-
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 -
Pediatric Emergency Care Nov 2021This study aimed to investigate the feasibility of point-of-care ultrasound (POCUS) for diagnosing hypertrophic pyloric stenosis (HPS) in the emergency department (ED).
OBJECTIVES
This study aimed to investigate the feasibility of point-of-care ultrasound (POCUS) for diagnosing hypertrophic pyloric stenosis (HPS) in the emergency department (ED).
METHODS
A retrospective study was conducted in infants aged younger than 90 days who were brought to the ED due to vomiting between January 2015 and December 2019. Of these, infants who were clinically suspected of having HPS and underwent ultrasound were included and categorized into 3 groups: POCUS only, POCUS followed by radiologist-performed ultrasound (RADUS), and RADUS only. All confirmative diagnoses of HPS were made by RADUS. The diagnostic performance of POCUS was analyzed, and the ED patient flow was compared between the POCUS-performed (POCUS only or POCUS followed by RADUS) and RADUS-only groups.
RESULTS
Overall, 171 patients with a median age of 34 days were included. Of these, 79 patients (46.2%) underwent POCUS only, and none had HPS; 50 patients (29.2%) underwent POCUS followed by RADUS; and 42 patients (24.5%) underwent RADUS only. Overall, 41 patients (24.0%) were diagnosed with HPS, and POCUS showed a sensitivity of 96.6% and specificity of 94.0%. In the total cohort, length of stay in the ED (EDLOS) was shorter in the POCUS-performed group than in the RADUS-only group (2.6 vs 3.8 hours, P = 0.015). Among non-HPS patients, time to disposition (1.8 vs 2.7 hours, P = 0.005) and EDLOS (2.0 vs 3.0 hours, P = 0.004) were shorter in the POCUS-performed group than in the RADUS-only group. Performing POCUS followed by RADUS did not significantly delay the treatment among HPS patients.
CONCLUSIONS
Point-of-care ultrasound is accurate and useful for diagnosing HPS and improved the ED patient flow by reducing EDLOS and door-to-disposition time in non-HPS patients.
Topics: Emergency Service, Hospital; Feasibility Studies; Humans; Infant; Point-of-Care Systems; Pyloric Stenosis, Hypertrophic; Retrospective Studies; Ultrasonography
PubMed: 34550920
DOI: 10.1097/PEC.0000000000002532 -
BMC Medical Imaging Apr 2021Cardiac lipoma is a rare primary tumor in the heart and pericardium. Multimodality imaging methods, especially magnetic resonance imaging (MRI), are crucial in detecting...
BACKGROUND
Cardiac lipoma is a rare primary tumor in the heart and pericardium. Multimodality imaging methods, especially magnetic resonance imaging (MRI), are crucial in detecting and diagnosing cardiac lipomas. Besides, they are of significant importance in management of cardiac lipomas. The aim of this study was to evaluate the value of multimodality imaging methods in diagnosing and treatment of cardiac lipoma by describing a series of cases of cardiac lipoma.
MATERIALS AND METHODS
Data of patients with cardiac lipoma at a local institution were retrospectively collected. Their imaging findings on echocardiography, computed tomography (CT), and cardiac MRI and clinical management were described in detail.
RESULTS
12 patients with cardiac lipoma were retrospectively included with thirteen lipomas found within heart and pericardium. Two patients' lipoma were symptomatic, while lipomas in other 10 patients were found incidentally. Most lipomas were sensitively detected with echocardiography. Accurate diagnoses were achieved with CT and MRI in all cases. Surgical resection was performed in one symptomatic patient due to the obstruction of the left ventricular outflow tract, while the removal of pericardial lipoma in another symptomatic patient was not possible due to diffuse myocardial infiltration observed in MRI. Based on MRI findings, two patients without clinical symptoms also underwent surgery to prevent the risk of detachment of ventricular lipoma with a narrow pedicle in one patient and potential further thinning of the myocardium by pericardial lipoma growth in another patient.
CONCLUSIONS
Cardiac lipoma could be sensitively detected and accurately diagnosed with multiple noninvasive imaging tools. Comprehensive evaluation with multimodality imaging methods should also be conducted for better management planning and follow-up in all patients.
Topics: Adult; Aged; Aged, 80 and over; Echocardiography; Female; Heart Neoplasms; Humans; Incidental Findings; Lipoma; Magnetic Resonance Imaging; Male; Middle Aged; Multimodal Imaging; Pericardium; Retrospective Studies; Tomography, X-Ray Computed; Young Adult
PubMed: 33858367
DOI: 10.1186/s12880-021-00603-6 -
World Journal of Gastroenterology Jun 2008Chronic viral hepatitis is a common disease in the general population. During chronic hepatitis, the prognosis and clinical management are highly dependent on the extent... (Review)
Review
Chronic viral hepatitis is a common disease in the general population. During chronic hepatitis, the prognosis and clinical management are highly dependent on the extent of liver fibrosis. The fibrosis evaluation can be performed by FibroTest (using serological markers), by Elastography or FibroScan (a noninvasive percutaneous technique using the elastic properties of the hepatic tissue) and by liver biopsy (LB), considered to be the "gold standard". Currently, there are three techniques for performing LB: percutaneous, transjugular and laparoscopic. The percutaneous LB can be performed blind, ultrasound (US) guided or US assisted. There are two main categories of specialists who perform LB: gastroenterologists (hepatologists) and radiologists, and the specialty of the individual who performs the LB determines if the LB is performed under ultrasound guidance or not. There are two types of biopsy needles used for LB: cutting needles (Tru-Cut, Vim-Silverman) and suction needles (Menghini, Klatzkin, Jamshidi). The rate of major complications after percutaneous LB ranges from 0.09% to 2.3%, but the echo-guided percutaneous liver biopsy is a safe method for the diagnosis of chronic diffuse hepatitis (cost-effective as compared to blind biopsy) and the rate of complications seems to be related to the experience of the physician and the type of the needle used (Menghini type needle seems to be safer). Maybe, in a few years we will use non-invasive markers of fibrosis, but at this time, most authorities in the field consider that the LB is useful and necessary for the evaluation of chronic hepatopathies, despite the fact that it is not a perfect test.
Topics: Biomarkers; Biopsy, Needle; Chronic Disease; Clinical Competence; Elasticity; Equipment Design; Hepatitis, Viral, Human; Humans; Laparoscopy; Liver; Liver Cirrhosis; Needles; Patient Selection; Severity of Illness Index; Ultrasonography, Interventional
PubMed: 18528937
DOI: 10.3748/wjg.14.3396 -
Respiratory Medicine Aug 2017Chronic obstructive pulmonary disease (COPD) has serious implications at both the individual and the societal level. It is crucial that COPD is diagnosed correctly to... (Review)
Review
BACKGROUND
Chronic obstructive pulmonary disease (COPD) has serious implications at both the individual and the societal level. It is crucial that COPD is diagnosed correctly to ensure provision of the right treatment. However, the current diagnostic procedures may lead to misdiagnosis.
AIM
The aim of this scoping review was to disseminate knowledge about potential causes of misdiagnosis of COPD.
METHODS
A systematic, comprehensive search was performed in PubMed, Embase and Cinahl.
RESULTS
A thorough review produced a sample of 73 articles. The synthesis revealed five potential causes of misdiagnosis of COPD, including: the threshold for defining COPD (n = 36), errors made in primary care (n = 15), errors linked to the spirometry test (n = 13), differential diagnoses (n = 10), and patient-related factors (n = 8).
CONCLUSIONS
The causes of misdiagnosis of COPD are attributable mainly to spirometry and to the healthcare professional performing the diagnostic assessment. With a view to limiting misdiagnosis of COPD, future research should help clarify strategies for alternative objective tests for determining if a patient has COPD and explore how to better support primary care in the diagnosing of COPD.
Topics: Awareness; Comorbidity; Diagnosis, Differential; Diagnostic Errors; Female; Forced Expiratory Volume; Humans; Male; Primary Health Care; Pulmonary Disease, Chronic Obstructive; Spirometry; Vital Capacity
PubMed: 28732838
DOI: 10.1016/j.rmed.2017.05.015 -
Scientific Reports Nov 2020Central serous chorioretinopathy (CSC) is a common condition characterized by serous detachment of the neurosensory retina at the posterior pole. We built a deep...
Central serous chorioretinopathy (CSC) is a common condition characterized by serous detachment of the neurosensory retina at the posterior pole. We built a deep learning system model to diagnose CSC, and distinguish chronic from acute CSC using spectral domain optical coherence tomography (SD-OCT) images. Data from SD-OCT images of patients with CSC and a control group were analyzed with a convolutional neural network. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC) were used to evaluate the model. For CSC diagnosis, our model showed an accuracy, sensitivity, and specificity of 93.8%, 90.0%, and 99.1%, respectively; AUROC was 98.9% (95% CI, 0.983-0.995); and its diagnostic performance was comparable with VGG-16, Resnet-50, and the diagnoses of five different ophthalmologists. For distinguishing chronic from acute cases, the accuracy, sensitivity, and specificity were 97.6%, 100.0%, and 92.6%, respectively; AUROC was 99.4% (95% CI, 0.985-1.000); performance was better than VGG-16 and Resnet-50, and was as good as the ophthalmologists. Our model performed well when diagnosing CSC and yielded highly accurate results when distinguishing between acute and chronic cases. Thus, automated deep learning system algorithms could play a role independent of human experts in the diagnosis of CSC.
Topics: Adult; Algorithms; Central Serous Chorioretinopathy; Choroid; Deep Learning; Female; Humans; Male; Middle Aged; Neural Networks, Computer; Retina; Tomography, Optical Coherence
PubMed: 33139813
DOI: 10.1038/s41598-020-75816-w -
Frontiers in Oncology 2023Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their...
BACKGROUND
Pancreatic cystic neoplasms are increasingly diagnosed with the development of medical imaging technology and people's self-care awareness. However, two of their sub-types, serous cystic neoplasms (SCN) and mucinous cystic neoplasms (MCN), are often misclassified from each other. Because SCN is primarily benign and MCN has a high rate of malignant transformation. Distinguishing SCN and MCN is challenging and essential.
PURPOSE
MRIs have many different modalities, complete with SCN and MCN diagnosis information. With the help of an artificial intelligence-based algorithm, we aimed to propose a multi-modal hybrid deep learning network that can efficiently diagnose SCN and MCN using multi-modality MRIs.
METHODS
A cross-modal feature fusion structure was innovatively designed, combining features of seven modalities to realize the classification of SCN and MCN. 69 Patients with multi-modalities of MRIs were included, and experiments showed performances of every modality.
RESULTS
The proposed method with the optimized settings outperformed all other techniques and human radiologists with high accuracy of 75.07% and an AUC of 82.77%. Besides, the proposed disentanglement method outperformed other fusion methods, and delayed contrast-enhanced T1-weighted MRIs proved most valuable in diagnosing SCN and MCN.
CONCLUSIONS
Through the use of a contemporary artificial intelligence algorithm, physicians can attain high performance in the complex challenge of diagnosing SCN and MCN, surpassing human radiologists to a significant degree.
PubMed: 37795452
DOI: 10.3389/fonc.2023.1181270 -
Gastrointestinal Endoscopy Dec 2023Data on how to teach endosonographers needle-based confocal laser endomicroscopy (nCLE)-guided histologic diagnosis of pancreatic cystic lesions (PCLs) are limited.... (Randomized Controlled Trial)
Randomized Controlled Trial
Structured training program on confocal laser endomicroscopy for pancreatic cystic lesions: a multicenter prospective study among early-career endosonographers (with video).
BACKGROUND AND AIMS
Data on how to teach endosonographers needle-based confocal laser endomicroscopy (nCLE)-guided histologic diagnosis of pancreatic cystic lesions (PCLs) are limited. Hence, we developed and tested a structured educational program to train early-career endosonographers in nCLE-guided diagnosis of PCLs.
METHODS
Twenty-one early-career nCLE-naïve endosonographers watched a teaching module outlining nCLE criteria for diagnosing PCLs. Participants then reviewed 80 high-yield nCLE videos, recorded diagnoses, and received expert feedback (phase 1). Observers were then randomized to a refresher feedback session or self-learning at 4 weeks. Eight weeks after training, participants independently assessed the same 80 nCLE videos without feedback and provided histologic predictions (phase 2). Diagnostic performance of nCLE to differentiate mucinous versus nonmucinous PCLs and to diagnose specific subtypes were analyzed using histopathology as the criterion standard. Learning curves were determined using cumulative sum analysis.
RESULTS
Accuracy and diagnostic confidence for differentiating mucinous versus nonmucinous PCLs improved as endosonographers progressed through nCLE videos in phase 1 (P < .001). Similar trends were observed with the diagnosis of PCL subtypes. Most participants achieved competency interpreting nCLE, requiring a median of 38 assessments (range, 9-67). During phase 2, participants independently differentiated PCLs with high accuracy (89%), high confidence (83%), and substantial interobserver agreement (κ = .63). Accuracy for nCLE-guided PCL subtype diagnoses ranged from 82% to 96%. The learned nCLE skills did not deteriorate at 8 weeks and were not impacted by a refresher session.
CONCLUSIONS
We developed a practical, effective, and durable educational intervention to train early-career endosonographers in nCLE-guided diagnosis of PCLs.
Topics: Humans; Prospective Studies; Endoscopic Ultrasound-Guided Fine Needle Aspiration; Microscopy, Confocal; Pancreatic Cyst; Lasers
PubMed: 37473969
DOI: 10.1016/j.gie.2023.07.019 -
International Journal of Geriatric... Aug 2015Dementia is a common clinical presentation among older adults with Down syndrome. The presentation of dementia in Down syndrome differs compared with typical Alzheimer's...
OBJECTIVE
Dementia is a common clinical presentation among older adults with Down syndrome. The presentation of dementia in Down syndrome differs compared with typical Alzheimer's disease. The performance of manualised dementia criteria in the International Classification of Diseases (ICD)-10 and Diagnostic and Statistical Manual of Mental Disorders-IV-Text Revision (DSM-IV-TR) is uncertain in this population.We aimed to determine the concurrent validity and reliability of clinicians' diagnoses of dementia against ICD-10 and DSM-IV-TR diagnoses. Validity of clinical diagnoses were also explored by establishing the stability of diagnoses over time.
METHODS
We used clinical data from memory assessments of 85 people with Down syndrome, of whom 64 (75.3%) had a diagnosis of dementia. The cases of dementia were presented to expert raters who rated the case as dementia or no dementia using ICD-10 and DSM-IV-TR criteria and their own clinical judgement.
RESULTS
We found that clinician's judgement corresponded best with clinically diagnosed cases of dementia, identifying 84.4% cases of clinically diagnosed dementia at the time of diagnosis. ICD-10 criteria identified 70.3% cases, and DSM-IV-TR criteria identified 56.3% cases at the time of clinically diagnosed dementia. Over time, the proportion of cases meeting ICD-10 or DSM-IV-TR diagnoses increased, suggesting that experienced clinicians used their clinical knowledge of dementia presentation in Down syndrome to diagnose the disorder at an earlier stage than would have been possible had they relied on the classic description contained in the diagnostic systems.
CONCLUSIONS
Clinical diagnosis of dementia in Down syndrome is valid and reliable and can be used as the standard against which new criteria such as the DSM-5 are measured.
Topics: Adult; Aged; Dementia; Diagnostic and Statistical Manual of Mental Disorders; Down Syndrome; Female; Humans; International Classification of Diseases; Male; Middle Aged; Observer Variation; Psychiatric Status Rating Scales; Reproducibility of Results
PubMed: 25363568
DOI: 10.1002/gps.4228 -
Scientific Reports Mar 2021The reverse transcription-polymerase chain reaction (RT-PCR) assay is the accepted standard for coronavirus disease 2019 (COVID-19) diagnosis. As any test, RT-PCR...
The reverse transcription-polymerase chain reaction (RT-PCR) assay is the accepted standard for coronavirus disease 2019 (COVID-19) diagnosis. As any test, RT-PCR provides false negative results that can be rectified by clinicians by confronting clinical, biological and imaging data. The combination of RT-PCR and chest-CT could improve diagnosis performance, but this would requires considerable resources for its rapid use in all patients with suspected COVID-19. The potential contribution of machine learning in this situation has not been fully evaluated. The objective of this study was to develop and evaluate machine learning models using routine clinical and laboratory data to improve the performance of RT-PCR and chest-CT for COVID-19 diagnosis among post-emergency hospitalized patients. All adults admitted to the ED for suspected COVID-19, and then hospitalized at Rennes academic hospital, France, between March 20, 2020 and May 5, 2020 were included in the study. Three model types were created: logistic regression, random forest, and neural network. Each model was trained to diagnose COVID-19 using different sets of variables. Area under the receiving operator characteristics curve (AUC) was the primary outcome to evaluate model's performances. 536 patients were included in the study: 106 in the COVID group, 430 in the NOT-COVID group. The AUC values of chest-CT and RT-PCR increased from 0.778 to 0.892 and from 0.852 to 0.930, respectively, with the contribution of machine learning. After generalization, machine learning models will allow increasing chest-CT and RT-PCR performances for COVID-19 diagnosis.
Topics: Area Under Curve; COVID-19; COVID-19 Testing; Diagnosis, Computer-Assisted; Humans; Machine Learning; Proof of Concept Study; Reverse Transcriptase Polymerase Chain Reaction; Tomography, X-Ray Computed
PubMed: 33785852
DOI: 10.1038/s41598-021-86735-9