Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 126
Filter
Add filters

Document Type
Year range
1.
PLoS One ; 16(12): e0261307, 2021.
Article in English | MEDLINE | ID: covidwho-1598199

ABSTRACT

Medical images commonly exhibit multiple abnormalities. Predicting them requires multi-class classifiers whose training and desired reliable performance can be affected by a combination of factors, such as, dataset size, data source, distribution, and the loss function used to train deep neural networks. Currently, the cross-entropy loss remains the de-facto loss function for training deep learning classifiers. This loss function, however, asserts equal learning from all classes, leading to a bias toward the majority class. Although the choice of the loss function impacts model performance, to the best of our knowledge, we observed that no literature exists that performs a comprehensive analysis and selection of an appropriate loss function toward the classification task under study. In this work, we benchmark various state-of-the-art loss functions, critically analyze model performance, and propose improved loss functions for a multi-class classification task. We select a pediatric chest X-ray (CXR) dataset that includes images with no abnormality (normal), and those exhibiting manifestations consistent with bacterial and viral pneumonia. We construct prediction-level and model-level ensembles to improve classification performance. Our results show that compared to the individual models and the state-of-the-art literature, the weighted averaging of the predictions for top-3 and top-5 model-level ensembles delivered significantly superior classification performance (p < 0.05) in terms of MCC (0.9068, 95% confidence interval (0.8839, 0.9297)) metric. Finally, we performed localization studies to interpret model behavior and confirm that the individual models and ensembles learned task-specific features and highlighted disease-specific regions of interest. The code is available at https://github.com/sivaramakrishnan-rajaraman/multiloss_ensemble_models.


Subject(s)
Algorithms , Diagnostic Imaging , Image Processing, Computer-Assisted/classification , Area Under Curve , Entropy , Humans , Lung/diagnostic imaging , ROC Curve , Thorax/diagnostic imaging , X-Rays
2.
PLoS One ; 16(3): e0247686, 2021.
Article in English | MEDLINE | ID: covidwho-1574773

ABSTRACT

OBJECTIVES: The aim of this study was to investigate possible patterns of demand for chest imaging during the first wave of the SARS-CoV-2 pandemic and derive a decision aid for the allocation of resources in future pandemic challenges. MATERIALS AND METHODS: Time data of requests for patients with suspected or confirmed coronavirus disease 2019 (COVID-19) lung disease were analyzed between February 27th and May 27th 2020. A multinomial logistic regression model was used to evaluate differences in the number of requests between 3 time intervals (I1: 6am - 2pm, I2: 2pm - 10pm, I3: 10pm - 6am). A cosinor model was applied to investigate the demand per hour. Requests per day were compared to the number of regional COVID-19 cases. RESULTS: 551 COVID-19 related chest imagings (32.8% outpatients, 67.2% in-patients) of 243 patients were conducted (33.3% female, 66.7% male, mean age 60 ± 17 years). Most exams for outpatients were required during I2 (I1 vs. I2: odds ratio (OR) = 0.73, 95% confidence interval (CI) 0.62-0.86, p = 0.01; I2 vs. I3: OR = 1.24, 95% CI 1.04-1.48, p = 0.03) with an acrophase at 7:29 pm. Requests for in-patients decreased from I1 to I3 (I1 vs. I2: OR = 1.24, 95% CI 1.09-1.41, p = 0.01; I2 vs. I3: OR = 1.16, 95% CI 1.05-1.28, p = 0.01) with an acrophase at 12:51 pm. The number of requests per day for outpatients developed similarly to regional cases while demand for in-patients increased later and persisted longer. CONCLUSIONS: The demand for COVID-19 related chest imaging displayed distinct distribution patterns depending on the sector of patient care and point of time during the SARS-CoV-2 pandemic. These patterns should be considered in the allocation of resources in future pandemic challenges with similar disease characteristics.


Subject(s)
COVID-19/diagnostic imaging , Diagnostic Imaging/trends , Thorax/diagnostic imaging , Adult , Aged , COVID-19/epidemiology , Diagnostic Tests, Routine/trends , Female , Humans , Male , Middle Aged , Models, Theoretical , Pandemics , Pilot Projects , SARS-CoV-2/pathogenicity , Thorax/virology
3.
J Med Internet Res ; 23(2): e24266, 2021 02 22.
Article in English | MEDLINE | ID: covidwho-1574391

ABSTRACT

BACKGROUND: Transition to digital pathology usually takes months or years to be completed. We were familiarizing ourselves with digital pathology solutions at the time when the COVID-19 outbreak forced us to embark on an abrupt transition to digital pathology. OBJECTIVE: The aim of this study was to quantitatively describe how the abrupt transition to digital pathology might affect the quality of diagnoses, model possible causes by probabilistic modeling, and qualitatively gauge the perception of this abrupt transition. METHODS: A total of 17 pathologists and residents participated in this study; these participants reviewed 25 additional test cases from the archives and completed a final psychologic survey. For each case, participants performed several different diagnostic tasks, and their results were recorded and compared with the original diagnoses performed using the gold standard method (ie, conventional microscopy). We performed Bayesian data analysis with probabilistic modeling. RESULTS: The overall analysis, comprising 1345 different items, resulted in a 9% (117/1345) error rate in using digital slides. The task of differentiating a neoplastic process from a nonneoplastic one accounted for an error rate of 10.7% (42/392), whereas the distinction of a malignant process from a benign one accounted for an error rate of 4.2% (11/258). Apart from residents, senior pathologists generated most discrepancies (7.9%, 13/164). Our model showed that these differences among career levels persisted even after adjusting for other factors. CONCLUSIONS: Our findings are in line with previous findings, emphasizing that the duration of transition (ie, lengthy or abrupt) might not influence the diagnostic performance. Moreover, our findings highlight that senior pathologists may be limited by a digital gap, which may negatively affect their performance with digital pathology. These results can guide the process of digital transition in the field of pathology.


Subject(s)
COVID-19/epidemiology , Clinical Competence , Diagnostic Imaging/methods , Diagnostic Imaging/standards , Image Processing, Computer-Assisted/methods , Image Processing, Computer-Assisted/standards , Pathology, Clinical/methods , Pathology, Clinical/standards , Bayes Theorem , Disease Outbreaks , Humans , Internship and Residency/methods , Internship and Residency/standards , Italy/epidemiology , Microscopy , Surveys and Questionnaires
4.
Am J Phys Med Rehabil ; 100(10): 919-939, 2021 10 01.
Article in English | MEDLINE | ID: covidwho-1480014

ABSTRACT

ABSTRACT: The objective of this review was to analyze the existing data on acute inflammatory myelopathies associated with coronavirus disease 2019 infection, which were reported globally in 2020. PubMed, CENTRAL, MEDLINE, and online publication databases were searched. Thirty-three acute inflammatory myelopathy cases (among them, seven cases had associated brain lesions) associated with coronavirus disease 2019 infection were reported. Demyelinating change was seen in cervical and thoracic regions (27.3% each, separately). Simultaneous involvement of both regions, cervical and thoracic, was seen in 45.4% of the patients. Most acute inflammatory myelopathy disorders reported sensory motor and bowel bladder dysfunctions. On cerebrospinal fluid analysis, pleocytosis and increased protein were reported in 56.7% and 76.7% of the patients, respectively. Cerebrospinal fluid severe acute respiratory syndrome coronavirus 2 reverse transcriptase-polymerase chain reaction was positive in five patients. On T2-weighted imaging, longitudinally extensive transverse myelitis and short-segment demyelinating lesions were reported in 76% and 21%, respectively. Among the patients with longitudinally extensive transverse myelitis, 61% reported "moderate to significant" improvement and 26% demonstrated "no improvement" in the motor function of lower limbs. Demyelinating changes in the entire spinal cord were observed in three patients. Most of the patients with acute inflammatory myelopathy (including brain lesions) were treated with methylprednisolone (81.8%) and plasma-exchange therapy (42.4%). An early treatment, especially with intravenous methylprednisolone with or without immunoglobulin and plasma-exchange therapy, helped improve motor recovery in the patients with acute inflammatory myelopathy associated with coronavirus disease 2019.


Subject(s)
COVID-19/complications , Spinal Cord Diseases/diagnosis , Spinal Cord Diseases/virology , Diagnostic Imaging , Glucocorticoids/therapeutic use , Humans , Methylprednisolone/therapeutic use , Pandemics , SARS-CoV-2 , Spinal Cord Diseases/drug therapy
5.
Int J Med Inform ; 156: 104599, 2021 12.
Article in English | MEDLINE | ID: covidwho-1440101

ABSTRACT

BACKGROUND: An image sharing framework is important to support downstream data analysis especially for pandemics like Coronavirus Disease 2019 (COVID-19). Current centralized image sharing frameworks become dysfunctional if any part of the framework fails. Existing decentralized image sharing frameworks do not store the images on the blockchain, thus the data themselves are not highly available, immutable, and provable. Meanwhile, storing images on the blockchain provides availability/immutability/provenance to the images, yet produces challenges such as large-image handling, high viewing latency while viewing images, and software inconsistency while storing/loading images. OBJECTIVE: This study aims to store chest x-ray images using a blockchain-based framework to handle large images, improve viewing latency, and enhance software consistency. BASIC PROCEDURES: We developed a splitting and merging function to handle large images, a feature that allows previewing an image earlier to improve viewing latency, and a smart contract to enhance software consistency. We used 920 publicly available images to evaluate the storing and loading methods through time measurements. MAIN FINDINGS: The blockchain network successfully shares large images up to 18 MB and supports smart contracts to provide code immutability, availability, and provenance. Applying the preview feature successfully shared images 93% faster than sharing images without the preview feature. PRINCIPAL CONCLUSIONS: The findings of this study can guide future studies to generalize our framework to other forms of data to improve sharing and interoperability.


Subject(s)
Blockchain , Diagnostic Imaging , Humans , Software , X-Rays
6.
Med Biol Eng Comput ; 59(10): 1993-2017, 2021 Oct.
Article in English | MEDLINE | ID: covidwho-1427400

ABSTRACT

Emerging medical imaging applications in healthcare, the number and volume of medical images is growing dramatically. Information needs of users in such circumstances, either for clinical or research activities, make the role of powerful medical image search engines more significant. In this paper, a text-based multi-dimensional medical image indexing technique is proposed in which correlation of the features-usages (according to the user's queries) is considered to provide an off-the content indexing while taking users' interestingness into account. Assuming that each medical image has some extracted features (e.g., based on the DICOM standard), correlations of the features are discovered by performing data mining techniques (i.e., quantitative association pattern discovery), on the history of users' queries as a data set. Then, based on the pairwise correlation of the features of medical images (a.k.a. Affinity), set of the all features is fragmented into subsets (using method like the vertical fragmentation of the tables in distribution of relational DBs). After that, each of these subsets of the features turn into a hierarchy of the features (by applying a hierarchical clustering algorithm on that subset), subsequently all of these distinct hierarchies together make a multi-dimensional structure of the features of medical images, which is in fact the proposed text-based (feature-based) multi-dimensional index structure. Constructing and using such text-based multi-dimensional index structure via its specific required operations, medical image retrieval process would be improved in the underlying medical image search engine. Generally, an indexing technique is to provide a logical representation of documents in order to optimize the retrieval process. The proposed indexing technique is designed such that can improve retrieval of medical images in a medical image search engine in terms of its effectiveness and efficiency. Considering correlation of the features of the image would semantically improve precision (effectiveness) of the retrieval process, while traversing them through the hierarchy in one dimension would try to optimize (i.e., minimize) the resources to have a better efficiency. The proposed text-based multi-dimensional indexing technique is implemented using the open source search engine Lucene, and compared with the built-in indexing technique available in the Lucene search engine, and also with the Terrier platform (available for the benchmarking of information retrieval systems) and other the most related indexing techniques. Evaluation results of memory usage and time complexity analysis, beside the experimental evaluations efficiency and effectiveness measures show that the proposed multi-dimensional indexing technique significantly improves both efficiency and effectiveness for a medical image search engine.


Subject(s)
Algorithms , Data Mining , Diagnostic Imaging
7.
AJR Am J Roentgenol ; 217(3): 527-528, 2021 09.
Article in English | MEDLINE | ID: covidwho-1403390
8.
Am J Otolaryngol ; 43(1): 103220, 2022.
Article in English | MEDLINE | ID: covidwho-1401162

ABSTRACT

BACKGROUND: It is an incontrovertible fact that the Rhino Orbital Cerebral Mucormycosis (ROCM) upsurge is being seen in the context of COVID-19 in India. Briefly presented is evidence that in patients with uncontrolled diabetes, a dysfunctional immune system due to SARS-COV-2 and injudicious use of corticosteroids may be largely responsible for this malady. OBJECTIVE: To find the possible impact of COVID 19 infection and various co-morbidities on occurrence of ROCM and demonstrate the outcome based on medical and surgical interventions. METHODOLOGY: Prospective longitudinal study included patients diagnosed with acute invasive fungal rhinosinusitis after a recent COVID-19 infection. Diagnostic nasal endoscopy (DNE) was performed on each patient and swabs were taken and sent for fungal KOH staining and microscopy. Medical management included Injection Liposomal Amphotericin B, Posaconazole and Voriconazole. Surgical treatment was restricted to patients with RT PCR negative results for COVID-19. Endoscopic, open, and combined approaches were utilized to eradicate infection. Follow-up for survived patients was maintained regularly for the first postoperative month. RESULTS: Out of total 131 patients, 111 patients had prior history of SARS COVID 19 infection, confirmed with a positive RT-PCR report and the rest 20 patients had no such history. Steroids were received as a part of treatment in 67 patients infected with COVID 19. Among 131 patients, 124 recovered, 1 worsened and 6 died. Out of 101 known diabetics, 98 recovered and 3 had fatal outcomes. 7 patients with previous history of COVID infection did not have any evidence of Diabetes mellitus, steroid intake or any other comorbidity. CONCLUSION: It can be concluded that ROCM upsurge seen in the context of COVID-19 in India was mainly seen in patients with uncontrolled diabetes, a dysfunctional immune system due to SARS-COV-2 infection and injudicious use of corticosteroids.


Subject(s)
COVID-19/immunology , Mucormycosis/immunology , Adrenal Cortex Hormones/adverse effects , Antifungal Agents/therapeutic use , COVID-19/epidemiology , Diabetes Complications/immunology , Diagnostic Imaging , Endoscopy , Female , Humans , India/epidemiology , Longitudinal Studies , Male , Middle Aged , Mucormycosis/drug therapy , Mucormycosis/epidemiology , Pandemics , Prospective Studies , Risk Factors , SARS-CoV-2
9.
J Appl Clin Med Phys ; 21(12): 325-328, 2020 Dec.
Article in English | MEDLINE | ID: covidwho-1384081

ABSTRACT

PURPOSE: To investigate the feasibility and practicality of ultraviolet (UV) germicidal irradiation of the inner bore of a computed tomography (CT) gantry as a means of viral decontamination. METHOD: A UV lamp (PADNUT 38 W, 253 nm UV-C light tube) and UV-C dosimeter (GENERAL UV-C Digital Light Meter No. UV512C) were used to measure irradiance throughout the inner bore of a CT scanner gantry. Irradiance (units µW/cm2 ) was related to the time required to achieve 6-log viral kill (10-6 survival fraction). RESULTS: A warm-up time of ~120 s was required for the lamp to reach stable irradiance. Irradiance at the scan plane (z = 0 cm) of the CT scanner was 580.9 µW/cm2 , reducing to ~350 µW/cm2 at z = ±20 cm toward the front or back of the gantry. The angular distribution of irradiation was uniform within 10% coefficient of variation. A conservative estimate suggests at least 6-log kill (survival fraction ≤ 10-6 ) of viral RNA within ±20 cm of the scan plane with an irradiation time of 120 s from cold start. More conservatively, running the lamp for 180 s (3 min) or 300 s (5 min) from cold start is estimated to yield survival fraction <<10-7 survival fraction within ±20 cm of the scan plane. CONCLUSION: Ultraviolet irradiation of the inner bore of the CT gantry can be achieved with a simple UV-C lamp attached to the CT couch. Such practice could augment manual wipe-down procedures, improve safety for CT technologists or housekeeping staff, and could potentially reduce turnover time between scanning sessions.


Subject(s)
COVID-19/prevention & control , Disinfection/methods , Infection Control/methods , Tomography Scanners, X-Ray Computed , Tomography, X-Ray Computed/instrumentation , Calibration , Decontamination/instrumentation , Diagnostic Imaging/methods , Infection Control/instrumentation , RNA, Viral/radiation effects , Radiometry , SARS-CoV-2/radiation effects , Ultraviolet Rays
10.
Br J Radiol ; 94(1127): 20210753, 2021 Nov 01.
Article in English | MEDLINE | ID: covidwho-1379813

ABSTRACT

Adrenal hemorrhage (AH) is a rare condition. It can be traumatic or non-traumatic. Most common causes are septicemia, coagulopathy or bleeding diathesis, and underlying neoplasms. Other reported less common causes of AH are COVID-19 and neonatal stress. Clinical diagnosis of AH is challenging due to its non-specific presentation and occurrence in the setting of acute medical illness. Therefore, most cases are diagnosed incidentally on imaging. Having high clinical suspicion in the proper clinical setting for AH is crucial to avoid life-threatening adrenal insufficiency that occurs in 16-50% of patients with bilateral AH. We discuss the clinical situations that predispose to AH, review the imaging features on different imaging modalities, highlight a variety of clinical cases, imaging features that should be concerning for an underlying neoplasm, and outline the potential role of interventional radiology in management of AH.


Subject(s)
Adrenal Gland Diseases/diagnostic imaging , Diagnostic Imaging/methods , Hemorrhage/diagnostic imaging , Adrenal Gland Diseases/physiopathology , Adrenal Glands/diagnostic imaging , Adrenal Glands/physiopathology , Hemorrhage/physiopathology , Humans
11.
Acad Med ; 96(7): 954-957, 2021 07 01.
Article in English | MEDLINE | ID: covidwho-1364834

ABSTRACT

Machine learning (ML) algorithms are powerful prediction tools with immense potential in the clinical setting. There are a number of existing clinical tools that use ML, and many more are in development. Physicians are important stakeholders in the health care system, but most are not equipped to make informed decisions regarding deployment and application of ML technologies in patient care. It is of paramount importance that ML concepts are integrated into medical curricula to position physicians to become informed consumers of the emerging tools employing ML. This paradigm shift is similar to the evidence-based medicine (EBM) movement of the 1990s. At that time, EBM was a novel concept; now, EBM is considered an essential component of medical curricula and critical to the provision of high-quality patient care. ML has the potential to have a similar, if not greater, impact on the practice of medicine. As this technology continues its inexorable march forward, educators must continue to evaluate medical curricula to ensure that physicians are trained to be informed stakeholders in the health care of tomorrow.


Subject(s)
Delivery of Health Care/organization & administration , Education, Medical/methods , Evidence-Based Medicine/history , Machine Learning/statistics & numerical data , Aged , Algorithms , COVID-19 Testing/instrumentation , Clinical Decision-Making/ethics , Clinical Trials as Topic , Curriculum/statistics & numerical data , Delivery of Health Care/statistics & numerical data , Diabetic Retinopathy/diagnosis , Diagnostic Imaging/instrumentation , Female , History, 20th Century , Humans , Liability, Legal , Male , Physician-Patient Relations/ethics , Physicians/organization & administration , Stakeholder Participation , United States , United States Food and Drug Administration/legislation & jurisprudence
14.
Lancet Oncol ; 22(8): 1066, 2021 08.
Article in English | MEDLINE | ID: covidwho-1333820
16.
J Nucl Med ; 62(7): 1020, 2021 07 01.
Article in English | MEDLINE | ID: covidwho-1315941
17.
J Med Imaging Radiat Sci ; 52(2): 156, 2021 06.
Article in English | MEDLINE | ID: covidwho-1313259
19.
Clin Imaging ; 77: 276-282, 2021 Sep.
Article in English | MEDLINE | ID: covidwho-1275221

ABSTRACT

PURPOSE: Racial and ethnic disparities have exacerbated during the COVID-19 pandemic as the healthcare system is overwhelmed. While Hispanics are disproportionately affected by COVID-19, little is known about ethnic disparities in the hospital settings. This study investigates imaging utilization and clinical outcomes between Hispanic and non-Hispanic COVID-19 patients in the Emergency Department (ED) and during hospitalization. METHODS: Through retrospective chart review, we included 331 symptomatic COVID-19 patients (mean age 53.2 years) at a metropolitan healthcare system from March to June 2020. Poisson regression was used to compare diagnostic imaging utilization and clinical outcomes between Hispanic and non-Hispanic patients. RESULTS: After adjusting for confounders, no statistically significant difference was found between Hispanic and non-Hispanic patients for the number of weekly chest X-rays. Results were categorized into four clinical outcomes: ED management (0.16 ± 0.05 vs. 0.14 ± 0.8, p:0.79); requiring inpatient management (1.31 ± 0.11 vs. 1.46 ± 0.16, p:0.43); ICU admission without invasive ventilation (1.4 ± 0.17 vs. 1.35 ± 0.26, p:0.86); and ICU admission and ventilator support (3.29 ± 0.22 vs. 3.59 ± 0.37, p:0.38). There were no statistically significant relative differences in adjusted prevalence rate between ethnic groups for all clinical outcomes (p > 0.05). There was a statistically significant longer adjusted length of stay (days) in non-Hispanics for two subcohorts: inpatient management (8.16 ± 0.31 vs. 9.72 ± 0.5, p < 0.01) and ICU admission without invasive ventilation (10.39 ± 0.57 vs. 13.45 ± 1.13, p < 0.01). CONCLUSIONS: For Hispanic and non-Hispanic COVID-19 patients in the ED or hospitalized, there were no statistically significant differences in imaging utilization and clinical outcomes.


Subject(s)
COVID-19 , Diagnostic Imaging , Humans , Middle Aged , Pandemics , Retrospective Studies , SARS-CoV-2
20.
Indian J Ophthalmol ; 69(7): 1648-1649, 2021 07.
Article in English | MEDLINE | ID: covidwho-1278616
SELECTION OF CITATIONS
SEARCH DETAIL
...