-
Journal of Biomedical Optics Dec 2020Processing and diagnosing a set of 12 prostate biopsies using conventional histology methods typically take at least one day. A rapid and accurate process performed...
SIGNIFICANCE
Processing and diagnosing a set of 12 prostate biopsies using conventional histology methods typically take at least one day. A rapid and accurate process performed while the patient is still on-site could significantly improve the patient's quality of life.
AIM
We develop and assess the feasibility of a one-hour-to-diagnosis (1Hr2Dx) method for processing and providing a preliminary diagnosis of a set of 12 prostate biopsies.
APPROACH
We developed a fluorescence staining, optical clearing, and 3D open-top light-sheet microscopy workflow to enable 12 prostate needle core biopsies to be processed and diagnosed within an hour of receipt. We analyzed 44 biopsies by the 1Hr2Dx method, which does not consume tissue. The biopsies were then processed for routine, slide-based 2D histology. Three pathologists independently evaluated the 3D 1Hr2Dx and 2D slide-based datasets in a blinded, randomized fashion. Turnaround times were recorded, and the accuracy of our method was compared with gold-standard slide-based histology.
RESULTS
The average turnaround time for tissue processing, imaging, and diagnosis was 44.5 min. The sensitivity and specificity of 1Hr2Dx in diagnosing cancer were both >90 % .
CONCLUSIONS
The 1Hr2Dx method has the potential to improve patient care by providing an accurate preliminary diagnosis within an hour of biopsy.
Topics: Biopsy; Biopsy, Needle; Humans; Male; Microscopy; Prostate; Prostatic Neoplasms; Quality of Life
PubMed: 33325186
DOI: 10.1117/1.JBO.25.12.126502 -
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 -
JAMA Network Open Dec 2021The proposed MOLEM (Management of Lesion to Exclude Melanoma) schema is more clinically relevant than Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis...
IMPORTANCE
The proposed MOLEM (Management of Lesion to Exclude Melanoma) schema is more clinically relevant than Melanocytic Pathology Assessment Tool and Hierarchy for Diagnosis (MATH-Dx) for the management classification of melanocytic and nonmelanocytic lesions excised to exclude melanoma. A more standardized way of establishing diagnostic criteria will be crucial in the training of artificial intelligence (AI) algorithms.
OBJECTIVE
To examine pathologists' variability, reliability, and confidence in reporting melanocytic and nonmelanocytic lesions excised to exclude melanoma using the MOLEM schema in a population of higher-risk patients.
DESIGN, SETTING, AND PARTICIPANTS
This cohort study enrolled higher-risk patients referred to a primary care skin clinic in New South Wales, Australia, between April 2019 and December 2019. Baseline demographic characteristics including age, sex, and related clinical details (eg, history of melanoma) were collected. Patients with lesions suspicious for melanoma assessed by a primary care physician underwent clinical evaluation, dermoscopy imaging, and subsequent excision biopsy of the suspected lesion(s). A total of 217 lesions removed and prepared by conventional histologic method and stained with hematoxylin-eosin were reviewed by up to 9 independent pathologists for diagnosis using the MOLEM reporting schema. Pathologists evaluating for MOLEM schema were masked to the original histopathologic diagnosis.
MAIN OUTCOMES AND MEASURES
Characteristics of the lesions were described and the concordance of cases per MOLEM class was assessed. Interrater agreement and the agreement between pathologists' ratings and the majority MOLEM diagnosis were calculated by Gwet AC1 with quadratic weighting applied. The diagnostic confidence of pathologists was then assessed.
RESULTS
A total of 197 patients were included in the study (102 [51.8%] male; 95 [48.2%] female); mean (SD) age was 64.2 (15.8) years (range, 24-93 years). Overall, 217 index lesions were assessed with a total of 1516 histological diagnoses. Of 1516 diagnoses, 677 (44.7%) were classified as MOLEM class I; 120 (7.9%) as MOLEM class II; 564 (37.2%) as MOLEM class III; 114 (7.5%) as MOLEM class IV; and 55 (3.6%) as MOLEM class V. Concordance rates per MOLEM class were 88.6% (class I), 50.8% (class II), 76.2% (class III), 77.2% (class IV), and 74.2% (class V). The quadratic weighted interrater agreement was 91.3%, with a Gwet AC1 coefficient of 0.76 (95% CI, 0.72-0.81). The quadratic weighted agreement between pathologists' ratings and majority MOLEM was 94.7%, with a Gwet AC1 coefficient of 0.86 (95% CI, 0.84-0.88). The confidence in diagnosis data showed a relatively high level of confidence (between 1.0 and 1.5) when diagnosing classes I (mean [SD], 1.3 [0.3]), IV (1.3 [0.3]) and V (1.1 [0.1]); while classes II (1.8 [0.2]) and III (1.5 [0.4]) were diagnosed with a lower level of pathologist confidence (≥1.5). The quadratic weighted interrater confidence rating agreement was 95.2%, with a Gwet AC1 coefficient of 0.92 (95% CI, 0.90-0.94) for the 1314 confidence ratings collected. The confidence agreement for each MOLEM class was 95.0% (class I), 93.5% (class II), 95.3% (class III), 96.5% (class IV), and 97.5% (class V).
CONCLUSIONS AND RELEVANCE
The proposed MOLEM schema better reflects clinical practice than the MPATH-Dx schema in lesions excised to exclude melanoma by combining diagnoses with similar prognostic outcomes for melanocytic and nonmelanocytic lesions into standardized classification categories. Pathologists' level of confidence appeared to follow the MOLEM schema diagnostic concordance trend, ie, atypical naevi and melanoma in situ diagnoses were the least agreed upon and the most challenging for pathologists to confidently diagnose.
Topics: Adult; Aged; Aged, 80 and over; Artificial Intelligence; Biopsy; Cohort Studies; Confidence Intervals; Female; Humans; Male; Melanoma; Middle Aged; New South Wales; Pathologists; Reproducibility of Results; Skin Neoplasms; Young Adult
PubMed: 34889949
DOI: 10.1001/jamanetworkopen.2021.34614 -
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 -
Life (Basel, Switzerland) Oct 2022Mandibular fractures are the most common fractures in dentistry. Since diagnosing a mandibular fracture is difficult when only panoramic radiographic images are used,...
Mandibular fractures are the most common fractures in dentistry. Since diagnosing a mandibular fracture is difficult when only panoramic radiographic images are used, most doctors use cone beam computed tomography (CBCT) to identify the patient's fracture location. In this study, considering the diagnosis of mandibular fractures using the combined deep learning technique, YOLO and U-Net were used as auxiliary diagnostic methods to detect the location of mandibular fractures based on panoramic images without CBCT. In a previous study, mandibular fracture diagnosis was performed using YOLO learning; in the detection performance result of the YOLOv4-based mandibular fracture diagnosis module, the precision score was approximately 97%, indicating that there was almost no misdiagnosis. In particular, fractures in the symphysis, body, angle, and ramus tend to be distributed in the middle of the mandible. Owing to the irregular fracture types and overlapping location information, the recall score was approximately 79%, which increased the detection of undiagnosed fractures. In many cases, fractures that are clearly visible to the human eye cannot be grasped. To overcome these shortcomings, the number of undiagnosed fractures can be reduced using a combination of the U-Net and YOLOv4 learning modules. U-Net is advantageous for the segmentation of fractures spread over a wide area because it performs semantic segmentation. Consequently, the undiagnosed case in the middle of the mandible, where YOLO was weak, was somewhat supplemented by the U-Net module. The precision score of the combined module was 95%, similar to that of the previous method, and the recall score improved to 87%, as the number of undiagnosed cases was reduced. Through this study, the performance of a deep learning method that can be used for the diagnosis of the mandibular bone has been improved, and it is anticipated that as an auxiliary diagnostic inspection device, it will assist dentists in making diagnoses.
PubMed: 36362866
DOI: 10.3390/life12111711 -
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 -
Frontiers in Endocrinology 2023The aim of this study was to improve the diagnostic performance of nuclear medicine physicians using a deep convolutional neural network (DCNN) model and validate the...
OBJECTIVES
The aim of this study was to improve the diagnostic performance of nuclear medicine physicians using a deep convolutional neural network (DCNN) model and validate the results with two multicenter datasets for thyroid disease by analyzing clinical single-photon emission computed tomography (SPECT) image data.
METHODS
In this multicenter retrospective study, 3194 SPECT thyroid images were collected for model training (n=2067), internal validation (n=514) and external validation (n=613). First, four pretrained DCNN models (AlexNet, ShuffleNetV2, MobileNetV3 and ResNet-34) for were tested multiple medical image classification of thyroid disease types (i.e., Graves' disease, subacute thyroiditis, thyroid tumor and normal thyroid). The best performing model was then subjected to fivefold cross-validation to further assess its performance, and the diagnostic performance of this model was compared with that of junior and senior nuclear medicine physicians. Finally, class-specific attentional regions were visualized with attention heatmaps using gradient-weighted class activation mapping.
RESULTS
Each of the four pretrained neural networks attained an overall accuracy of more than 0.85 for the classification of SPECT thyroid images. The improved ResNet-34 model performed best, with an accuracy of 0.944. For the internal validation set, the ResNet-34 model showed higher accuracy ( < 0.001) when compared to that of the senior nuclear medicine physician, with an improvement of nearly 10%. Our model achieved an overall accuracy of 0.931 for the external dataset, a significantly higher accuracy than that of the senior physician (0.931 vs. 0.868, < 0.001).
CONCLUSION
The DCNN-based model performed well in terms of diagnosing thyroid scintillation images. The DCNN model showed higher sensitivity and greater specificity in identifying Graves' disease, subacute thyroiditis, and thyroid tumors compared to those of nuclear medicine physicians, illustrating the feasibility of deep learning models to improve the diagnostic efficiency for assisting clinicians.
Topics: Humans; Thyroiditis, Subacute; Retrospective Studies; Thyroid Diseases; Thyroid Neoplasms; Graves Disease; Neural Networks, Computer; Tomography, Emission-Computed, Single-Photon
PubMed: 37635985
DOI: 10.3389/fendo.2023.1224191 -
Neural network methods for diagnosing patient conditions from cardiopulmonary exercise testing data.BioData Mining Aug 2022Cardiopulmonary exercise testing (CPET) provides a reliable and reproducible approach to measuring fitness in patients and diagnosing their health problems. However, the...
BACKGROUND
Cardiopulmonary exercise testing (CPET) provides a reliable and reproducible approach to measuring fitness in patients and diagnosing their health problems. However, the data from CPET consist of multiple time series that require training to interpret. Part of this training teaches the use of flow charts or nested decision trees to interpret the CPET results. This paper investigates the use of two machine learning techniques using neural networks to predict patient health conditions with CPET data in contrast to flow charts. The data for this investigation comes from a small sample of patients with known health problems and who had CPET results. The small size of the sample data also allows us to investigate the use and performance of deep learning neural networks on health care problems with limited amounts of labeled training and testing data.
METHODS
This paper compares the current standard for interpreting and classifying CPET data, flowcharts, to neural network techniques, autoencoders and convolutional neural networks (CNN). The study also investigated the performance of principal component analysis (PCA) with logistic regression to provide an additional baseline of comparison to the neural network techniques.
RESULTS
The patients in the sample had two primary diagnoses: heart failure and metabolic syndrome. All model-based testing was done with 5-fold cross-validation and metrics of precision, recall, F1 score, and accuracy. As a baseline for comparison to our models, the highest performing flow chart method achieved an accuracy of 77%. Both PCA regression and CNN achieved an average accuracy of 90% and outperformed the flow chart methods on all metrics. The autoencoder with logistic regression performed the best on each of the metrics and had an average accuracy of 94%.
CONCLUSIONS
This study suggests that machine learning and neural network techniques, in particular, can provide higher levels of accuracy with CPET data than traditional flowchart methods. Further, the CNN performed well with a small data set showing that these techniques can be designed to perform well on small data problems that are often found in health care and the life sciences. Further testing with larger data sets is needed to continue evaluating the use of machine learning to interpret CPET data.
PubMed: 35964102
DOI: 10.1186/s13040-022-00299-6 -
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