-
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 -
Journal of Anaesthesiology, Clinical... 2021Diagnosing accurate placement of the tip of the endotracheal tube is crucial in pediatric practice. This study was conducted to find out the efficacy of five clinical...
BACKGROUND AND AIMS
Diagnosing accurate placement of the tip of the endotracheal tube is crucial in pediatric practice. This study was conducted to find out the efficacy of five clinical methods to ascertain the tube position by a resident anesthesiologist.
MATERIAL AND METHODS
This was a randomized crossover study conducted in a research institute. Fifty pediatric patients were enrolled. All patients were randomly allocated to tracheal (group T) or bronchial group (group B). The five clinical methods which were evaluated include the auscultation, observation of chest movements, bag compliance, tube depth, and capnography. In group T, the tube was placed in the trachea and later positioned in bronchus (assisted by fiberoptic bronchoscopy). The vice versa was done in group B. In each position, a single test followed by all tests was performed and after the change of position, the same single test followed by all tests was performed. Correct and incorrect diagnoses by tests in detecting tube positions were made and their sensitivity and odds ratio were estimated.
RESULTS
The tube depth and combination of all tests detected endobronchial intubation with a sensitivity of 88% and 97%, respectively, which is more than that of auscultation (70%) and observation (55%). Evaluation of the difference in agreement level of tube depth to detect tube-position showed the odds ratio of 2.28 (0.17-30.95) for detecting endobronchial intubation.
CONCLUSION
We observed that the tube-depth was better than the other individual tests in diagnosing endobronchial intubation in pediatric patients. However, its efficacy is lesser than that of performing all clinical tests together.
PubMed: 34759557
DOI: 10.4103/joacp.JOACP_272_19 -
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 -
The Journal of International Medical... Jan 2021To construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy.
OBJECTIVE
To construct deep learning (DL) models to improve the accuracy and efficiency of thyroid disease diagnosis by thyroid scintigraphy.
METHODS
We constructed DL models with AlexNet, VGGNet, and ResNet. The models were trained separately with transfer learning. We measured each model's performance with six indicators: recall, precision, negative predictive value (NPV), specificity, accuracy, and F1-score. We also compared the diagnostic performances of first- and third-year nuclear medicine (NM) residents with assistance from the best-performing DL-based model. The Kappa coefficient and average classification time of each model were compared with those of two NM residents.
RESULTS
The recall, precision, NPV, specificity, accuracy, and F1-score of the three models ranged from 73.33% to 97.00%. The Kappa coefficient of all three models was >0.710. All models performed better than the first-year NM resident but not as well as the third-year NM resident in terms of diagnostic ability. However, the ResNet model provided "diagnostic assistance" to the NM residents. The models provided results at speeds 400 to 600 times faster than the NM residents.
CONCLUSION
DL-based models perform well in diagnostic assessment by thyroid scintigraphy. These models may serve as tools for NM residents in the diagnosis of Graves' disease and subacute thyroiditis.
Topics: Deep Learning; Graves Disease; Humans; Radionuclide Imaging; Thyroid Diseases
PubMed: 33445994
DOI: 10.1177/0300060520982842 -
International Journal of Pediatric... Feb 2022This study aims to investigate the inter-rater reliability and agreement of the diagnosis of otitis media with effusion, acute otitis media, and no effusion cases based...
OBJECTIVES
This study aims to investigate the inter-rater reliability and agreement of the diagnosis of otitis media with effusion, acute otitis media, and no effusion cases based on an otoscopy image and in some cases an additional wideband tympanometry measurement of the patient.
METHODS
1409 cases were examined and diagnosed by an otolaryngologist in the clinic, and otoscopy examination and wideband tympanometry (WBT) measurement were conducted. Afterwards, four otolaryngologists (Ear, Nose, and Throat doctors, ENTs), who did not perform the acute examination of the patients, evaluated the otoscopy images and WBT measurements results for diagnosis (acute otitis media, otitis media with effusion, or no effusion). They also specified their diagnostic certainty for each case, and reported whether they used the image, wideband tympanometry, or both, for diagnosis.
RESULTS
All four ENTs agreed on the diagnosis in 57% of the cases, with a pairwise agreement of 74%, and a Light's Kappa of 0.58. There are, however, large differences in agreement and certainty between the three diagnoses. Acute otitis media yields the highest agreement (77% between all four ENTs) and certainty (0.90), while no effusion shows much lower agreement and certainty (34% and 0.58, respectively). There is a positive correlation between certainty and agreement between the ENTs across all cases, and both certainty and agreement increase for cases where a WBT measurement is shown in addition to the otoscopy image.
CONCLUSIONS
The inter-rater reliability between four ENTs was high when diagnosing acute otitis media and lower when diagnosing otitis media with effusion. However, WBT can add valuable information to get closer to the ground-truth diagnosis without myringotomy. Furthermore, the diagnostic certainty increases when the WBT is examined together with the otoscopy image.
Topics: Acoustic Impedance Tests; Humans; Infant; Otitis Media; Otitis Media with Effusion; Otoscopes; Otoscopy; Reproducibility of Results
PubMed: 35033784
DOI: 10.1016/j.ijporl.2021.111034 -
Cancer Cytopathology Jun 2022The American Thyroid Association recommends either repeat fine-needle aspiration biopsy (FNAB) or molecular testing (eg, ThyroSeq) of Bethesda category III (atypia of...
BACKGROUND
The American Thyroid Association recommends either repeat fine-needle aspiration biopsy (FNAB) or molecular testing (eg, ThyroSeq) of Bethesda category III (atypia of undetermined significance/follicular lesion of undetermined significance [AUS/FLUS]) nodules to provide further risk stratification. How a testing algorithm that uses ancillary molecular tests performs as a reflex test for repeat sampling of indeterminant nodules remains unclear.
METHODS
Thyroid FNABs performed over a 24-month period that received a diagnosis of AUS/FLUS and underwent subsequent FNAB were analyzed.
RESULTS
In total, 187 patients were identified who received an FNAB diagnosis of AUS/FLUS and had repeat sampling. Of these patients, 64% received a subsequent indeterminant diagnosis on repeat biopsy: 7 (3.7%) repeat biopsies were diagnosed as nondiagnostic/unsatisfactory, 104 (55.6%) were diagnosed as AUS/FLUS, and 8 (4.3%) were diagnosed as follicular neoplasm/suspicious for follicular neoplasm. Of the repeat biopsied nodules, 63% underwent subsequent testing with ThyroSeq version 3. The diagnostic performance was calculated using only surgically confirmed nodules (sensitivity, 100%; specificity, 30%; positive predictive value, 41%; negative predictive value, 100%) and by assigning nonresected nodules with negative ThyroSeq or benign cytology results as benign (sensitivity, 100%; specificity, 88%; positive predictive value, 41%; negative predictive value, 100%).
CONCLUSIONS
In the majority of patients, repeat FNAB for AUS/FLUS did not preclude subsequent molecular ancillary testing because of the high rate of indeterminant results on repeat biopsy. The diagnostic performance of the testing algorithm reported here was very similar to other reports using either repeat biopsy or molecular testing alone. Ultimately, the algorithm of performing molecular testing on repeat indeterminant nodules increased the number of biopsies performed and lengthened the time to definitive risk stratification without a disproportionate decrease in the use of molecular testing or an appreciable improvement in diagnostic performance.
Topics: Adenocarcinoma, Follicular; Biopsy, Fine-Needle; Genomics; Humans; Reflex; Retrospective Studies; Thyroid Neoplasms; Thyroid Nodule
PubMed: 35045202
DOI: 10.1002/cncy.22552 -
Abdominal Radiology (New York) Nov 2022To compare the diagnostic performance of T1 mapping and MR elastography (MRE) for staging of hepatic fibrosis and grading inflammation with histopathology as standard of...
PURPOSE
To compare the diagnostic performance of T1 mapping and MR elastography (MRE) for staging of hepatic fibrosis and grading inflammation with histopathology as standard of reference.
METHODS
68 patients with various liver diseases undergoing liver biopsy for suspected fibrosis or with an established diagnosis of cirrhosis prospectively underwent look-locker inversion recovery T1 mapping and MRE. T1 relaxation time and liver stiffness (LS) were measured by two readers. Hepatic fibrosis and inflammation were histopathologically staged according to a standardized fibrosis (F0-F4) and inflammation (A0-A2) score. For statistical analysis, independent t test, and Mann-Whitney U test and ROC analysis were performed, the latter to determine the performance of T1 mapping and MRE for fibrosis staging and inflammation grading, as compared to histopathology.
RESULTS
Histopathological analysis diagnosed 9 patients with F0 (13.2%), 21 with F1 (30.9%), 11 with F2 (16.2%), 10 with F3 (14.7%), and 17 with F4 (25.0%). Both T1 mapping and MRE showed significantly higher values for patients with significant fibrosis (F0-1 vs. F2-4; T1 mapping p < 0.0001, MRE p < 0.0001) as well as for patients with severe fibrosis or cirrhosis (F0-2 vs. F3-4; T1 mapping p < 0.0001, MRE p < 0.0001). T1 values and MRE LS were significantly higher in patients with inflammation (A0 vs. A1-2, both p = 0.01). T1 mapping showed a tendency toward lower diagnostic performance without statistical significance for significant fibrosis (F2-4) (AUC 0.79 vs. 0.91, p = 0.06) and with a significant difference compared to MRE for severe fibrosis (F3-4) (AUC 0.79 vs. 0.94, p = 0.03). For both T1 mapping and MRE, diagnostic performance for diagnosing hepatic inflammation (A1-2) was low (AUC 0.72 vs. 0.71, respectively).
CONCLUSION
T1 mapping is able to diagnose hepatic fibrosis, however, with a tendency toward lower diagnostic performance compared to MRE and thus may be used as an alternative to MRE for diagnosing hepatic fibrosis, whenever MRE is not available or likely to fail due to intrinsic factors of the patient. Both T1 mapping and MRE are probably not sufficient as standalone methods to diagnose hepatic inflammation with relatively low diagnostic accuracy.
Topics: Elasticity Imaging Techniques; Fibrosis; Humans; Inflammation; Liver; Liver Cirrhosis; Magnetic Resonance Imaging; Reference Standards
PubMed: 36038643
DOI: 10.1007/s00261-022-03647-6 -
EUS - Fine- Needle Aspiration Biopsy (FNAB) in the Diagnosis of Pancreatic Adenocarcinoma: A Review.Romanian Journal of Internal Medicine =... 2016Solid masses of the pancreas represent a variety of benign and malignant neoplasms of the exocrine and endocrine tissues of the pancreas. A tissue diagnosis is often... (Review)
Review
Solid masses of the pancreas represent a variety of benign and malignant neoplasms of the exocrine and endocrine tissues of the pancreas. A tissue diagnosis is often required to direct therapy in the face of uncertain diagnosis or if the patient is not a surgical candidate either due to advanced disease or comorbidities. Endoscopic ultrasound (EUS) is a relatively new technology that employs endoscopy and high-frequency ultrasound (US). EUS involves imaging of the pancreatic head and the uncinate from the duodenum and imaging of the body and tail from the stomach. It has been shown to be a highly sensitive method for the detection of pancreatic masses. It is superior to extracorporeal US and computed tomographic (CT) scans, especially when the pancreatic tumor is smaller than 2-3 cm. Although EUS is highly sensitive in detecting pancreatic solid masses, its ability to differentiate between inflammatory masses and malignant disease is limited. Endoscopic retrograde cholangiopancreatography (ERCP) brushing, CT-guided biopsies, and transabdominal ultrasound (US) have been the standard nonsurgical methods for obtaining a tissue diagnosis of pancreatic lesions, but a substantial false-negative rate has been reported. Transabdominal US-guided fine-needle aspiration biopsy (US-FNAB) has been used for tissue diagnosis in patients with suspected pancreatic carcinoma. It has been shown to be highly specific, with no false-positive diagnoses. With the advent of curvilinear echoendoscopes, transgastric and transduodenal EUS-FNAB of the pancreas have become a reality EUS with FNAB has revolutionized the ability to diagnose and stage cancers of the gastrointestinal tract and assess the pancreas. Gastrointestinal cancers can be looked at with EUS and their depth of penetration into the intestinal wall can be determined. Any suspicious appearing lymph nodes can be biopsied using EUS/FNAB. The pancreas is another organ that is well visualized with EUS. Abnormalities such as tumors and cysts of the pancreas can be carefully evaluated using EUS and then biopsied with FNAB. There are many new applications of EUS using FNAB. Researchers are looking to deliver chemotherapeutics into small pancreatic cancers and cysts. Nerve blocks using EUS/FNAB to inject numbing medicines into the celiac ganglia, a major nerve cluster, are now routinely performed in patients with pain due to pancreatic cancer. The aim of this study is to perform a review of the literature regarding the usefulness of EUS/FNAB in the diagnosis of pancreatic adenocarcinoma.
Topics: Biopsy, Fine-Needle; Carcinoma, Pancreatic Ductal; Endoscopic Ultrasound-Guided Fine Needle Aspiration; Humans; Image-Guided Biopsy; Lymph Nodes; Pancreatic Neoplasms
PubMed: 27141567
DOI: 10.1515/rjim-2016-0002