Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 17.923
Filtrar
1.
Ann Anat ; 239: 151842, 2022 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-34673201

RESUMO

BACKGROUND: The detailed morphology and topography of the sympathetic cardiac nerves (SCNs) and ganglia with their surrounding structures in Syrian hamsters were examined to document the general topography and morphology and variations and to discuss the comparative anatomy between the SCNs and ganglia in Syrian hamsters and other rodents, as well as their comparative morphology and macroscopic evolutionary changes among rodents, rabbits, domestic animals (cats, dogs, sheep, goats, oxen, pigs and horses), primates, and humans. METHODS: The composition of the cervical and thoracic parts of the sympathetic trunks and ganglia was bilaterally microdissected in twenty-eight sides of 14 adult male and female Syrian hamsters under a stereomicroscope. RESULTS: The general morphology of the SCNs and related ganglia in Syrian hamsters was obtained and noted as follows: (1) the absence of the vago-sympathetic trunk, (2) the absence of the middle cervical ganglion (MG), (3) constant presence of the cervicothoracic ganglion (CT) comprising generally from the caudal cervical ganglion and 1-2 thoracic ganglia and locating over the lateral surface of the longus colli muscle ventral to the heads of the first two ribs and communicating to the eight cervical and first two thoracic spinal nerves (C8-T2) in addition to the vertebral nerve, (4) extensive coverage of the lateral surface of the CT by branches of the subclavian artery, (5) the cranial and caudal limbs of the ansa subclavia (AS) joining the CT to the caudal end of the cervical sympathetic trunk, (6) the presence of an independent thoracic ganglion from the 2nd or 3rd to the 13th and connecting by single interganglionic branches, and communicating to each thoracic spinal nerve, (7) close relationship between the caudal portion of the thoracic sympathetic trunk and the psoas minor muscle, (8) the primary cardiac nerves (CNs) arising from the CT, and (9) the absence of CNs originating generally from the cervical sympathetic trunk, AS, MG, or independent thoracic ganglia or their interganglionic branches. Individual variations of the SCNs and ganglia in Syrian hamsters were noted, including the absence of the ansa subclavia on 5/28 sides (17.86%), the presence of the intermediate ganglia (IG) placed on the C7 on 3/28 sides (10.71%) or the C8 on 3/28 sides (10.71%), and no CNs arising from the IG as well as the presence of the double thoracic sympathetic trunk on 5/28 sides (17.86%). The anatomical characteristics of the SCNs and related ganglia were also exhibited sex and laterality differences. CONCLUSIONS: From a comparative anatomy viewpoint, the general morphology of the SCNs and related ganglia in Syrian hamsters was very similar to that in rats but was considerably different from that in guinea pigs, especially concerning the MG, cranial position and composition of the CT. The general morphology of the SCNs and related ganglia in Syrian hamsters and other laboratory rodents resembled that of rabbits but was essentially different from that in rabbits with respect to the cranial position and composition of the CT. The general morphology of the SCNs and ganglia exhibited significant morphological differences and similarities among laboratory rodents, rabbits, domestic animals, primates, and humans. The main differences include the relationship between the cervical parts of the vagus nerve and sympathetic trunk, the presence of the MG, the position and composition of the CT, the origins and frequencies of the cardiac nerves, and the primary sympathetic contributor. From macroscopic evolutionary change, the expansion of the range of the SCNs origin has occurred from laboratory rodents, rabbits, domestic animals, and primates to humans.


Assuntos
Gânglios Simpáticos , Sistema Nervoso Simpático , Animais , Gatos , Cricetinae , Cães , Feminino , Cobaias , Cavalos , Masculino , Mesocricetus , Pescoço , Coelhos , Ratos , Ovinos , Tórax
2.
Ann Card Anaesth ; 24(4): 493-494, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34747763

RESUMO

Solitary fibrous tumors of the pleura (SFTP) are rare mesenchymal tumors that arise from visceral or parietal tissue. Surgical resection of massive SFTP can be complicated by airway collapse, vascular compression/hemodynamic instability, and hemorrhage. Patients with SFTP may also present with metabolic derangements secondary to paraneoplastic processes. We present a case of successful removal of massive right-sided SFTP via clamshell sternotomy and discuss the perioperative considerations for which providers should be familiar.


Assuntos
Tumor Fibroso Solitário Pleural , Humanos , Pleura , Tumor Fibroso Solitário Pleural/complicações , Tumor Fibroso Solitário Pleural/diagnóstico por imagem , Tumor Fibroso Solitário Pleural/cirurgia , Tórax
4.
Indian J Tuberc ; 68(4): 450-456, 2021 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-34752312

RESUMO

BACKGROUND: Moderate and severe COVID-19 patients typically present with pneumonia. In this study we aimed to detect the occurrence of pulmonary residuals as a late sequela of COVID-19 and to identify it's predictors among moderate and severe cases. METHODS: This observational prospective study involved 85 COVID-19 patients confirmed by real time polymerase chain reaction (RT-PCR) nasopharyngeal swab, patients were recruited in the period of 1 st of June to 1 st of July. Demographic and clinical data were obtained for each patient. Chest imaging was performed initially and after 3 weeks to detect post COVID pulmonary residuals. RESULTS: The study population included 74 (87.1%) moderate and 11 (12.9%) severe patients. Patients with older age, male gender, high BMI and initial chest CT of consolidation/mixed consolidation and ground glass opacities (GGOs) had more frequent post COVID-19 pulmonary residuals (P 0.003, 0.026, 0.031, 0.035) respectively. There was a statistically significant difference between patients who showed complete resolution and patients who developed pulmonary residuals regarding the lymphocyte count, serum CRP and ferritin levels (P 0.0001). After logistic regression, male gender, high BMI, initial chest CT of consolidation/mixed consolidation and GGOs, lymphocytopenia, high serum CRP and ferritin levels were the predictors of pulmonary residuals. While the age wasn't statistically significant. CONCLUSION: 38.5% of moderate and severe COVID-19 patients tend to have pulmonary residuals. Independent predictors of pulmonary residuals as a sequela of COVID-19 are male gender, high BMI, initial chest CT of consolidation and mixed consolidation/GGOs, lymphocytopenia, high serum CRP and ferritin levels.


Assuntos
COVID-19/complicações , COVID-19/diagnóstico por imagem , Pulmão/diagnóstico por imagem , Fibrose Pulmonar/epidemiologia , SARS-CoV-2/isolamento & purificação , Tórax/diagnóstico por imagem , Adulto , Idoso , COVID-19/epidemiologia , COVID-19/terapia , Teste de Ácido Nucleico para COVID-19 , Humanos , Masculino , Pessoa de Meia-Idade , Nasofaringe/virologia , Estudos Prospectivos , Fibrose Pulmonar/diagnóstico por imagem , Reação em Cadeia da Polimerase em Tempo Real , SARS-CoV-2/genética , Tomografia Computadorizada por Raios X/métodos , Resultado do Tratamento
5.
Radiographics ; 41(7): 2071-2089, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34723703

RESUMO

Fluorodeoxyglucose (FDG) PET/CT is a vital imaging technique used for staging, assessing treatment response, and restaging following completion of therapy in patients who are undergoing or have completed oncologic treatment. A variety of adverse effects from chemotherapy, targeted therapy, immunotherapy, and radiation therapy are commonly encountered in oncologic patients. It is important to be aware of the manifestations of these adverse effects seen on FDG PET/CT images to avoid misinterpreting these findings as disease progression. Furthermore, early identification of these complications is important, as it may significantly affect patient management and even lead to a change in treatment strategy. The authors focus on the FDG PET/CT manifestations of a broad spectrum of oncologic therapy-related adverse effects in the thorax, as well as some treatment-related changes that may potentially mimic malignancy. Online supplemental material is available for this article. ©RSNA, 2021.


Assuntos
Fluordesoxiglucose F18 , Tomografia por Emissão de Pósitrons combinada à Tomografia Computadorizada , Humanos , Oncologia , Tomografia por Emissão de Pósitrons , Tórax
6.
BMJ Case Rep ; 14(11)2021 Nov 17.
Artigo em Inglês | MEDLINE | ID: mdl-34789525

RESUMO

A man in his 70s, admitted to intensive care unit following an out of hospital cardiac arrest, had a nasogastric (NG) tube inserted on admission. Correct placement of the NG tube had been confirmed using National Patient Safety Agency (NPSA) criteria and was used for feeding without incident. He remained intubated and ventilated throughout his stay. On day 9 his oxygen requirements increased with subsequent chest imaging revealing an incidental gastric perforation secondary to NG tube migration. The NG tube was removed intact and undamaged. The patient appeared to improve without sequelae from the perforation or signs of abdominal sepsis. Unfortunately his condition deteriorated due to a large right atrial thrombus and life sustaining treatments were withdrawn.


Assuntos
Unidades de Terapia Intensiva , Intubação Gastrointestinal , Hospitalização , Humanos , Intubação Gastrointestinal/efeitos adversos , Masculino , Segurança do Paciente , Tórax
7.
An Bras Dermatol ; 96(6): 771-773, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34600788

RESUMO

Carcinoma of the mammary crease is a very rare variant of breast carcinoma, in which the skin lesions are usually the presenting sign. The authors present the case of an 88-year-old woman with an exophytic plaque in the mammary crease of approximately ten years duration. The histopathological and immunohistochemical studies confirmed the diagnosis of infiltrative breast carcinoma (carcinoma of the mammary crease variant). This case highlights the important role of the dermatologist in the early diagnosis of this rare variant of breast cancer.


Assuntos
Neoplasias da Mama , Carcinoma , Idoso de 80 Anos ou mais , Mama , Neoplasias da Mama/diagnóstico , Feminino , Humanos , Tórax
8.
Eur Respir Rev ; 30(162)2021 Dec 31.
Artigo em Inglês | MEDLINE | ID: mdl-34615698

RESUMO

OBJECTIVE: Immunoglobulin G4-related disease (IgG4-RD) is a rare orphan disease. Lung, pleura, pericardium, mediastinum, aorta and lymph node involvement has been reported with variable frequency and mostly in Asian studies. The objective of this study was to describe thoracic involvement assessed by high-resolution thoracic computed tomography (CT) in Caucasian patients with IgG4-RD. METHODS: Thoracic CT scans before treatment were retrospectively collected through the French case registry of IgG4-RD and a single tertiary referral centre. CT scans were reviewed by two experts in thoracic imagery blinded from clinical data. RESULTS: 48 IgG4-RD patients with thoracic involvement were analysed. All had American College of Rheumatology/European League Against Rheumatism classification scores ≥20 and comprehensive diagnostic criteria for IgG4-RD. CT scan findings showed heterogeneous lesions. Seven patterns were observed: peribronchovascular involvement (56%), lymph node enlargement (31%), nodular disease (25%), interstitial disease (25%), ground-glass opacities (10%), pleural disease (8%) and retromediastinal fibrosis (4%). In 37% of cases two or more patterns were associated. Asthma was significantly associated with peribronchovascular involvement (p=0.04). Among eight patients evaluated by CT scan before and after treatments, only two patients with interstitial disease displayed no improvement. CONCLUSION: Thoracic involvement of IgG4-RD is heterogeneous and likely underestimated. The main thoracic CT scan patterns are peribronchovascular thickening and thoracic lymph nodes.


Assuntos
Doença Relacionada a Imunoglobulina G4 , Humanos , Pulmão/diagnóstico por imagem , Estudos Retrospectivos , Tórax , Tomografia Computadorizada por Raios X
9.
Radiat Prot Dosimetry ; 196(3-4): 190-198, 2021 Nov 12.
Artigo em Inglês | MEDLINE | ID: mdl-34635920

RESUMO

The purpose of this study is to examine radiation doses and image quality of a low-dose (LD) protocol for chest and abdomen/pelvis (CAP) CT compared with a standard (STD) protocol. A total of 361 patients were included between October 2019 and April 2020; 104 patients with LD-protocol (100 kV, ref mAs 80 (chest)/145 (abdomen/pelvis)) and 257 patients with STD-protocol (100 kV, ref mAs 100 (chest)/180 (abdomen/pelvis)) at second-generation dual-source CT. Radiation doses for CTDIvol and DLP, and objective and subjective image qualities of 50 examinations from each group were evaluated. The LD-protocol applied significantly lower radiation doses compared with the STD-protocol (p < 0.001), achieving a dose reduction by 37% for the median DLP in chest, 19% in abdomen/pelvis and 22% in total. Median total DLP was 342 mGy·cm (LD) vs. 436 mGy·cm (STD). The LD-CAP CT protocol achieved a significant dose reduction far below national diagnostic reference levels, ensuring acceptable and good image quality.


Assuntos
Pelve , Tomografia Computadorizada por Raios X , Abdome/diagnóstico por imagem , Humanos , Pelve/diagnóstico por imagem , Doses de Radiação , Tórax/diagnóstico por imagem
10.
Eur J Radiol ; 144: 109983, 2021 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-34627107

RESUMO

PURPOSE: The aim of the study was to investigate differences in non-small cell lung cancer (NSCLC) intra-thoracic staging by using contrast-enhanced computed tomography (ce-CT) at the arterial phase (AP), at the arterial plus delayed phases (AP + DEP), and at the delayed phase (DEP), and to evaluate their potential impact on disease staging. MATERIALS AND METHODS: Two chest radiologists with different level of expertise and a general radiologist independently reviewed the chest CT exams of 150 patients with NSCLC; CT scans were performed 40 s (AP) and 60 s (DEP) after contrast material injection. Image assessment included three reading sessions: session A (AP), session B (AP + DEP) and session C (DEP). CT descriptors for the primary tumour (T), regional nodal involvement (N), and intra-thoracic metastases (M) were evaluated in each reading session. Readers had to assign a confidence level (CL) for the assessment of each descriptor and define the TNM stage. Friedman and Cochran Q test was used to compare the assessments of the 3 reading sessions; inter-reader agreement was determined (Intraclass Correlation Coefficient - ICC). RESULTS: The CL was significantly higher in sessions B and C than in session A for all descriptors, with the exception of pulmonary arterial invasion. Primary tumour inner necrosis and regional nodal involvement were detected in a significantly higher number of cases in sessions B and C as compared to session A (p ≤ 0.001). DEP significantly changed N stage determination (p < 0.001), particularly N3, and excluded chest wall invasion (p = 0.05) and venous invasion (p = 0.001). The agreement was good among the 3 readers (ICC = 0.761) and excellent between the 2 chest radiologists (ICC ≥ 0.940), regardless of the contrast phase. CONCLUSIONS: The 60-second DEP ce-CT for staging NSCLC significantly increased the readers' CL, changed the N stage determination, and helped excluding chest wall invasion and venous invasion.


Assuntos
Carcinoma Pulmonar de Células não Pequenas , Neoplasias Pulmonares , Carcinoma Pulmonar de Células não Pequenas/diagnóstico por imagem , Carcinoma Pulmonar de Células não Pequenas/patologia , Humanos , Neoplasias Pulmonares/diagnóstico por imagem , Neoplasias Pulmonares/patologia , Estadiamento de Neoplasias , Tórax/patologia , Tomografia Computadorizada por Raios X
11.
Medicine (Baltimore) ; 100(40): e27444, 2021 Oct 08.
Artigo em Inglês | MEDLINE | ID: mdl-34622862

RESUMO

ABSTRACT: Severe acute respiratory syndrome coronavirus-2 may cause low oxygen saturation (SpO2) and respiratory failure in patients with coronavirus disease (COVID-19). Hence, increased SpO2 levels in COVID-19 patients could be crucial for their quality of life and recovery. This study aimed to demonstrate that a 30-minute single session of dorsal low-field thoracic magnetic stimulation (LF-ThMS) can be employed to increase SpO2 levels in COVID-19 patients significantly. Furthermore, we hypothesized that the variables associated with LF-ThMS, such as frequency, magnetic flux density, and temperature in the dorsal thorax, might be correlated to SpO2 levels in these patients.Here we employed an LF-ThMS device to noninvasively deliver a pulsed magnetic field from 100 to 118 Hz and 10.5 to 13.1 milliTesla (i.e., 105 to 131 Gauss) to the dorsal thorax. These values are within the intensity range of several pulsed electromagnetic field devices employed in physical therapy worldwide. We designed a single-blind, sham-controlled, crossover study on 5 COVID-19 patients who underwent 2 sessions of the study (real and sham LF-ThMS) and 12 patients who underwent only the real LF-ThMS.We found a statistically significant positive correlation between magnetic flux density, frequency, or temperature, associated with the real LF-ThMS and SpO2 levels in all COVID-19 patients. However, the 5 patients in the sham-controlled study did not exhibit a significant change in their SpO2 levels during sham stimulation. The employed frequencies and magnetic flux densities were safe for the patients. We did not observe adverse events after the LF-ThMS intervention.This study is a proof-of-concept that a single session of LF-ThMS applied for 30 minutes to the dorsal thorax of 17 COVID-19 patients significantly increased their SpO2 levels. However, future research will be needed to understand the physiological mechanisms behind this finding.The study was registered at ClinicalTrials.gov (Identifier: NCT04895267, registered on May 20, 2021) retrospectively registered. https://clinicaltrials.gov/ct2/show/NCT04895267.


Assuntos
COVID-19/terapia , Terapia de Campo Magnético/métodos , Oxigênio/sangue , Adulto , Idoso , Idoso de 80 Anos ou mais , Estudos Cross-Over , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Qualidade de Vida , SARS-CoV-2 , Método Simples-Cego , Tórax
12.
Sci Rep ; 11(1): 19638, 2021 10 04.
Artigo em Inglês | MEDLINE | ID: mdl-34608186

RESUMO

The main purpose of this work is to investigate and compare several deep learning enhanced techniques applied to X-ray and CT-scan medical images for the detection of COVID-19. In this paper, we used four powerful pre-trained CNN models, VGG16, DenseNet121, ResNet50,and ResNet152, for the COVID-19 CT-scan binary classification task. The proposed Fast.AI ResNet framework was designed to find out the best architecture, pre-processing, and training parameters for the models largely automatically. The accuracy and F1-score were both above 96% in the diagnosis of COVID-19 using CT-scan images. In addition, we applied transfer learning techniques to overcome the insufficient data and to improve the training time. The binary and multi-class classification of X-ray images tasks were performed by utilizing enhanced VGG16 deep transfer learning architecture. High accuracy of 99% was achieved by enhanced VGG16 in the detection of X-ray images from COVID-19 and pneumonia. The accuracy and validity of the algorithms were assessed on X-ray and CT-scan well-known public datasets. The proposed methods have better results for COVID-19 diagnosis than other related in literature. In our opinion, our work can help virologists and radiologists to make a better and faster diagnosis in the struggle against the outbreak of COVID-19.


Assuntos
COVID-19/diagnóstico , Aprendizado Profundo , COVID-19/virologia , Humanos , Processamento de Imagem Assistida por Computador , SARS-CoV-2/isolamento & purificação , Tórax/diagnóstico por imagem , Tomografia Computadorizada por Raios X , Raios X
13.
In Vivo ; 35(6): 3321-3323, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34697164

RESUMO

BACKGROUND: Due to the high risk of COVID-19 transmission by asymptomatic patients, the aim of this study was to evaluate chest computed tomography (CT) and blood differential test as an additional COVID-19 screening tool for patients undergoing elective or urgent surgery. PATIENTS AND METHODS: The preoperative assessment of 118 patients hospitalized from June to July 2020 included real-time reverse transcriptase polymerase chain reaction RNA test before elective surgery or rapid antigen test in emergency patients. The diagnostics were supplemented by chest CT and a complete blood count with a blood smear in all patients. RESULTS: None of the hospitalized patients had molecular, serological or radiographic symptoms of COVID-19 infection. The chest CT revealed non-COVID-19 pathologies in a total of 48 patients. Leukocytosis and lymphopenia were typical of emergency patients. CONCLUSION: Routine chest CT scans have no benefit in screening for potential COVID-19 changes in asymptomatic patients. Blood differential tests are readily available, which makes them more helpful in COVID-19 screening.


Assuntos
COVID-19 , Procedimentos Cirúrgicos Eletivos , Humanos , Programas de Rastreamento , SARS-CoV-2 , Tórax
14.
PLoS One ; 16(10): e0257884, 2021.
Artigo em Inglês | MEDLINE | ID: mdl-34648509

RESUMO

Recent studies show the potential of artificial intelligence (AI) as a screening tool to detect COVID-19 pneumonia based on chest x-ray (CXR) images. However, issues on the datasets and study designs from medical and technical perspectives, as well as questions on the vulnerability and robustness of AI algorithms have emerged. In this study, we address these issues with a more realistic development of AI-driven COVID-19 pneumonia detection models by generating our own data through a retrospective clinical study to augment the dataset aggregated from external sources. We optimized five deep learning architectures, implemented development strategies by manipulating data distribution to quantitatively compare study designs, and introduced several detection scenarios to evaluate the robustness and diagnostic performance of the models. At the current level of data availability, the performance of the detection model depends on the hyperparameter tuning and has less dependency on the quantity of data. InceptionV3 attained the highest performance in distinguishing pneumonia from normal CXR in two-class detection scenario with sensitivity (Sn), specificity (Sp), and positive predictive value (PPV) of 96%. The models attained higher general performance of 91-96% Sn, 94-98% Sp, and 90-96% PPV in three-class compared to four-class detection scenario. InceptionV3 has the highest general performance with accuracy, F1-score, and g-mean of 96% in the three-class detection scenario. For COVID-19 pneumonia detection, InceptionV3 attained the highest performance with 86% Sn, 99% Sp, and 91% PPV with an AUC of 0.99 in distinguishing pneumonia from normal CXR. Its capability of differentiating COVID-19 pneumonia from normal and non-COVID-19 pneumonia attained 0.98 AUC and a micro-average of 0.99 for other classes.


Assuntos
Inteligência Artificial , COVID-19/diagnóstico por imagem , Pneumonia/diagnóstico por imagem , Tórax/diagnóstico por imagem , Humanos , Valor Preditivo dos Testes , Radiografia Torácica , Sensibilidade e Especificidade
15.
Artigo em Inglês | MEDLINE | ID: mdl-34682471

RESUMO

Previous pilot experience has shown the ability of visually impaired and blind people (BP) to learn basic life support (BLS), but no studies have compared their abilities with blindfolded people (BFP) after participating in the same instructor-led, real-time feedback training. Twenty-nine BP and 30 BFP participated in this quasi-experimental trial. Training consisted of a 1 h theoretical and practical training session with an additional 30 min afterwards, led by nurses with prior experience in BLS training of various collectives. Quantitative quality of chest compressions (CC), AED use and BLS sequence were evaluated by means of a simulation scenario. BP's median time to start CC was less than 35 s. Global and specific components of CC quality were similar between groups, except for compression rate (BFP: 123.4 + 15.2 vs. BP: 110.8 + 15.3 CC/min; p = 0.002). Mean compression depth was below the recommended target in both groups, and optimal CC depth was achieved by 27.6% of blind and 23.3% of blindfolded people (p = 0.288). Time to discharge was significantly longer in BFP than BP (86.0 + 24.9 vs. 66.0 + 27.0 s; p = 0.004). Thus, after an adapted and short training program, blind people were revealed to have abilities comparable to those of blindfolded people in learning and performing the BLS sequence and CC.


Assuntos
Reanimação Cardiopulmonar , Capacitação de Professores , Retroalimentação , Humanos , Manequins , Tórax
16.
Infect Dis Poverty ; 10(1): 126, 2021 Oct 21.
Artigo em Inglês | MEDLINE | ID: mdl-34674774

RESUMO

BACKGROUND: The computed tomography (CT) diagnostic value of COVID-19 is controversial. We summarized the value of chest CT in the diagnosis of COVID-19 through a meta-analysis based on the reference standard. METHODS: All Chinese and English studies related to the diagnostic value of CT for COVID-19 across multiple publication platforms, was searched for and collected. Studies quality evaluation and plotting the risk of bias were estimated. A heterogeneity test and meta-analysis, including plotting sensitivity (Sen), specificity (Spe) forest plots, pooled positive likelihood ratio (+LR), negative likelihood ratio (-LR), dignostic odds ratio (DOR) values and 95% confidence interval (CI), were estimated. If there was a threshold effect, summary receiver operating characteristic curves (SROC) was further plotted. Pooled area under the receiver operating characteristic curve (AUROC) and 95% CI were also calculated. RESULTS: Twenty diagnostic studies that represented a total of 9004 patients were included from 20 pieces of literatures after assessing all the aggregated studies. The reason for heterogeneity was caused by the threshold effect, so the AUROC = 0.91 (95% CI: 0.89-0.94) for chest CT of COVID-19. Pooled sensitivity, specificity, +LR, -LR from 20 studies were 0.91 (95% CI: 0.88-0.94), 0.71 (95% CI: 0.59-0.80), 3.1(95% CI: 2.2-4.4), 0.12 (95% CI: 0.09-0.17), separately. The I2 was 85.6% (P = 0.001) by Q-test. CONCLUSIONS: The results of this study showed that CT diagnosis of COVID-19 was close to the reference standard. The diagnostic value of chest CT may be further enhanced if there is a unified COVID-19 diagnostic standard. However, please pay attention to rational use of CT.


Assuntos
COVID-19 , Tórax , Tomografia Computadorizada por Raios X , COVID-19/diagnóstico por imagem , Humanos , Reação em Cadeia da Polimerase Via Transcriptase Reversa , Sensibilidade e Especificidade , Tórax/diagnóstico por imagem
17.
19.
Int J Comput Assist Radiol Surg ; 16(11): 1901-1913, 2021 Nov.
Artigo em Inglês | MEDLINE | ID: mdl-34652606

RESUMO

PURPOSE: The three-dimensional (3D) voxel labeling of lesions requires significant radiologists' effort in the development of computer-aided detection software. To reduce the time required for the 3D voxel labeling, we aimed to develop a generalized semiautomatic segmentation method based on deep learning via a data augmentation-based domain generalization framework. In this study, we investigated whether a generalized semiautomatic segmentation model trained using two types of lesion can segment previously unseen types of lesion. METHODS: We targeted lung nodules in chest CT images, liver lesions in hepatobiliary-phase images of Gd-EOB-DTPA-enhanced MR imaging, and brain metastases in contrast-enhanced MR images. For each lesion, the 32 × 32 × 32 isotropic volume of interest (VOI) around the center of gravity of the lesion was extracted. The VOI was input into a 3D U-Net model to define the label of the lesion. For each type of target lesion, we compared five types of data augmentation and two types of input data. RESULTS: For all considered target lesions, the highest dice coefficients among the training patterns were obtained when using a combination of the existing data augmentation-based domain generalization framework and random monochrome inversion and when using the resized VOI as the input image. The dice coefficients were 0.639 ± 0.124 for the lung nodules, 0.660 ± 0.137 for the liver lesions, and 0.727 ± 0.115 for the brain metastases. CONCLUSIONS: Our generalized semiautomatic segmentation model could label unseen three types of lesion with different contrasts from the surroundings. In addition, the resized VOI as the input image enables the adaptation to the various sizes of lesions even when the size distribution differed between the training set and the test set.


Assuntos
Aprendizado Profundo , Humanos , Fígado , Imageamento por Ressonância Magnética , Tórax , Tomografia Computadorizada por Raios X
20.
Sensors (Basel) ; 21(19)2021 Oct 07.
Artigo em Inglês | MEDLINE | ID: mdl-34640976

RESUMO

Lung cancer is the leading cause of cancer death and morbidity worldwide. Many studies have shown machine learning models to be effective in detecting lung nodules from chest X-ray images. However, these techniques have yet to be embraced by the medical community due to several practical, ethical, and regulatory constraints stemming from the "black-box" nature of deep learning models. Additionally, most lung nodules visible on chest X-rays are benign; therefore, the narrow task of computer vision-based lung nodule detection cannot be equated to automated lung cancer detection. Addressing both concerns, this study introduces a novel hybrid deep learning and decision tree-based computer vision model, which presents lung cancer malignancy predictions as interpretable decision trees. The deep learning component of this process is trained using a large publicly available dataset on pathological biomarkers associated with lung cancer. These models are then used to inference biomarker scores for chest X-ray images from two independent data sets, for which malignancy metadata is available. Next, multi-variate predictive models were mined by fitting shallow decision trees to the malignancy stratified datasets and interrogating a range of metrics to determine the best model. The best decision tree model achieved sensitivity and specificity of 86.7% and 80.0%, respectively, with a positive predictive value of 92.9%. Decision trees mined using this method may be considered as a starting point for refinement into clinically useful multi-variate lung cancer malignancy models for implementation as a workflow augmentation tool to improve the efficiency of human radiologists.


Assuntos
Neoplasias Pulmonares , Humanos , Pulmão , Neoplasias Pulmonares/diagnóstico por imagem , Sensibilidade e Especificidade , Tórax , Raios X
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA
...