Accuracy Of Clinical Diagnosis Research Articles

Diagnostic value of high-frequency ultrasound combined with magnetic resonance in different clinical stages of frozen shoulder: A retrospective cohort study

Background Frozen shoulder (FS) is a common musculoskeletal disease. Imaging plays an active role in the clinical diagnosis and staging of FS. Objective This study is undertaken to assess the application value of high-frequency ultrasound (HFU) combined with magnetic resonance (MR) in clinical staging diagnosis of FS. Methods This was a retrospective cohort study. The medical records of FS patients (from January 2021 to February 2022, n = 100) were collected. Patients were categorized into stage I (n = 30), stage II (n = 35) and stage III (n = 35) groups. The diagnostic value of HFU-related and MR-related indicators was assessed by the receiver operating characteristic (ROC) curve. The correlation between HFU/MR indicator and passive range of motion-related indicators was analyzed by Spearman rank method. Results There were no statistically significant differences in gender, age, height, weight, and affected shoulder (left: right) among the three groups at different stages ( p > 0.05). HFU and MR in combination had a higher diagnostic coincidence rate when compared to their single use (96.00% vs. 91.00% or 93.00%). There was high diagnostic value for inferior capsule thickness (ICT) (area under the curve (AUC) = 0.914, p < 0.001, 95% CI (0.836–0.992)), glenohumeral distance (GHD) (AUC = 0.999, p < 0.001, 95% CI (0.996–1.000)) and articular capsule thickness (ACT) (AUC = 1.000, p < 0.001, 95% CI (0.998–1.000)) in stage I FS, for ICT (AUC = 0.947, p < 0.001, 95% CI (0.885–1.000)) and GHD (AUC = 0.974, p < 0.001, 95% CI (0.949–0.999)) in stage II FS, and for ACT (AUC = 0.989, p < 0.001, 95% CI (0.975–1.000)) in stage III FS. ICT/ACT positively correlated with internal rotation (IR), and negatively correlated with external rotation (ER)/extension (EX)/flexion (FL)/abduction (AB). GHD had a negative correlation with IR, and a positive correlation with ER/EX/FL/AB. Conclusion High-frequency ultrasound combined with magnetic resonance can improve the accuracy in clinical diagnosis of FS, promote better staging of FS, and provide a more reliable basis for clinical diagnosis and treatment of FS.

Metabolomics based early warning model for acute kidney injury risk in patients exposed to diquat.

Acute kidney injury (AKI) is one of the most important indications of severe clinical symptoms in patients with diquat poisoning and is closely related to poor prognosis. However, current studies have rarely focused on early warnings of diquat-related AKI, which is not conducive to the treatment of patients with early clinical diquat poisoning. In this study, untargeted plasma metabolomics was employed to reveal the differences between diquat-poisoned patients with and without AKI, as well as between patients and healthy volunteers. The results showed that 48 metabolites were significantly changed in the patients, among which 3-hydroxybutyrylcarnitine, SAICAR, dodecanoic acid, and tetrahydrofolyl-[Glu](2) could be used to effectively differentiate the above three groups. Based on the ratios of the first two metabolites and the ratios of the last two metabolites, a decision tree model for the early warning of diquat-induced AKI was established with an accuracy rate of 88.7 %. This model provides great support for accurate clinical diagnosis and intervention regarding the AKI risk of diquat-exposed patients.

MSG-YOLO: A Lightweight Detection Algorithm for Clubbing Finger Detection

Clubbing finger is a significant clinical indicator, and its early detection is essential for the diagnosis and treatment of associated diseases. However, traditional diagnostic methods rely heavily on the clinician’s subjective assessment, which can be prone to biases and may lack standardized tools. Unlike other diagnostic challenges, the characteristic changes of clubbing finger are subtle and localized, necessitating high-precision feature extraction. Existing models often fail to capture these delicate changes accurately, potentially missing crucial diagnostic features or generating false positives. Furthermore, these models are often not suited for accurate clinical diagnosis in resource-constrained settings. To address these challenges, we propose MSG-YOLO, a lightweight clubbing finger detection model based on YOLOv8n, designed to enhance both detection accuracy and efficiency. The model first employs a multi-scale dilated residual module, which expands the receptive field using dilated convolutions and residual connections, thereby improving the model’s ability to capture features across various scales. Additionally, we introduce a Selective Feature Fusion Pyramid Network (SFFPN) that dynamically selects and enhances critical features, optimizing the flow of information while minimizing redundancy. To further refine the architecture, we reconstruct the YOLOv8 detection head with group normalization and shared-parameter convolutions, significantly reducing the model’s parameter count and increasing computational efficiency. Experimental results indicate that the model maintains high detection accuracy with reduced parameter and computational requirements. Compared to YOLOv8n, MSG-YOLO achieves a 48.74% reduction in parameter count and a 24.17% reduction in computational load, while improving the mAP0.5 score by 2.86%, reaching 93.64%. This algorithm strikes a balance between accuracy and lightweight design, offering efficient and reliable clubbing finger detection even in resource-constrained environments.

Low Dose CT Image Denoising: A Comparative Study of Deep Learning Models and Training Strategies

Article Low Dose CT Image Denoising: A Comparative Study of Deep Learning Models and Training Strategies Heng Zhao 1, Like Qian 1, Yaqi Zhu 1 and Dingcheng Tian 1,2,∗ 1 Research Institute for Medical and Biological Engineering, Ningbo University, Ningbo 315211, China 2 College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110016, China ∗ Correspondence: 2310520@stu.neu.edu.cn Received: 8 August 2024; Revised: 10 October 2024; Accepted: 14 October 2024; Published: 5 November 2024 Abstract: Low-dose computed tomography (LDCT) denoising is an important topic in CT image research. Compared with normal-dose CT images, LDCT can reduce the radiation dose of X-rays, decreasing the radiation burden on the human body, which is beneficial to human health. However, quantum noise caused by low-dose rays will reduce the quality of CT images, thereby decreasing the accuracy of clinical diagnosis. In recent years, deep learning-based denoising methods have shown promising advantages in this field. Researchers have proposed some optimized models for low-dose CT image denoising. These methods have enhanced the application of low-dose CT image denoising from different aspects. From the perspective of experimental research, this paper investigates and evaluates some top deep learning models proposed in the field of low-dose image denoising in recent years, with the aim of determining the best models and training strategies for this task. We conducted experiments on seven deep learning models (REDCNN, EDCNN, QAE, OCTNet, UNet, WGAN, CTformer) on the AAPM dataset and the Piglet dataset. Our research shows that UNet has the best denoising effect among the models, obtaining PSNR = 33.06 (AAPM dataset) and PSNR = 31.21 (Piglet dataset), and good generalization capacity is also observed. However, UNet has a large number of parameters, and the time it takes to process an image is about 8 ms, while EDCNN takes about 4.8 ms to process an image, and its average PSNR is ranked second after UNet. EDCNN strikes a balance between denoising performance and processing efficiency, making it ideal for low-dose CT image denoising tasks.

Accuracy of clinical diagnosis, imaging methods, and biopsy in tumours and pseudo-tumours of the hand.

The appropriate use of imaging methods in bone and soft tissue tumours of the hand is well established in the radiological literature. However, since most of the tumoral conditions of the hand are benign, the use of imaging methods may be based on clinician preferences and technical availability. The aim of this work is to present the experience in our institution in the management of tumours and pseudo-tumours of the hand and to review the utility of different imaging methods in their diagnosis. We present a retrospective and consecutive case series of patients referred to Hospital Universitario Virgen de las Nieves due to clinical suspicion of hand tumour in the last 10 years. We assessed the accuracy of clinical and imaging diagnoses, matching the final pathological or surgical results, considering a diagnosis as "correct" if it was included in the differential diagnosis suggested in the clinical (including all provided diagnoses) or radiological report (only the first 2 diagnoses), respectively. Biopsy accuracy was contrasted with surgical findings. We included 175 patients with a pathological or microbiological diagnosis of hand tumors, obtained through surgery (n=124) and/or core needle biopsy (n=62), or puncture-drainage (n=30). Among these, 21 cases were identified as infectious, metabolic, or inflammatory processes, while 154 were classified as hand tumours or pseudotumours (101 in soft tissues and 53 in bone). The overall diagnostic accuracy (95% confidence interval) for each approach was as follows: clinical diagnosis, 26.3% (19.8-32.8%); ultrasound, 72.6% (64.3-80.8%); magnetic resonance imaging (MRI), 80.6% (73.8-87.4%); computed tomography (CT), 84.6% (74.8-94.4%); and radiography, 46.8% (38.6-55.0%). The overall accuracy of imaging was 81.1% (75.3-86.9%). For soft tissue masses, the diagnostic accuracy was: clinical, 30.7% (25.5-42.1%); ultrasound, 69.8% (62.9-80.1%); MRI, 73.9% (65.5-83.4%); CT, 75.0% (30-92%); and radiography, 20.3% (14-33%), with an overall imaging accuracy of 75.2% (69.2-84.1%). For bone tumours, the accuracy was: clinical, 10.9% (5.2-21.8%); ultrasound, 75.0% (46.8-91.1%); MRI, 90.7% (78.4-96.3%); CT, 92.3% (79.7-97.3%); and radiography, 83.3% (71.3-91%), with an overall imaging accuracy of 89.1% (78.2-94.9%). Biopsy accuracy was 90.7% (83-98.5%) overall, 86.4% (74-98%) for soft tissue masses, and 100% (81.5-100%) for bone tumours. Imaging outperforms clinical diagnosis in terms of accuracy and should be mandatory before any interventional procedure. Imaging-guided biopsy is an efficient complementary technique when doubts persist about the nature or potential malignancy of a hand tumour.

Conjunctivitis: A review.

General practitioners (GPs) face the challenge of diagnosing conjunctivitis accurately and confidently. Conjunctivitis and red eye are common presentations that confer diagnostic uncertainty. GPs are pivotal in diagnosing and managing conjunctivitis-like symptoms, making them a critical first port of call for patients. Accurately identifying and treating this common eye infection can help ensure the best possible outcomes. This article presents an overview of conjunctivitis, exploring its causes and how to accurately assess and diagnose. We also discuss how to safely refer patients for investigation and provide appropriate safety netting. Conjunctivitis can be secondary to a range of conditions, commonly viral, bacterial and allergic pathogens. It tends to be a self-limiting disease; however, symptoms might persist for up to three weeks. Accurate clinical diagnosis for conjunctivitis is difficult, and thus it can be useful to send a swab for polymerase chain reaction and culture to confirm thediagnosis.

Synergistic Effect of Aβ42 and Tau Protein in Alzheimer's Disease

Alzheimer's disease (AD) is a neurodegenerative disease that can't be cured at present, which is different from what we call infectious diseases, and is usually related to senile dementia. Although there is no radical cure at present, early diagnosis and intervention can delay the progress of the disease and improve the quality of life of patients. The mechanism of Aβ42 and Tau protein in AD is of great significance for early diagnosis and treatment of diseases. In this paper, the interaction between these two proteins is deeply analyzed, and their role in the pathological development of AD is discussed, and how to use this knowledge to improve the accuracy of clinical diagnosis and develop new treatment strategies.

Enhancing bone scan image quality: an improved self-supervised denoising approach.

Bone scans play an important role in skeletal lesion assessment, but gamma cameras exhibit challenges with low sensitivity and high noise levels. Deep learning (DL) has emerged as a promising solution to enhance image quality without increasing radiation exposure or scan time. However, existing self-supervised denoising methods, such as Noise2Noise (N2N), may introduce deviations from the clinical standard in bone scans. This study proposes an improved self-supervised denoising technique to minimize discrepancies between DL-based denoising and full scan images. 
Retrospective analysis of 351 whole-body bone scan data sets was conducted. In this study, we used N2N and Noise2FullCount (N2F) denoising models, along with an interpolated version of N2N (iN2N). Denoising networks were separately trained for each reduced scan time from 5 to 50%, and also trained for mixed training datasets, which include all shortened scans. We performed quantitative analysis and clinical evaluation by nuclear medicine experts.
The denoising networks effectively generated images resembling full scans, with N2F revealing distinctive patterns for different scan times, N2N producing smooth textures with slight blurring, and iN2N closely mirroring full scan patterns. Quantitative analysis showed that denoising improved with longer input times and mixed count training outperformed fixed count training. Traditional denoising methods lagged behind DL-based denoising. N2N demonstrated limitations in long-scan images. Clinical evaluation favored N2N and iN2N in resolution, noise, blurriness, and findings, showcasing their potential for enhanced diagnostic performance in quarter-time scans.
The improved self-supervised denoising technique presented in this study offers a viable solution to enhance bone scan image quality, minimizing deviations from clinical standards. The method's effectiveness was demonstrated quantitatively and clinically, showing promise for quarter-time scans without compromising diagnostic performance. This approach holds potential for improving bone scan interpretations, aiding in more accurate clinical diagnoses.

Analysis of the Accuracy of Clinical Diagnosis and PA Diagnosis in Appendectomy Patients at AN-NISA Tangerang Hospital Period 2019-2024

Analysis of the Accuracy of Clinical Diagnosis and PA Diagnosis in Appendectomy Patients at AN-NISA Tangerang Hospital Period 2019-2024

Observation of dynamic position and morphological changes of temporomandibular joint discs under Angle's classification

Objective: To observe the dynamic changes of the temporomandibular joint (TMJ) disc in joint movement under different Angle's classification, providing reference for understanding joint functional movement and providing a basis for more accurate clinical imaging diagnosis. Methods: A total of 30 patients (13 males and 17 females) with temporomandibular disorders who were admitted to Beijing Friendship Hospital, Capital Medical University and General Hospital of the People's Liberation Army from January 2022 to April 2024 were enrolled. Thirty adults (13 males and 17 females) with different Angle's classification, with an average age of (34.4±8.5) years, were subjected to dynamic imaging of their TMJ from the closed position to the maximum opening position, and then to the closed position using MRI. The position and morphological changes of the articular discs were observed. Results: The results showed that volunteers with no displacement of the articular disc in class Ⅰ, Ⅱ, and Ⅲ relationships had different shapes of the articular disc during open and closed mouth movements. However, in the maximum opening position, the articular disc were all located directly below the maxillary nodules, and their shape is double concave. In terms of irreversible anterior displacement of the articular disc, in class Ⅰ Angle, the posterior zone of the disc contacts the anterior inclined plane of condyle from the maximum opening position back to the front of the closing position. In class Ⅱ, the posterior zone of the disc contacts the anterior inclined plane of condyle from the beginning of opening position to maximum opening position. In class Ⅲ, the posterior zone of the disc is always in contact with the anterior inclined plane of condyle throughout the entire movement process. And among them, the articular disc presents a forward displacement state at the closing position, its morphology undergoes folding phenomenon. When the openness is 2.5 cm, the articular disc moves up to a certain extent, and is closer to the anterior inclined plane of condyle, and its shape is also partially changed. When the openness is 4.3 cm, the shape of the articular disc, located between the anterior inclined plane of the joint node and the posterior inclined plane of the condyle, is typical double concave, which is sufficient to show that the articular disc is reversible when maximum opening position is reached. In terms of reversible anterior disc displacement, in class Ⅰ Angle, the posterior zone of the disc contact with the anterior inclined plane of condyle at the beginning of the opening position and the end of the closing position. In classⅡ Angle, the posterior zone of the articular disc is not in contact with the anterior inclined plane of condyle. In class Ⅲ Angle, the posterior zone of the articular disc contact with the anterior inclined plane of condyle at the end of the closing position. Conclusions: Multi level dynamic MR imaging data of the temporomandibular joint can dynamically observe the movement of the temporomandibular joint, intuitively and accurately display the position and shape of the articular disc during movement, and can serve as a useful supplement to static conventional MR imaging of the TMJ. The patient's TMJ needs to reach the maximum opening position in order to determine whether the joint disc displacement can be reversible or not.

Improving the diagnostic strategy for thyroid nodules: a combination of artificial intelligence-based computer-aided diagnosis system and shear wave elastography.

Thyroid nodules are highly prevalent in the general population, posing a clinical challenge in accurately distinguishing between benign and malignant cases. This study aimed to investigate the diagnostic performance of different strategies, utilizing a combination of a computer-aided diagnosis system (AmCAD) and shear wave elastography (SWE) imaging, to effectively differentiate benign and malignant thyroid nodules in ultrasonography. A total of 126 thyroid nodules with pathological confirmation were prospectively included in this study. The AmCAD was utilized to analyze the ultrasound imaging characteristics of the nodules, while the SWE was employed to measure their stiffness in both transverse and longitudinal thyroid scans. Twelve diagnostic patterns were formed by combining AmCAD diagnosis and SWE values, including isolation, series, parallel, and integration. The diagnostic performance was assessed using the receiver operating characteristic curve and area under the curve (AUC). Sensitivity, specificity, accuracy, missed malignancy rate, and unnecessary biopsy rate were also determined. Various diagnostic schemes have shown specific advantages in terms of diagnostic performance. Overall, integrating AmCAD with SWE imaging in the transverse scan yielded the most favorable diagnostic performance, achieving an AUC of 72.2% (95% confidence interval (CI): 63.0-81.5%), outperforming other diagnostic schemes. Furthermore, in the subgroup analysis of nodules measuring <2 cm or 2-4 cm, the integrated scheme consistently exhibited promising diagnostic performance, with AUCs of 74.2% (95% CI: 61.9-86.4%) and 77.4% (95% CI: 59.4-95.3%) respectively, surpassing other diagnostic schemes. The integrated scheme also effectively addressed thyroid nodule management by reducing the missed malignancy rate to 9.5% and unnecessary biopsy rate to 22.2%. The integration of AmCAD and SWE imaging in the transverse thyroid scan significantly enhances the diagnostic performance for distinguishing benign and malignant thyroid nodules. This strategy offers clinicians the advantage of obtaining more accurate clinical diagnoses and making well-informed decisions regarding patient management.

Pulmonary microbial spectrum in late-stage SARS-CoV-2 infection: a case series.

Coronavirus disease 2019 (COVID-19), a kind of respiratory disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), primarily spreads through the respiratory tract from human to human. Its extensive and rapid spread has led to a global pandemic, causing great harm to human health and economic development all over the world. Current known evidence indicates that SARS-CoV-2 has evolved accumulating multiple mutations, with altered infectivity and viral replication capacity. A better understanding of the complications of COVID-19 and its relationship with underlying diseases is crucial for the prevention and treatment of SARS-CoV-2. This case series reviewed case data of our 4 recent patients with severe or critical COVID-19, including treatment plan, status of pulmonary infection and their microbiology workup with metagenomic next-generation sequencing with bronchoalveolar lavage fluid. This report shed light on the significance of rapid and accurate clinical diagnosis and treatment on COVID-19.

A Fatal Co-infections of Aspergillus latus and Pneumocystis jirovecii in COVID-19 Pneumonia Patient: Case Report

Introduction: For coronavirus disease 2019 (COVID-19) positive patients, co-infection with fungi has previously been reported. Owing to non-specific clinical manifestations and radiographic evidence, it is difficult to distinguish fungal infection from COVID-19 alone, resulting in delayed diagnosis and lack of appropriate treatment. Aspergillus latus infection, a newly rare species with life-threatening characteristics, requires rapid detection with accurate diagnosis to reduce mortality. However, there is little literature that provides a reference for a better understanding of this rare pathogen and guides medical practitioners in choosing the right diagnostics and therapies. Case Presentation: We reported a 67-year-old female complaining of fever, cough, and chest tightness, who had previously been hospitalized for a week due to initial COVID-19 pneumonia. On admission, clinical manifestations and radiological evidence were consistent with COVID-19 pneumonia, and there was no obvious improvement after anti-infective therapy. In terms of etiology for the patient, Galactomannan test was positive for Aspergillus genus, and Metagenomic next-generation sequencing further determined co-infections of A. latus and Pneumocystis jirovecii. Subsequently, isolation of A. latus was obtained through microbial culture. Despite targeted antifungal therapy, no clinical improvement was observed, possibly due to delayed diagnosis and treatment. Finally, the patient died of respiratory failure. Conclusions: This case report demonstrated that metagenomic next-generation sequencing is a fast, unbiased, culture-free approach that can increase the detection of rare pathogens, helping clinicians improve the accuracy of clinical diagnosis and take therapeutic action as quickly as possible. Clinicians should be aware of the risk of COVID-19-associated pulmonary Aspergillosis in COVID-19 patients, and we hope to optimize diagnosis and improve outcomes of COVID-19-associated pulmonary Aspergillosis.

Real-world outcomes of a dedicated fast-track polymyalgia rheumatica clinic.

To examine the clinical impact of a fast-track PMR clinic to enable early diagnosis and treatment, and to define both patient and disease characteristics in newly diagnosed PMR. Primary care physicians were invited to refer patients with new PMR to our fast-track clinic. Referral criteria included new onset shoulder or pelvic girdle pain and/or stiffness with elevated inflammatory markers in patients over 50 years. All patients were seen within 72 h of referral. Patients with a rheumatology diagnosis of PMR had an ultrasound (US) of their temporal and axillary arteries. 172 patients were referred from primary care over 12 months. 39% of patients referred with suspected PMR had an alternative diagnosis for which PMR regimen glucocorticoids was inappropriate. 55% of the non-PMR diagnoses were other inflammatory rheumatological conditions requiring follow-up. Only 20% of patients referred from primary care already on glucocorticoids were commenced on bone protection. PMR patients were co-morbid with a mean of 2.5 other conditions. 75% of PMR patients experienced a glucocorticoid-related adverse event in the first 12 months of treatment. 16% of patients with new PMR had ultrasound features of subclinical giant cell arteritis. The commencement of glucocorticoid therapy should be deferred until after specialist evaluation to enable an accurate clinical diagnosis. A delay in treatment can only realistically be avoided if GPs have access to a Fast-track PMR clinic. We believe that rheumatologists should consider establishing fast-track PMR clinics and this study provides a strong case for and a template to support this practice innovation.

Diagnostic Enigma in a rare Case of Primary Neuritic Leprosy

Leprosy is one of the most prevalent diseases affecting peripheral nerves. Pure neuritic leprosy accounts for 4-10% of all leprosy cases, with clinical symptoms restricted to the peripheral nerves and no skin abnormalities. Leprosy is diagnosed based on the skin and nerves' typical clinical and histological involvement.The absence of typical dermatological characteristics significantly reduces clinical diagnosis accuracy, necessitating histological confirmation. We presented the case of a 26-year-old male with an 8-year history of growing numbness in his right leg, recurrent ulcers in his right foot, and hand abnormalities. The patient was subsequently identified with pure neural leprosy (PNL), a kind of leprosy that affects peripheral nerves but lacks conventional skin lesions. As a result, in leprosy-endemic countries such as Bangladesh, this kind of leprosy should be extensively explored, especially in patients with no skin abnormalities. Bangladesh J Medicine 2024; 35: 214-217

Information sparsity guided transformer for multi-modal medical image super-resolution

Multi-modal medical image super-resolution (SR) plays a vital role in enhancing the resolution of medical images, providing more detailed visuals that aid in accurate clinical diagnosis. Recently, Transformer-based super-resolution methods have significantly promoted performance improvement in this field due to their capacity to capture global dependencies. They usually process all non-overlapping patches as tokens and densely sample these tokens without screening for calculating attention mechanisms. However, this strategy ignores the spatial sparsity of medical images, resulting in redundant or even detrimental computations on less informative regions. Hence, this paper proposes a novel sparsity-guided medical image SR network, namely SG-SRNet, by exploiting the spatial sparsity characteristics of the medical images. SG-SRNet mainly consists of two components: a sparsity mask (SM) generator for image sparsity estimation, and a sparsity-guided Transformer (SGTrans) for high-resolution image reconstruction. Specially, the SM generator generates a sparsity mask by minimizing our cross-sparsity loss which can respond to the informative positions. SGTrans first screens out the informative patches according to the sparsity mask. Then, SGTrans utilizes the designed cluster-based attention to only calculate attention between information-related tokens. We perform comprehensive experiments on three datasets to show that SG-SRNet brings significant performance enhancements with low computational complexity.

Deep learning-based binary classification of beta-amyloid plaques using 18 F florapronol PET.

This study aimed to investigate a deep learning model to classify amyloid plaque deposition in the brain PET images of patients suspected of Alzheimer's disease. A retrospective study was conducted on patients who were suspected of having a mild cognitive impairment or dementia, and brain amyloid 18 F florapronol PET/computed tomography images were obtained from 2019 to 2022. Brain PET images were visually assessed by two nuclear medicine specialists, who classified them as either positive or negative. Image rotation was applied for data augmentation. The dataset was split into training and testing sets at a ratio of 8 : 2. For the convolutional neural network (CNN) analysis, stratified k-fold ( k = 5) cross-validation was applied using training set. Trained model was evaluated using testing set. A total of 175 patients were included in this study. The average age at the time of PET imaging was 70.4 ± 9.3 years and included 77 men and 98 women (44.0% and 56.0%, respectively). The visual assessment revealed positivity in 62 patients (35.4%) and negativity in 113 patients (64.6%). After stratified k-fold cross-validation, the CNN model showed an average accuracy of 0.917 ± 0.027. The model exhibited an accuracy of 0.914 and an area under the curve of 0.958 in the testing set. These findings affirm the model's high reliability in distinguishing between positive and negative cases. The study verifies the potential of the CNN model to classify amyloid positive and negative cases using brain PET images. This model may serve as a supplementary tool to enhance the accuracy of clinical diagnoses.

Identification of Bipolar Disorder and Schizophrenia Based on Brain CT and Deep Learning Methods.

With the increasing prevalence of mental illness, accurate clinical diagnosis of mental illness is crucial. Compared with MRI, CT has the advantages of wide application, low price, short scanning time, and high patient cooperation. This study aims to construct a deep learning (DL) model based on CT images to make identification of bipolar disorder (BD) and schizophrenia (SZ). A total of 506 patients (BD = 227, SZ = 279) and 179 healthy controls (HC) was collected from January 2022 to May 2023 at two hospitals, and divided into an internal training set and an internal validation set according to a ratio of 4:1. An additional 65 patients (BD = 35, SZ = 30) and 40 HC were recruited from different hospitals, and served as an external test set. All subjects accepted the conventional brain CT examination. The DenseMD model for identify BD and SZ using multiple instance learning was developed and compared with other classical DL models. The results showed that DenseMD performed excellently with an accuracy of 0.745 in the internal validation set, whereas the accuracy of the ResNet-18, ResNeXt-50, and DenseNet-121model was 0.672, 0.664, and 0.679, respectively. For the external test set, DenseMD again outperformed other models with an accuracy of 0.724; however, the accuracy of the ResNet-18, ResNeXt-50, and DenseNet-121model was 0.657, 0.638, and 0.676, respectively. Therefore, the potential of DL models for identification of BD and SZ based on brain CT images was established, and identification ability of the DenseMD model was better than other classical DL models.

Integrated Ultrasound-Enrichment and Machine Learning in Colorimetric Lateral Flow Assay for Accurate and Sensitive Clinical Alzheimer's Biomarker Diagnosis.

The colloidal gold nanoparticle (AuNP)-based colorimetric lateral flow assay (LFA) is one of the most promising analytical tools for point-of-care disease diagnosis. However, the low sensitivity and insufficient accuracy still limit its clinical application. In this work, a machine learning (ML)-optimized colorimetric LFA with ultrasound enrichment is developed to achieve the sensitive and accurate detection of tau proteins for early screening of Alzheimer's disease (AD). The LFA device is integrated with a portable ultrasonic actuator to rapidly enrich microparticles using ultrasound, which is essential for sample pre-enrichment to improve the sensitivity, followed by ML algorithms to classify and predict the enhanced colorimetric signals. The results of the undiluted serum sample testing show that the protocol enables efficient classification and accurate quantification of the AD biomarker tau protein concentration with an average classification accuracy of 98.11% and an average prediction accuracy of 99.99%, achieving a limit of detection (LOD) as sensitive as 10.30pgmL-1. Further point-of-care testing (POCT) of human plasma samples demonstrates the potential use of LFA in clinical trials. Such a reliable lateral flow immunosensor with high precision and superb sensing performance is expected to put LFA in perspective as an AD clinical diagnostic platform.

Brain Evaluation by Dual PET/CT with [18F] FDOPA and [18F] FDG in Differential Diagnosis of Parkinsonian Syndromes.

Parkinsonian syndromes are considered clinicopathological conditions that are challenging to diagnose. Molecular imaging with [18F]-FDOPA and [18F]-FDG contributes to a more accurate clinical diagnosis by evaluating presynaptic dopaminergic pathways and glucose metabolism, respectively. The aim of this study was to correlate diagnoses made from dual PET/CT with the initial clinical diagnoses, as well as during follow-ups in patients with Parkinsonian syndromes. A secondary objective was to describe the imaging findings. Methods: A total of 150 patients with a clinical diagnosis of neurodegenerative Parkinsonism were evaluated using dual PET/CT. Clinically, 82% were diagnosed with PD, while the remaining 18% had an atypical Parkinsonism. Results: Using dual PET/CT, the most frequent diagnosis was PD in 67% of the patients, with the rest being diagnosed with an atypical Parkinsonism. In an agreement analysis between the initial clinical diagnosis and the imaging diagnosis by dual PET/CT, a concordance of 94.1% (n = 95) was observed for PD. In the remaining patients, the clinical diagnosis differed from that suggested by dual PET/CT, with atypical Parkinsonian syndromes being diagnosed as DLB in 40% (n = 4), PSP in 46.7% (n = 7), MSA-C in 75% (n = 6), MSA-P in 70% (n = 7), and CBD in 66.7% (n = 4). A total of 38.66% (n = 58) of patients were followed up (median follow-up of 27 months), with a Kappa coefficient of 0.591 (p < 0.001), suggesting substantial agreement. Conclusions: Dual FDOPA-FDG PET/CT demonstrated moderate agreement with the initial clinical diagnosis of Parkinsonism and moderate to substantial agreement during follow-up. This dual technique, therefore, stands out in differentiating between types of Parkinsonisms.