-
Scientific Reports Jul 2022Computed tomography (CT) has been widely used to diagnose Graves' orbitopathy, and the utility is gradually increasing. To develop a neural network (NN)-based method for...
Computed tomography (CT) has been widely used to diagnose Graves' orbitopathy, and the utility is gradually increasing. To develop a neural network (NN)-based method for diagnosis and severity assessment of Graves' orbitopathy (GO) using orbital CT, a specific type of NN optimized for diagnosing GO was developed and trained using 288 orbital CT scans obtained from patients with mild and moderate-to-severe GO and normal controls. The developed NN was compared with three conventional NNs [GoogleNet Inception v1 (GoogLeNet), 50-layer Deep Residual Learning (ResNet-50), and 16-layer Very Deep Convolutional Network from Visual Geometry group (VGG-16)]. The diagnostic performance was also compared with that of three oculoplastic specialists. The developed NN had an area under receiver operating curve (AUC) of 0.979 for diagnosing patients with moderate-to-severe GO. Receiver operating curve (ROC) analysis yielded AUCs of 0.827 for GoogLeNet, 0.611 for ResNet-50, 0.540 for VGG-16, and 0.975 for the oculoplastic specialists for diagnosing moderate-to-severe GO. For the diagnosis of mild GO, the developed NN yielded an AUC of 0.895, which is better than the performances of the other NNs and oculoplastic specialists. This study may contribute to NN-based interpretation of orbital CTs for diagnosing various orbital diseases.
Topics: Graves Ophthalmopathy; Humans; Neural Networks, Computer; Tomography, X-Ray Computed
PubMed: 35840769
DOI: 10.1038/s41598-022-16217-z -
Journal of Lower Genital Tract Disease Apr 2023Reproducibility of cervical biopsy diagnoses is low and may vary based on where the diagnostic test is performed and by whom. Our objective was to measure multilevel...
OBJECTIVES
Reproducibility of cervical biopsy diagnoses is low and may vary based on where the diagnostic test is performed and by whom. Our objective was to measure multilevel variation in diagnoses across colposcopists, pathologists, and laboratory facilities.
METHODS
We cross-sectionally examined variation in cervical biopsy diagnoses within the 5 sites of the Population-Based Research Optimizing Screening through Personalized Regimens (PROSPR I) consortium within levels defined by colposcopists, pathologists, and laboratory facilities. Patients aged 18 to 65 years with a colposcopy with biopsy performed were included, with diagnoses categorized as normal, cervical intraepithelial neoplasia grade 1 (CIN1), grade 2 (CIN2), and grade 3 (CIN3). Using Markov Chain Monte-Carlo methods, we fit mixed-effects logistic regression models for biopsy diagnoses and presented median odds ratios (MORs), which reflect the variability within each level. Median odds ratios can be interpreted as the average increased odds a patient would have for a given outcome (e.g., CIN2 or CIN3 vs normal or CIN1) when switching to a provider with higher odds of diagnosing that outcome. The MOR is always 1 or greater, and a value of 1 indicates no variation in outcome for that level, with higher values indicating greater variation.
RESULTS
A total of 130,110 patients were included who received care across 82 laboratory facilities, 2,620 colposcopists, and 489 pathologists. Substantial variation in biopsy diagnoses was found at each level, with the most occurring between laboratory facilities, followed by pathologists and colposcopists. Substantial variation in biopsy diagnoses of CIN2 or CIN3 (vs normal or CIN1) was present between laboratory facilities (MOR: 1.26; 95% credible interval = 1.19-1.36).
CONCLUSIONS
Improving consistency in cervical biopsy diagnoses is needed to reduce underdiagnosis, overdiagnosis, and unnecessary treatment resulting from variation in cervical biopsy diagnoses.
Topics: Female; Pregnancy; Humans; Uterine Cervical Neoplasms; Reproducibility of Results; Uterine Cervical Dysplasia; Biopsy; Colposcopy; Papillomavirus Infections
PubMed: 36728078
DOI: 10.1097/LGT.0000000000000721 -
BMC Medical Informatics and Decision... Sep 2023One of the most common sleep disorders is sleep apnea syndrome. To diagnose sleep apnea syndrome, polysomnography is typically used, but it has limitations in terms of...
BACKGROUND
One of the most common sleep disorders is sleep apnea syndrome. To diagnose sleep apnea syndrome, polysomnography is typically used, but it has limitations in terms of labor, cost, and time. Therefore, studies have been conducted to develop automated detection algorithms using limited biological signals that can be more easily diagnosed. However, the lack of information from limited signals can result in uncertainty from artificial intelligence judgments. Therefore, we performed selective prediction by using estimated respiratory signals from electrocardiogram and oxygen saturation signals based on confidence scores to classify only those sleep apnea occurrence samples with high confidence. In addition, for samples with high uncertainty, this algorithm rejected them, providing a second opinion to the clinician.
METHOD
Our developed model utilized polysomnography data from 994 subjects obtained from Massachusetts General Hospital. We performed feature extraction from the latent vector using the autoencoder. Then, one dimensional convolutional neural network-long short-term memory (1D CNN-LSTM) was designed and trained to measure confidence scores for input, with an additional selection function. We set a confidence score threshold called the target coverage and performed optimization only on samples with confidence scores higher than the target coverage. As a result, we demonstrated that the empirical coverage trained in the model converged to the target coverage.
RESULT
To confirm whether the model has been optimized according to the objectives, the coverage violation was used to measure the difference between the target coverage and the empirical coverage. As a result, the value of coverage violation was found to be an average of 0.067. Based on the model, we evaluated the classification performance of sleep apnea and confirmed that it achieved 90.26% accuracy, 91.29% sensitivity, and 89.21% specificity. This represents an improvement of approximately 7.03% in all metrics compared to the performance achieved without using a selective prediction.
CONCLUSION
This algorithm based on selective prediction utilizes confidence measurement method to minimize the problem caused by limited biological information. Based on this approach, this algorithm is applicable to wearable devices despite low signal quality and can be used as a simple detection method that determine the need for polysomnography or complement it.
Topics: Humans; Artificial Intelligence; Algorithms; Benchmarking; Electrocardiography; Sleep Apnea Syndromes
PubMed: 37735681
DOI: 10.1186/s12911-023-02292-3 -
The Tohoku Journal of Experimental... Dec 2022Imaging features of the lung in postmortem computed tomography (CT) scans have been reported in drowning cases. However, it is difficult for forensic pathologists with...
Imaging features of the lung in postmortem computed tomography (CT) scans have been reported in drowning cases. However, it is difficult for forensic pathologists with limited experience to distinguish subtle differences in CT images. In this study, artificial intelligence (AI) with deep learning capability was used to diagnose drowning in postmortem CT images, and its performance was evaluated. The samples consisted of high-resolution CT images of the chest of 153 drowned and 160 non-drowned bodies captured by an 8- or 64-row multislice CT system. The images were captured with an image slice thickness of 1.0 mm and spacing of 30 mm, and 28 images were typically captured. A modified AlexNet was used as the AI architecture. The output result was the drowning probability for each component image. To evaluate the performance of the proposed model, the area under the receiver operating characteristic curve (AUC) was analyzed, and the AUC value of 0.95 was obtained. This indicates that the proposed AI architecture is a useful and powerful complementary testing approach for diagnosing drowning in postmortem CT images. Notably, the accuracy was 81% (62/77) for cases in which resuscitation was performed, and 92% (216/236) for cases in which resuscitation was not attempted. Therefore, the proposed AI method should not be used to diagnose the cause of death when aggressive cardiopulmonary resuscitation was performed. Additionally, because honeycomb lungs are likely to exhibit different morphologies, emphysema cases should also be treated with caution when the proposed AI method is used to diagnose drowning.
Topics: Humans; Drowning; Artificial Intelligence; Tomography, X-Ray Computed; Lung; ROC Curve
PubMed: 36384859
DOI: 10.1620/tjem.2022.J097 -
The Journal of Evidence-based Dental... Mar 2023This review analyses the diagnostic performance of cone-beam computed tomography (CBCT) for the in vivo/in vitro detection of external root resorption (ERR) and... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
This review analyses the diagnostic performance of cone-beam computed tomography (CBCT) for the in vivo/in vitro detection of external root resorption (ERR) and critically analyses current and past methods of measuring or classifying ERR in vivo/in vitro in terms of radiation doses and cumulative radiation risks.
METHODS
A diagnostic test accuracy (DTA) protocol was used for a systematic review of diagnostic methods following PRISMA guidelines. The protocol was registered with PROSPERO (ID: CRD42019120513). A thorough and exhaustive electronic search of 6 core electronic databases was performed, applying the ISSG Search Filter Resource. The eligibility criteria were designed [problem-intervention-comparison-outcomes (PICO) statement: Population, Index test, Comparator, Outcome] and methodological quality was assessed by QUADAS-2.
RESULTS
Seventeen papers were selected from a total of 7841 articles. Six in vivo studies were assessed as having a low risk of bias. The overall sensitivity and specificity of CBCT for diagnosis of ERR was 78.12% and 79.25%, respectively. The highest and lowest sensitivity and specificity of CBCT for diagnosis of external root resorption are 42%-98% and 49.3%-96.3%.
DISCUSSION
Most of the selected studies reported quantitative diagnoses with single linear measurements of ERR even though multislice radiographs were available. The cumulative radiation dose (μS) to radiation-sensitive structures, such as the bone marrow, brain and thyroid, was observed to increase using the 3-dimensional (3D) radiography methods reported.
CONCLUSIONS
The highest and lowest sensitivity and specificity of CBCT for diagnosis of external root resorption are 42%-98% and 49.3%-96.3%. The minimum and maximum effective doses of dental CBCT for external root resorption diagnosis are 34 μSv and 1073 μSv.
Topics: Humans; Root Resorption; Cone-Beam Computed Tomography; Sensitivity and Specificity
PubMed: 36914301
DOI: 10.1016/j.jebdp.2022.101803 -
Australian Journal of General Practice Jun 2024General practitioners manage a significant proportion of inflammatory and neoplastic skin conditions on a daily basis. Various surgical techniques can be employed to aid...
BACKGROUND
General practitioners manage a significant proportion of inflammatory and neoplastic skin conditions on a daily basis. Various surgical techniques can be employed to aid in diagnosis, including punch biopsies, shave biopsy, shave excision, incisional biopsy, curettage and formal excision with closure. Requiring minimal equipment, shave procedures are quick to perform, produce good cosmetic outcomes and minimise costs.
OBJECTIVE
Our aim is to discuss shave procedures in detail and highlight the difference between shave biopsies and shave excisions, as well as the role they each have in diagnosing an array of benign, inflammatory and malignant skin conditions, including melanocytic lesions.
DISCUSSION
Shave procedures performed on suitable lesions by trained practitioners can be used for sampling or removing suspect lesions. Where the intent is complete removal, margin involvement is rare given good lesion selection and technique.
Topics: Humans; General Practice; Biopsy; Skin Diseases
PubMed: 38840380
DOI: 10.31128/AJGP-06-23-6872 -
Medicina (Kaunas, Lithuania) Nov 2023: although musculoskeletal alterations are common in patients with Down syndrome (DS), studies investigating this association are scarce, and proposals for diagnostic...
: although musculoskeletal alterations are common in patients with Down syndrome (DS), studies investigating this association are scarce, and proposals for diagnostic standardization are limited. We aimed to evaluate the prevalence of musculoskeletal disorders in the lower limbs in a sample of children and adolescents with DS and to investigate the diagnostic capacity of orthopedic clinical examinations performed by orthopedists and pediatricians to diagnose these alterations. : Twenty-two patients aged between three and ten years with DS were included. Patients and guardians answered a simple questionnaire regarding orthopedic complaints and underwent a systematic orthopedic physical examination, performed twice: once by an orthopedist and again by a pediatrician. Patients underwent a series of radiographs to diagnose anisomelia, hip dysplasia, epiphysiolysis, flatfoot valgus, mechanical axis varus, and mechanical axis valgus. The radiological diagnosis was considered the gold standard, and the diagnostic capacity of the physical examination performed by each physician was determined. : The median age was 6.50 years. Only four patients (18.2%) presented with orthopedic complaints. All patients were diagnosed with at least one musculoskeletal disorder. The only musculoskeletal disorder with a good diagnostic capacity was flatfoot valgus. Limited sensitivity values were found for hip dysplasia, mechanical axis varus, and mechanical axis valgus. The agreement between the orthopedic physical examinations performed by the two examiners was weak, poor, or indeterminate for most of the analyzed items. : There was a high prevalence of orthopedic alterations in children with DS who did not present with musculoskeletal complaints. The diagnostic capacity of the physical examination was limited. Therefore, all children with DS should undergo a radiological evaluation of the musculoskeletal system and subsequent specialized orthopedic evaluation. Level of Evidence: Level II (Diagnostic Studies).
Topics: Adolescent; Humans; Child; Child, Preschool; Flatfoot; Down Syndrome; Hip Dislocation; Lower Extremity; Musculoskeletal Diseases; Hip Dislocation, Congenital; Physical Examination
PubMed: 38004035
DOI: 10.3390/medicina59111986 -
Breast Cancer Research : BCR May 2023Multiparametric magnetic resonance imaging (MP-MRI) has high sensitivity for diagnosing breast cancers but cannot always be used as a routine diagnostic tool. The...
BACKGROUND
Multiparametric magnetic resonance imaging (MP-MRI) has high sensitivity for diagnosing breast cancers but cannot always be used as a routine diagnostic tool. The present study aimed to evaluate whether the diagnostic performance of perfluorobutane (PFB) contrast-enhanced ultrasound (CEUS) is similar to that of MP-MRI in breast cancer and whether combining the two methods would enhance diagnostic efficiency.
PATIENTS AND METHODS
This was a head-to-head, prospective, multicenter study. Patients with breast lesions diagnosed by US as Breast Imaging Reporting and Data System (BI-RADS) categories 3, 4, and 5 underwent both PFB-CEUS and MP-MRI scans. On-site operators and three reviewers categorized the BI-RADS of all lesions on two images. Logistic-bootstrap 1000-sample analysis and cross-validation were used to construct PFB-CEUS, MP-MRI, and hybrid (PFB-CEUS + MP-MRI) models to distinguish breast lesions.
RESULTS
In total, 179 women with 186 breast lesions were evaluated from 17 centers in China. The area under the receiver operating characteristic curve (AUC) for the PFB-CEUS model to diagnose breast cancer (0.89; 95% confidence interval [CI] 0.74, 0.97) was similar to that of the MP-MRI model (0.89; 95% CI 0.73, 0.97) (P = 0.85). The AUC of the hybrid model (0.92, 95% CI 0.77, 0.98) did not show a statistical advantage over the PFB-CEUS and MP-MRI models (P = 0.29 and 0.40, respectively). However, 90.3% false-positive and 66.7% false-negative results of PFB-CEUS radiologists and 90.5% false-positive and 42.8% false-negative results of MP-MRI radiologists could be corrected by the hybrid model. Three dynamic nomograms of PFB-CEUS, MP-MRI and hybrid models to diagnose breast cancer are freely available online.
CONCLUSIONS
PFB-CEUS can be used in the differential diagnosis of breast cancer with comparable performance to MP-MRI and with less time consumption. Using PFB-CEUS and MP-MRI as joint diagnostics could further strengthen the diagnostic ability. Trial registration Clinicaltrials.gov; NCT04657328. Registered 26 September 2020. IRB number 2020-300 was approved in Chinese PLA General Hospital. Every patient signed a written informed consent form in each center.
Topics: Humans; Female; Breast Neoplasms; Multiparametric Magnetic Resonance Imaging; Contrast Media; Sensitivity and Specificity; Prospective Studies; Ultrasonography, Mammary; Magnetic Resonance Imaging
PubMed: 37254149
DOI: 10.1186/s13058-023-01650-3 -
Sensors (Basel, Switzerland) May 2022The neural correlates of intentional emotion transfer by the music performer are not well investigated as the present-day research mainly focuses on the assessment of...
The neural correlates of intentional emotion transfer by the music performer are not well investigated as the present-day research mainly focuses on the assessment of emotions evoked by music. In this study, we aim to determine whether EEG connectivity patterns can reflect differences in information exchange during emotional playing. The EEG data were recorded while subjects were performing a simple piano score with contrasting emotional intentions and evaluated the subjectively experienced success of emotion transfer. The brain connectivity patterns were assessed from the EEG data using the Granger Causality approach. The effective connectivity was analyzed in different frequency bands-delta, theta, alpha, beta, and gamma. The features that (1) were able to discriminate between the neutral baseline and the emotional playing and (2) were shared across conditions, were used for further comparison. The low frequency bands-delta, theta, alpha-showed a limited number of connections (4 to 6) contributing to the discrimination between the emotional playing conditions. In contrast, a dense pattern of connections between regions that was able to discriminate between conditions (30 to 38) was observed in beta and gamma frequency ranges. The current study demonstrates that EEG-based connectivity in beta and gamma frequency ranges can effectively reflect the state of the networks involved in the emotional transfer through musical performance, whereas utility of the low frequency bands (delta, theta, alpha) remains questionable.
Topics: Brain; Brain Mapping; Electroencephalography; Emotions; Humans; Music
PubMed: 35684685
DOI: 10.3390/s22114064 -
Sensors (Basel, Switzerland) Nov 2022Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an...
Computer-aided diagnosis (CAD) has proved to be an effective and accurate method for diagnostic prediction over the years. This article focuses on the development of an automated CAD system with the intent to perform diagnosis as accurately as possible. Deep learning methods have been able to produce impressive results on medical image datasets. This study employs deep learning methods in conjunction with meta-heuristic algorithms and supervised machine-learning algorithms to perform an accurate diagnosis. Pre-trained convolutional neural networks (CNNs) or auto-encoder are used for feature extraction, whereas feature selection is performed using an ant colony optimization (ACO) algorithm. Ant colony optimization helps to search for the best optimal features while reducing the amount of data. Lastly, diagnosis prediction (classification) is achieved using learnable classifiers. The novel framework for the extraction and selection of features is based on deep learning, auto-encoder, and ACO. The performance of the proposed approach is evaluated using two medical image datasets: chest X-ray (CXR) and magnetic resonance imaging (MRI) for the prediction of the existence of COVID-19 and brain tumors. Accuracy is used as the main measure to compare the performance of the proposed approach with existing state-of-the-art methods. The proposed system achieves an average accuracy of 99.61% and 99.18%, outperforming all other methods in diagnosing the presence of COVID-19 and brain tumors, respectively. Based on the achieved results, it can be claimed that physicians or radiologists can confidently utilize the proposed approach for diagnosing COVID-19 patients and patients with specific brain tumors.
Topics: Humans; COVID-19; Deep Learning; Diagnosis, Computer-Assisted; Brain Neoplasms; Computers
PubMed: 36433595
DOI: 10.3390/s22228999