Test Images Research Articles

A case of complete response to radiotherapy combined with durvalumab and tremelimumab in a patient with unknown primary hepatocellular carcinoma arising in the lumbar spine.

A 58-year-old man visited an orthopedic clinic complaining of pain in his right lower back and numbness in his lower limbs for one month. Imaging tests revealed a tumorous lesion from the left side of the second lumbar vertebra to the paraspinal muscles. CT-guided biopsy of the tumor was performed, and immunostaining results diagnosed hepatocellular carcinoma (HCC). Although the liver showed signs of chronic liver damage, no primary tumor was found within the liver or in other organs. Blood tests showed negative hepatitis virus markers for both HBV and HCV. The tumor markers AFP, AFP-L3, and DCP were high. Because he developed spinal cord compression syndrome due to a lumbar tumor, radiation therapy and denosumab administration were performed. Subsequently, systemic therapy with durvalumab plus tremelimumab was started. In the year following the start of treatment, the tumor has shrunk, and no new lesions have been observed. Tumor markers have also decreased. We have experienced a case of HCC in the lumbar spine without a primary tumor in the liver. This is a very rare case, and the combination therapy with durvalumab and tremelimumab resulted in a complete response, which we consider to be a valuable case.

Benign and malignant breast lesions in children and adolescents - diagnostic and therapeutic approach.

Benign and malignant breast lesions in children and adolescents are rare compared to adults. Most tumors are benign. Malignant breast lesions are extremely rare. Fibroadenomas are the most common, accounting for 95% of all lesions. Diagnosis is based on history and physical examination of the breast and armpit. Imaging studies include ultrasound, mammography, and magnetic resonance imaging. Ultrasound is the most commonly used imaging test. Other tests are used in cases of diagnostic doubt. Core needle biopsy should be considered for appropriate diagnostic management. Excisional biopsy should be considered for complex clinical conditions and imaging studies. Except in doubtful situations in children and adolescent girls, a conservative approach and observation of the lesions along with periodic ultrasound examination initially every 6-12 months is advisable. Management of malignant breast lesions in children typically involves a multidisciplinary team consisting of pediatric oncologists, surgeons, radiation oncologists, pathologists, and other specialists and depends on the clinical condition of the patient. An important aspect is the experience of the clinician and radiologist in the treatment of breast lesions, as well as increasing patient and family awareness of possible breast lesions and self-examination. This review aims to provide a scoping overview of the available literature on benign and malignant lesions of the breast in pediatric and adolescent populations to assist physicians and surgeons in making decisions regarding the appropriate diagnosis and management of pediatric breast disease.

Epispadic accessory urethra in an 8 months old female with urethral duplication: a case report

Introduction and Importance: Urethral duplication is an uncommon urogenital congenital disability that presents as an accessory urethra in an atypical location. This condition is often coupled with other congenital anomalies like bladder exstrophy, pseudohermaphroditism, and renal disorders. Case Presentation: We report a case of a female infant aged eight months with urethral duplication, showing an unusual urinary opening in the prepubic area and urinary discharge. A comprehensive diagnostic assessment, consisting of a clinical exam, imaging tests, and cystoscopy, verified the existence of an accessory urethra and the normal one in epispadias. The patient had a successful surgery to remove the accessory tract with primary closure. Clinical Discussion: Urethral duplication is associated with diverse clinical signs and symptoms. Accurate diagnosis needs thorough imaging studies, and treatment should be tailored according to the type and anatomical location of the accessory tract. Conclusion: The histological confirmation of urethral duplication was obtained following the surgical excision of the additional tract. This case underscores the significance of accurate diagnosis and treatment approaches to manage this case.

Non-classical monocyte levels correlate negatively with HIV-associated cerebral small vessel disease and cognitive performance.

Despite antiretroviral treatment (cART), aging people living with HIV (PWH) are more susceptible to neurocognitive impairment (NCI) probably due to synergistic/additive contribution of traditional cerebrovascular risk factors. Specifically, transmigration of inflammatory CD16+ monocytes through the altered blood brain barrier (BBB) may exacerbate cerebral small vessel disease (CSVD), a known cause of vascular cognitive impairment. PWH on cART (n=108) and age, sex, and Reynold's cardiovascular risk score-matched uninfected individuals (PWoH, n=111) were enrolled. This is a longitudinal observational study but only cross-sectional data from entry visit are reported. Neuropsychological testing and brain magnetic resonance imaging (MRI) were performed. CSVD was diagnosed by Fazekas score ≥1. Flow cytometric analyses of fresh whole blood were conducted to evaluate circulating levels of monocyte subsets (classical, intermediate, and non-classical) and markers of monocyte activation (CCR2, CD40, PSGL-1, TNFR2 and tissue factor). ELISAs were used to measure sCD14, ICAM, and Osteoprotegerin. Two-way analysis of variance (ANOVA), and linear regression models were performed to study the effects of HIV status, CSVD status, and their interaction to outcome variables such as cognitive score. Two-sample t-tests and correlation analyses were performed between and within PWoH with CSVD and PWH with CSVD participants. PWH with CSVD (n=81) had significantly lower total cognitive scores, higher levels of NCMs and soluble CD14 and intracellular adhesion molecule 1 (ICAM-1) as compared to PWoH with CSVD group (n=68). sCD14 and ICAM1 were positively correlated with each other indicating that monocyte and endothelial activation are associated with each other. Cognition was negatively correlated with NCMs, especially in the PWH with CSVD group. Among other blood biomarkers measured, osteoprotegerin levels showed mild negative correlation with cognitive performance in individuals with CSVD irrespective of HIV status. Elevated levels of NCMs may contribute to neuroinflammation, CSVD and subsequent cognitive impairment. This finding is of particular relevance in aging PWH as both HIV and aging are associated with increased levels of NCMs. NCMs may serve as a potential biomarker to address these comorbidities. Further longitudinal studies are needed to evaluate whether changes in NCM levels are associated with changes in CSVD burden and cognitive impairment.

Dyadic Partition-Based Training Schemes for TV/TGV Denoising.

Due to their ability to handle discontinuous images while having a well-understood behavior, regularizations with total variation (TV) and total generalized variation (TGV) are some of the best-known methods in image denoising. However, like other variational models including a fidelity term, they crucially depend on the choice of their tuning parameters. A remedy is to choose these automatically through multilevel approaches, for example by optimizing performance on noisy/clean image pairs. In this work, we consider such methods with space-dependent parameters which are piecewise constant on dyadic grids, with the grid itself being part of the minimization. We prove existence of minimizers for fixed discontinuous parameters under mild assumptions on the data, which lead to existence of finite optimal partitions. We further establish that these assumptions are equivalent to the commonly used box constraints on the parameters. On the numerical side, we consider a simple subdivision scheme for optimal partitions built on top of any other bilevel optimization method for scalar parameters, and demonstrate its improved performance on some representative test images when compared with constant optimized parameters.

Enterotomia para remoção de corpo estranho no jejuno

In the small animal clinic, dogs that ingest non-digestible objects are frequently seen, which end up causing obstruction in the animal's digestive system. Young canines are the most affected, when playing or/and eating indiscriminately with inedible objects. The diagnosis of intestinal obstruction is essential, as it can cause clinical repercussions such as erosions and ulcers. Therefore, it is based on anamnesis and clinical signs such as emesis, anorexia and apathy, in addition, when necessary, the professional may request imaging tests and exploratory laparotomy to confirm the diagnostic hypothesis. From this perspective, a Shih Tzu dog, approximately two years old, weighing 4 kg, was seen at the clinic. In the anamnesis, the guardian reports that the patient was apathetic and had recurrent vomiting. On clinical examination, only moderate dehydration was evident. The treatment was carried out surgically using the laparotomy technique followed by enterotomy, which is the most recommended treatment in cases of intestinal obstruction caused by a foreign body. The animal had a positive prognosis and a good recovery. Therefore, the aim of this work is to report a case of obstruction of the intestinal tract by a foreign body in a dog and the surgical techniques used to treat it.

Clinical and Genetic characteristics of patients with Peripheral Retinal Fleck in Koreans.

To describe the clinical and genetic features of Korean patients with peripheral retinal flecks unrelated to aging. A retrospective analysis was conducted on the clinical characteristics of patients with symmetric peripheral retinal flecks. Age-related deposits such as reticular pseudodrusen were excluded, as well as secondary deposits related to intraocular inflammation, tumor, and drug toxicity. Multimodal imaging, electrophysiological examinations, and genetic testing were analyzed. A total of 10 patients (2 males and 8 females) with bilateral peripheral flecks were enrolled in this study. A mean age at diagnosis was 30.5±19.6 years (4-59 years). Within the 10 patients, 6 were genetically confirmed with monogenic retinal disorders. Biallelic pathogenic variants in RDH5 were found in 5 patients, and 1 patient was diagnosed with retinopathy related to Alport syndrome due to a pathogenic variant in COL4A5. Although not genetically confirmed, one case associated with nanophthalmos and another case showing chorioretinal mottling in a carrier of ocular albinism have been identified. In one patient, genetic testing also revealed unknown causes. The mean logMAR initial visual acuity was 0.12±0.18 and 0.07±0.18 in right and left eyes, respectively. Night blindness was reported by 4 patients (40%), with 3 showing decreased or delayed rod response in electroretinogram, particularly those with RDH5 mutations. Differences in the deposit layers and the patterns of flecks were observed on multimodal imaging. In the study population, we observed various causes and clinical differences in the retinal fleck patterns among Koreans, including RDH5-related fundus albipunctatus and Alport syndrome. Despite reports of night blindness symptoms in some cases, all patients demonstrated satisfactory corrected visual acuity.

Type I Branchial Cyst of the Sedunda Cleft Uncommon presentation: Case Report

Introduction: The cyst branchial is a rare tumor as well known as cysts lymphoepithelial, are dysembryological rare and benign second cleft tumors. Tumors cystic that HE develop in the part anterolateral of the neck; represent he 2% of the tumors laterocervical of the neck [1]. Clinical Case: We present he clinical case of a patient male of 37 years, does not report personal pathological history, with a clinical picture of approximately 8 months of evolution approximately characterized by a laterocervical tumor right with progressive growth in size, not accompanied by any other symptoms. Upon examination Physical: A mobile, fluctuating tumor of approximately 5 cm in diameter is observed in the right cervical region III, with no changes in skin color. No symptoms of a sinus or fistulous tract are observed. Discussion: The cyst branchial is a rare tumor and benign second cleft tumors. Tumors cystic that HE develop in the part anterolateral of the neck, represent he 2% of the tumors laterocervical of the neck, proper physical examination determines its prompt diagnosis and surgical treatment [6]. Conclusion: In conclusion, despite their low incidence, third branchial cleft cysts should be included in the differential diagnosis of laterocervical tumors. An adequate history and physical examination, complemented by the indicated imaging tests, will allow establishing a presumptive diagnosis that should be confirmed histologically after surgical resection.

Psychotropic Polypharmacy Leading to Reversible Dementia: A Case Report.

Psychotropic polypharmacy presents a diagnostic challenge that may be further complicated by inadequate medication history and underappreciation of the cognitive effects of such polypharmacy. Here we present the case of a 57-year-old man who presented to our memory clinic with progressive cognitive decline and a prior neuropsychological evaluation supporting the diagnosis of a neurodegenerative disorder. He was taking multiple psychotropic medications at the time, but the exact dosages were unclear due to a lack of collateral history. He was also taking prescribed opioids and a combination of buprenorphine and naloxone for pain relief, again with unclear dosages at the time of presentation. Brain imaging and cerebrospinal spinal fluid biomarker testing were negative for Alzheimer pathophysiologic processes. Months later, the patient was taken to the emergency room after an overdose caused by overuse of opioid medications. Once he was taken off all psychoactive medications, the patient's cognitive impairment completely reversed, and he became independent in activities of daily living. Psychotropic polypharmacy can have a myriad of cognitive manifestations which need to be better recognized by clinicians. Deprescription of such medications should be attempted whenever clinically appropriate.

A Multilayer Nonlinear Permutation Framework and Its Demonstration in Lightweight Image Encryption

As information systems become more widespread, data security becomes increasingly important. While traditional encryption methods provide effective protection against unauthorized access, they often struggle with multimedia data like images and videos. This necessitates specialized image encryption approaches. With the rise of mobile and Internet of Things (IoT) devices, lightweight image encryption algorithms are crucial for resource-constrained environments. These algorithms have applications in various domains, including medical imaging and surveillance systems. However, the biggest challenge of lightweight algorithms is balancing strong security with limited hardware resources. This work introduces a novel nonlinear matrix permutation approach applicable to both confusion and diffusion phases in lightweight image encryption. The proposed method utilizes three different chaotic maps in harmony, namely a 2D Zaslavsky map, 1D Chebyshev map, and 1D logistic map, to generate number sequences for permutation and diffusion. Evaluation using various metrics confirms the method’s efficiency and its potential as a robust encryption framework. The proposed scheme was tested with 14 color images in the SIPI dataset. This approach achieves high performance by processing each image in just one iteration. The developed scheme offers a significant advantage over its alternatives, with an average NPCR of 99.6122, UACI of 33.4690, and information entropy of 7.9993 for 14 test images, with an average correlation value as low as 0.0006 and a vast key space of 2800. The evaluation results demonstrated that the proposed approach is a viable and effective alternative for lightweight image encryption.

Joint subarray acoustic tweezers enable controllable cell translation, rotation, and deformation

Contactless microscale tweezers are highly effective tools for manipulating, patterning, and assembling bioparticles. However, current tweezers are limited in their ability to comprehensively manipulate bioparticles, providing only partial control over the six fundamental motions (three translational and three rotational motions). This study presents a joint subarray acoustic tweezers platform that leverages acoustic radiation force and viscous torque to control the six fundamental motions of single bioparticles. This breakthrough is significant as our manipulation mechanism allows for controlling the three translational and three rotational motions of single cells, as well as enabling complex manipulation that combines controlled translational and rotational motions. Moreover, our tweezers can gradually increase the load on an acoustically trapped cell to achieve controllable cell deformation critical for characterizing cell mechanical properties. Furthermore, our platform allows for three-dimensional (3D) imaging of bioparticles without using complex confocal microscopy by rotating bioparticles with acoustic tweezers and taking images of each orientation using a standard microscope. With these capabilities, we anticipate the JSAT platform to play a pivotal role in various applications, including 3D imaging, tissue engineering, disease diagnostics, and drug testing.

Diagnostic Approach to Children with Unexplained Global Developmental Delay in Pediatric Neurology Outpatient Clinic.

Global developmental delay (GDD) is a common pediatric disorder that affects up to 3% of children. Due to the heterogeneous etiology of GDD, diagnostic procedures and algorithms are complex and diverse. The aim of our study was to investigate the diagnostic yield of genetic, metabolic, and imaging studies in establishing the etiology of unexplained GDD (UGDD). In this retrospectively observational study, we examined the medical records of all children diagnosed with UGDD at the Department of Pediatric Neurology, University Medical Centre Ljubljana, Slovenia, between January and December 2019. We evaluated the effectiveness of various genetic, metabolic, and magnetic resonance imaging (MRI) tests in identifying the underlying cause of GDD. Additionally, we assessed subgroups of patients to determine whether any of the studied tests were particularly beneficial based on their clinical symptoms. A total of 123 patients met the inclusion criteria, with a median age of 4.3 years (range, 0-16 years), of which 71 (57.7%) were males. Genetic diagnosis was established in 47.1% (58/123) of patients. Metabolic laboratory testing did not identify a metabolic disease in any of the tested participants (114/123) and MRI was critical for diagnosis in only 1/81 (1.2%) patient. Our findings strongly suggest that genetic testing surpasses MRI and metabolic testing in establishing the etiology of UGDD in a pediatric neurology outpatient setting. This information will help guide the diagnostic evaluation of these children.

Pruning convolution neural networks using filter clustering based on normalized cross-correlation similarity

ABSTRACT Despite all the recent development and success of deep neural networks, deployment of a deep model onto the resource-constrained devices still remains challenging. However, model pruning can resolve this issue for Convolutional Neural Networks (CNNs), since it is one of the most popular approaches to reducing computational complexities. Therefore, this article presents a pruning model for convolutional neural networks. The proposed method classifies and arranges similar filters into the same cluster where the similarity is calculated using a three-dimensional normalized cross-correlation. Moreover, these steps can be completed entirely based on the filter values while not requiring a set of test images as well as the acquisition of any filter activation. In the research, the performances of the proposed model pruning method have been evaluated, where it is observed that the proposed approach is computationally light and requires significantly less time and resources compared to ML and activation-based approaches. In the experiments, using the VGG16 model on the Cifar10 dataset, the proposed approach results in the pruned model(s) which are comparable in performance with models found using activation-based methods and expensive ML-based methods. Similar results are found when pruning a custom CNN on the MNIST and Fashion MNIST datasets as well.

On the influence of artificially distorted images in firearm detection performance using deep learning

Detecting people carrying firearms in outdoor or indoor scenes usually identifies (or avoids) potentially dangerous situations. Nevertheless, the automatic detection of these weapons can be greatly affected by the scene conditions. Commonly, in real scenes these firearms can be seen from different perspectives. They also may have different real and apparent sizes. Moreover, the images containing these targets are usually cluttered, and firearms can appear as partially occluded. It is also common that the images can be affected by several types of distortions such as impulse noise, image darkening or blurring. All these perceived variabilities could significantly degrade the accuracy of firearm detection. Current deep detection networks offer good classification accuracy, with high efficiency and under constrained computational resources. However, the influence of practical conditions in which the objects are to be detected has not sufficiently been analyzed. Our article describes an experimental study on how a set of selected image distortions quantitatively degrade the detection performance on test images when the detection networks have only been trained with images that do not present the alterations. The analyzed test image distortions include impulse noise, blurring (or defocus), image darkening, image shrinking and occlusions. In order to quantify the impact of each individual distortion on the firearm detection problem, we have used a standard YOLOv5 network. Our experimental results have shown that the increased addition of impulse salt-and-pepper noise is by far the distortion that affects the most the performance of the detection network.

An interpretable and transparent machine learning framework for appendicitis detection in pediatric patients.

Appendicitis, an infection and inflammation of the appendix is a prevalent condition in children that requires immediate treatment. Rupture of the appendix may lead to several complications, such as peritonitis and sepsis. Appendicitis is medically diagnosed using urine, blood, and imaging tests. In recent times, Artificial Intelligence and machine learning have been a boon for medicine. Hence, several supervised learning techniques have been utilized in this research to diagnose appendicitis in pediatric patients. Six heterogeneous searching techniques have been used to perform hyperparameter tuning and optimize predictions. These are Bayesian Optimization, Hybrid Bat Algorithm, Hybrid Self-adaptive Bat Algorithm, Firefly Algorithm, Grid Search, and Randomized Search. Further, nine classification metrics were utilized in this study. The Hybrid Bat Algorithm technique performed the best among the above algorithms, with an accuracy of 94% for the customized APPSTACK model. Five explainable artificial intelligence techniques have been tested to interpret the results made by the classifiers. According to the explainers, length of stay, means vermiform appendix detected on ultrasonography, white blood cells, and appendix diameter were the most crucial markers in detecting appendicitis. The proposed system can be used in hospitals for an early/quick diagnosis and to validate the results obtained by other diagnostic modalities.

Unconventional mechanical responses and mechanisms of Ti-6Al-4V sheet subjected to electrically-assisted cyclic loading-unloading: Thermal and athermal effects

For the sake of unveiling the macro-micro behaviors and underlying control mechanisms of electroplastic effect (EPE) of sheet metals during recent thriving electrically-assisted incremental forming (EAIF) processes, electrically-assisted cyclic loading-unloading tension (EACT) experiments were carried out at a current density of 14～20A/mm2 followed by forced and unforced cooling. The electro-thermo-mechanical responses and the evolution rules of dislocation configurations, fracture modes, phase composition and local orientation distribution were characterized by IR imaging, SEM, quantitative EBSD and TEM tests. Moreover, the thermal and athermal components of the electrically-induced stress drop throughout the EACT processes were decoupled and systematically analyzed via temperature control tests and isothermal correction. The results show that thermal effect of electric current possesses a great proportion of 75 % in the overall stress drop and plays a key role in elastic modulus degradation and ductility enhancement by activating pyramidal {101‾1}⟨12‾10⟩ slip systems, weakening (0001) texture and promoting dynamic recrystallization (DRX) and α→β→α′ phase transformation. While the athermal effect only operates after reaching both threshold current density and plastic strain, it increases monotonically with current density, brings about “hot spots” effect, local charge imbalance and weakened atomic bonding, and further causes intensified local strain gradient, substructure formation and DRX nucleation. The ratio of athermal stress drop first decreases and then increases significantly with loading cycle at the later stage of EACT under the combined effect of local Joule heating effect and flow localization. Additionally, the athermal effect only activates short-range solute diffusion and localized diffusional α→β phase transformation, while the combined thermal and athermal effects promote long-range solute diffusion and an increasing rate in β content of 261.8 %. The present work provides theoretical basis for optimizing the EAIF forming process and realizing extreme manufacture of light-weight thin-walled complex components.

Navigating therapeutic sequencing in the metastatic castration-resistant prostate cancer patient journey.

Novel therapies for metastatic castration-resistant prostate cancer (mCRPC) have improved patient outcomes. However, there is uncertainty on the optimal selection of therapeutic agents for subsequent lines of therapy. We conducted a comprehensive review of published evidence from pivotal clinical trials and recent guidelines for the treatment of mCRPC. We further identify gaps in knowledge and areas for future research. Key considerations to help guide treatment selection for patients with mCRPC include personal treatment history, individual clinical characteristics, symptoms, prognosis, availability of clinical trials, and other patient-specific factors. Genetic testing and prostate-specific membrane antigen-targeted imaging are important tools to evaluate candidacy for newer therapeutic options such as poly (ADP-ribose) polymerase inhibitors, alone or in combination with androgen receptor pathway inhibitors, and [177Lu]Lu-PSMA-617. This article provides an overview of the evolving treatment landscape of mCRPC, discussing guideline-recommended treatment options and data from key clinical trials, while highlighting ongoing trials that may impact the future treatment landscape. Recommendations for optimal treatment sequencing based on individual patient factors are provided.

Computed tomography employing sensing of high energy particle current

Objective. We demonstrate High Energy Current Computed Tomography (HEC-CT) employing megavoltage linac x-rays.Approach. Using deterministic radiation transport we simulate two-parameter HEC-CT projections and using inverse Fourier transform we reconstruct two distinct material parameters for water phantoms with ICRP tissue inserts and materials of different atomic number Z. The HEC-CT projections are obtained by beam scanning and rotating the object.Main Results. The first HEC-CT material parameter is alike the standard attenuation coefficient with dependence on atomic number and material density similar to the Hounsfield Units. The second material parameter has opposite trends and does not find any analogy in the standard CT framework.Significance. New CT method has been invented for medical imaging or non-destructive testing. The key feature of the technique is a two-value CT reconstruction based on particle current instead of transmitted dose.

Genetic Biomarkers in Heart Failure: From Gene Panels to Polygenic Risk Scores.

This review aims to provide a comprehensive overview of the current understanding of genetic markers associated with heart failure (HF) and its underlying causative diseases, such as cardiomyopathies. It highlights the relevance of genetic biomarkers in diagnosing HF, predicting prognosis, potentially identifying its preclinical stages and identifying targets to enable the implementation of individualized medicine approaches. The prevalence of HF is increasing due to an aging population but with greater access to disease-modifying therapies. Advanced diagnostic tools such as cardiac magnetic resonance, nuclear imaging, and AI-enabled diagnostic testing are now being utilized to further characterize HF patients. Additionally, the importance of genetic testing in HF diagnosis and management is increasingly being recognized. Genetic biomarkers, including single nucleotide polymorphisms (SNPs) and rare genetic variants, are emerging as crucial tools for diagnosing HF substrates, determining prognosis and increasingly directing therapy. These genetic insights are key to optimizing HF management and delivering personalized treatment tailored to individual patients. HF is a complex syndrome affecting millions globally, characterized by high mortality and significant economic burden. Understanding the underlying etiologies of HF is essential for improving management and clinical outcomes. Recent advances highlight the use of multimodal assessments, including AI-enabled diagnostics and genetic testing, to better characterize and manage HF. Genetic biomarkers are particularly promising in identifying preclinical HF stages and providing personalized treatment options. The genetic contribution to HF is heterogeneous, with both monogenic and polygenic bases playing a role. These developments underscore the shift towards personalized medicine in HF management.

Comparative Study of GPT-4Vision and Convolutional Neural Networks in Histopathological Image Analysis

Abstract Introduction/Objective Recent advancements in artificial intelligence (AI), particularly with Large Language Models like ChatGPT-4Vision (GPT-4V), have expanded the potential for automated interpretation of medical images. This study evaluates the diagnostic accuracy of GPT-4V in histopathological analysis of neurodegenerative diseases and compares its performance with traditional Convolutional Neural Networks (CNNs). Methods/Case Report We utilized 1515 histopathological images, including hematoxylin and eosin (H&E) staining and tau immunohistochemistry, from patients with various neurodegenerative diseases, such as Alzheimer’s disease, progressive supranuclear palsy, and corticobasal degeneration. GPT-4V’s performance was assessed through multi- step prompts to assess how textual context influences the image interpretation. In the quantitative analysis, the diagnostic accuracy of GPT-4V and the CNN-based model YOLOv8 was assessed for classifying three tau lesions—astrocytic plaques, neuritic plaques, and tufted astrocytes. The analysis used both zero-shot and few-shot learning methods, where GPT-4V and YOLOv8 were evaluated on their ability to distinguish these lesions using ten hold-out test images and 490 training images per lesion. Results (if a Case Study enter NA) GPT-4V accurately recognized Lewy bodies in all cases, but it showed limited accuracy in identifying neurofibrillary tangles (20%) and Pick bodies (0%) on H&E slides. Notably, GPT-4V often suggested Alzheimer’s disease as a potential diagnosis, relying more on contextual clues, such as the prevalence of certain diseases, rather than direct image analysis. In the tau immunohistochemical analysis, GPT-4V’s diagnoses were strongly influenced by additional information about staining and brain region. However, few-shot learning markedly improved GPT-4V’s diagnostic capabilities from 40% accuracy with zero-shot learning to 90% with few-shot learning, reaching best accuracy with 20-shot learning. This performance compared favorably against YOLOv8, which also achieved 90% accuracy but required 100-shot learning. Conclusion While GPT-4V faces challenges in independently interpreting histopathological images, few-shot learning significantly improves its accuracy. This approach is particularly promising for neuropathology, where acquiring extensive labeled datasets is challenging. The findings highlight the need for ongoing refinement of AI applications in pathology, emphasizing balanced integration of textual and visual data to optimize diagnostic efficacy and reliability.