scholarly journals A 3D CNN Classification Model for Accurate Diagnosis of Coronavirus Disease 2019 using Computed Tomography Images

2021 ◽  
Author(s):  
Yifan Li ◽  
Xuan Pei ◽  
Yandong Guo
Keyword(s):  
Computed Tomography ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Classification Model ◽  
Computed Tomography Images ◽  
Image Investigation ◽  
Overall Performance ◽  
3D Cnn ◽  
Ct Slices ◽  
Normal Controls

AbstractThe coronavirus disease (COVID-19) has been spreading rapidly around the world. As of August 25, 2020, 23.719 million people have been infected in many countries. The cumulative death toll exceeds 812,000. Early detection of COVID-19 is essential to provide patients with appropriate medical care and protect uninfected people. Leveraging a large computed tomography (CT) database from 1,112 patients provided by China Consortium of Chest CT Image Investigation (CC-CCII), we investigated multiple solutions in detecting COVID-19 and distinguished it from other common pneumonia (CP) and normal controls. We also compared the performance of different models for complete and segmented CT slices. In particular, we studied the effects of CT-superimposition depths into volumes on the performance of our models. The results show that the optimal model can identify the COVID-19 slices with 99.76% accuracy (99.96% recall, 99.35% precision and 99.65% F1-score). The overall performance for three-way classification obtained 99.24% accuracy and the area under the receiver operating characteristic curve (AUROC) of 0.9986. To the best of our knowledge, our method achieves the highest accuracy and recall with the largest public available COVID-19 CT dataset. Our model can help radiologists and physicians perform rapid diagnosis, especially when the healthcare system is overloaded.

scholarly journals Sarcopenia measured with paraspinous muscle using computed tomography for predicting prognosis in elderly pneumonia patients

2021 ◽  
pp. 102490792110418
Author(s):  
Sung Jin Bae ◽  
Keon Kim ◽  
Seong Jong Yun ◽  
Sun Hwa Lee
Keyword(s):  
Computed Tomography ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Muscle Size ◽  
Icu Admission ◽  
Computed Tomography Images ◽  
Prediction Of Mortality ◽  
Paraspinous Muscle ◽  
Receiver Operating

Background: In the elderly, diagnostic findings of pneumonia are often atypical. Computed tomography was recommended for the diagnosis of pneumonia in elderly patients. Recently, the usage of computed tomography as a screening tool for pneumonia in emergency departments has increased. Sarcopenia is defined as the loss of skeletal muscle mass and strength with aging. In this study, the association between sarcopenia and prognosis measured through computed tomography was evaluated compared to CURB-65. Methods: This study was conducted on patients diagnosed with pneumonia through computed tomography from 1 March 2018 to 31 March 2020. The paraspinous muscle size and attenuation were measured at a level located at the T12 pedicle level on axial computed tomography images. Paraspinous muscle size was presented as paraspinous muscle index. Differences in the prognostic performance among the paraspinous muscle size and attenuation, and CURB-65 were evaluated by the area under the receiver operating characteristic curve. Results: A total of 509 patients were included and 132 patients (25.9%) were admitted to the ICU, and 58 patients (11.4%) died in hospital. Paraspinous muscle index was the significant factor for predicting in-hospital mortality and ICU admission. The area under the receiver operating characteristic value of paraspinous muscle index for prediction of mortality was 0.738 and CURB-65 was 0.707. The area under the receiver operating characteristic of paraspinous muscle index and CURB-65 for predicting ICU admission were 0.766 and 0.704, respectively. Conclusion: As a method of measuring sarcopenia, paraspinous muscle index was superior to CURB-65 in elderly pneumonia patients. The use of computed tomography in predicting prognosis for elderly pneumonia patients will ease the economic burden.

scholarly journals Predictive Value of Preoperative Computed Tomography in Sternotomy for Substernal Goiter

2021 ◽  
Author(s):  
Da-Wei Zhao ◽  
Tai-Hua Xiang ◽  
Yi-Zeng Sun ◽  
Yao Li ◽  
Xiang Cui ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Operating Characteristic ◽  
Independent Predictor ◽  
Characteristic Curve ◽  
Area Under The Curve ◽  
Computed Tomography Imaging ◽  
Substernal Goiter ◽  
Computed Tomography Images ◽  
Length Width ◽  
Tomography Data

Abstract Objective The aim of this study was to validate the predictors of peropertive computed tomography imaging parameters for sternotomy in patients with substernal goiter.Methods We retrospectively reviewed complete clinical and computed tomography data of 37 patients who had substernal goiter and underwent surgery from January 2010 to February 2019. The patients were divided into two groups based on whether or not underwent sternotomy surgery. The maximum length and width, length behind sternum of tumors were measured on preoperative computed tomography images, the volume above and below sternum, and total volume of tumors was calculated. Logstic regression model and receiver operating characteristic curve analysis were performed to identify siginificant predictors associated with sternotomy.Results Out of a total of 37 patients, 4 patients (10.8%) underwent sternotomy. The length, width and length behind sternum, as well as the volume below sternum and the total volume of tumors were significantly greater in patients with sternotomy compared to those without sternotomy (all P<0.05). The length behind sternum (OR 1.152, 95% CI: 1.012-1.312, P = 0.033) of tumors was the simple and convenient predictor for sternotomy in substernal goiter. The optimal cut-off value of length behind sternum was 46.7 mm (area under the curve: 0.962, 95% CI: 0.896-1.028, P ≤ 0.01), and the sensitivity and specificity was 100% and 87.9%, respectively.Conclusion Computed tomography examination plays an important role in determining the surgery need for substernal goiter. The length behind sternum of tumor is a convenient and independent predictor of sternotomy for substernal goiter.

Clinical implication of psoas muscle mass measurement for predicting death within 3 months in patients with incurable uterine cervical or corpus malignancy

2021 ◽  
Author(s):  
Hiroyuki Kurosu ◽  
Yukiharu Todo ◽  
Ryutaro Yamada ◽  
Kaoru Minowa ◽  
Tomohiko Tsuruta ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Muscle Mass ◽  
Cancer Cachexia ◽  
Mass Measurement ◽  
Characteristic Curve ◽  
Lumbar Vertebra ◽  
Psoas Muscle ◽  
Data Set ◽  
Cutoff Value ◽  
Computed Tomography Images

Abstract Objective The aim of this study was to find a clinical marker for identifying refractory cancer cachexia. Methods We analyzed computed tomography imaging data, which included the third lumbar vertebra, from 94 patients who died of uterine cervix or corpus malignancy. The time between the date of examination and date of death was the most important attribute for this study, and the computed tomography images were classified into &gt;3 months before death and ≤ 3 months before death. Psoas muscle mass index was defined as the left–right sum of the psoas muscle areas (cm2) at the level of third lumbar vertebra, divided by height squared (m2). Results A data set of 94 computed tomography images was obtained at baseline hospital visit, and a data set of 603 images was obtained at other times. One hundred (16.6%) of the 603 non-baseline images were scanned ≤3 months before death. Mean psoas muscle mass index change rates at &gt;3 months before death and ≤3 months before death were −1.3 and −20.1%, respectively (P &lt; 0.001). Receiver operating characteristic curve analysis yielded a cutoff value of −13.0%. The area under the curve reached a moderate accuracy level (0.777, 95% confidence interval 0.715–0.838). When we used the cutoff value to predict death within 3 months, sensitivity and specificity were 74.0 and 82.1%, respectively. Conclusions Measuring change in psoas muscle mass index might be useful for predicting cancer mortality within 3 months. It could become a potential tool for identifying refractory cancer cachexia.

scholarly journals Diagnostic Accuracy of Chest Computed Tomography Scans for Suspected Patients With COVID-19: Receiver Operating Characteristic Curve Analysis (Preprint)

2020 ◽  
Author(s):  
Lianpin Wu ◽  
Qike Jin ◽  
Jie Chen ◽  
Jiawei He ◽  
David M Brett-Major ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Nucleic Acid ◽  
Ct Scan ◽  
Receiver Operating Characteristic Curve ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Curve Analysis ◽  
Ct Scans ◽  
Nucleic Acid Testing ◽  
Operating Characteristic Curve

BACKGROUND Computed tomography (CT) scans are increasingly available in clinical care globally. They enable a rapid and detailed assessment of tissue and organ involvement in disease processes that are relevant to diagnosis and management, particularly in the context of the COVID-19 pandemic. OBJECTIVE The aim of this paper is to identify differences in the CT scan findings of patients who were COVID-19 positive (confirmed via nucleic acid testing) to patients who were confirmed COVID-19 negative. METHODS A retrospective cohort study was proposed to compare patient clinical characteristics and CT scan findings in suspected COVID-19 cases. A multivariable logistic model with LASSO (least absolute shrinkage and selection operator) selection for variables was used to identify the good predictors from all available predictors. The area under the curve (AUC) with 95% CI was calculated for each of the selected predictors and the combined selected key predictors based on receiver operating characteristic curve analysis. RESULTS A total of 94 (56%) patients were confirmed positive for COVID-19 from the suspected 167 patients. We found that elderly people were more likely to be infected with COVID-19. Among the 94 confirmed positive patients, 2 (2%) patients were admitted to an intensive care unit. No patients died during the study period. We found that the presence, distribution, and location of CT lesions were associated with the presence of COVID-19. White blood cell count, cough, and a travel history to Wuhan were also the top predictors for COVID-19. The overall AUC of these selected predictors is 0.97 (95% CI 0.93-1.00). CONCLUSIONS Taken together with nucleic acid testing, we found that CT scans can allow for the rapid diagnosis of COVID-19. This study suggests that chest CT scans should be more broadly adopted along with nucleic acid testing in the initial assessment of suspected COVID-19 cases, especially for patients with nonspecific symptoms.

Application of the genetic risk model for the analysis of predisposition to nonlacunar ischemic stroke

2019 ◽  
Vol 16 (5) ◽  
pp. 369-378
Author(s):  
Vitaly Korchagin ◽  
Konstantin Mironov ◽  
Alexander Platonov ◽  
Olga Dribnokhodova ◽  
Elina Akselrod ◽  
...  
Keyword(s):  
Ischemic Stroke ◽  
Genetic Risk ◽  
Operating Characteristic ◽  
Risk Model ◽  
Characteristic Curve ◽  
Predictive Ability ◽  
Classification Model ◽  
Nucleotide Polymorphisms ◽  
Single Nucleotide ◽  
Satisfactory Performance

Aim: The purpose of our study was to analyze the predictive ability of the multiplicative model of genetic risk of nonlacunar ischemic stroke (IS) for independent samples from Russia. Patients & methods: A total of 181 patients and 360 healthy controls were included in this study. The discriminative accuracy of model was evaluated by the area under the receiver operating characteristic curve (AUC). Results: Classification model based on 15 single-nucleotide polymorphisms (SNPs), which are associated with a cardioembolic subtype of IS, had an AUC of 0.62 in patients with corresponding subtypes and an AUC of 0.58 for all patients. Conclusion: Risk calculation approach based on IS-associated SNPs had satisfactory performance in predicting the predisposition to the disease.

scholarly journals The Morphological Characteristics of Choriocapillaris In the Fellow Eyes of Polypoidal Choroidal Vasculopathy.Co-authors

2021 ◽  
Author(s):  
Huajui Wu ◽  
Yukinori Sugano ◽  
Kanako Itagaki ◽  
Akihito Kasai ◽  
Hiroaki Shintake ◽  
...  
Keyword(s):  
Operating Characteristic ◽  
Optical Coherence Tomography Angiography ◽  
Characteristic Curve ◽  
Morphological Characteristics ◽  
Swept Source ◽  
Flow Void ◽  
Operating Characteristic Curve ◽  
Normal Controls ◽  
Choroidal Vascular Hyperpermeability ◽  
Fellow Eyes

Abstract To evaluate the morphological characteristics of the flow void (FV) in the fellow eyes of the unilateral polypoidal choroidal vasculopathy (PCV). 52 eyes of PCV fellow eyes (PCVF) and 57 age-matched normal controls were recruited in this prospective study. The number of FV was analyzed according to the size which from 6×6-mm swept source optical coherence tomography angiography scans. We used indocyanine green angiography images to determine whether choroidal vascular hyperpermeability (CVH) has occurred. For the PCVF, the incidence of CVH was 70% (35 of 50. Two of participants were allergic to the dye.) The number of FV significantly lower in all sizes (P = .002), 400 ~ 500µm2 (P = .002), 525 ~ 625µm2 (P = .002) and 650 ~ 750µm2 (P = .005). And the distribution significantly different in all sizes (P = .002), 400 ~ 500µm2 (P = .001), 525 ~ 625µm2 (P = .002) and 650 ~ 750µm2 (P = .001) compared to the controls. And showed no differences in the size from 775 to 1125µm2 between two groups. The area under the receiver operating characteristic curve of PCVF with CVH and controls was 0.93 (95% CI: 0.88 ~ 0.98) (P < .001). We found that the FV is a useful predictor for distinguishing the fellow eyes of PCV from normal eyes.

scholarly journals Diagnostic Accuracy of Chest Computed Tomography Scans for Suspected Patients With COVID-19: Receiver Operating Characteristic Curve Analysis

10.2196/19424 ◽  
2020 ◽  
Vol 6 (4) ◽  
pp. e19424
Author(s):  
Lianpin Wu ◽  
Qike Jin ◽  
Jie Chen ◽  
Jiawei He ◽  
David M Brett-Major ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Nucleic Acid ◽  
Ct Scan ◽  
Receiver Operating Characteristic Curve ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Curve Analysis ◽  
Ct Scans ◽  
Nucleic Acid Testing ◽  
Operating Characteristic Curve

Background Computed tomography (CT) scans are increasingly available in clinical care globally. They enable a rapid and detailed assessment of tissue and organ involvement in disease processes that are relevant to diagnosis and management, particularly in the context of the COVID-19 pandemic. Objective The aim of this paper is to identify differences in the CT scan findings of patients who were COVID-19 positive (confirmed via nucleic acid testing) to patients who were confirmed COVID-19 negative. Methods A retrospective cohort study was proposed to compare patient clinical characteristics and CT scan findings in suspected COVID-19 cases. A multivariable logistic model with LASSO (least absolute shrinkage and selection operator) selection for variables was used to identify the good predictors from all available predictors. The area under the curve (AUC) with 95% CI was calculated for each of the selected predictors and the combined selected key predictors based on receiver operating characteristic curve analysis. Results A total of 94 (56%) patients were confirmed positive for COVID-19 from the suspected 167 patients. We found that elderly people were more likely to be infected with COVID-19. Among the 94 confirmed positive patients, 2 (2%) patients were admitted to an intensive care unit. No patients died during the study period. We found that the presence, distribution, and location of CT lesions were associated with the presence of COVID-19. White blood cell count, cough, and a travel history to Wuhan were also the top predictors for COVID-19. The overall AUC of these selected predictors is 0.97 (95% CI 0.93-1.00). Conclusions Taken together with nucleic acid testing, we found that CT scans can allow for the rapid diagnosis of COVID-19. This study suggests that chest CT scans should be more broadly adopted along with nucleic acid testing in the initial assessment of suspected COVID-19 cases, especially for patients with nonspecific symptoms.

scholarly journals Correction：Diagnostic Accuracy of Chest Computed Tomography Scans for Suspected Patients With COVID-19: Receiver Operating Characteristic Curve Analysis (Preprint)

2020 ◽  
Author(s):  
Lianpin Wu ◽  
Qike Jin ◽  
Jie Chen ◽  
Jiawei He ◽  
David M Brett-Major ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Receiver Operating Characteristic Curve ◽  
Receiver Operating Characteristic ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Curve Analysis ◽  
Chest Computed Tomography ◽  
Computed Tomography Scans ◽  
Operating Characteristic Curve ◽  
Medical University

UNSTRUCTURED In “Diagnostic Accuracy of Chest Computed Tomography Scans for Suspected Patients With COVID-19: Receiver Operating Characteristic Curve Analysis”(JMIR public health and surveillance. 2020 10 20; 6 (4) :e19424. doi:10.2196/19424),we noted one error. The affiliation for authors Lianpin Wu, QIke Jin and Jiawei He was incorrectly listed as: Department of Cardiology, Wenzhou Medical University, Wenzhou, China The correct affiliation for these auhors was: Department of Cardiology, the Second Affiliated Hospital & Yuying Children’s Hospital of Wenzhou Medical University, Wenzhou , China

Sign in / Sign up

Export Citation Format

Share Document