Detection Of Cancer Research Articles

Harmonizing data across the accelerating colorectal cancer screening and follow-up through implementation science (ACCSIS) program to enhance data quality and promote data sharing

BackgroundThe purpose of the Accelerating Colorectal Cancer Screening and Follow-up through Implementation Science (ACCSIS) Program, a Cancer Moonshot℠ Initiative, is to support research to build the evidence base on multilevel interventions that increase rates of colorectal cancer screening, follow-up, and referral to care to address disparities in colorectal cancer screening. The National Cancer Institute funded eight Research Projects to implement multilevel interventions to improve colorectal cancer screening among communities who traditionally have been medically underserved. To analyze the impact of ACCSIS across Research Projects, the consortium developed a set of common data elements. The purpose of this paper is to describe the process of developing the common data elements to facilitate analysis of ACCSIS data as well as support and inform implementation science research studies.MethodsThe ACCSIS Data, Design, and Analysis Work Group was tasked with designing common data elements through a review of existing data collection instruments, examination of data elements proposed by the ACCSIS Research Projects, and deliberations on the data required to compare across the Research Projects. ACCSIS Consortium members drafted, revised, and finalized a common data elements document consisting of variables to collect and surveys to administer to evaluate ACCSIS implementation activities and outcomes in a standardized manner across the Research Projects.ResultsThe ACCSIS Consortium decided to collect the following categories of common data elements: characteristics across multiple levels of the multicomponent interventions, implementation climate, and determinants; interventions and strategies; implementation outcome constructs and definitions; colorectal cancer screening episodes (screening, diagnostic testing follow-up, cancer detection, and cancer treatment); and cost measures. To assess implementation climate, the consortium prioritized constructs from five domains of the Consolidated Framework for Implementation Research.ConclusionsThe ACCSIS common data elements offer a set of harmonization data for future implementation efforts. The consortium is conducting a systematic assessment using both quantitative and qualitative approaches to assess data quality and approaches to improve and sustain data collection. Lessons learned from these ongoing activities will offer additional insights to tailor the ACCSIS common data elements and support efforts to increase colorectal cancer screening for populations experiencing disparities.

TtAgo-coupled-multiplex-digtal-RPA-CRISPR/Cas12a (TCMDC) for EGFR mutations detection

Epidermal Growth Factor Receptor (EGFR) is an important target for the early evaluation, treatment, and postoperative follow-up in non-small cell lung cancer (NSCLC). Current detection technologies suffer from extended detection time and high rate of false positive amplification. Therefore, the development of rapid, highly sensitive and specific detection methods is of great significance for improving the diagnosis and treatment of lung cancer. In this study, we proposed a fast and sensitive detection method termed Thermus thermophilus Argonaute (Ttago)-Coupled-Multiplex-digital-recombinase polymerase amplification (RPA)-Clustered regularly interspaced short palindromic repeats (CRISPR)/Cas12a (TCMDC) detection method, integrating EGFR mutation template enrichment. Based on the cleavage principle of TtAgo, the wild type (WT) template was enriched under the action of double-guide DNA. Two CRISPR RNAs, not restricted by protospacer adjacent motif (PAM) sites, were introduced to target EGFR genes. By combining RPA with CRISPR-Cas12a, we established a single-pot, ultra-sensitive (1 copy, 0.1 %), and visually detectable method for EGFR detection. We further verified the feasibility of this approach using clinical serum samples from lung cancer patients, achieving rapid (within 1 h) and visual detection of EGFR, thereby presenting a promising clinical tool for the detection of lung cancer.

Enhanced convolutional neural network architecture optimized by improved chameleon swarm algorithm for melanoma detection using dermatological images.

Early detection and treatment of skin cancer are important for patient recovery and survival. Dermoscopy images can help clinicians for timely identification of cancer, but manual diagnosis is time-consuming, costly, and prone to human error. To conduct this, an innovative deep learning-based approach has been proposed for automatic melanoma detection. The proposed method involves preprocessing dermoscopy images to remove artifacts, enhance contrast, and cancel noise, followed by feeding them into an optimized Convolutional Neural Network (CNN). The CNN is trained using an innovative metaheuristic called the Improved Chameleon Swarm Algorithm (CSA) to optimize its performance. The approach has been validated using the SIIM-ISIC Melanoma dataset and the results have been confirmed through rigorous evaluation metrics. Simulation results demonstrate the efficacy of the proposed method in accurately diagnosing melanoma from dermoscopy images by highlighting its potential as a valuable tool for clinicians in early cancer detection.

Advanced Disease Detection and Personalized Medicine: Integrated Data Approaches for Enhanced Parkinson's Disease and Breast Cancer Detection and Treatment in the USA

This present study focuses on integrating data-driven approaches into personalized medicine for better detection and treatment of Parkinson's disease and breast cancer through the US healthcare system. The deeper integration of genomics, clinical records, and patient self-reported data with machine learning algorithms will enhance early disease detection and optimization of treatment pathways. The results show that, more precisely, Random Forest and XGBoost machine learning models hold great promise for considerably improving diagnostic precision and predictive power. This realization opens a door for precision medicine-tailored health services according to the peculiarities of individual patients, which would improve treatment outcomes and encourage preventive healthcare. In addition, this approach aligns with the latest US efforts in precision medicine and contributes to evidence-based transformation in healthcare practice.

Enhanced Magnetic Resonance Imaging-Based Brain Tumor Classification with a Hybrid Swin Transformer and ResNet50V2 Model

Brain tumors can be serious; consequently, rapid and accurate detection is crucial. Nevertheless, a variety of obstacles, such as poor imaging resolution, doubts over the accuracy of data, a lack of diverse tumor classes and stages, and the possibility of misunderstanding, present challenges to achieve an accurate and final diagnosis. Effective brain cancer detection is crucial for patients’ safety and health. Deep learning systems provide the capability to assist radiologists in quickly and accurately detecting diagnoses. This study presents an innovative deep learning approach that utilizes the Swin Transformer. The suggested method entails integrating the Swin Transformer with the pretrained deep learning model Resnet50V2, called (SwT+Resnet50V2). The objective of this modification is to decrease memory utilization, enhance classification accuracy, and reduce training complexity. The self-attention mechanism of the Swin Transformer identifies distant relationships and captures the overall context. Resnet 50V2 improves both accuracy and training speed by extracting adaptive features from the Swin Transformer’s dependencies. We evaluate the proposed framework using two publicly accessible brain magnetic resonance imaging (MRI) datasets, each including two and four distinct classes, respectively. Employing data augmentation and transfer learning techniques enhances model performance, leading to more dependable and cost-effective training. The suggested model achieves an impressive accuracy of 99.9% on the binary-labeled dataset and 96.8% on the four-labeled dataset, outperforming the VGG16, MobileNetV2, Resnet50V2, EfficientNetV2B3, ConvNeXtTiny, and convolutional neural network (CNN) algorithms used for comparison. This demonstrates that the Swin transducer, when combined with Resnet50V2, is capable of accurately diagnosing brain tumors. This method leverages the combination of SwT+Resnet50V2 to create an innovative diagnostic tool. Radiologists have the potential to accelerate and improve the detection of brain tumors, leading to improved patient outcomes and reduced risks.

Non-small cell lung cancer detection through knowledge distillation approach with teaching assistant.

Non-small cell lung cancer (NSCLC) exhibits a comparatively slower rate of metastasis in contrast to small cell lung cancer, contributing to approximately 85% of the global patient population. In this work, leveraging CT scan images, we deploy a knowledge distillation technique within teaching assistant (TA) and student frameworks for NSCLC classification. We employed various deep learning models, CNN, VGG19, ResNet152v2, Swin, CCT, and ViT, and assigned roles as teacher, teaching assistant and student. Evaluation underscores exceptional model performance in performance metrics achieved via cost-sensitive learning and precise hyperparameter (alpha and temperature) fine-tuning, highlighting the model's efficiency in lung cancer tumor prediction and classification. The applied TA (ResNet152) and student (CNN) models achieved 90.99% and 94.53% test accuracies, respectively, with optimal hyperparameters (alpha = 0.7 and temperature = 7). The implementation of the TA framework improves the overall performance of the student model. After obtaining Shapley values, explainable AI is applied with a partition explainer to check each class's contribution, further enhancing the transparency of the implemented deep learning techniques. Finally, a web application designed to make it user-friendly and classify lung types in recently captured images. The execution of the three-stage knowledge distillation technique proved efficient with significantly reduced trainable parameters and training time applicable for memory-constrained edge devices.

Diagnostic performance of artificial intelligence in detecting oral potentially malignant disorders and oral cancer using medical diagnostic imaging: a systematic review and meta-analysis

ObjectiveOral cancer is a widespread global health problem characterised by high mortality rates, wherein early detection is critical for better survival outcomes and quality of life. While visual examination is the primary method for detecting oral cancer, it may not be practical in remote areas. AI algorithms have shown some promise in detecting cancer from medical images, but their effectiveness in oral cancer detection remains Naïve. This systematic review aims to provide an extensive assessment of the existing evidence about the diagnostic accuracy of AI-driven approaches for detecting oral potentially malignant disorders (OPMDs) and oral cancer using medical diagnostic imaging.MethodsAdhering to PRISMA guidelines, the review scrutinised literature from PubMed, Scopus, and IEEE databases, with a specific focus on evaluating the performance of AI architectures across diverse imaging modalities for the detection of these conditions.ResultsThe performance of AI models, measured by sensitivity and specificity, was assessed using a hierarchical summary receiver operating characteristic (SROC) curve, with heterogeneity quantified through I2 statistic. To account for inter-study variability, a random effects model was utilized. We screened 296 articles, included 55 studies for qualitative synthesis, and selected 18 studies for meta-analysis. Studies evaluating the diagnostic efficacy of AI-based methods reveal a high sensitivity of 0.87 and specificity of 0.81. The diagnostic odds ratio (DOR) of 131.63 indicates a high likelihood of accurate diagnosis of oral cancer and OPMDs. The SROC curve (AUC) of 0.9758 indicates the exceptional diagnostic performance of such models. The research showed that deep learning (DL) architectures, especially CNNs (convolutional neural networks), were the best at finding OPMDs and oral cancer. Histopathological images exhibited the greatest sensitivity and specificity in these detections.ConclusionThese findings suggest that AI algorithms have the potential to function as reliable tools for the early diagnosis of OPMDs and oral cancer, offering significant advantages, particularly in resource-constrained settings.Systematic Review Registrationhttps://www.crd.york.ac.uk/, PROSPERO (CRD42023476706).

Mex3a promoter hypomethylation can be utilized to diagnose HBV-associated hepatocellular carcinoma: a randomized controlled trial

BackgroundHepatocellular carcinoma remains a health challenge for humanity. Therefore, there is an urgent need to develop novel biomarkers with high efficiency yet fast ability to meet the requirements of hepatocellular carcinoma treatment.MethodsA total of 229 patients with HBV-associated hepatocellular carcinoma (HCC), 298 patients with chronic hepatitis B (CHB), and 96 healthy controls were retrospectively analyzed. Methylation levels of the Mex3a promoter in peripheral blood mononuclear cells (PBMCs) were measured using MethyLight to obtain clinical and laboratory parameters.ResultsThe Mex3a promoter methylation level in HCC patients (median: 0.289% and interquartile range: 0.126%–0.590%) was significantly lower than that in CHB patients (median: 0.999%, interquartile range: 0.417%–1.268%, and p < 0.001) and healthy people (median: 2.172%, interquartile range: 1.225%–3.098%, and p < 0.001). The Mex3a mRNA levels in HCC patients (median: 12.198 and interquartile range: 3.112–18.996) were significantly higher than those in CHB patients (median: 1.623 and interquartile range: 0.066–6.000, and p < 0.001) and healthy controls (median: 0.329, interquartile range: 0.031–1.547, and p < 0.001). MethyLight data were expressed as a percentage of the methylated reference (PMR) value. The Mex3a PMR value was negatively correlated with the mRNA expression level (Spearman’s R = −0.829 and p < 0.001). The Mex3a PMR value of HCC patients was significantly correlated with age (Spearman’s R = 0.113 and p = 0.044), and the mRNA level was significantly correlated with ALT (Spearman’s R = 0.132 and p = 0.046). The Mex3a promoter methylation levels and mRNA levels were also independent factors in the development of liver cancer. The Mex3a promoter methylation and mRNA levels were better at distinguishing HCC from CHB than AFP [area under the receiver operating characteristic curve (AUC) for predicting HCC vs. CHB: 0.915 vs. 0.715: p < 0.001]. The combined use of AFP and Mex3a methylation levels and mRNA levels further improved the area under the receiver operating characteristic curve.ConclusionThe presence of Mex3a promoter hypomethylation in hepatocellular carcinoma can be used as a non-invasive biomarker for the early detection of liver cancer.

Follow-up on patients with initial negative mpMRI target and systematic biopsy for PI-RADS ≥ 3 lesions - an EAU-YAU study enhancing prostate cancer detection.

To investigate the detection and predictors of prostate cancer (PCA) and clinically significant prostate cancer (csPCA) in patients with positive multiparametric MRI (mpMRI) followed by a negative MRI - guided target biopsy (TB) and systematic biopsy (SB). This retrospective multicenter study included 694 patients from 10 tertiary referral centers with an initial positive mpMRI (PI-RADS ≥ 3) and negative results on both MRI-TB and SB. Patients were classified into three groups based on follow-up: Group 1 (prostate re-biopsy without new mpMRI), Group 2 (standardized second prostate mpMRI and subsequent re-biopsy), and Group 3 (follow-up with mpMRIs and biopsy based on clinical and radiological triggers). The primary outcomes were the detection of any PCA and csPCA during follow up. Study groups were compared according to their probability of PCA and csPCA assessed with the ERSPC-MRI risk calculator. Statistical analysis included Kaplan - Meier analysis, Cox regression, and multivariable analysis for the detection of (cs)PCa. The overall detection of PCA and csPCA was 26.8% and 19.3%, respectively, with varying rates in different PI-RADS groups. Group 3 had the highest 2-year and 5-year PCA-free survival (94 and 84%) and csPCA - free survival (96 and 86%). Multivariable analysis revealed a significantly higher risk of PCA and csPCA in Group 1 and 2 compared to Group 3 (p < 0.01). Clinical and radiological predictors for PCA and csPCA included higher age, prostate volume, PI-RADS score, the presence of atypical small acinar proliferation (ASAP), and a smaller number of TB and SB performed during the initial biopsy. Study limitations, include the retrospective design and reliance on clinical and radiological triggers for follow-up decisions. Patients with positive mpMRI but negative TB and SB results exhibit varying rates of PCA and csPCA depending on the follow up scheme. Tailored follow-up strategies are essential for optimal management in this clinical scenario.

Prospective evaluation of MRI artefacts following breast conserving surgery and sentinel lymph node dissection with the magnetic technique

IntroductionSuperparamagnetic Iron Oxide (SPIO) nanoparticles serve as a promising tracer for sentinel lymph node (SLN) detection in breast cancer. Concerns exist regarding artefacts on postoperative Magnetic Resonance Imaging (MRI), especially following breast conservation (BCS). Materials and methodsIn this prospective observational study, 97 women with DCIS or invasive breast cancer underwent BCS and SLN detection with peritumoral SPIO injection administered up to four weeks before surgery. Postoperatively, patients were followed with MRI and mammograms, and imaging outcomes were evaluated by four, independent breast radiologists, blinded to clinical data, using a predefined, standardized questionnaire. ResultsIn 97 patients included, there was inter-rater discordance in the prevalence of “any artefact” (range: 24.1–74.4 %; weighted average: 32.4 %) and “SPIO specific artefact” (range: 12.0–49.4 %; weighted average: 20.9 %). The median area of “any artefact” was 9.24 cm2 (iqr 4.72, 15.50) and SPIO specific artefact 9.88 (iqr 5.32, 15.5). Likert scores indicated higher difficulty interpreting MRI if artefacts were present (OR: 2.295, 95 % CI 1.028, 5.123; p = 0.043), but this was reduced if intravenous contrast was administered (OR: 0.177, 95 % CI 0.091, 0.342; p < 0.001). Multivariable analysis identified free-hand SPIO administration as a risk factor (OR 8.929, 95 % CI 2.849, 27.778; p < 0.001). All six patients with local recurrence were successfully diagnosed on MRI by all raters. ConclusionThis prospective cohort study suggests that a targeted peritumoral SPIO injection can result in the removal of SPIO during lumpectomy and address the concerns for artefacts on postoperative MRI follow-up, in the selected patients that MRI may be warranted.

Red Cell Distribution Width and the Early Detection of Ovarian Cancer

Ovarian Cancer is a leading cause of mortality and morbidity, lacking clinical manifestations and effective early diagnostic techniques. The majority of cases are diagnosed at later stages; however, asymptomatic screening is currently not recommended due to its low predictive value and invasive nature. Furthermore, the current CA-125 biomarker used to monitor Ovarian Cancer is elevated in other conditions, including endometriosis or pelvic inflammation. Red Cell Distribution Width (RDW) is a parameter measured in a complete blood count, measuring the range of variation in red blood cell size and heterogeneity of red blood cell volume. RDW levels positively correlate with Ovarian Cancer progression, additionally increased in Ovarian Cancer groups compared to benign ovarian tumour groups. RDW possesses high sensitivity in distinguishing between cancerous and benign ovarian tumours, in line with ideal screening method standards. RDW additionally shows potential as a diagnostic biomarker in combination with other blood parameters, such as hemoglobin. The hemoglobin-RDW ratio (HRR) acts as an independent predictor of Ovarian Cancer stage. RDW’s mechanism of action is not fully elucidated but can be associated with iron/folic acid deficiency, ineffective hematopoiesis caused by chronic inflammation, or inflammatory cytokines such as IL-1 and IL-17. High RDW levels additionally possess prognostic value, acting as an indicator of low cumulative overall survival and poor chemotherapy responses in various cancers. Further research is needed on RDW’s mechanism of action and its implication as a marker in female cancers, particularly Ovarian Cancer, to implement effective early screening techniques and reduce fatalities.

Permutation Test for Image-on-Scalar Regression With an Application to Breast Cancer.

Image based screening is now routinely available for early detection of cancer and other diseases. Quantitative analysis for effects of risk factors on digital images is important to extract biological insights for modifiable factors in prevention studies and understand pathways for targets in preventive drugs. However, current approaches are restricted to summary measures within the image with the assumption that all relevant features needed to characterize an image can be identified and appropriately quantified. Motivated by data challenges in breast cancer, we propose a nonparametric statistical framework for risk factor screening that uses the whole mammogram image as outcome. The proposed permutation test allows assessment of whether a set of scalar risk factors is associated with the whole image in the presence of correlated residuals across the spatial domain. We provide extensive simulation studies and illustrate an application to the Joanne Knight Breast Health Cohort using the mammogram imaging data.

Label-free differential chemiluminescent immunosensor based on magnetic nanoparticles CuFe2O4@ABEI-GNPs with dual catalytic sites

BackgroundCancer has become one of the main causes of death globally. The level of tumor markers in serum is correlated with the occurrence of cancer. Carcinoembryonic antigen (CEA) is the most commonly utilized tumor marker for cancer detection. Recently, various analytical technologies have been reported to detect biomarkers. However, developing a simple, sensitive, and noninvasive approach for CEA detection remains challenging in cancer diagnosis. Consequently, there is an urgent need for researchers to carry out innovative approaches for CEA detection. ResultIn this work, copper ferrite nanoparticles (CuFe2O4 NPs) with excellent dispersity and fascinating magnetism have been successfully synthesized. To get CuFe2O4@ABEI-GNPs, ABEI-gold NPs (ABEI-GNPs) were generated on the surface of CuFe2O4 NPs by using N-(4-Aminobutyl)-N-ethylisoluminol (ABEI) as a mild reduction reagent to reduce chloroauric acid tetrahydrate (HAuCl4·4H2O). The CuFe2O4@ABEI-GNPs exhibited a superior chemiluminescence (CL) performance compared with CuFe2O4@ABEI NPs, which was attributed to the synergistic catalysis effects of CuFe2O4 NPs and GNPs. Interestingly, two unique CL emission peaks were observed in the kinetic curve of CuFe2O4@ABEI-GNPs. Furthermore, it was found that the kinetic curve could be regulated by the pH of hydrogen peroxide (H2O2) and a possible CL mechanism was proposed. Owing to the favorable CL properties of CuFe2O4@ABEI-GNPs, a label-free differential immunosensor was fabricated for CEA monitoring using the intensity difference between CL-1 and CL-2. The developed immunosensor exhibited a wide linear range from 0.1 to 5000 pg/mL, and a low detection limit of 0.05 pg/mL. Significance and noveltyThe immunosensor was capable of determining CEA in real samples with simple operation, high accuracy, and good sensitivity. This study introduces a novel approach for developing CL functionalized materials, which have broad application potential in bioassays. The proposed differential method could serve as a novel tool for determining CEA in the diagnosis of clinical cancer.

Spotlight on Mitochondrial Health: A Trailblazing Fluorescent Tool for Cancer Detection and Surgical Guidance.

Mitochondria play a pivotal role in maintaining normal physiological functions. Mitochondrial autophagy, namely, mitophagy, is a selective catabolic disposal of impaired mitochondria through an autophagic mechanism during episodes of mitochondrial harm. This selective removal, e.g., mitophagy, is essential for mitochondrial quality control and is closely related to the pathogenesis of many diseases. The abnormal buildup of defective mitochondria in vivo was used as a target to prevent the development of cancer. The mitochondrial autophagy process of disease-related cells is usually accompanied by a decrease in polarity and pH, and the fluorescence sensing effects caused by these two factors are usually contradictory. Here, we propose a reinventing strategy to develop a dual-channel and dual-responsive fluorescent probe HDTVB that is capable of tracking mitochondrial autophagy by monitoring fluctuations in mitochondrial pH and polarity. Based on the aggregation-induced emission (AIE) moiety and hemicarpine moiety push-pull system with activated near-infrared (NIR) emission and pH-activatable cyclization reaction, HDTVB was able to differentiate tumors from normal sites via polarity- and acidity-triggered structural changes of the probe in the course of mitochondrial autophagy. HDTVB is expected to be applied to clinical diagnosis and tumor excision guided by fluorescence, offering a new route in physiological and biochemical research.

Artificial Intelligence in Lung Cancer Detection: Clinical and Economic Assessment of Retrospective CT Analysis Two Years Post-COVID-19 Pandemic

BACKGROUND: The use of chest computed tomography (CT) scans in Krasnoyarsk Krai, Russia, has increased since 2020, during the COVID-19 pandemic. This period also saw a 5.2% decrease in lung cancer (LC) incidence. The potential for missed LC cases has led to the investigation of new diagnostic methods, including the use of artificial intelligence (AI) for analyzing retrospective data. AIM: The study aimed to evaluate the effectiveness of an AI algorithm in identifying patients at high risk for LC using chest CT data from the COVID-19 pandemic. METHODS: A retrospective analysis was conducted on chest CTs from patients diagnosed with COVID-19 in the Krasnoyarsk region, using scans from November 1, 2020, to February 28, 2021. The AI algorithm "Chest-IRA" was applied to detect pulmonary nodules larger than 100 mm³. Radiologists classified the nodules detected by AI into three categories based on LC probability. The economic assessment of the AI algorithm included salary costs and potential savings from early LC treatment. RESULTS: Out of 10,500 CTs, the AI algorithm found nodules in 484 cases. Of these, 192 were highly likely to have LC, 103 showed no signs, and 60 were inconclusive. 112 patients with high or intermediate risk did not seek treatment. The AI confirmed lung cancer in 100 cases, 28.2% of those detected. Early-stage LC was found in 35% of cases, while 65% were at later stages. AI could save about 25.04 months of radiologist work, costing 2.43 million RUB. Early detection savings are estimated at 10.6 to 12.5 million RUB per 10,500 CTs, with a five-year economic impact of 259.4 to 305.1 million RUB. CONCLUSION: AI has proven effective in identifying pulmonary nodules amidst COVID-19, highlighting its potential to improve early detection and diagnostic accuracy, leading to earlier and more precise treatments.

A deep learning approach for gastroscopic manifestation recognition based on Kyoto Gastritis Score.

The risk of gastric cancer can be predicted by gastroscopic manifestation recognition and the Kyoto Gastritis Score. This study aims to validate the applicability of AI approaches for recognizing gastroscopic manifestations according to the definition of Kyoto Gastritis Score, with the goal of improving early gastric cancer detection and reducing gastric cancer mortality. In this retrospective study, 29013 gastric endoscopy images were collected and carefully annotated into five categories according to the Kyoto Gastritis Score, i.e. atrophy (A), diffuse redness (DR), enlarged folds (H), intestinal metaplasia (IM), and nodularity (N). As a multi-label recognition task, we propose a deep learning approach composed of five GAM-EfficientNet models, each performing a multiple classification to quantify gastroscopic manifestations, i.e. no presentation or the severity score 0-2. This approach was compared with endoscopists of varying years of experience in terms of accuracy, specificity, precision, recall, and F1 score. The approach demonstrated good performance in identifying the five manifestations of the Kyoto Gastritis Score, with an average accuracy, specificity, precision, recall, and F1 score of 78.70%, 91.92%, 80.23%, 78.70%, and 0.78, respectively. The average performance of five experienced endoscopists was 72.63%, 90.00%, 77.68%, 72.63%, and 0.73, while that of five less experienced endoscopists was 66.60%, 87.44%, 70.88%, 66.60%, and 0.66, respectively. The sample t-test indicates that the approach's average accuracy, specificity, precision, recall, and F1 score for identifying the five manifestations were significantly higher than those of less experienced endoscopists, experienced endoscopists, and all endoscopists on average (p < 0.05). Our study demonstrates the potential of deep learning approaches on gastric manifestation recognition over junior, even senior endoscopists. Thus, the deep learning approach holds potential as an auxiliary tool, although prospective validation is still needed to assess its clinical applicability.

Breast cancer in women with previous gestational diabetes: a nationwide register-based cohort study

BackgroundGestational diabetes mellitus (GDM) is a common pregnancy complication characterized by insulin resistance. A link has been suggested between insulin resistance and breast cancer, which is the most common cancer in women. Hence, women with previous GDM may be at increased risk of developing breast cancer, yet, the existing evidence is conflicting. This study explored the association between GDM and incident breast cancer, including age at cancer diagnosis. Additionally, we investigated the potential impact of severity of insulin resistance during pregnancy and of subsequent diabetes development on the breast cancer risk.MethodsWe conducted a nationwide, register-based cohort study including all women giving birth in Denmark from 1997 to 2018. We defined GDM and breast cancer based on ICD-10 codes. Premenopausal and postmenopausal breast cancer was pragmatically defined as age at outcome < 50 years and ≥ 50 years, respectively. A proxy for severity of insulin resistance during pregnancy was based on insulin treatment; subsequent diabetes was defined as presence of ICD-10 codes and/or antidiabetic medication after pregnancy. The statistical analyses included Cox regression, logistic regression and t-test.ResultsOf 708,121 women, 3.4% had GDM. The median follow-up period was 11.9 years (range 0-21.9). The overall breast cancer risk was comparable in women with and without previous GDM (adjusted hazard ratio 0.96 [95% CI 0.83–1.12]). Premenopausal and postmenopausal breast cancer risk also did not differ; however, women with previous GDM had a breast cancer diagnosis at younger age (42.6 vs. 43.5 years, p-value 0.01). All-cause mortality was similar regardless of GDM history. Severity of insulin resistance during pregnancy and subsequent diabetes did not affect breast cancer risk.ConclusionsThis large, population-based cohort study showed no higher risk of incident breast cancer in women with previous GDM compared to women without previous GDM after a median of almost 12 years of follow-up. This was evident irrespective of menopausal state. The breast cancer risk was not influenced by the severity of insulin resistance during pregnancy and by subsequent diabetes development. Regardless of GDM history, attention towards prevention, early detection and treatment of breast cancer should be prioritized.

Capsule endoscopy: clinical insights, challenges, and evolving perspectives in the 21st century

Capsule endoscopy (CE) is widely employed in clinical practice owing to its minimally invasive nature and high diagnostic accuracy. It is the primary modality for evaluating suspected diseases of the small-bowel, as recommended by guidelines from various countries. Advancements in CE technology have introduced various models for evaluating not only the small-bowel but also the colon, esophagus, stomach, and the entire gastrointestinal tract. Moreover, colon CE enables early detection of colorectal polyps and cancers, as well as surveillance of inflammatory bowel disease. Furthermore, innovative developments, such as magnetically controlled CE, offer enhanced maneuverability, particularly in the stomach. Recent reports highlight the growing use of artificial intelligence in CE, with promising potential for reducing physician burden, and clinical implementation is anticipated. Furthermore, novel CE technologies are expected to enable the diagnosis of gastrointestinal diseases through a less invasive approach in the near future. Key questions/aims: Herewith we provide a comprehensive review of the current status and clinical applications of CE while addressing the challenges that remain in its implementation in practice and highlighting the key areas for future research and development.

Assessment of Dental Students' Knowledge and Attitudes About the Epidemiologic and Clinical Characteristics of Oral Cancer: Implications for Other Middle-income Countries.

The stage of detection of head and neck cancer and the time between detection and treatment are critical to prognosis. The importance of the dentist in primary diagnosis and treatment planning has been emphasized. The purpose of this study was to evaluate the knowledge of dental students in the prevention and early diagnosis of oral cancer. A descriptive cross-sectional study was conducted on 199 students from different institutions. A self-administered questionnaire with 34 multiple-choice questions on clinical and epidemiologic knowledge and opinions about oral cancer was used. Descriptive analysis to show means and frequencies and the binomial logistic regression test were used to perform the statistical analysis. The confidence level used was 95%. The results showed that all students in the study had heard of the existence of oral cancer, but only 24.6% knew someone with the disease. The majority reported a lack of information in the population about prevention and self-examination, as well as a lack of information campaigns in institutions. Although the majority perform clinical examinations of the oral mucosa (73.4%) and refer patients with suspicious lesions to specialists, there is low confidence in performing biopsies (73.4%) and gaps in training during graduation (84.4%). The majority have never attended continuing education courses on oral cancer but show interest (97.5%). The study identifies deficiencies in the knowledge and practices of dental students and highlights the need for improved teaching and training to promote oral cancer prevention and early detection. Further research in this area and ongoing assessment of students' skills are suggested.

Cancer incidence following non-neoplastic medical conditions: a prospective population-based cohort study.

Many non-neoplastic diseases have been established to be tumorigenic, and cancers are sometimes misdiagnosed as non-neoplastic diseases. We conducted a comprehensive registry-based study of site-specific cancer diagnosis risk following the diagnosis of any preceding medical condition (PMC) encoded by the International Classification of Diseases (ICD)-10 classification. We analyzed healthcare data and cancer data for a random population-based sample of 2.5 million individuals living in Finland on January 1, 2000. Hazard ratios for each PMC and cancer pair were estimated using piecewise constant hazard regression models. P-values were corrected for multiple testing with the Bonferroni method. Several lifestyle-related PMCs were associated with the risk of cancer diagnosis, exemplified by chronic obstructive pulmonary disease and subsequent lung cancer diagnosis risk (female hazard ratio [HR] = 9.91, 95% confidence interval [CI]: 9.18-19.7, p-adj. < 0.0001; male HR = 5.69, 95% CI: 5.43-5.96, p-adj. < 0.0001). Diagnosis risk of ill-defined cancers appeared to increase following diagnosis of Alzheimer's disease (AD). We identified rare PMCs of potential interest. A considerable proportion of the statistically significant associations were explainable by tobacco smoking and alcohol use. The enrichment of ill-defined cancer diagnoses in persons with AD, together with the overall inverse association between AD and cancer, may reflect underdiagnosis of cancer in this patient population. Our results provide a useful resource for research on the prevention and early detection of cancer.