Exosome Detection for Early Cancer Diagnosis

In situ amplification based on assembly of aptamer sandwiches on nanochannels for ultrasensitive detection of exosomes

Early diagnosis in oral cancer is essential to reduce both morbidity and mortality. This study explores the use of uncertainty estimation in deep learning for early oral cancer diagnosis. We develop a Bayesian deep learning model termed 'Probabilistic HRNet', which utilizes the ensemble MC dropout method on HRNet. Additionally, two oral lesion datasets with distinct distributions are created. We conduct a retrospective study to assess the predictive performance and uncertainty of Probabilistic HRNet across these datasets. Probabilistic HRNet performs optimally on the In-domain test set, achieving an F1 score of 95.3% and an AUC of 96.9% by excluding the top 30% high-uncertainty samples. For evaluations on the Domain-shift test set, the results show an F1 score of 64.9% and an AUC of 80.3%. After excluding 30% of the high-uncertainty samples, these metrics improve to an F1 score of 74.4% and an AUC of 85.6%. Redirecting samples with high uncertainty to experts for subsequent diagnosis significantly decreases the rates of misdiagnosis, which highlights that uncertainty estimation is vital to ensure safe decision making for computer-aided early oral cancer diagnosis.

Early liver cancer diagnosis has clinical significance in treating cancer. Joint detection of multiple biomarkers has been considered as an effective and reliable method for early cancer diagnosis. In this work, a novel biosensor based on microcantilever array was batch-fabricated for multiple liver cancer biomarkers detection with high sensitivity, high accuracy, high throughput, and high specification. A micro-cavity was designed in the free end of the cantilever for local reaction between antibody and antigen, which can dramatically reduce the effect of adsorption-induced stiffness coefficient k variation. Furthermore,the pillar arrays in the micro-cavity were designed for increasing detection upper limit. A linear relationship between the relative frequency shift and the antigen concentration was observed for three liver cancer biomarkers, alpha-fetoprotein (AFP), γ-glutamyltranspeptidase II (GGT-2), and hepatocyte growth factor (HGF). Slight cross-reaction response to different antigens ensures high specificity of the sensor. These features will promote clinical application of the cantilever sensors in early cancer diagnosis.

The key to reducing the mortality of gastric cancer is early detection, early diagnosis, and early treatment of gastric cancer. Early diagnosis of gastric cancer is the key to early detection and diagnosis of gastric cancer. Early diagnosis and treatment of gastric cancer is of great significance for improving the curative effect and reducing mortality of gastric cancer. The purpose of this paper is to study the diagnosis of early gastric cancer based on medical imaging techniques and mathematical modeling. The effect of W-DeepLab network-assisted diagnosis of images under white light was analyzed, and the value of Narrow Band Imaging and Blue Laser Imaging in the diagnosis of early gastric cancer was compared. Because Blue Laser Imaging endoscopy can clearly observe the demarcation line and microvascular morphology; but when using Narrow Band Imaging observation, part of the demarcation line and microvascular morphology is not observed. The results show that Blue Laser Imaging is brighter than Narrow Band Imaging's endoscopic images, and it is easier to observe the microstructure of lesions under endoscopy, so as to accurately determine the nature of lesions.

Two years after SARS-CoV-2 (COVID-19) was declared a global public health emergency, the restoration, at least, to the pre-pandemic level of early diagnostic services for prostate cancer has remained enormously challenging for many health systems, worldwide. This is particularly true of West Africa as the region grapples also with the broader impacts of changing demographics and overly stretched healthcare systems. With the lingering COVID-19 crisis, it is likely that the current trend of late prostate cancer diagnosis in the region will worsen with a concomitant increase in the burden of the disease. There is, therefore, a compelling need for innovative and evidence-based solutions to de-escalate the current situation and forestall the collapse of existing structures supporting early prostate cancer diagnosis in the region. In this viewpoint, we make a case for the operationalization of the World Health Organization (WHO) guide to early cancer diagnosis to strengthen the capacity for early prostate cancer diagnosis in West Africa using a realist approach, drawing on participatory health research and evidence-based co-creation. Ultimately, we demonstrate the potential for developing COVID-19 responsive and context-specific models to optimize patient navigation/journey along the essential steps of the World Health Organization guide to early cancer diagnosis.

Early cancer diagnosis from bisulfite-treated cell-free DNA (cfDNA) fragments requires tedious data analytical procedures. Here, we present a deep-learning-based approach for early cancer interception and diagnosis (DECIDIA) that can achieve accurate cancer diagnosis exclusively from bisulfite-treated cfDNA sequencing fragments. DECIDIA relies on transformer-based representation learning of DNA fragments and weakly supervised multiple-instance learning for classification. We systematically evaluate the performance of DECIDIA for cancer diagnosis and cancer type prediction on a curated dataset of 5389 samples that consist of colorectal cancer (CRC; n = 1574), hepatocellular cell carcinoma (HCC; n = 1181), lung cancer (n = 654), and non-cancer control (n = 1980). DECIDIA achieved an area under the receiver operating curve (AUROC) of 0.980 (95% CI, 0.976-0.984) in 10-fold cross-validation settings on the CRC dataset by differentiating cancer patients from cancer-free controls, outperforming benchmarked methods that are based on methylation intensities. Noticeably, DECIDIA achieved an AUROC of 0.910 (95% CI, 0.896-0.924) on the externally independent HCC testing set in distinguishing HCC patients from cancer-free controls, although there was no HCC data used in model development. In the settings of cancer-type classification, we observed that DECIDIA achieved a micro-average AUROC of 0.963 (95% CI, 0.960-0.966) and an overall accuracy of 82.8% (95% CI, 81.8-83.9). In addition, we distilled four sequence signatures from the raw sequencing reads that exhibited differential patterns in cancer versus control and among different cancer types. Our approach represents a new paradigm towards eliminating the tedious data analytical procedures for liquid biopsy that uses bisulfite-treated cfDNA methylome.

Abstract. Early diagnosis and treatment are vital to improving lung cancer patients’ quality of life and survival rate. This study aimed to investigate the value of dynamic enhanced scanning examination by computed tomography (CT) in early lung cancer diagnosis. One hundred and twenty patients with isolated lung nodules were selected to analyze this diagnostic method, using pathological diagnostic results of cancer as the gold standard. Of the 120 pa-tients with isolated pulmonary nodules, the diagnosis was confirmed by patho-logical examination in 96 patients with early lung cancer (adenocarcinoma of the lung) and 24 patients with benign lung lesions. The sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of CT dynamic enhancement scans for the diagnosis of early-stage lung cancer were 93.75%, 83.33%, 91.67%, 95.74%, and 76.92%, respectively. Early-stage lung cancer had significantly less blood volume and a noticeably shorter mean time to passage than benign lung lesions (p<0.01). Blood flow and surface permeability were higher in early-stage lung cancer than in benign lung lesions (p<0.05). The ar-eas under the receiver operating characteristic (ROC) curves for blood volume, blood flow, surface permeability, and mean time to passage for the diagnosis of early-stage lung cancer were 0.737, 0.724, 0.779, and 0.946, respectively. In conclusion, CT dynamic enhancement scan has good application value in diag-nosing early lung cancer and is worth promoting in clinical practice.

According to recent studies, breast cancer is the most common cancer among women, and its prevalence is steadily increasing. An early diagnosis and treatment of this condition can greatly increase the chances of a cure. Further, Long-term mortality rates from breast cancer dramatically lowered by early cancer identification. Finding cancer cells in their early stages is the most important step for the best prognosis. Researchers have examined a variety of breast diagnostic techniques, including mammography, ultrasound, positron emission tomography, and biopsy. These methods have some drawbacks, though, such the fact that they are expensive, time-consuming, and unsuitable for young women. Therefore, it is vital to create a quick and sensitive early-stage breast cancer diagnosis tool. Recently, the rapid advancement of nanotechnology has increased research on nanoparticles, especially those that can be applied to the medical field. Gold nanoparticles (AuNPs) are continuously being studied and used as tools for further research resulting in ever-expanding knowledge that constantly challenges the frontiers of nanotechnology. An increasing interest is being manifested in the use of AuNPs to treat cancer, from diagnosis and monitoring through to treatment. Cancer is a multifactorial disease that requires multifaceted treatments, so these efforts aim to revolutionize current methods of treating it. In this review, the current applications of AuNPs in early breast cancer diagnosis and the importance of biosensors in predicting early cancer occurrence are discussed.

BackgroundArtificial intelligence (AI) has shown great promise in the field of healthcare as a means of improving the diagnosis of skin cancer. The objective of this research is to enhance the precision and effectiveness of skin cancer identification by the incorporation of convolutional neural networks (CNNs) and discrete wavelet transformation (DWT). Making use of AI-driven techniques has the potential to completely transform the diagnosis process by providing quicker and more accurate evaluations of skin lesions. In an effort to improve dermatology and give physicians reliable resources for early and precise skin cancer diagnosis, this work explores the combination of CNNs with DWT.MethodsThe accurate and timely classification of skin cancer lesions plays a crucial role in early diagnosis and effective treatment. In this, we propose a novel approach for skin cancer classification using discrete wavelet transformation (DWT). The DWT is employed to extract relevant features from skin lesion images, which are then used to train a classification model. The effectiveness of the suggested approach is assessed through the examination of a dataset of skin lesion images with known classes (malignant or benign).ResultsThe outcomes of the experiment demonstrate that the suggested model successfully attained a classification result of sensitivity as 94% and specificity as 91% when compared with artificial neural network (ANN) and multilayer perceptron methods.ConclusionsThe HAM 10000 dataset is employed to explore and evaluate the effectiveness of the proposed model, leading to improved accuracy compared to the existing machine learning algorithms in utilization. The results demonstrate the effectiveness of the DWT-based approach in accurately classifying skin cancer lesions, thus aiding in early detection and diagnosis.

BackgroundAn increase in the prevalence of lung cancer that is not smoking-related has been noticed in recent years. Unfortunately, these patients are not included in low dose computer tomography (LDCT) screening programs and are not actually considered in early diagnosis. Therefore, improved early diagnosis methods are urgently needed for non-smokers. It is necessary to establish a prediction model for non-smoking individuals at intermediate to high risk of developing lung cancer (LC) and develop a tool to address the significant gap in evaluating pulmonary nodules in non-smokers.MethodsWe retrospectively investigated 1121 patients with pulmonary nodules, who underwent LDCT examinations between September 2019 and March 2023. Five artificial intelligence (AI) algorithms were used to build two kinds of models and identify which one was better at diagnosing non-smoking pulmonary nodules patients. In the first model, we assigned 554 non-smoking individuals to a training cohort and 150 non-smoking patients to an independent validation cohort. The second model included 971 patients for the training set and 150 non-smoking patients for an independent validation set. All LDCT images of participants were obtained for AI analysis. AI of LDCT scans, liquid biopsy, and clinical characteristics were collected for model building.ResultsAmong LC patients, 58,4% were non-smokers. Non-smoking patients had a high incidence of LC (71.4%), and women showed a significant excess risk compared with non-smoking men in terms of LC risk. Furthermore, our results indicated that the model built using random forest (RF) method, which integrates clinical characteristics (age, extra-thoracic cancer history, gender), radiological characteristics of pulmonary nodules (nodule diameter, nodule count, upper lobe location, malignant sign at the nodule edge, subsolid status), the artificial intelligence analysis of LDCT data, and liquid biopsy achieved the best diagnostic performance in the independent external non-smokers validation cohort (sensitivity 92%, specificity 97%, area under the curve [AUC] = 0.99).ConclusionsThese results could significantly improve early non-smoker LC diagnosis and treatment for non-smoker patients with malignant nodules. The established multi-omics model is a noninvasive prediction tool for non-smoking malignant pulmonary nodule diagnosis. Validation revealed that these models exhibited excellent discrimination and calibration capacities, especially the first model built using the RF method, suggesting their clinical utility in the early screening and diagnosis of non-smoking LC.

Since 2019, invasive cancer diagnoses in people younger than 50 years old have increased by 12.8%, which impacts people of childbearing age. Currently, family interventions for parents with cancer primarily focus on the impacted parent communicating the initial cancer diagnosis or at end-of-life messages with their dependents through in-person interventions. Limited web-based interventions have been developed to increase communication across all family members (e.g., parents with cancer with co-parents or children with their parents) about communicating the impact of cancer on the individual's and family's well-being across the cancer trajectory, a key gap to improved outcomes in this population. This scoping review aimed to comprehensively summarize family communication interventions designed for a parent with cancer who has dependents and to identify and analyze any knowledge gaps regarding family communication interventions in this population. A comprehensive informationist-assisted search was completed in seven databases. Two reviewers independently performed title/abstract reviews and full-text reviews within the Rayyan software system. Two reviewers performed data extraction. Thirty-five articles were included, and 24 different interventions were investigated. Most articles were published by European teams (45%). Fourteen articles (40%) evaluated interventions that included the entire family, seven (20%) reported family theories, and three (9%) used a web-based delivery. Most articles focused on the outcomes of the parent with cancer and the outcomes of their dependents (31%). Most interventions aimed to increase parent communication with dependents at end-of-life (43%) or at early diagnosis (32%) in the breast cancer population. In-person communication interventions have been developed to communicate with dependents about an early or terminal cancer diagnosis. The impact of the intervention on parents with cancer and their children's outcomes were also investigated. No web-based interventions have been published that focus on the entire family, include family-level outcomes, or completed dyadic analysis across the family on the family-level outcomes to determine relationships. Web-based interventions are needed to address communication challenges for all family members affected by a cancer diagnosis, and equitable access to such interventions should be supported.

Optimization and normalization strategies for long term untargeted HILIC-LC-qTOF-MS based metabolomics analysis: Early diagnosis of breast cancer

e13557 Background: As one of the most frequent malignant tumors in China, the morbidity and mortality of lung cancer remain high. Early diagnosis and normative treatment is the key to improve the prognosis of lung cancer. The aim of this study is to explore the practice of early lung cancer screening with low-dose spiral computed tomography (CT) based on the current situation in community health service, with integration of superior resources of medical institutions at all levels in Jiaxing City from Zhejiang Province. Methods: From Jan. 2017 to Dec. 2019, we screened 13491 (male 8783, female 4708) individuals high-risk population in selected communities of Nanhu District, Pinghu County and Haiyan County, Zhejiang Province, for early diagnosis of lung cancer with low-dose spiral CT combined with multidisciplinary comprehensive treatment models including minimally invasive surgery, exploring the medical service network covering prevention, diagnosis, treatment, rehabilitation and follow-up. Results: Screening resulted in a diagnosis of cancer in 27 participants. Of these participants, 24 cases of primary lung cancer, 1 case of lung metastasis, 1 case of breast cancer, 1 case of thyroid cancer. The morbidity of primary lung cancer is 224.53×10-5. There were 20 cases of Stage 0-Ⅰlung cancer accounting for 83.33% of all diagnosed primary lung cancer. Conclusions: Based on community health service, screening with LDCT could improve the early diagnosis rate of lung cancer in both smokers and nonsmokers with feasibility and validity, which could be applicable in qualified eligible medical centers and communities in China. It is not reasonable to exclude nonsmokers from screening with LDCT.

The primary site of cancer in Turkish women is breast cancer. The incidence of breast cancer is increasing in Turkey. The aim of the research was to educate women 40 years and older to increase their awareness on early detection and diagnosis, to facilitate the use of the early diagnosis methods, to improve the women's beliefs in relation breast cancer, and to increase the use of Cancer Early Diagnosis and Screening Centers available in the city. The target population of the research was 5000 women. Forty selected women were educated as peer educators. Twenty-five of them were selected as principal peer educator. Each peer educator was expected to educate 200 women. Peer trainers educated their peer and also arranged for the mammography appointment of the women who decided to have theirs taken. Data were obtained before and after the training by Champion's Health Belief Model Scale, questionnaire forms, and Cancer Early Diagnosis and Screening Centers data for mammography practice. Breast cancer was detected in 8 women. Statistical analyses showed positive changes in women's health beliefs and breast self-examination knowledge. There were 20.4% of women (n = 1040) who did get mammograms, and 8% (n = 8) of women were found to have cancer in all of those screened. Peer education was found to be effective for increasing the knowledge, beliefs, and practice of women related to breast cancer. Peers can reinforce learning through ongoing contact. Peer education can be used to improve early diagnosis of breast cancer and breast cancer awareness in asymptomatic women.

Mitochondria and lysosomes are pivotal intracellular organelles, and the injury or dysfunction of these organelles can trigger a range of pathological processes. Early diagnosis and treatment of cancer are of paramount importance due to cancer's status as a leading health threat. This study introduces a novel fluorescent probe, BDHV, for detecting mitochondrial and lysosomal viscosity and pH abnormalities in tumors, facilitating early cancer detection and screening of anticancer drugs. Under acidic conditions, the red fluorescence of the probe gradually increases with increasing viscosity. Conversely, in alkaline environments, an increase in viscosity leads to a decrease in green fluorescence and an increase in red fluorescence. The inclusion of a benzothiazole group endows BDHV with strong dual-targeting capability for mitochondria and lysosomes and without being affected by the mitochondrial membrane potential. Most notably, BDHV has potential applications for early cancer diagnosis and in effectively assessing the efficacy of various anticancer drugs.