-
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 -
World Journal of Surgical Oncology Jan 2019In this study, images of 2450 benign thyroid nodules and 2557 malignant thyroid nodules were collected and labeled, and an automatic image recognition and diagnosis...
BACKGROUND
In this study, images of 2450 benign thyroid nodules and 2557 malignant thyroid nodules were collected and labeled, and an automatic image recognition and diagnosis system was established by deep learning using the YOLOv2 neural network. The performance of the system in the diagnosis of thyroid nodules was evaluated, and the application value of artificial intelligence in clinical practice was investigated.
METHODS
The ultrasound images of 276 patients were retrospectively selected. The diagnoses of the radiologists were determined according to the Thyroid Imaging Reporting and Data System; the images were automatically recognized and diagnosed by the established artificial intelligence system. Pathological diagnosis was the gold standard for the final diagnosis. The performances of the established system and the radiologists in diagnosing the benign and malignant thyroid nodules were compared.
RESULTS
The artificial intelligence diagnosis system correctly identified the lesion area, with an area under the receiver operating characteristic (ROC) curve of 0.902, which is higher than that of the radiologists (0.859). This finding indicates a higher diagnostic accuracy (p = 0.0434). The sensitivity, positive predictive value, negative predictive value, and accuracy of the artificial intelligence diagnosis system for the diagnosis of malignant thyroid nodules were 90.5%, 95.22%, 80.99%, and 90.31%, respectively, and the performance did not significantly differ from that of the radiologists (p > 0.05). The artificial intelligence diagnosis system had a higher specificity (89.91% vs 77.98%, p = 0.026).
CONCLUSIONS
Compared with the performance of experienced radiologists, the artificial intelligence system has comparable sensitivity and accuracy for the diagnosis of malignant thyroid nodules and better diagnostic ability for benign thyroid nodules. As an auxiliary tool, this artificial intelligence diagnosis system can provide radiologists with sufficient assistance in the diagnosis of benign and malignant thyroid nodules.
Topics: Adult; Aged; Diagnosis, Differential; Female; Humans; Image Interpretation, Computer-Assisted; Male; Middle Aged; Neural Networks, Computer; Predictive Value of Tests; Prognosis; ROC Curve; Retrospective Studies; Thyroid Gland; Thyroid Nodule; Ultrasonography; Young Adult
PubMed: 30621704
DOI: 10.1186/s12957-019-1558-z -
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 -
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 -
Journal of Nuclear Medicine : Official... Mar 2016(18)F-FDG PET/CT has become the reference standard in oncologic imaging against which the performance of other imaging modalities is measured. The promise of PET/MRI... (Review)
Review
(18)F-FDG PET/CT has become the reference standard in oncologic imaging against which the performance of other imaging modalities is measured. The promise of PET/MRI includes multiparametric imaging to further improve diagnosis and phenotyping of cancer. Rather than focusing on these capabilities, many investigators have examined whether (18)F-FDG PET combined with mostly anatomic MRI improves cancer staging and restaging. After a description of PET/MRI scanner designs and a discussion of technical and operational issues, we review the available literature to determine whether cancer assessments are improved with PET/MRI. The available data show that PET/MRI is feasible and performs as well as PET/CT in most types of cancer. Diagnostic advantages may be achievable in prostate cancer and in bone metastases, whereas disadvantages exist in lung nodule assessments. We conclude that (18)F-FDG PET/MRI and PET/CT provide comparable diagnostic information when MRI is used simply to provide the anatomic framework. Thus, PET/MRI could be used in lieu of PET/CT if this approach becomes economically viable and if reasonable workflows can be established. Future studies should explore the multiparametric potential of MRI.
Topics: Humans; Magnetic Resonance Imaging; Multimodal Imaging; Neoplasm Staging; Neoplasms; Positron-Emission Tomography
PubMed: 26742709
DOI: 10.2967/jnumed.115.158808 -
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 -
MedEdPORTAL : the Journal of Teaching... 2023Cervical intraepithelial neoplasia 3 is associated with a high degree of progression to cervical cancer. Its risk is markedly reduced after excisional treatment. Hence,...
INTRODUCTION
Cervical intraepithelial neoplasia 3 is associated with a high degree of progression to cervical cancer. Its risk is markedly reduced after excisional treatment. Hence, it is critical that providers accurately diagnose and treat this condition. We present a simulation-based module focused on resident mastery of performance of colposcopy and loop electrosurgical excision procedure (LEEP).
METHODS
Learners were obstetrics and gynecology residents. Guidelines on performance of colposcopy and LEEP were presented prior to module participation. We used pelvic task trainers, kielbasa sausages, and routine equipment for performance of colposcopy and LEEP. Colposcopy and LEEP sessions each lasted 30 minutes. Learners completed questionnaires before and after regarding comfort level on aspects of colposcopy and LEEP performance and level of agreement with statements on performing procedures independently. Comfort levels and degrees of agreement were based on 5-point Likert scales (1 = 3 = 5 = respectively).
RESULTS
Modules were held in November 2021 and May 2022. Thirty-four residents participated. Mean comfort scores significantly increased from 3.1 to 4.3 ( < .001) before and after the module for all steps. There was an increase in level of agreement with statements on being able to independently perform colposcopy (2.2 to 3.5, < .01) and LEEP (2.9 to 3.6, = .06).
DISCUSSION
Simulation-based modules on performance of colposcopy and LEEP significantly increased resident learner comfort in the performance of these procedures. Comfort in performing these procedures is important in providing comprehensive gynecologic care.
Topics: Pregnancy; Female; Humans; Colposcopy; Electrosurgery; Computer Simulation; Obstetrics; Pelvis
PubMed: 37691878
DOI: 10.15766/mep_2374-8265.11344 -
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 -
The Quarterly Journal of Economics May 2022Physicians, judges, teachers, and agents in many other settings differ systematically in the decisions they make when faced with similar cases. Standard approaches to...
Physicians, judges, teachers, and agents in many other settings differ systematically in the decisions they make when faced with similar cases. Standard approaches to interpreting and exploiting such differences assume they arise solely from variation in preferences. We develop an alternative framework that allows variation in preferences and diagnostic skill and show that both dimensions may be partially identified in standard settings under quasi-random assignment. We apply this framework to study pneumonia diagnoses by radiologists. Diagnosis rates vary widely among radiologists, and descriptive evidence suggests that a large component of this variation is due to differences in diagnostic skill. Our estimated model suggests that radiologists view failing to diagnose a patient with pneumonia as more costly than incorrectly diagnosing one without, and that this leads less skilled radiologists to optimally choose lower diagnostic thresholds. Variation in skill can explain 39% of the variation in diagnostic decisions, and policies that improve skill perform better than uniform decision guidelines. Failing to account for skill variation can lead to highly misleading results in research designs that use agent assignments as instruments.
PubMed: 35422677
DOI: 10.1093/qje/qjab048