4.Differential diagnosis of malignant and benign peripheral pulmonary lesions based on two characteristic echo features of endobronchial ultrasonography.
Yu HUANG ; Zhengxian CHEN ; Hongyan REN ; Bifang HE ; Xiuyu LI
Journal of Southern Medical University 2012;32(7):1016-1019
OBJECTIVETo assess the feasibility of endobronchial ultrasonography (EBUS) in the differential diagnosis of malignant and benign lesions based on the two characteristic echo features of malignancy.
METHODSEBUS images from 102 patients undergoing bronchoscopy for peripheral lung lesions were analyzed. The sensitivity and specificity were determined for each echo feature, namely the halo sign and low-level echoes that indicated malignancy, or their combination in diagnosing malignant and benign lesions.
RESULTSLow-level echoes showed a sensitivity of 89.46% and a specificity of 83% in the diagnosis of malignancy, both higher than those of the halo sign (69.51% and 65%, respectively). The presence of either of the two echo features had a diagnostic sensitivity of 94.6% for malignant lesions, and the coexistence of the two features had a specificity of 93% for a diagnosis of malignant lesions.
CONCLUSIONEBUS is a useful adjunctive modality for lung cancer diagnosis, especially in cases where peripheral lung lesions are invisible in conventional bronchoscopy.
Diagnosis, Differential ; Endosonography ; methods ; Humans ; Lung Neoplasms ; diagnostic imaging ; Pneumonia ; diagnostic imaging ; Sensitivity and Specificity
5.Research on coronavirus disease 2019 (COVID-19) detection method based on depthwise separable DenseNet in chest X-ray images.
Yibo FENG ; Dawei QIU ; Hui CAO ; Junzhong ZHANG ; Zaihai XIN ; Jing LIU
Journal of Biomedical Engineering 2020;37(4):557-565
Coronavirus disease 2019 (COVID-19) has spread rapidly around the world. In order to diagnose COVID-19 more quickly, in this paper, a depthwise separable DenseNet was proposed. The paper constructed a deep learning model with 2 905 chest X-ray images as experimental dataset. In order to enhance the contrast, the contrast limited adaptive histogram equalization (CLAHE) algorithm was used to preprocess the X-ray image before network training, then the images were put into the training network and the parameters of the network were adjusted to the optimal. Meanwhile, Leaky ReLU was selected as the activation function. VGG16, ResNet18, ResNet34, DenseNet121 and SDenseNet models were used to compare with the model proposed in this paper. Compared with ResNet34, the proposed classification model of pneumonia had improved 2.0%, 2.3% and 1.5% in accuracy, sensitivity and specificity respectively. Compared with the SDenseNet network without depthwise separable convolution, number of parameters of the proposed model was reduced by 43.9%, but the classification effect did not decrease. It can be found that the proposed DWSDenseNet has a good classification effect on the COVID-19 chest X-ray images dataset. Under the condition of ensuring the accuracy as much as possible, the depthwise separable convolution can effectively reduce number of parameters of the model.
Betacoronavirus
;
Coronavirus Infections
;
diagnostic imaging
;
Deep Learning
;
Humans
;
Pandemics
;
Pneumonia, Viral
;
diagnostic imaging
;
X-Rays
6.Development and validation of a CT-based radiomics model for differentiating pneumonia-like primary pulmonary lymphoma from infectious pneumonia: A multicenter study.
Xinxin YU ; Bing KANG ; Pei NIE ; Yan DENG ; Zixin LIU ; Ning MAO ; Yahui AN ; Jingxu XU ; Chencui HUANG ; Yong HUANG ; Yonggao ZHANG ; Yang HOU ; Longjiang ZHANG ; Zhanguo SUN ; Baosen ZHU ; Rongchao SHI ; Shuai ZHANG ; Cong SUN ; Ximing WANG
Chinese Medical Journal 2023;136(10):1188-1197
BACKGROUND:
Pneumonia-like primary pulmonary lymphoma (PPL) was commonly misdiagnosed as infectious pneumonia, leading to delayed treatment. The purpose of this study was to establish a computed tomography (CT)-based radiomics model to differentiate pneumonia-like PPL from infectious pneumonia.
METHODS:
In this retrospective study, 79 patients with pneumonia-like PPL and 176 patients with infectious pneumonia from 12 medical centers were enrolled. Patients from center 1 to center 7 were assigned to the training or validation cohort, and the remaining patients from other centers were used as the external test cohort. Radiomics features were extracted from CT images. A three-step procedure was applied for radiomics feature selection and radiomics signature building, including the inter- and intra-class correlation coefficients (ICCs), a one-way analysis of variance (ANOVA), and least absolute shrinkage and selection operator (LASSO). Univariate and multivariate analyses were used to identify the significant clinicoradiological variables and construct a clinical factor model. Two radiologists reviewed the CT images for the external test set. Performance of the radiomics model, clinical factor model, and each radiologist were assessed by receiver operating characteristic, and area under the curve (AUC) was compared.
RESULTS:
A total of 144 patients (44 with pneumonia-like PPL and 100 infectious pneumonia) were in the training cohort, 38 patients (12 with pneumonia-like PPL and 26 infectious pneumonia) were in the validation cohort, and 73 patients (23 with pneumonia-like PPL and 50 infectious pneumonia) were in the external test cohort. Twenty-three radiomics features were selected to build the radiomics model, which yielded AUCs of 0.95 (95% confidence interval [CI]: 0.94-0.99), 0.93 (95% CI: 0.85-0.98), and 0.94 (95% CI: 0.87-0.99) in the training, validation, and external test cohort, respectively. The AUCs for the two readers and clinical factor model were 0.74 (95% CI: 0.63-0.83), 0.72 (95% CI: 0.62-0.82), and 0.73 (95% CI: 0.62-0.84) in the external test cohort, respectively. The radiomics model outperformed both the readers' interpretation and clinical factor model ( P <0.05).
CONCLUSIONS
The CT-based radiomics model may provide an effective and non-invasive tool to differentiate pneumonia-like PPL from infectious pneumonia, which might provide assistance for clinicians in tailoring precise therapy.
Humans
;
Retrospective Studies
;
Pneumonia/diagnostic imaging*
;
Analysis of Variance
;
Tomography, X-Ray Computed
;
Lymphoma/diagnostic imaging*
7.Early differential diagnosis between COVID-19 and mycoplasma pneumonia with chest CT scan.
Xianluo HUO ; Xiaohua XUE ; Shuhui YUAN ; Dianchun ZHANG ; Qing'e GAO ; Tao GONG
Journal of Zhejiang University. Medical sciences 2020;49(4):468-473
OBJECTIVE:
To early differentiate between coronavirus disease 2019 (COVID-19) and adult mycoplasma pneumonia with chest CT scan.
METHODS:
Twenty-six patients with COVID-19 and 21 patients with adult mycoplasma pneumonia confirmed with RT-PCR test were enrolled from Zibo First Hospital and Lanshan People's Hospital during December 1st 2019 and March 14th 2020. The early chest CT manifestations were analyzed and compared between the two groups.
RESULTS:
The interstitial changes with ground glass density shadow (GGO) were similar in two groups during first chest CT examination (>0.05). There were more lung lobes involved on the first chest CT in COVID-19 patients, which were mostly distributed in the dorsal outer zone (23/26, 88.5%), and nearly half of them (12/26, 46.2%) were accompanied by crazy-paving sign; while the lesions in adult mycoplasma pneumonia patients were mostly distributed along the bronchi, and the bronchial wall was thickened (19/21, 90.5%), accompanied with tree buds / fog signs (19/21, 90.5%). The above CT signs were significantly different between the two kinds of pneumonia (all <0.01). COVID-19 had a longer course compared with mycoplasma pneumonia, the disease peaks of COVID-19 patients was on day (10.5±3.8), while the disease on CT was almost absorbed on day (7.9±2.2) in adult mycoplasma pneumonia. The length of hospital stay in COVID-19 patients was significantly longer than that of mycoplasma pneumonia patients [(19.5±4.3) d vs (7.9±2.2) d, <0.01].
CONCLUSIONS
The lesions of adult mycoplasma pneumonia are mostly distributed along the bronchi with tree buds/fog signs, while the lesions of COVID-19 are mainly distributed in the dorsal outer zone accompanied by crazy-paving sign, which can early distinguish two diseases.
Adult
;
Betacoronavirus
;
Clinical Laboratory Techniques
;
standards
;
Coronavirus Infections
;
diagnosis
;
diagnostic imaging
;
Diagnosis, Differential
;
Humans
;
Lung
;
diagnostic imaging
;
Pandemics
;
Pneumonia, Mycoplasma
;
diagnostic imaging
;
Pneumonia, Viral
;
diagnostic imaging
;
Tomography, X-Ray Computed
9.CT imaging features of patients with different clinical types of COVID-19.
Qi ZHONG ; Zhi LI ; Xiaoyong SHEN ; Kaijin XU ; Yihong SHEN ; Qiang FANG ; Feng CHEN ; Tingbo LIANG
Journal of Zhejiang University. Medical sciences 2020;49(2):198-202
OBJECTIVE:
To investigate the CT findings of patients with different clinical types of coronavirus disease 2019 (COVID-19).
METHODS:
A total of 67 patients diagnosed as COVID-19 by nucleic acid testing were collected and divided into 4 groups according to the clinical stages based on . The CT imaging characteristics were analyzed among patients with different clinical types.
RESULTS:
Among 67 patients, 3(4.5%) were mild, 35 (52.2%) were moderate, 22 (32.8%) were severe, and 7(10.4%) were critical ill. No significant abnormality in chest CT imaging in mild patients. The 35 cases of moderate type included 3 (8.6%) single lesions, the 22 cases of severe cases included 1 (4.5%) single lesion and the rest cases were with multiple lesions. CT images of moderate patients were mainly manifested by solid plaque shadow and halo sign (18/35, 51.4%); while fibrous strip shadow with ground glass shadow was more frequent in severe cases (7/22, 31.8%). Consolidation shadow as the main lesion was observed in 7 cases, and all of them were severe or critical ill patients.
CONCLUSIONS
CT images of patients with different clinical types of COVID-19 have characteristic manifestations, and solid shadow may predict severe and critical illness.
Betacoronavirus
;
isolation & purification
;
Coronavirus Infections
;
classification
;
diagnostic imaging
;
Humans
;
Lung
;
diagnostic imaging
;
Pandemics
;
classification
;
Pneumonia, Viral
;
classification
;
diagnostic imaging
;
Tomography, X-Ray Computed
10.CT imaging features of patients with different clinical types of coronavirus disease 2019 (COVID-19).
Qi ZHONG ; Zhi LI ; Xiaoyong SHEN ; Kaijin XU ; Yihong SHEN ; Qiang FANG ; Feng CHEN ; Tingbo LIANG
Journal of Zhejiang University. Medical sciences 2020;49(1):198-202
OBJECTIVE:
To analyze the CT findings of patients with different clinical types of coronavirus disease 2019 (COVID-19).
METHODS:
A total of 67 patients diagnosed as COVID-19 by nucleic acid testing were included and divided into 4 groups according to the clinical staging based on . The CT imaging characteristics were analyzed among patients with different clinical types.
RESULTS:
Among 67 patients, 3 (4.5%) were mild cases, 35 (52.2%) were ordinary cases, 22 (32.8%) were severe cases, and 7 (10.4%) were critically ill. There were no abnormal CT findings in mild cases. In 35 ordinary cases, there were single lesions in 3 cases (8.6%) and multiple lesions in 33 cases (91.4%), while in severe case 1 case had single lesion (4.5%) and 21 had multiple lesions (95.5%). CT images of ordinary patients were mainly manifested as solid plaque shadow and halo sign (18/35, 51.4%); while fibrous strip shadow with ground glass shadow was more frequent in severe cases (7/22, 31.8%). Consolidation shadow as the main lesion was observed in 7 cases, and all of them were severe or critical ill patients.
CONCLUSIONS
CT images in patients with different clinical types of COVID-19 have characteristic manifestations, and solid shadow may predict severe and critical illness.
Betacoronavirus
;
Clinical Laboratory Techniques
;
Coronavirus Infections
;
diagnosis
;
diagnostic imaging
;
Humans
;
Lung
;
diagnostic imaging
;
pathology
;
Pneumonia, Viral
;
diagnostic imaging
;
pathology
;
Severity of Illness Index
;
Tomography, X-Ray Computed
;
methods