinically relevant features from a limited number of images. In the medical domain, training samples from different classes often exhibit visual similarities. Consequently, certain medical conditions may present striking resemblances, resulting in minimal inter-class variation. In this paper, we propose a prototypical network-based approach for few-shot medical image classification for low-prevalence diseases detection. Our method leverages meta-learning to use prior knowledge gained from common diseases, enabling generalization to new cases with limited data. However, the episodic training inherent in meta-learning tends to disproportionately emphasize the connections between elements in the support set and those in the query set, which can compromise the understanding of complex relationships within medical image data during the training phase. To address this, we propose an auxiliary network as a regularizer in the meta-training phase, designed to enhance the similarity of image representations from the same class while enforcing dissimilarity between representations from different classes in both the query and support sets. The proposed method has been evaluated using three medical diagnosis problems with different imaging modalities and different levels of visual imaging details and patterns. The obtained model is lightweight and efficient, demonstrating superior performance in both efficiency and accuracy compared to state-of-the-art. These findings highlight the potential of our approach to improve performance in practical applications, balancing resource limitations with the need for high diagnostic accuracy.

Advancements in Computer Vision: A Comprehensive Survey of Image Processing and Interdisciplinary Applications

Computer vision and image processing are rapidly evolving fields with broad applications across numerous domains, including healthcare, autonomous driving, surveillance, and entertainment. These fields have transformed from simple data recording techniques into sophisticated systems that incorporate digital image processing, pattern recognition, machine learning, and computer graphics. This evolution has prompted interdisciplinary interest, pushed the technology’s boundaries and expanded its practical uses. This paper offers a comprehensive survey of recent advancements in computer vision, focusing on image processing and its applications across various fields. It delves into the theoretical foundations and technologies that make computer vision a valuable tool for interpreting images and videos, extracting relevant information, recognizing patterns, and understanding events. The ability of computer vision to analyze large datasets across multiple application domains makes it instrumental in tasks such as object identification, facial recognition, scene understanding, and even real-time action prediction. This versatility has established computer vision as a key driver of data-driven insights in both scientific and commercial sectors. The study categorizes computer vision into four main areas: image processing, object recognition, machine learning, and computer graphics. Each of these categories is essential to the functionality of modern computer vision systems. Image processing involves techniques for enhancing image quality and extracting important features. Object recognition and machine learning enable the identification of specific elements within images and allow systems to learn from large datasets, enhancing accuracy over time. Computer graphics, on the other hand, aid in visualizing and interpreting processed data. By offering insights into the latest techniques and evaluating their performance, this survey highlights the current state of computer vision while shedding light on future trends. Computer vision’s expanding utility across various fields underscores its critical role in driving interdisciplinary innovation and addressing complex challenges.

Symptoms and joint degeneration correlate with the temperature of osteoarthritic knees: an infrared thermography analysis.

This study aim was to analyze the joint temperature of patients affected by bilateral knee osteoarthritis (OA) using infrared thermography to investigate whether thermographic imaging patterns are influenced by the severity of symptoms and joint degeneration. Sixty-sixpatients ranging from 43 to 78 years old (63.3 ± 8.8 years) with bilateral knee OA and one symptomatic knee were enrolled. Thermograms of the two knees were captured using a thermographic camera FLIR T1020 and analyzed with the ResearchIR software to calculate the temperature of the overall knee and the four regions of interest (ROIs): patella, suprapatellar, medial, and lateral areas. The temperature of knees affected by OA was influenced by joint degeneration level and symptoms: patients with higher OA grade in the symptomatic knees presented higher total knee temperatures compared to the asymptomatic ones (p = 0.002), as well as in the patellar (p = 0.005), lateral (p = 0.002), and medial (p = 0.001) areas. On the other hand, patients with the same OA level in the two knees presented a higher temperature in the symptomatic knee only in the medial area (p = 0.037). Symptomatic knees demonstrated a different pattern compared to asymptomatic knees, with the medial area presenting the highest temperature changes (p = 0.020). Patients reporting prevalent pain in the lateral knee area presented higher differences in total knee temperature (0.7 ± 0.7°C) than patients with pain in the medial area (0.1 ± 0.5°C) (p = 0.023). The temperature of knees affected by OA is influenced by the degree of joint degeneration and by the presence of symptoms, with higher temperatures found in symptomatic joints, especially with prevalent lateral knee pain, and in more severe OA. Symptomatic knees demonstrated a different pattern compared to asymptomatic knees, with the medial area presenting the highest temperature changes.

Enhancing advanced cervical cell categorization with cluster-based intelligent systems by a novel integrated CNN approach with skip mechanisms and GAN-based augmentation

Cervical cancer is one of the biggest challenges in global health, thus it forms a critical need for early detection technologies that could improve patient prognosis and inform treatment decisions. This development in the form of an early detection mechanism increases the chances of successful treatment and survival, as early diagnosis promptly offers interventions that can dramatically reduce the rate of deaths attributed to this disease. Here, a customized Convolutional Neural Network (CNN) model is proposed for cervical cancerous cell detection. It includes three convolutional layers with increasing filter sizes and max-pooling layers, followed by dropout and dense layers for improved feature extraction and robust learning. By using ResNet models as inspiration, the model further innovates by incorporating skip connections into the CNN design. By enabling direct feature transmission from earlier to later layers, skip links enhance gradient flow and help preserve important spatial information. By boosting feature propagation, this integration increases the model’s ability to recognize minute patterns in cervical cell images, hence increasing classification accuracy. In our methodology, the SIPaKMeD dataset has been employed which contains 4049 cervical cell images that are arranged into five different categories. To address class imbalance, Generative Adversarial Networks (GANs) have been applied for data augmentation; that is, synthetic images have been created, that improve the diversity of the dataset and further enhance the robustness of the same. The present model is astonishingly accurate in classifying five cervical cell types: koilocytes, superficial-intermediate, parabasal, dyskeratotic, and metaplastic, thus significantly enhancing early detection and diagnosis of cervical cancer. The model gives an excellent performance because it has a validation accuracy of 99.11% and a training accuracy of 99.82%. It is a reliable model in the diagnosis of cervical cancerous cells because it ensures advancement in the computer-assisted cervical cancer detection system.

Hypometabolic mismatch with atrophy and tau pathology in mixed Alzheimer and Lewy body disease.

Polypathology is a major driver of heterogeneity in clinical presentation and extent of neurodegeneration (N) in patients with Alzheimer Disease (AD). Beyond amyloid (A) and tau (T) pathologies, over half of patients with AD have concomitant pathology such as α-synuclein (S) in mixed AD with Lewy Body Disease (LBD). Patients with Mixed Etiology Dementia (MED) such as AD+LBD have faster progression and potentially differential responses to targeted treatments, though the diagnosis of AD+LBD can be challenging given overlapping clinical and imaging features. Development and validation of improved in vivo biomarkers are required to study relationships between N and S and identify imaging patterns reflecting mixed AD+LBD pathologies. We hypothesize that individual proteinopathies, such as T and S, are associated with commensurate levels of N. Thus, we assessed biomarkers of A, T, N and S with positron emission tomography (PET), magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) seeding amplification assay (SAA) data to determine molecular presentations of mixed A+S+ vs. A+S- cognitively impaired patients from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We found A+S+ patients had parieto-occipital 18F-Fluorodeoxyglucose hypometabolism (a measure of N) disproportionate to the degree of regional atrophy or T burden, highlighting worse hypometabolism associated with S+ SAA. Following up on this hypometabolic mismatch with CSF metabolite and proteome analyses, we found that A+S+ patients exhibited lower CSF levels of dopamine metabolites and synaptic markers like neuronal pentraxin-2 (NPTX2), suggesting that altered neurotransmission and neuron integrity contribute to this dissociation between metabolic PET and MRI. Potential confounders exist when studying relations between N, AD and LBD pathologies, including neuroinflammation and other non-Alzheimer pathologies in MED, though our findings imply posterior hypometabolic mismatch is related more to S than vascular or TDP-43 pathology. A+S+ patients had posterior mismatch with excessive 18F-Fluorodeoxyglucose hypometabolism relative to atrophy or T load, possibly reflecting impaired neuron integrity. Further research must disentangle the impact of multiple proteinopathies and clinicopathologic factors on hypometabolism and atrophy. Cumulatively, patients with mixed AD+LBD etiologies harbor a unique metabolic PET mismatch signature.

Decoding Glioblastoma Heterogeneity: Neuroimaging Meets Machine Learning.

Recent advancements in neuroimaging and machine learning have significantly improved our ability to diagnose and categorize isocitrate dehydrogenase (IDH)-wildtype glioblastoma, a disease characterized by notable tumoral heterogeneity, which is crucial for effective treatment. Neuroimaging techniques, such as diffusion tensor imaging and magnetic resonance radiomics, provide noninvasive insights into tumor infiltration patterns and metabolic profiles, aiding in accurate diagnosis and prognostication. Machine learning algorithms further enhance glioblastoma characterization by identifying distinct imaging patterns and features, facilitating precise diagnoses and treatment planning. Integration of these technologies allows for the development of image-based biomarkers, potentially reducing the need for invasive biopsy procedures and enabling personalized therapy targeting specific pro-tumoral signaling pathways and resistance mechanisms. Although significant progress has been made, ongoing innovation is essential to address remaining challenges and further improve these methodologies. Future directions should focus on refining machine learning models, integrating emerging imaging techniques, and elucidating the complex interplay between imaging features and underlying molecular processes. This review highlights the pivotal role of neuroimaging and machine learning in glioblastoma research, offering invaluable noninvasive tools for diagnosis, prognosis prediction, and treatment planning, ultimately improving patient outcomes. These advances in the field promise to usher in a new era in the understanding and classification of IDH-wildtype glioblastoma.

Alteration of the Morphological and Physicochemical Characteristics of Corn and Wheat Starch via Dry Heating with Whey Protein Isolates.

This study investigated the impact of whey protein isolate (WPI) addition on the dry heat modification of corn (CS) and wheat starch (WS). Starches were treated under dry heating conditions at 130 °C for 2 and 4 h. The physicochemical and structural properties of the modified starches, such as color, particle size, thermal behavior (DSC), crystalline structure (XRD), and surface morphology (SEM), were analyzed. The results show that adding WPI significantly altered the gelatinization properties, surface morphology, and crystalline structure of both starches. DSC indicated that the gelatinization properties of starch/WPI mixtures varied, with corn starch showing a decreased gelatinization temperature and increased enthalpy, whereas wheat starch exhibited a more complex response, likely due to different structural changes. The XRD and FTIR results revealed WPI-enhanced crystallinity and structural changes, highlighting WPI-induced aggregation. Wheat starch, in particular, exhibited stronger interactions with WPI than corn starch, as evidenced by the accumulation patterns in the SEM images. The oil-binding capacity of native starches increased with dry heating and WPI addition, suggesting an improved hydrophobicity of starch granules. Dry heating and WPI addition significantly altered starch properties, highlighting the potential of thermal modulation to enhance starch-protein systems for targeted food applications.

“Rosary Sign” at Somatostatin Receptor PET in a Case of Recurrent Meningioma

“Rosary Sign” at Somatostatin Receptor PET in a Case of Recurrent Meningioma

Modeling the Wavelength Dependence of Pixel Response Nonuniformity of a CCD Sensor

Precision measurements in astronomy require stringent control of systematics such as those arising from imperfect correction of sensor effects. In this work, we develop a parametric method to model the wavelength dependence of pixel response nonuniformity (PRNU) for a laser-annealed backside-illuminated charge-coupled device. The model accurately reproduces the PRNU patterns of flat-field images taken at nine wavelengths from 290 to 950 nm, leaving the rms residuals no more than 0.2% in most cases. By removing the large-scale nonuniformity in the flat fields, the rms residuals are further reduced. This model fitting approach gives more accurate predictions of the PRNU than cubic-spline interpolation does with fewer free parameters. It can be applied to make PRNU corrections for individual objects according to their spectral energy distribution to reduce the photometry errors caused by the wavelength-dependent PRNU, if sub-percent level precision is required.

LIDeepDet: Deepfake Detection via Image Decomposition and Advanced Lighting Information Analysis

The proliferation of AI-generated content (AIGC) has empowered non-experts to create highly realistic Deepfake images and videos using user-friendly software, posing significant challenges to the legal system, particularly in criminal investigations, court proceedings, and accident analyses. The absence of reliable Deepfake verification methods threatens the integrity of legal processes. In response, researchers have explored deep forgery detection, proposing various forensic techniques. However, the swift evolution of deep forgery creation and the limited generalizability of current detection methods impede practical application. We introduce a new deep forgery detection method that utilizes image decomposition and lighting inconsistency. By exploiting inherent discrepancies in imaging environments between genuine and fabricated images, this method extracts robust lighting cues and mitigates disturbances from environmental factors, revealing deeper-level alterations. A crucial element is the lighting information feature extractor, designed according to color constancy principles, to identify inconsistencies in lighting conditions. To address lighting variations, we employ a face material feature extractor using Pattern of Local Gravitational Force (PLGF), which selectively processes image patterns with defined convolutional masks to isolate and focus on reflectance coefficients, rich in textural details essential for forgery detection. Utilizing the Lambertian lighting model, we generate lighting direction vectors across frames to provide temporal context for detection. This framework processes RGB images, face reflectance maps, lighting features, and lighting direction vectors as multi-channel inputs, applying a cross-attention mechanism at the feature level to enhance detection accuracy and adaptability. Experimental results show that our proposed method performs exceptionally well and is widely applicable across multiple datasets, underscoring its importance in advancing deep forgery detection.

Inhibition SNN: unveiling the efficacy of various lateral inhibition learning in image pattern recognition

This study presents an enhanced spiking neural network (SNN) with inhibition, referred to as Inhibition SNN, which advances the field of pattern recognition through efficient event-driven computation. We incorporate a winner-take-all (WTA) mechanism into leaky integrate-and-fire neurons. This, combined with spike timing dependent plasticity, simulates the biological learning process. We propose two network prototypes, namely Inhibition V1 and Inhibition V2. Inhibition V1 differentiates between an excitatory layer and an inhibitory layer, while Inhibition V2 uses self-connections in the excitatory layer to implement WTA dynamics, enhancing signal contrast without a separate inhibitory layer. Our experiments on the MNIST dataset show that both Inhibition V1 and Inhibition V2 can match the accuracy of current advanced networks, with Inhibition V2 performing better. An unsupervised learning network of two layers (784–100) achieves 86% accuracy on MNIST and 61% on Fashion-MNIST. The scalability and robustness of these networks in neural computation underscore their potential for practical applications. This research offers a fresh perspective on SNN design, highlighting the impact of inhibition on learning efficiency. With plans to adapt these networks to neuromorphic hardware, Inhibition SNN could pave the way for energy-efficient intelligent systems.

Abstract 4136394: Elucidation of a novel genetic substrate responsible for genetically elusive ring-like arrhythmogenic cardiomyopathy

Background: Arrhythmogenic cardiomyopathy (ACM) is a genetic heart disease characterized by fibrofatty replacement of ventricular myocardium. Arrhythmogenic left ventricular (LV) cardiomyopathy (ALVC) is a phenotypic variant of ACM predominantly involving the LV. Mutations in genes encoding for desmosome proteins and filamin C have been implicated in ALVC, especially in the setting of a ring-like late gadolinium enhancement (LGE) imaging pattern. Objective: To identify the underlying genetic substrate responsible for genetically elusive ring-like ALVC in a patient with seemingly sporadic/recessive disease. Methods: A 38-year-old male was referred for genetic investigation to determine the underlying genetic substrate responsible for his ALVC phenotype. The patient fulfilled both electrocardiographic (low voltage in the limb leads and anterolateral T-wave inversions) and imaging (&gt;1 segment of subepicardial LGE) criteria for ALVC. Additionally, the patient experienced unexplained episodes of tachycardia, shakiness, sweating, and nausea prompting concern for an underlying neuromuscular disease. Genome sequencing (GS) was performed on DNA isolated from the affected patient and both of his unaffected parents. Variants were filtered assuming either a sporadic de novo occurrence or an autosomal recessive inheritance pattern. Results: GS identified compound heterozygous GNPTAB variants in the affected patient. A previously reported maternally derived p.Leu257Leu (c.771G&gt;A) variant involving the last nucleotide of exon 7 of the GNPTAB gene and a novel paternally inherited Lys834fs*5 frame-shift variant were identified. The p.Leu257Leu variant has been reported to cause aberrant splicing and exon skipping of the GNPTAB mRNA transcript. Pathogenic variants in the GNPTAB encoded N-acetylglucosamine-1 (GlcNAc)-phosphotransferase subunits alpha/beta cause mucolipidosis type III, a rare recessive lysosomal storage disease characterized by coarse facial features, developmental delay, short stature, skeletal deformities, and cardiac involvement including valvular thickening and cardiomyopathy. Conclusions: Here, using a genome sequencing trio analysis we identified a compound heterozygous GNPTAB pathogenic variants as the underlying genetic substrate in a patient with ring-like ALVC and concomitant neuromuscular disease manifestation. Genome sequencing may identify the genetic etiology responsible for an otherwise undifferentiated diagnosis of cardiomyopathy.