-
Gastric Cancer : Official Journal of... Mar 2024Patients with gastric atrophy and intestinal metaplasia (IM) were at risk for gastric cancer, necessitating an accurate risk assessment. We aimed to establish and... (Randomized Controlled Trial)
Randomized Controlled Trial
OBJECTIVE
Patients with gastric atrophy and intestinal metaplasia (IM) were at risk for gastric cancer, necessitating an accurate risk assessment. We aimed to establish and validate a diagnostic approach for gastric biopsy specimens using deep learning and OLGA/OLGIM for individual gastric cancer risk classification.
METHODS
In this study, we prospectively enrolled 545 patients suspected of atrophic gastritis during endoscopy from 13 tertiary hospitals between December 22, 2017, to September 25, 2020, with a total of 2725 whole-slide images (WSIs). Patients were randomly divided into a training set (n = 349), an internal validation set (n = 87), and an external validation set (n = 109). Sixty patients from the external validation set were randomly selected and divided into two groups for an observer study, one with the assistance of algorithm results and the other without. We proposed a semi-supervised deep learning algorithm to diagnose and grade IM and atrophy, and we compared it with the assessments of 10 pathologists. The model's performance was evaluated based on the area under the curve (AUC), sensitivity, specificity, and weighted kappa value.
RESULTS
The algorithm, named GasMIL, was established and demonstrated encouraging performance in diagnosing IM (AUC 0.884, 95% CI 0.862-0.902) and atrophy (AUC 0.877, 95% CI 0.855-0.897) in the external test set. In the observer study, GasMIL achieved an 80% sensitivity, 85% specificity, a weighted kappa value of 0.61, and an AUC of 0.953, surpassing the performance of all ten pathologists in diagnosing atrophy. Among the 10 pathologists, GasMIL's AUC ranked second in OLGA (0.729, 95% CI 0.625-0.833) and fifth in OLGIM (0.792, 95% CI 0.688-0.896). With the assistance of GasMIL, pathologists demonstrated improved AUC (p = 0.013), sensitivity (p = 0.014), and weighted kappa (p = 0.016) in diagnosing IM, and improved specificity (p = 0.007) in diagnosing atrophy compared to pathologists working alone.
CONCLUSION
GasMIL shows the best overall performance in diagnosing IM and atrophy when compared to pathologists, significantly enhancing their diagnostic capabilities.
Topics: Humans; Gastritis, Atrophic; Stomach Neoplasms; Deep Learning; Gastroscopy; Biopsy; Risk Factors; Atrophy; Metaplasia
PubMed: 38095766
DOI: 10.1007/s10120-023-01451-9 -
Journal of Neurology Sep 2022Numerous sonographic modalities and parameters have been used to diagnose carpal tunnel syndrome (CTS), with varying accuracy. Our umbrella review aimed to summarize the... (Review)
Review
BACKGROUND
Numerous sonographic modalities and parameters have been used to diagnose carpal tunnel syndrome (CTS), with varying accuracy. Our umbrella review aimed to summarize the evidence from systematic reviews and meta-analyses regarding the use of ultrasound imaging to diagnose CTS.
METHODS
Systematic reviews and meta-analyses meeting the inclusion criteria were searched in PubMed, Embase, Medline, Web of Science, and Cochrane databases from inception to March 2022. Critical appraisal, data extraction, and synthesis were performed in accordance with the criteria for conducting an umbrella review.
RESULTS
Sixteen reviews were included. Three reviews were classified as high quality, one as moderate, four as low, and eight as critically low. The cross-sectional area (CSA) of the median nerve at the carpal tunnel inlet demonstrated the best reliability and diagnostic accuracy among multiple parameters. A cutoff CSA value of 9-10.5 mm gave the highest diagnostic performance in the general population. The degree of CSA enlargement was correlated with CTS severity. Sonoelastography and Doppler ultrasound might provide additional insights into CTS evaluation as median nerve stiffness and vascularity at the wrist were increased in these patients.
CONCLUSIONS
Sonography is a reliable tool to diagnose CTS, with inlet CSA being the most robust parameter. Sonoelastography and Doppler ultrasound can serve as auxiliary tools to confirm CTS diagnoses. Further studies are needed to expand the use of sonography for diagnosing CTS, especially in the presence of concomitant neuromuscular disease(s).
Topics: Carpal Tunnel Syndrome; Humans; Median Nerve; Neural Conduction; Reproducibility of Results; Sensitivity and Specificity; Ultrasonography
PubMed: 35639198
DOI: 10.1007/s00415-022-11201-z -
Journal of Medical Internet Research Jul 2021Diabetic retinopathy (DR), whose standard diagnosis is performed by human experts, has high prevalence and requires a more efficient screening method. Although machine... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
Diabetic retinopathy (DR), whose standard diagnosis is performed by human experts, has high prevalence and requires a more efficient screening method. Although machine learning (ML)-based automated DR diagnosis has gained attention due to recent approval of IDx-DR, performance of this tool has not been examined systematically, and the best ML technique for use in a real-world setting has not been discussed.
OBJECTIVE
The aim of this study was to systematically examine the overall diagnostic accuracy of ML in diagnosing DR of different categories based on color fundus photographs and to determine the state-of-the-art ML approach.
METHODS
Published studies in PubMed and EMBASE were searched from inception to June 2020. Studies were screened for relevant outcomes, publication types, and data sufficiency, and a total of 60 out of 2128 (2.82%) studies were retrieved after study selection. Extraction of data was performed by 2 authors according to PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), and the quality assessment was performed according to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis of diagnostic accuracy was pooled using a bivariate random effects model. The main outcomes included diagnostic accuracy, sensitivity, and specificity of ML in diagnosing DR based on color fundus photographs, as well as the performances of different major types of ML algorithms.
RESULTS
The primary meta-analysis included 60 color fundus photograph studies (445,175 interpretations). Overall, ML demonstrated high accuracy in diagnosing DR of various categories, with a pooled area under the receiver operating characteristic (AUROC) ranging from 0.97 (95% CI 0.96-0.99) to 0.99 (95% CI 0.98-1.00). The performance of ML in detecting more-than-mild DR was robust (sensitivity 0.95; AUROC 0.97), and by subgroup analyses, we observed that robust performance of ML was not limited to benchmark data sets (sensitivity 0.92; AUROC 0.96) but could be generalized to images collected in clinical practice (sensitivity 0.97; AUROC 0.97). Neural network was the most widely used method, and the subgroup analysis revealed a pooled AUROC of 0.98 (95% CI 0.96-0.99) for studies that used neural networks to diagnose more-than-mild DR.
CONCLUSIONS
This meta-analysis demonstrated high diagnostic accuracy of ML algorithms in detecting DR on color fundus photographs, suggesting that state-of-the-art, ML-based DR screening algorithms are likely ready for clinical applications. However, a significant portion of the earlier published studies had methodology flaws, such as the lack of external validation and presence of spectrum bias. The results of these studies should be interpreted with caution.
Topics: Algorithms; Diabetes Mellitus; Diabetic Retinopathy; Diagnostic Techniques, Ophthalmological; Humans; Machine Learning; Neural Networks, Computer
PubMed: 34407500
DOI: 10.2196/23863 -
Computational and Mathematical Methods... 2022Breast cancer incidence has been rising steadily during the past few decades. It is the second leading cause of death in women. If it is diagnosed early, there is a good... (Comparative Study)
Comparative Study
Breast cancer incidence has been rising steadily during the past few decades. It is the second leading cause of death in women. If it is diagnosed early, there is a good possibility of recovery. Mammography is proven to be an excellent screening technique for breast tumor diagnosis, but its detection and classification in mammograms remain a significant challenge. Previous studies' major limitation is an increase in false positive ratio (FPR) and false negative ratio (FNR), as well as a drop in Matthews correlation coefficient (MCC) value. A model that can lower FPR and FNR while increasing MCC value is required. To overcome prior research limitations, a modified network of YOLOv5 is used in this study to detect and classify breast tumors. Our research is conducted using publicly available datasets Curated Breast Imaging Subset of DDSM (CBIS-DDSM). The first step is to perform preprocessing, which includes image enhancing techniques and the removal of pectoral muscles and labels. The dataset is then annotated, augmented, and divided into 60% for training, 30% for validation, and 10% for testing. The experiment is then performed using a batch size of 8, a learning rate of 0.01, a momentum of 0.843, and an epoch value of 300. To evaluate the performance of our proposed model, our proposed model is compared with YOLOv3 and faster RCNN. The results show that our proposed model performs better than YOLOv3 and faster RCNN with 96% mAP, 93.50% MCC value, 96.50% accuracy, 0.04 FPR, and 0.03 FNR value. The results show that our suggested model successfully identifies and classifies breast tumors while also overcoming previous research limitations by lowering the FPR and FNR and boosting the MCC value.
Topics: Breast; Breast Neoplasms; Computational Biology; Databases, Factual; Diagnosis, Computer-Assisted; False Negative Reactions; False Positive Reactions; Female; Humans; Machine Learning; Mammography; Neural Networks, Computer; Radiographic Image Enhancement; Sensitivity and Specificity
PubMed: 35027940
DOI: 10.1155/2022/1359019 -
Chronic Respiratory Disease 2021Asthma is a common, chronic, and heterogeneous disease with a global impact and substantial economic costs. It is also associated with significant mortality and... (Review)
Review
Asthma is a common, chronic, and heterogeneous disease with a global impact and substantial economic costs. It is also associated with significant mortality and morbidity and the burden of undiagnosed asthma is significant. Asthma can be difficult to diagnose as there is no gold standard test and, while spirometry is central in diagnosing asthma, it may not be sufficient to confirm or exclude the diagnosis. The most commonly reported spirometric measures (forced expiratory volume in one second (FEV) and forced vital capacity assess function in the larger airways. However, small airway dysfunction is highly prevalent in asthma and some studies suggest small airway involvement is one of the earliest disease manifestations. Moreover, there are new inhaled therapies with ultrafine particles that are specifically designed to target the small airways. Potentially, tests of small airways may more accurately diagnose early or mild asthma and assess the response to treatment than spirometry. Furthermore, some assessment techniques do not rely on forced ventilatory manoeuvres and may, therefore, be easier for certain groups to perform. This review discusses the current evidence of small airways tests in asthma and future research that may be needed to further assess their utility.
Topics: Asthma; Forced Expiratory Volume; Humans; Respiratory Function Tests; Spirometry; Vital Capacity
PubMed: 34693751
DOI: 10.1177/14799731211053332 -
Neuroscience Mar 2022This study investigates the error processing components in the EEG signal of Performers and Observers using an auditory lexical decision task, in which participants...
This study investigates the error processing components in the EEG signal of Performers and Observers using an auditory lexical decision task, in which participants heard spoken items and decided for each item if it was a real word or not. Pairs of participants were tested in both the role of the Performer and the Observer. In the literature, an Error Related Negativity (ERN)-Error Positivity (Pe) complex has been identified for performed (ERN-Pe) and observed (oERN-oPe) errors. While these effects have been widely studied for performance errors in speeded decision tasks relying on visual input, relatively little is known about the performance monitoring signatures in observed language processing based on auditory input. In the lexical decision task, native Dutch speakers listened to real Dutch Words, Non-Words, and crucially, long Pseudowords that resembled words until the final syllable and were shown to be error-prone in a pilot study, because they were responded to too soon. We hypothesised that the errors in the task would result in a response locked ERN-Pe pattern both for the Performer and for the Observer. Our hypothesis regarding the ERN was not supported, however a Pe-like effect, as well as a P300 were present. Analyses to disentangle lexical and error processing similarly indicated a P300 for errors, and the results furthermore pointed to differences between responses before and after word offset. The findings are interpreted as marking attention during error processing during auditory word recognition.
Topics: Attention; Electroencephalography; Evoked Potentials; Humans; Language; Pilot Projects; Reaction Time
PubMed: 33577954
DOI: 10.1016/j.neuroscience.2021.02.001 -
Medicina Oral, Patologia Oral Y Cirugia... Jul 2023Knowledge of oral mucosal lesions (OMLs) among dentists is relevant in diagnosing potentially malignant diseases and oral cancer at an early stage. The aim of this...
BACKGROUND
Knowledge of oral mucosal lesions (OMLs) among dentists is relevant in diagnosing potentially malignant diseases and oral cancer at an early stage. The aim of this survey was to explore dentists' knowledge about OMLs.
MATERIAL AND METHODS
Respondents to a web-based questionnaire, containing 11 clinical vignettes representing patients with various OMLs, provided a (differential) diagnosis and management for each. Information about demographics and clinical experience of the participants was acquired as well. Descriptive statistics were performed and T-tests were used to test for significant (p<0.05) differences in mean scores for correct diagnosis and management between subgroups based on demographic variables.
RESULTS
Forty-four of 500 invited dentists completed the questionnaire. For (potentially) malignant OMLs, the number of correct diagnoses ranged from 14 to 93%, whilst the number of correct management decisions ranged from 43 to 86%. For benign OMLs, the number of correct diagnoses and management decisions ranged from 32 to 100% and 9 to 48%, respectively. For 11 clinical vignettes, mean scores for correct diagnosis, correct management and correct diagnosis and management were respectively 7.2 (±1.8), 5.7 (±1.5), and 3.8 (±1.7).
CONCLUSIONS
The results show that dentists in the Netherlands do not have sufficient knowledge to accurately diagnose some OMLs and to select a correct management. This may result in over-referral of benign OMLs and under-referral for (potentially) malignant OMLs. Clinical guidelines, that include standardized criteria for referral, and continuing education, may improve dentists' ability to correctly diagnose and accurately manage OMLs.
Topics: Humans; Netherlands; Mouth Neoplasms; Referral and Consultation; Diagnosis, Differential; Dentists; Surveys and Questionnaires
PubMed: 36641742
DOI: 10.4317/medoral.25774 -
Advances in Experimental Medicine and... 2020Lung cancer is the most common cancer among men and the third most common among women in the world. Many diagnostic techniques have been introduced to diagnose lung... (Review)
Review
Lung cancer is the most common cancer among men and the third most common among women in the world. Many diagnostic techniques have been introduced to diagnose lung cancer. Positron emission tomography (PET)/computed tomography (CT) examination is an image diagnostic method that performs automatic detection and distinction of lung lesions. In addition, pathological examination by biopsy is performed for lesions that are suspected of being malignant, and appropriate treatment methods are applied according to the diagnosis results. Currently, lung cancer diagnosis is performed through coordination between respiratory, radiation, and pathological diagnosis experts, but there are some tasks, such as image diagnosis, that require a large amount of time and effort to complete. Therefore, we developed a decision support system using PET/CT and microscopic images at the time of image diagnosis, which leads to appropriate treatment. In this chapter, we introduce the proposed system using deep learning and radiomic techniques.
Topics: Decision Support Systems, Clinical; Deep Learning; Humans; Lung Neoplasms; Positron Emission Tomography Computed Tomography
PubMed: 32030664
DOI: 10.1007/978-3-030-33128-3_5 -
Preferred diagnostic methods of pyriform sinus fistula in different situations: A systematic review.American Journal of Otolaryngology 2023Pyriform sinus fistula (PSF) diagnosis is often easily delayed and incorrect. Diagnostic values of modalities vary in different situations. The aim of this study was to... (Review)
Review
PURPOSE
Pyriform sinus fistula (PSF) diagnosis is often easily delayed and incorrect. Diagnostic values of modalities vary in different situations. The aim of this study was to recommend optimal schemes for diagnosing PSF at different ages and infection stages.
METHODS
A search of PubMed, Embase, Cochrane Library, and CBM databases was conducted to identify articles written in Chinese and English concerning PSF diagnosis using keywords: "pyriform sinus fistula", "diagnosis", and relevant synonymous terms. Quality assessment was performed using the Joanna Briggs Institute (JBI) levels of evidence and critical appraisal checklist tool.
RESULTS
111 studies describing 3692 patients were included. The highest true positive rate (TPR) of ultrasonography was 66.67 % in adult cases. Computed tomography (CT) yielded a good TPR (approximately 73 %) in both neonatal and adult patients, and contrast-enhanced CT (84.21 %) was better in adult patients. Most children cases could be accurately diagnosed by barium swallow (BS) examination which was significantly different in acute and non-infection stages (AIS, NIS). Magnetic resonance imaging (MRI) produced a nice TPR in fetal cases (69.23 %) and neonatal cases (54.44 %). Laryngoscopy was also affected by infection stages. TPR of gastroscopy (GS) was the highest in children (86.36 %) and adult cases (87.50 %).
CONCLUSION
For fetal cases suspected of PSF, an MRI is recommended. MRI or CT is preferred for neonatal cases regardless of infection stages. Children and adult patients are advised to undergo GS during NIS or AIS, while BS is suggested for NIS. Contrast-enhanced CT can also diagnose adults with PSF in AIS.
Topics: Child; Infant, Newborn; Humans; Pyriform Sinus; Tomography, X-Ray Computed; Ultrasonography; Laryngoscopy; Fistula; Retrospective Studies
PubMed: 36584597
DOI: 10.1016/j.amjoto.2022.103747 -
Acta Radiologica (Stockholm, Sweden :... Jan 2023Preoperative identification of intramuscular hemangioma (IMH) subtypes (capillary hemangioma, cavernous hemangioma, and mixed hemangioma) is urgently necessary. Enhanced...
BACKGROUND
Preoperative identification of intramuscular hemangioma (IMH) subtypes (capillary hemangioma, cavernous hemangioma, and mixed hemangioma) is urgently necessary. Enhanced T2*-weighted angiography (ESWAN) is sensitive to vessels and metabolites and can be used to diagnose IMH subtypes.
PURPOSE
To compare the diagnostic performances of ESWAN and conventional magnetic resonance imaging (MRI) for qualitative and quantitative diagnosis of IMH subtypes.
MATERIAL AND METHODS
In total, 23 patients with IMHs were examined using conventional MRI and ESWAN. The signal intensity ratios (SIRs) of conventional MRI and ESWAN were measured.
RESULTS
There was no significant difference for volume among the three subtypes ( = 0.124, = 0.145). Various shapes and MRI signals were shown in the three subtypes of IMH. There was no significant difference for SIRs of conventional MRI ( = 0.558, = 0.259, = 0.385, = 0.347). However, there was a significant difference for SIRs of ESWAN parameters ( = 0.050, < 0.001, = 0.005, = 0.002). Capillary hemangiomas can be diagnosed when R2* SIR is <0.912 and intratumoral susceptibility signal (ITSS) percentage is <29.085%. Cavernous hemangiomas should be considered when R2* SIR is >0.912, ITSS percentage >35.226%, and phase SIR >2.536. In addition, mixed hemangiomas should be considered when T2* SIR is >0.662 and R2* SIR <1.618.
CONCLUSION
Conventional MRI can only display the volume, shape, and signal of IMHs. 3D-MinIP imaging of ESWAN can show the veins and minor hemorrhage. SIRs of ESWAN parameters including T2* value, R2* value, phase value, and percentage of ITSS can be used to quantitatively diagnose capillary hemangiomas, cavernous hemangiomas, and mixed hemangiomas.
Topics: Humans; Magnetic Resonance Imaging; Hemangioma; Angiography; Hemangioma, Cavernous
PubMed: 34918569
DOI: 10.1177/02841851211065145