-
The Journal of Maternal-fetal &... Jan 2021Lung ultrasonography has become an important tool in the diagnosis and follow-up of lung diseases in the newborn period in recent years. Lung diseases such as... (Review)
Review
Lung ultrasonography has become an important tool in the diagnosis and follow-up of lung diseases in the newborn period in recent years. Lung diseases such as pneumonia, transient tachypnea of the newborn and respiratory distress syndrome (RDS) can be diagnosed with lung ultrasound. Lung USG is a simple, practical and low-cost method in diagnosing neonatal RDS. This study was performed in Hacettepe University Neonatal Intensive Care Unit From December 2015 to February 2017. Forty patients who were diagnosed as RDS and given surfactant [200 mg/kg poractant alfa (CUROSURF®, Chiesi, Italy) intratracheal Suspension] were included in the study. Lung ultrasonography was performed at the bedside by a single expert, once before surfactant treatment and three times after surfactant treatment. Post-treatment ultrasonographic examinations were carried out at 2, 4 and 6 h after surfactant treatment. Before surfactant treatment, lung USG findings of patients were as follows: lung consolidation with air bronchograms (40/40), B-pattern (36/40), pleural line abnormalities (37/40), severe B-pattern (12/40) and disappearance of A-lines in all USG of patients. In the second hour of treatment, we did not see any valuable change or difference in lung USG findings of patients. The only change was the disappearance of air bronchograms and lung consolidation in five patients. Four hours after treatment we saw a reduction in lung consolidation in 14 patients, B-pattern had decreased in 15 patients, the appearance of A-lines and spared areas. But after 6 h, we started to see A-lines clearly, loss of B-pattern, an appearance of pleural line, and lung sliding in nearly all patients except three. Ultrasound is nonionizing and gives no hazard to the patient. Also, making it bedside is feasible and comfortable than other methods. Responsive and unresponsive patients to surfactant treatment can be determined in the early course of the disease and the cases needing re-treatment can be diagnosed easily by performing lung USG. This review focuses on ultrasonographic changes of the lung after surfactant treatment in premature newborns.
Topics: Humans; Infant, Newborn; Italy; Lung; Pulmonary Surfactants; Respiratory Distress Syndrome, Newborn; Ultrasonography
PubMed: 30957609
DOI: 10.1080/14767058.2019.1605350 -
European Radiology Sep 2021To evaluate the ability of shear wave elastography (SWE) in diagnosing medial epicondylitis and to compare the diagnostic performance of SWE with that of grey-scale...
OBJECTIVES
To evaluate the ability of shear wave elastography (SWE) in diagnosing medial epicondylitis and to compare the diagnostic performance of SWE with that of grey-scale ultrasound (GSU) and strain elastography (SE).
METHODS
GSU, SE, and SWE were performed on 61 elbows of 54 patients from March 2018 to April 2019. An experienced radiologist evaluated the GSU findings (swelling, cortical irregularity, hypoechogenicity, calcification, and tear), colour Doppler findings (hyperaemia), SE findings (strain ratio [SR]), and SWE findings (stiffness and shear wave velocity [SWV]). Participants were divided in two groups: patients with clinically diagnosed medial epicondylitis and patients without medial elbow pain. Findings from the two groups were compared, and the receiver operating characteristic (ROC) curves were calculated for significant features.
RESULTS
Of the 54 patients, 25 patients with 28 imaged elbows were clinically diagnosed with medial epicondylitis and 29 patients with 33 imaged elbows had no medial elbow pain. Cortical irregularity, hypoechogenicity, calcification, hyperaemia, SR, stiffness, and SWV were significantly different between the two groups. The areas under the ROC curves were 0.838 for hypoechogenicity, 0.948 for SR, 0.999 for stiffness, and 0.999 for SWV. The diagnostic performances of SR, stiffness, and SWV were significantly superior compared to that of hypoechogenicity. However, there were no significant differences among SR, stiffness, and SWV.
CONCLUSIONS
SWE can obtain both stiffness and SWV, which are valuable diagnostic tools in the diagnosis of medial epicondylitis. The diagnostic performance of SWE and SE is similar in detecting medial epicondylitis.
KEY POINTS
• Shear wave elastography providing stiffness and shear wave velocity showed excellent performance in the diagnosis of medial epicondylitis. • There was no significant difference in the ability of SE and SWE for diagnosing medial epicondylitis.
Topics: Elasticity Imaging Techniques; Elbow Joint; Elbow Tendinopathy; Humans; ROC Curve; Ultrasonography
PubMed: 33634322
DOI: 10.1007/s00330-021-07791-3 -
American Journal of Obstetrics &... Sep 2021Telemedicine can extend essential health services to under-resourced settings and improve the quality of obstetrical care. Specifically, the evaluation and management of...
BACKGROUND
Telemedicine can extend essential health services to under-resourced settings and improve the quality of obstetrical care. Specifically, the evaluation and management of fetal anomalies require perinatal subspecialists, rendering prenatal diagnosis essential, and may benefit from telemedicine platforms to improve access to care.
OBJECTIVE
This study aimed to evaluate the impact of a maternal-fetal medicine telemedicine ultrasound program on the diagnostic accuracy of fetal anomalies when used within practices where ultrasounds are interpreted by general obstetricians or family medicine physicians.
STUDY DESIGN
This was a cross-sectional study of all patients receiving care at 11 private obstetrical practices and imaging centers who had obstetrical ultrasounds performed from January 1, 2020, to July 6, 2020. All ultrasounds were performed by sonographers remotely trained under a standardized protocol and interpreted by maternal-fetal medicine physicians via telemedicine. Ultrasound characteristics and interpretation were extracted from ultrasound reports. Before the introduction of maternal-fetal medicine telemedicine, all ultrasound interpretations were reviewed by general obstetricians and family medicine physicians with reliance predominantly on the sonographer's impression. The primary outcome was potential missed diagnosis of a fetal anomaly, defined as an ultrasound designated as normal by a sonographer but diagnosed with an anomaly by a maternal-fetal medicine physician via telemedicine. This outcome serves as a proxy measure for anomaly diagnoses that would likely be missed without the supervision of a maternal-fetal medicine physician. The characteristics of the potential missed diagnoses were compared by type of scan and fetal organ system in univariable analysis. Moreover, a survey was conducted for sonographers and obstetrical providers to assess their perceptions of ultrasound interpretation via telemedicine.
RESULTS
Overall, 6403 ultrasound examinations were evaluated, 310 of which had a diagnosis of fetal anomaly by a maternal-fetal medicine physician (4.8%). Of the fetal anomalies, 43 were diagnosed on an anatomic survey (13.9%), and 89 were diagnosed as cardiac anomalies (28.7%). The overall rate of the potential missed diagnoses was 34.5% and varied significantly by type of ultrasound (anatomy scans vs other first-, second-, and third-trimester ultrasounds) (P<.01). Moreover, there were significant differences in the rate of the potential missed diagnoses by organ system, with the highest rate for cardiac anomalies (P<.01).
CONCLUSION
Expertise in maternal-fetal medicine telemedicine improves the diagnostic performance of antenatal ultrasound throughout pregnancy. However, there are implications for improving the quality of antenatal care, such as ensuring appropriate referrals and site of delivery, particularly for cardiac anomalies.
Topics: Cross-Sectional Studies; Female; Humans; Perinatology; Pregnancy; Pregnancy Trimester, Third; Prenatal Diagnosis; Ultrasonography, Prenatal
PubMed: 33957316
DOI: 10.1016/j.ajogmf.2021.100389 -
Journal of X-ray Science and Technology 2023Computer aided diagnosis has gained momentum in the recent past. The advances in deep learning and availability of huge volumes of data along with increased...
BACKGROUND
Computer aided diagnosis has gained momentum in the recent past. The advances in deep learning and availability of huge volumes of data along with increased computational capabilities has reshaped the diagnosis and prognosis procedures.
OBJECTIVE
These methods are proven to be relatively less expensive and safer alternatives of the otherwise traditional approaches. This study is focused on efficient diagnosis of three very common diseases: lung cancer, pneumonia and Covid-19 using X-ray images.
METHODS
Three different deep learning models are designed and developed to perform 4-way classification. Inception V3, Convolutional Neural Networks (CNN) and Long Short Term Memory models (LSTM) are used as building blocks. The performance of these models is evaluated using three publicly available datasets, the first dataset contains images for Lung cancer, second contains images for Covid-19 and third dataset contains images for Pneumonia and normal subjects. Combining three datasets creates a class imbalance problem which is resolved using pre-processing and data augmentation techniques. After data augmentation 1386 subjects are randomly chosen for each class.
RESULTS
It is observed that CNN when combined with LSTM (CNN-LSTM) produces significantly improved results (accuracy of 94.5 %) which is better than CNN and InceptionV3-LSTM. 3,5, and 10 fold cross validation is performed to verify all results calculated using three different classifiersConclusions:This research concludes that a single computer-aided diagnosis system can be developed for diagnosing multiple diseases.
Topics: Humans; Deep Learning; COVID-19; Diagnosis, Computer-Assisted; Lung Neoplasms; Lung; Computers; COVID-19 Testing
PubMed: 37522236
DOI: 10.3233/XST-230113 -
European Journal of Hybrid Imaging Dec 2022Patients with lower-limb osteomyelitis (LLOM) may experience major adverse events, such as lower-leg amputations or death; therefore, early diagnosis and risk...
BACKGROUND
Patients with lower-limb osteomyelitis (LLOM) may experience major adverse events, such as lower-leg amputations or death; therefore, early diagnosis and risk stratification are essential to improve outcomes. Ga-scintigraphy is commonly used for diagnosing inflammatory diseases. Although the diagnostic performance of planar and SPECT imaging for localized lesions is limited, SPECT/CT, which simultaneously acquires functional and anatomical definition, has resulted in significant improvements to diagnostic confidence. While quantitative Ga-SPECT/CT is an emerging approach to improve diagnoses, its diagnostic performance has not been sufficiently evaluated to date. Therefore, this study aimed to evaluate the diagnostic performance of Ga-SPECT/CT with quantitative analyses for patients with LLOM.
METHODS
A total of 103 consecutive patients suspected of LLOM between April 2012 and October 2016 were analyzed. All patients underwent Ga-scintigraphy with SPECT/CT imaging. Findings were assessed visually, with higher than background accumulation considered positive, and quantitatively, using Ga-SPECT/CT images to calculate the lesion-to-background ratio (LBR), the maximum standardized uptake value (SUVmax), and total lesion uptake (TLU). Diagnoses were confirmed using pathological examinations and patient outcomes, and diagnostic performances of planar, SPECT, and SPECT/CT images were compared. To evaluate prognostic performance, all patients were observed for 5 years for occurrences of major adverse events (MAE), defined as recurrence of osteomyelitis, major leg amputation, or fatal event. Multivariate Cox regression was performed to evaluate outcome factors.
RESULTS
The overall diagnoses indicated that 54 out of 103 patients had LLOM. LBR, SUVmax, and TLU were significantly higher in patients with LLOM (12.23 vs. 1.00, 4.85 vs. 1.34, and 68.77 vs. 8.63, respectively; p < 0.001). Sensitivity and specificity were 91% and 96% for SPECT/CT with LBR, 89% and 94% for SPECT/CT with SUVmax, and 91% and 92% for SPECT/CT with TLU, respectively. MAE occurred in 23 of 54 LLOM patients (43%). TLU was found to be an independent prognostic factor (p = 0.047).
CONCLUSIONS
Ga-SPECT/CT using quantitative parameters, namely LBR and TLU, had better diagnostic and prognostic performances for patients with LLOM compared to conventional imaging. The results suggest that Ga-SPECT/CT is a good alternative for diagnosing LLOM in countries where FDG-PET/CT is not commonly available.
PubMed: 36450868
DOI: 10.1186/s41824-022-00148-z -
BMC Oral Health Jun 2023Artificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple...
BACKGROUND
Artificial intelligence (AI) has been introduced to interpret the panoramic radiographs (PRs). The aim of this study was to develop an AI framework to diagnose multiple dental diseases on PRs, and to initially evaluate its performance.
METHODS
The AI framework was developed based on 2 deep convolutional neural networks (CNNs), BDU-Net and nnU-Net. 1996 PRs were used for training. Diagnostic evaluation was performed on a separate evaluation dataset including 282 PRs. Sensitivity, specificity, Youden's index, the area under the curve (AUC), and diagnostic time were calculated. Dentists with 3 different levels of seniority (H: high, M: medium, L: low) diagnosed the same evaluation dataset independently. Mann-Whitney U test and Delong test were conducted for statistical analysis (ɑ=0.05).
RESULTS
Sensitivity, specificity, and Youden's index of the framework for diagnosing 5 diseases were 0.964, 0.996, 0.960 (impacted teeth), 0.953, 0.998, 0.951 (full crowns), 0.871, 0.999, 0.870 (residual roots), 0.885, 0.994, 0.879 (missing teeth), and 0.554, 0.990, 0.544 (caries), respectively. AUC of the framework for the diseases were 0.980 (95%CI: 0.976-0.983, impacted teeth), 0.975 (95%CI: 0.972-0.978, full crowns), and 0.935 (95%CI: 0.929-0.940, residual roots), 0.939 (95%CI: 0.934-0.944, missing teeth), and 0.772 (95%CI: 0.764-0.781, caries), respectively. AUC of the AI framework was comparable to that of all dentists in diagnosing residual roots (p > 0.05), and its AUC values were similar to (p > 0.05) or better than (p < 0.05) that of M-level dentists for diagnosing 5 diseases. But AUC of the framework was statistically lower than some of H-level dentists for diagnosing impacted teeth, missing teeth, and caries (p < 0.05). The mean diagnostic time of the framework was significantly shorter than that of all dentists (p < 0.001).
CONCLUSIONS
The AI framework based on BDU-Net and nnU-Net demonstrated high specificity on diagnosing impacted teeth, full crowns, missing teeth, residual roots, and caries with high efficiency. The clinical feasibility of AI framework was preliminary verified since its performance was similar to or even better than the dentists with 3-10 years of experience. However, the AI framework for caries diagnosis should be improved.
Topics: Humans; Radiography, Panoramic; Artificial Intelligence; Tooth, Impacted; Dental Caries; Tooth
PubMed: 37270488
DOI: 10.1186/s12903-023-03027-6 -
Computer Methods and Programs in... May 2020Severe sepsis is a leading cause of intensive care unit (ICU) admission, length of stay, mortality, and cost. systemic inflammatory response syndrome (SIRS) and organ...
OBJECTIVE
Severe sepsis is a leading cause of intensive care unit (ICU) admission, length of stay, mortality, and cost. systemic inflammatory response syndrome (SIRS) and organ failure due to infection define it, but also make it hard to diagnose. Early diagnosis reduces morbidity, mortality and cost, and diagnosis is often significantly delayed due to a lack of effective biomarkers. This research employs kernel density estimation (KDE) methods fusing a personalized, model-based insulin sensitivity (SI) metric with standard bedside measures of: temperature, heart rate, respiratory rate, systolic and diastolic blood pressure, and SIRS, as these measures are available hourly or more frequently.
METHODS
Model-based SI is a derived metric, identified using clinical data and a clinically validated metabolic model. The KDE classifier discriminates severe sepsis and septic shock from moderate sepsis using accepted consensus sepsis scores. A best case in-sample estimate, a worst case independent cross validation estimate, and an accepted .632 bootstrap estimate are calculated to assess performance using multi-level likelihood ratios, and sensitivity and specificity. Performance is assessed against clinically and statistically defined thresholds denoted for the minimum acceptable level as: "high accuracy, often providing useful information, and clinical significance," and similar definitions for greater or lesser quality.
RESULTS
The .632 bootstrap estimate performs near clinically defined levels of high accuracy, often providing useful information, and clinical significance based on sensitivity, specificity, and multilevel likelihood ratios.
CONCLUSION AND SIGNIFICANCE
The classifier created and this overall approach is useful for clinical decision making in diagnosing severe sepsis and septic shock in real time, for both case and control hours. However, improvements could be made with larger clinical data sets.
Topics: Algorithms; Area Under Curve; Case-Control Studies; Critical Care; Decision Support Systems, Clinical; Heart Rate; Humans; Insulin; Intensive Care Units; Predictive Value of Tests; Probability; ROC Curve; Reproducibility of Results; Respiratory Rate; Sensitivity and Specificity; Sepsis; Systole; Temperature
PubMed: 31918193
DOI: 10.1016/j.cmpb.2019.105295 -
Computers in Biology and Medicine Jul 2022The exact nature, harmful effects and aetiology of autism spectrum disorder (ASD) have caused widespread confusion. Artificial intelligence (AI) science helps solve...
The exact nature, harmful effects and aetiology of autism spectrum disorder (ASD) have caused widespread confusion. Artificial intelligence (AI) science helps solve challenging diagnostic problems in the medical field through extensive experiments. Disease severity is closely related to triage decisions and prioritisation contexts in medicine because both have been widely used to diagnose various diseases via AI, machine learning and automated decision-making techniques. Recently, taking advantage of high-performance AI algorithms has achieved accessible success in diagnosing and predicting risks from clinical and biological data. In contrast, less progress has been made with ASD because of obscure reasons. According to academic literature, ASD diagnosis works from a specific perspective, and much of the confusion arises from the fact that how AI techniques are currently integrated with the diagnosis of ASD concerning the triage and priority strategies and gene contributions. To this end, this study sought to describe a systematic review of the literature to assess the respective AI methods using the available datasets, highlight the tools and strategies used for diagnosing ASD and investigate how AI trends contribute in distinguishing triage and priority for ASD and gene contributions. Accordingly, this study checked the Science Direct, IEEE Xplore Digital Library, Web of Science (WoS), PubMed, and Scopus databases. A set of 363 articles from 2017 to 2022 is collected to reveal a clear picture and a better understanding of all the academic literature through a final set of 18 articles. The retrieved articles were filtered according to the defined inclusion and exclusion criteria and classified into three categories. The first category includes 'Triage patients based on diagnosis methods' which accounts for 16.66% (n = 3/18). The second category includes 'Prioritisation for Risky Genes' which accounts for 66.6% (n = 12/18) and is classified into two subcategories: 'Mutations observation based', 'Biomarkers and toxic chemical observations'. The third category includes 'E-triage using telehealth' which accounts for 16.66% (n = 3/18). This multidisciplinary systematic review revealed the taxonomy, motivations, recommendations and challenges of ASD research that need synergistic attention. Thus, this systematic review performs a comprehensive science mapping analysis and discusses the open issues that help perform and improve the recommended solution of ASD research direction. In addition, this study critically reviews the literature and attempts to address the current research gaps in knowledge and highlights weaknesses that require further research. Finally, a new developed methodology has been suggested as future work for triaging and prioritising ASD patients according to their severity levels by using decision-making techniques.
Topics: Artificial Intelligence; Autism Spectrum Disorder; Humans; Machine Learning; Telemedicine; Triage
PubMed: 35561591
DOI: 10.1016/j.compbiomed.2022.105553 -
Abdominal Radiology (New York) Nov 2020The aim of the study is to describe the imaging features, complications and differential diagnoses of abdominal cystic lymphangiomas (ACLs). (Review)
Review
PURPOSE
The aim of the study is to describe the imaging features, complications and differential diagnoses of abdominal cystic lymphangiomas (ACLs).
RESULTS
ACLs are benign lymphatic malformations that mainly arise in the subperitoneal space and the retroperitoneum. The typical presentation of an ACL is a multilocular lesion with homogenous serous content, presenting a thin wall and septa, usually free from adjacent organ compression. Atypical findings, including fat or hemorrhagic content, septal calcifications and unilocular presentation, are not uncommon. Rarely, ACLs can be revealed by acute complications, such as infection, hemorrhage, intussusception, complications with a twisting mechanism (including torsion around its own pedicle) or spontaneous rupture, which can be diagnosed by imaging. Ultrasonography and CT are the most useful modalities in emergency situations. MRI performs best in the noninvasive characterization of cystic lesions. ACLs should be differentiated from normal anatomic structures (e.g., cisterna chyli) or pitfalls (e.g., ascites, extrapancreatic necrosis, lymphocele) that can simulate ACLs. Among other primary peritoneal cystic lesions, benign cystic mesothelioma can be difficult to differentiate from ACL. Some neoplastic peritoneal lesions may have cystic components or content that looks like fluid on imaging (such as mucinous or myxoid content) and be misdiagnosed as ACL. Nodular or thick enhancement of the wall or septa should then be considered worrisome features and should not suggest ACL. ACLs mostly require a simple follow-up. If treatment is necessary, percutaneous sclerotherapy is a safe and effective alternative to surgery.
CONCLUSION
Imaging, especially MRI, allows the noninvasive diagnosis of ACL and helps to exclude potential malignant differential diagnoses.
Topics: Diagnosis, Differential; Humans; Lymphangioma, Cystic; Retroperitoneal Neoplasms; Ultrasonography
PubMed: 32296900
DOI: 10.1007/s00261-020-02525-3 -
Journal of Gastroenterology and... Jan 2021Very early-onset inflammatory bowel disease is defined as inflammatory bowel disease diagnosed before 6 years of age. Very early-onset inflammatory bowel disease has...
BACKGROUND AND AIM
Very early-onset inflammatory bowel disease is defined as inflammatory bowel disease diagnosed before 6 years of age. Very early-onset inflammatory bowel disease has various differential diagnoses, including primary immunodeficiency disorders, and is known to be resistant to conventional treatment. Therefore, global attention is required to manage this challenging condition. We conducted a retrospective epidemiological survey of the number of patients, final diagnosis, and examinations performed to diagnose very early-onset inflammatory bowel disease in Japan.
METHODS
A primary questionnaire about the number of very early-onset bowel disease cases and its diagnosis was administered to 630 pediatric facilities nationwide in Japan. A secondary survey about the examinations performed to achieve diagnosis was sent to the facilities that responded to the first survey.
RESULTS
The answering rate was 92.2% (581/630 facilities); 81 facilities had 225 very early-onset bowel disease patients undergoing their care during the past 68 months. Twenty-six patients (11.6%) were diagnosed with immunodeficiency-associated inflammatory bowel disease. The answering rate of the secondary survey was 70.4% (57/81 facilities). Colonoscopy, esophagogastroduodenoscopy, and small bowel imaging were performed for 99.4%, 67.5%, and 28.8% of patients, respectively. Genetic analysis was performed for 26.9% (43/160 patients) of patients, and 51.2% (22/43) of patients were diagnosed with immunodeficiency-associated inflammatory bowel disease.
CONCLUSIONS
Approximately 40 patients are diagnosed yearly in Japan. Imaging studies, especially for small bowel lesions, can be challenging for this unique group of patients. However, a comprehensive approach including immunological and genetic analyses appears useful for diagnosing immunodeficiency-associated inflammatory bowel disease.
Topics: Age of Onset; Child; Colonoscopy; Endoscopy, Digestive System; Female; Humans; Inflammatory Bowel Diseases; Intestine, Small; Japan; Male; Retrospective Studies; Surveys and Questionnaires
PubMed: 32530546
DOI: 10.1111/jgh.15146