Advancements in acne detection: application of the CenterNet network in smart dermatology.

Introduction: Acne detection is critical in dermatology, focusing on quality control of acne imagery, precise segmentation, and grading. Traditional research has been limited, typically concentrating on singular aspects of acne detection. Methods: We propose a multi-task acne detection method, employing a CenterNet-based training paradigm to develop an advanced detection system. This system collects acne images via smartphones and features multi-task capabilities for detecting image quality and identifying various acne types. It differentiates between noninflammatory acne, papules, pustules, nodules, and provides detailed delineation for cysts and post-acne scars. Results: The implementation of this multi-task learning-based framework in clinical diagnostics demonstrated an 83% accuracy in lesion categorization, surpassing ResNet18 models by 12%. Furthermore, it achieved a 76% precision in lesion stratification, outperforming dermatologists by 16%. Discussion: Our framework represents a advancement in acne detection, offering a comprehensive tool for classification, localization, counting, and precise segmentation. It not only enhances the accuracy of remote acne lesion identification by doctors but also clarifies grading logic and criteria, facilitating easier grading judgments.

Optimizing skin disease diagnosis: harnessing online community data with contrastive learning and clustering techniques.

Skin diseases pose significant challenges in China. Internet health forums offer a platform for millions of users to discuss skin diseases and share images for early intervention, leaving large amount of valuable dermatology images. However, data quality and annotation challenges limit the potential of these resources for developing diagnostic models. In this study, we proposed a deep-learning model that utilized unannotated dermatology images from diverse online sources. We adopted a contrastive learning approach to learn general representations from unlabeled images and fine-tuned the model on coarsely annotated images from Internet forums. Our model classified 22 common skin diseases. To improve annotation quality, we used a clustering method with a small set of standardized validation images. We tested the model on images collected by 33 experienced dermatologists from 15 tertiary hospitals and achieved a 45.05% top-1 accuracy, outperforming the published baseline model by 3%. Accuracy increased with additional validation images, reaching 49.64% with 50 images per category. Our model also demonstrated transferability to new tasks, such as detecting monkeypox, with a 61.76% top-1 accuracy using only 50 additional images in the training process. We also tested our model on benchmark datasets to show the generalization ability. Our findings highlight the potential of unannotated images from online forums for future dermatology applications and demonstrate the effectiveness of our model for early diagnosis and potential outbreak mitigation.

Deep skin diseases diagnostic system with Dual-channel Image and Extracted Text.

Background: Due to the lower reliability of laboratory tests, skin diseases are more suitable for diagnosis with AI models. There are limited AI dermatology diagnostic models combining images and text; few of these are for Asian populations, and few cover the most common types of diseases. Methods: Leveraging a dataset sourced from Asia comprising over 200,000 images and 220,000 medical records, we explored a deep learning-based system for Dual-channel images and extracted text for the diagnosis of skin diseases model DIET-AI to diagnose 31 skin diseases, which covers the majority of common skin diseases. From 1 September to 1 December 2021, we prospectively collected images from 6,043 cases and medical records from 15 hospitals in seven provinces in China. Then the performance of DIET-AI was compared with that of six doctors of different seniorities in the clinical dataset. Results: The average performance of DIET-AI in 31 diseases was not less than that of all the doctors of different seniorities. By comparing the area under the curve, sensitivity, and specificity, we demonstrate that the DIET-AI model is effective in clinical scenarios. In addition, medical records affect the performance of DIET-AI and physicians to varying degrees. Conclusion: This is the largest dermatological dataset for the Chinese demographic. For the first time, we built a Dual-channel image classification model on a non-cancer dermatitis dataset with both images and medical records and achieved comparable diagnostic performance to senior doctors about common skin diseases. It provides references for exploring the feasibility and performance evaluation of DIET-AI in clinical use afterward.

Multidomain Narrowband Interference Intelligent Suppression Method Based on Cognitive Radio and MIMO in UAV Data Link.

In this paper, a kind of antinarrowband interference intelligent method based on cognitive MIMO (multiple-input multiple-output) airspace, time domain, frequency domain, and code domain is proposed. This method combines perceptual technology, spread spectrum code, MIMO space-time coding, and so on. Through coordinating space, time, frequency, and code element diversity, the narrowband interference in the UAV (unmanned aerial vehicle) monitoring and control link is effectively countered. The input and output model of MIMO monitoring and control link of UAV with natural interference are described. Then, the realization principle of the multidomain antinarrowband interference method based on CR-MIMO is presented, and the corresponding models of receiving and transmitting are also given. Finally, the anti-interference performance of the proposed method is analyzed theoretically and validated through simulation experiments, and the effectiveness of the proposed method is verified.

Artificial Intelligence-Based Spiral CT 3D Reconstruction in Transcatheter Aortic Valve Implantation.

To evaluate the clinical application effect of spiral computed tomography (CT) three-dimensional (3D) reconstruction based on artificial intelligence in transcatheter aortic valve implantation (TAVI), a CT 3D reconstruction model based on deep convolutional neural networks (DCNN) was established in this research, which was compared with the model-based iterative reconstruction (MBIR) and used in clinical practice. Then, 62 patients with aortic stenosis (AS) who underwent TAVI surgery were recruited as the research objects. The accuracy, sensitivity, and specificity of the multislice spiral CT scan (MSCT) and transthoracic echocardiography (TTE) in predicting the type of TAVI surgical valve were compared and analyzed. The results showed that the mean absolute error (MAE) (0.01) and root mean square error (RMSE) (0.086) of the MBIR model were higher than the reconstruction model in this research. The structural similarity (SSIM) (0.831) and peak signal-to noise ratio (PSNR) (32.77 dB) of the MBIR model were lower than the reconstruction model, and the differences were considerable (P < 0.05). Of the valve models selected based on the TTE measurement results, 35 cases were accurately predicted and 27 cases were incorrectly predicted. The accuracy of MSCT was 87.1%, the specificity was 98.84%, and the sensitivity was 92.87%; all of which were significantly higher than TTE (P < 0.05). In summary, compared with the MBIR reconstruction model, the imaging results of the model established in this research were closer to the real image. Compared with TTE, MSCT had higher accuracy, sensitivity, and specificity and can provide more accurate preoperative predictions for patients undergoing TAVI surgery.

Combined model of radiomics, clinical, and imaging features for differentiating focal pneumonia-like lung cancer from pulmonary inflammatory lesions: an exploratory study.

BACKGROUND: Only few studies have focused on differentiating focal pneumonia-like lung cancer (F-PLC) from focal pulmonary inflammatory lesion (F-PIL). This exploratory study aimed to evaluate the clinical value of a combined model incorporating computed tomography (CT)-based radiomics signatures, clinical factors, and CT morphological features for distinguishing F-PLC and F-PIL. METHODS: In total, 396 patients pathologically diagnosed with F-PLC and F-PIL from two medical institutions between January 2015 and May 2021 were retrospectively analyzed. Patients from center 1 were included in the training (n = 242) and internal validation (n = 104) cohorts. Moreover, patients from center 2 were classified under the external validation cohort (n = 50). The clinical and CT morphological characteristics of both groups were compared first. And then, a clinical model incorporating clinical and CT morphological features, a radiomics model reflecting the radiomics signature of lung lesions, and a combined model were developed and validated, respectively. RESULTS: Age, gender, smoking history, respiratory symptoms, air bronchogram, necrosis, and pleural attachment differed significantly between the F-PLC and F-PIL groups (all P < 0.05). For the clinical model, age, necrosis, and pleural attachment were the most effective factors to differentiate F-PIL from F-PLC, with the area under the curves (AUCs) of 0.838, 0.819, and 0.717 in the training and internal and external validation cohorts, respectively. For the radiomics model, five radiomics features were found to be significantly related to the identification of F-PLC and F-PIL (all P < 0.001), with the AUCs of 0.804, 0.877, and 0.734 in the training and internal and external validation cohorts, respectively. For the combined model, five radiomics features, age, necrosis, and pleural attachment were independent predictors for distinguishing between F-PLC and F-PIL, with the AUCs of 0.915, 0.899, and 0.805 in the training and internal and external validation cohorts, respectively. The combined model exhibited a better performance than had the clinical and radiomics models. CONCLUSIONS: The combined model, which incorporates CT-based radiomics signatures, clinical factors, and CT morphological characteristics, is effective in differentiating F-PLC from F-PIL.

Reduced pannexin 1-IL-33 axis function in donor livers increases risk of MRSA infection in liver transplant recipients.

Liver transplantation patients are at increased risk for methicillin-resistant Staphylococcus aureus (MRSA) infection, but the molecular mechanism remains unclear. We found that genetic predisposition to low pannexin 1 (PANX1) expression in donor livers was associated with MRSA infection in human liver transplantation recipients. Using Panx1 and Il-33-knockout mice for liver transplantation models with MRSA tail vein injection, we demonstrated that Panx1 deficiency increased MRSA-induced liver injury and animal death. We found that decreased PANX1 expression in the liver led to reduced release of adenosine triphosphate (ATP) from hepatocytes, which further reduced the activation of P2X2, an ATP-activating P2X receptor. Reduced P2X2 function further decreased the NLRP3-mediated release of interleukin-33 (IL-33), reducing hepatic recruitment of macrophages and neutrophils. Administration of mouse IL-33 to Panx1-/- mice significantly (P = 0.011) ameliorated MRSA infection and animal death. Reduced human hepatic IL-33 protein abundance also associated with increased predisposition to MRSA infection. Our findings reveal that genetic predisposition to reduced PANX1 function increases risk for MRSA infection after liver transplantation by decreasing hepatic host innate immune defense, which can be attenuated by IL-33 treatment.

Deep learning for predicting subtype classification and survival of lung adenocarcinoma on computed tomography.

OBJECTIVES: The subtype classification of lung adenocarcinoma is important for treatment decision. This study aimed to investigate the deep learning and radiomics networks for predicting histologic subtype classification and survival of lung adenocarcinoma diagnosed through computed tomography (CT) images. METHODS: A dataset of 1222 patients with lung adenocarcinoma were retrospectively enrolled from three medical institutions. The anonymised preoperative CT images and pathological labels of atypical adenomatous hyperplasia, adenocarcinoma in situ, minimally invasive adenocarcinoma, invasive adenocarcinoma (IAC) with five predominant components were obtained. These pathological labels were divided into 2-category classification (IAC; non-IAC), 3-category and 8-category. We modeled the classification task of histological subtypes based on modified ResNet-34 deep learning network, radiomics strategies and deep radiomics combined algorithm. Then we established the prognostic models in lung adenocarcinoma patients with survival outcomes. The accuracy (ACC), area under ROC curves (AUCs) and C-index were primarily performed to evaluate the algorithms. RESULTS: This study included a training set (n = 802) and two validation cohorts (internal, n = 196; external, n = 224). The ACC of deep radiomics algorithm in internal validation achieved 0.8776, 0.8061 in the 2-category, 3-category classification, respectively. Even in 8 classifications, the AUC ranged from 0.739 to 0.940 in internal set. Further, we constructed a prognosis model that C-index was 0.892(95% CI: 0.846-0.937) in internal validation set. CONCLUSIONS: The automated deep radiomics based triage system has achieved the great performance in the subtype classification and survival predictability in patients with CT-detected lung adenocarcinoma nodules, providing the clinical guide for treatment strategies.

Development and Validation of a Combined Model for Preoperative Prediction of Lymph Node Metastasis in Peripheral Lung Adenocarcinoma.

BACKGROUND: Based on the "seed and soil" theory proposed by previous studies, we aimed to develop and validate a combined model of machine learning for predicting lymph node metastasis (LNM) in patients with peripheral lung adenocarcinoma (PLADC). METHODS: Radiomics models were developed in a primary cohort of 390 patients (training cohort) with pathologically confirmed PLADC from January 2016 to August 2018. The patients were divided into the LNM (-) and LNM (+) groups. Thereafter, the patients were subdivided according to TNM stages N0, N1, N2, and N3. Radiomic features from unenhanced computed tomography (CT) were extracted. Radiomic signatures of the primary tumor (R1) and adjacent pleura (R2) were built as predictors of LNM. CT morphological features and clinical characteristics were compared between both groups. A combined model incorporating R1, R2, and CT morphological features, and clinical risk factors was developed by multivariate analysis. The combined model's performance was assessed by receiver operating characteristic (ROC) curve. An internal validation cohort containing 166 consecutive patients from September 2018 to November 2019 was also assessed. RESULTS: Thirty-one radiomic features of R1 and R2 were significant predictors of LNM (all P < 0.05). Sex, smoking history, tumor size, density, air bronchogram, spiculation, lobulation, necrosis, pleural effusion, and pleural involvement also differed significantly between the groups (all P < 0.05). R1, R2, tumor size, and spiculation in the combined model were independent risk factors for predicting LNM in patients with PLADC, with area under the ROC curves (AUCs) of 0.897 and 0.883 in the training and validation cohorts, respectively. The combined model identified N0, N1, N2, and N3, with AUCs ranging from 0.691-0.927 in the training cohort and 0.700-0.951 in the validation cohort, respectively, thereby indicating good performance. CONCLUSION: CT phenotypes of the primary tumor and adjacent pleura were significantly associated with LNM. A combined model incorporating radiomic signatures, CT morphological features, and clinical risk factors can assess LNM of patients with PLADC accurately and non-invasively.

Simplified ARCHITECT microfluidic chip through a dual-flip strategy enables stable and versatile tumoroid formation combined with label-free quantitative proteomic analysis.

Recent years, microfluidic three-dimensional (3D) tumor culture technique has made great progress in tumor microenvironment simulation and drug screening. Meanwhile, as their functionality and complexity increase, it is more difficult for current chip models to selectively collect specific-layer cells from tumoroids for further analysis. Moreover, a simplified and robust method for tumoroid formation with highly consistent size and repeatable 3D morphology is relatively ncessary. Here, we report an ARCHITECT (ARtificial CHIp for Tumor Enables Confocal Topography observation) chip, through a dual-flip strategy to implement straightforward tumoroid establishment. This platform guarantees stable batch-to-batch tumoroids formation and allows high resolution confocal imaging. Moreover, an initial cell density as low as 65 cells per chamber is efficient to deliver a tumoroid. With this ARCHITECT chip, different-layer cells of interest could be collected from tumoroid for label-free quantitative (LFQ) proteomic analysis. For application demonstration, we mainly verified this platform for lung carcinoma (A549) tumoroid construction and proteomic analysis at out layer. Our data indicate that the out-layer cells of A549 tumoroid show extensively distinct proteomic expressions compared to two-dimensional cultured A549 cells. The up-regulated proteins are mainly related to tumorigenicity, proliferation and metastasis. And the differentially expressed proteins are mainly relevant to lipid metabolism pathway which is essential to tumor progression and proliferation. This platform provides a simplified yet robust technique to connect microfluidic tumoroid construction and LFQ proteomic analysis. The simplicity of this technique should open the way to numerous applications such as discovering the innovative targets for cancer treatment, and studying the mophological and proteomic heterogeneity of different-layer cells across the tumoroid.

Characteristics of disease progress in patients with coronavirus disease 2019 in Wuhan, China.

Coronavirus disease 2019 (COVID-19) patients were classified into four clinical stages (uncomplicated illness, mild, severe and critical pneumonia) depending on disease severity. We aim to investigate the corresponding clinical, radiological and laboratory characteristics between different clinical stages. A retrospective, single-centre study of 101 confirmed patients with COVID-19 at Renmin Hospital of Wuhan University from 2 January to 28 January 2020 was enrolled; follow-up endpoint was on 8 February 2020. Clinical data were collected and compared during the course of illness. The median age of the 101 patients was 51.0 years and 33.6% were medical staff. Fever (68%), cough (50%) and fatigue (23%) are the most common symptoms. About 26% patients underwent the mechanical ventilation and 98% patients were treated with antibiotics. Thirty-seven per cent patients were cured and 11 died. On admission, the number of patients with uncomplicated illness, mild, severe and critical pneumonia were 2 [2%], 86 [85%], 11 [11%] and 2 [2%]. Forty-four of the 86 mild pneumonia progressed to severe illness within 4 days, with nine patients worsened due to critical pneumonia within 4 days. Two of the 11 severe patients improved to mild condition while three others deteriorated. Significant differences were observed among groups of different clinical stages in numbers of influenced pulmonary segments (6 vs. 12 vs. 17, P < 0.001). A significantly upward trend was witnessed in ground-glass opacities overlapped with striped shadows (33% vs. 42% vs. 55% vs. 80%, P < 0.001), while pure ground-glass opacities gradually decreased as disease progressed (45% vs. 35% vs. 24% vs. 13%, P < 0.001) within 12 days. Lymphocytes, prealbumin and albumin showed a downtrend as disease progressed from mild to severe or critical condition, an uptrend was found in white blood cells, C-reactive protein, neutrophils and lactate dehydrogenase. The proportions of serum amyloid A > 300 mg/l in mild, severe and critical conditions were 18%, 46% and 71%, respectively.

Immunocyte Profiling Using Single-Cell Mass Cytometry Reveals EpCAM+ CD4+ T Cells Abnormal in Colon Cancer.

Colon cancer (CC) is one of the leading causes of cancer related mortality. Research over past decades have profoundly enhanced our understanding of immunotherapy, a major clinical accomplishment, and its potential role toward treating CC. However, studies investigating the expression of these immune checkpoints, such as epithelial cell adhesion molecule (EpCAM), programmed death-1 (PD-1), and programmed death-ligand 1 (PD-L1), by peripheral blood mononuclear cells (PBMCs) is lacking. Here, high-dimensional mass cytometry (CyTOF) is used to investigate immune alterations and promising immunotherapeutic targets expression by PBMCs of CC patients. Results reveal that expression of EpCAM and PD-L1 on CD4+ T cells significantly increased in patients with CC, compared with age- and sex- matching healthy controls and patients with colonic polyps. These differences are also validated in an independent patient cohort using flow cytometry. Further analysis revealed that EpCAM+ CD4+ T cells are PD-L1+ CCR5+ CCR6+. Immunofluorescence staining results demonstrate that the increase of EpCAM+ CD4+ T cells is also observed in tumor tissues, rather than para-cancerous tissues. To ascertain the functional disorders of the identified cell subset, phosphorylated signaling protein levels are assessed using imaging mass cytometry. Increases in pp38 MAPK and pMAPKAPK2 are observable, indicating abnormal activation of pp38 MAPK-pMAPKAPK2 signaling pathway. Results in this study indicate that EpCAM+ CD4+ T cells may play a role in CC development. Detailed knowledge on the functionality of EpCAM+ CD4+ T cells is of high translational relevance.

A simple and rapid colorimetric bacteria detection method based on bacterial inhibition of glucose oxidase-catalyzed reaction.

Rapid and sensitive detection of live bacteria is crucial in the realm of clinical diagnosis, food industry and environmental quality control. A portable, feasible and cost-effective platform which enables rapid and accurate live bacteria detection is still challenging. Herein, we present a Bacterial Inhibition of GOX-catalyzed Reaction (BIGR) method for rapid and broad-spectrum detection of live bacteria, which results in a visible color change without any complex instrumentations. We validated this strategy with five common clinical bacteria, namely Escherichia coli, Staphylococcus aureus, Enterococcus faecalis, Streptococcus mutans and Salmonella pullorum. This method precludes the interference of dead bacteria. Only several microliters of samples and reagents are required in this assay and the overall analysis time is less than 20 min. In a further demonstration, the presented method is successfully applied for detection of ascites samples from infected mice. Our results suggest that this method serves as a rapid and dose-dependent visual detection of pathogens in the clinical and daily life.

Pharmacological Review on Asiatic Acid and Its Derivatives: A Potential Compound.

Natural triterpenes represent a group of pharmacologically active and structurally diverse organic compounds. The focus on these phytochemicals has been enormous in the past few years, worldwide. Asiatic acid (AA), a naturally occurring pentacyclic triterpenoid, is found mainly in the traditional medicinal herb Centella asiatica. Triterpenoid saponins, which are the primary constituents of C. asiatica, are commonly believed to be responsible for their extensive therapeutic actions. Published research work has described the molecular mechanisms underlying the various biological activities of AA and its derivatives, which vary for each chronic disease. However, a compilation of the various pharmacological properties of AA has not yet been done. Herein, we describe in detail the pharmacological properties of AA and its derivatives that inhibit multiple pathways of intracellular signaling molecules and transcription factors that are involved in the various stages of chronic diseases. Furthermore, the pharmacological activities of AA were compared with two natural compounds: curcumin and resveratrol. This review summarizes the research on AA and its derivatives and helps to provide future directions in the area of drug development.

Identification of Centella asiatica's Effective Ingredients for Inducing the Neuronal Differentiation.

Centella asiatica, commonly known as Gotu kola, has been widely used as a traditional herb for decades. Yet, the study on which compounds or compound combinations actually lead to its brain benefits remains scarce. To study the neuroprotection effects of Centella asiatica, neuronal differentiation of PC12 cells was applied. In our pilot study, we isolated 45 Centella asiatica fractions and tested their abilities for inducing neuronal differentiation on PC12 cells. The most effective fraction showed robust induction in neurite outgrowth and neurofilament expression. LC-MS fingerprint analysis of this fraction revealed asiatic acid and madecassic acid as the dominant components. A further investigation on the pure combination of these two compounds indicated that the combination of these two compounds extensively promoted nerve differentiation in vitro. Application of PD98059, a protein MEK inhibitor, attenuated combination-induced neurofilament expression, indicating the combination-induced nerve differentiation through activation of MEK signaling pathway. Our results support the use of combination of asiatic acid and madecassic acid as an effective mean to intervene neurodegenerative diseases in which neurotrophin deficiency is involved.

Primary myoepithelial carcinoma of the larynx: case report and review of the literature.

Myoepithelial carcinoma of the head and neck is a rare malignant tumor and usually arises from the salivary glands. The larynx is an uncommon condition of involvement in myoepithelial carcinoma. Here we describe the forth reported case of myoepithelial carcinoma in the larynx. It affected a 78-year-old male who presented initially with hoarseness and bloody sputum. The patient had suffered from continuing hoarseness and bloody sputum for three months before he consulted an otorhinolaryngologist one month ago. Computed tomography scan showed a polypoid tumor involving the right vocal cords. Biopsy was performed, and the disease was pathologically diagnosed as myoepithelial carcinoma of the larynx by hematoxylin-eosin and immunohistochemical staining. The total follow-up period was eleven months. The repeated laryngoscopy or CT scan revealed no recurring or residual lesion during the post-surgical course.