scholarly journals Dependence of radiomic features on pixel size affects the diagnostic performance of radiomic signature for the invasiveness of pulmonary ground-glass nodule

2020 ◽  
pp. 20200089
Author(s):  
Guangyu Tao ◽  
Lekang Yin ◽  
Dejun Shi ◽  
Jianding Ye ◽  
Zhenghai Lu ◽  
...  
Keyword(s):  
Diagnostic Performance ◽  
Size Variation ◽  
Field Of View ◽  
Ground Glass ◽  
Pixel Size ◽  
Matrix Size ◽  
Ground Glass Nodule ◽  
Ground Glass Nodules ◽  
Better Than ◽  
Small Pixel

Objective: To investigate the effect of reducing pixel size on the consistency of radiomic features and the diagnostic performance of the downstream radiomic signatures for the invasiveness for pulmonary ground-glass nodules (GGNs) on CTs. Methods: We retrospectively collected the clinical data of 182 patients with GGNs on high resolution CT (HRCT). The CT images of different pixel sizes (0.8mm, 0.4mm, 0.18 mm) were obtained by reconstructing the single HRCT scan using three combinations of field of view and matrix size. For each pixel size setting, radiomic features were extracted for all GGNs and radiomic signatures for the invasiveness of GGNs were built through two modeling pipelines for comparison. Results: The study finally extracted 788 radiomic features. 87% radiomic features demonstrated inter pixel size variation. By either modeling pipeline, the radiomic signature under small pixel size performed significantly better than those under middle or large pixel sizes in predicting the invasiveness of GGNs (p’s value <0.05 by Delong test). With the independent modeling pipeline, the three pixel size bounded radiomic signatures shared almost no common features. Conclusions: Reducing pixel size could cause inconsistency in most radiomic features and improve the diagnostic performance of the downstream radiomic signatures. Particularly, super HRCTs with small pixel size resulted in more accurate radiomic signatures for the invasiveness of GGNs. Advances in knowledge: The dependence of radiomic features on pixel size will affect the performance of the downstream radiomic signatures. The future radiomic studies should consider this effect of pixel size.

Invasiveness prediction of pure ground glass nodules(≤3cm)

2021 ◽  
Author(s):  
Ziyi Wang ◽  
Lindan Zuo ◽  
Zhimin Liao ◽  
Wei Zheng ◽  
Qi Hu ◽  
...  
Keyword(s):  
Clinical Data ◽  
Univariate Analysis ◽  
Multivariate Logistic Regression Analysis ◽  
Ground Glass ◽  
Maximum Diameter ◽  
Imaging Features ◽  
Invasive Adenocarcinoma ◽  
Maximal Diameter ◽  
Ground Glass Nodule ◽  
Ground Glass Nodules

Abstract Background Pure ground-glass nodules are considered to be radiologically noninvasive in lung adenocarcinoma. However, some pure ground-glass nodules are found to be invasive adenocarcinoma pathologically. This study aimed to find out the correlation between the clinical imaging features and the degree of invasion of pulmonary pure ground glass nodules (≤ 3cm). Methods The clinical data of 886 patients who underwent minimally invasive surgery for pulmonary nodules from June 2013 to June 2016 were collected. Among them, 72 patients had complete clinical data and isolated pulmonary ground glass nodule resection, and the diameter of pulmonary ground glass nodule was less than or equal to 3 cm. Results A total of 72 eligible patients were included in the study. Univariate analysis showed that there were significant differences in carcinoembryonic antigen, maximum diameter and area of pure ground glass nodules in patients with pre-invasive lesions and invasive lesions(P < 0.05). Multivariate logistic regression analysis showed that there were only statistical differences in the maximum diameter of nodule pre-invasive lesions and invasive lesions. The optimal cutoff value for CT-maximal diameter to predict pre-invasive lesions or invasive lesions was 1.08cm. Conclusion It is reliable to predict the pathological types of nodules (pre-invasive and invasive) by measuring the maximum diameter of pure ground glass nodules, and the most reliable cut-off value is 1.08cm.

scholarly journals Diagnostic performance of chest CT in differentiating COVID-19 from other causes of ground-glass opacities

2021 ◽  
Vol 52 (1) ◽  
Author(s):  
Ali H. Elmokadem ◽  
Dalia Bayoumi ◽  
Sherif A. Abo-Hedibah ◽  
Ahmed El-Morsy
Keyword(s):  
Diagnostic Performance ◽  
Pulmonary Nodules ◽  
Ground Glass Opacity ◽  
Chest Ct ◽  
Ground Glass ◽  
Rt Pcr ◽  
Laboratory Findings ◽  
Halo Sign ◽  
Traction Bronchiectasis ◽  
Chest Ct Scan

Abstract Background To evaluate the diagnostic performance of chest CT in differentiating coronavirus disease 2019 (COVID-19) and non-COVID-19 causes of ground-glass opacities (GGO). Results A total of 80 patients (49 males and 31 females, 46.48 ± 16.09 years) confirmed with COVID-19 by RT-PCR and who underwent chest CT scan within 2 weeks of symptoms, and 100 patients (55 males and 45 females, 48.94 ± 18.97 years) presented with GGO on chest CT were enrolled in the study. Three radiologists reviewed all CT chest exams after removal of all identifying data from the images. They expressed the result as positive or negative for COVID-19 and recorded the other pulmonary CT features with mention of laterality, lobar affection, and distribution pattern. The clinical data and laboratory findings were recorded. Chest CT offered diagnostic accuracy ranging from 59 to 77.2% in differentiating COVID-19- from non-COVID-19-associated GGO with sensitivity from 76.25 to 90% and specificity from 45 to 67%. The specificity was lower when differentiating COVID-19 from non-COVID-19 viral pneumonias (30.5–61.1%) and higher (53.1–70.3%) after exclusion of viral pneumonia from the non-COVID-19 group. Patients with COVID-19 were more likely to have lesions in lower lobes (p = 0.005), peripheral distribution (p < 0.001), isolated ground-glass opacity (p = 0.043), subpleural bands (p = 0.048), reverse halo sign (p = 0.005), and vascular thickening (p = 0.013) but less likely to have pulmonary nodules (p < 0.001), traction bronchiectasis (p = 0.005), pleural effusion (p < 0.001), and lymphadenopathy (p < 0.001). Conclusions Chest CT offered reasonable sensitivity when differentiating COVID-19- from non-COVID-19-associated GGO with low specificity when differentiating COVID-19 from other viral pneumonias and moderate specificity when differentiating COVID-19 from other causes of GGO.

CT Characteristics for Predicting Invasiveness in Pulmonary Pure Ground-Glass Nodules

2020 ◽  
Vol 215 (2) ◽  
pp. 351-358 ◽  
Author(s):  
Zhi-gang Chu ◽  
Wang-jia Li ◽  
Bin-jie Fu ◽  
Fa-jin Lv
Keyword(s):  
Ground Glass ◽  
Ground Glass Nodules

scholarly journals Diffuse Cystic Metastases in the Lung after Nivolumab Treatment in a Patient with Non-Small Cell Lung Cancer: A Case Report

2021 ◽  
pp. 34-38
Author(s):  
Satoshi Muto ◽  
Yuki Ozaki ◽  
Takuya Inoue ◽  
Naoyuki Okabe ◽  
Yuki Matsumura ◽  
...  
Keyword(s):  
Lung Adenocarcinoma ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitors ◽  
Checkpoint Inhibitors ◽  
Lung Metastases ◽  
Sialyl Lewis X ◽  
Ground Glass ◽  
Cystic Lesions ◽  
Positron Emission ◽  
Ground Glass Nodules

Although diffuse cysts in the lung can be found in many diseases, they are uncommon in metastatic lung adenocarcinoma. They are even more unusual after the administration of immune checkpoint inhibitors. A case of lung adenocarcinoma that developed diffuse cysts in the lungs during treatment with nivolumab is reported. The patient was a 60-year-old woman with postoperative recurrent lung adenocarcinoma in mediastinal lymph nodes and pleural dissemination. After first-line treatment with cisplatin, pemetrexed, and bevacizumab, computed tomography (CT) showed disease progression. Treatment was then switched to nivolumab. After 5 courses of nivolumab, CT showed multiple ground-glass nodules in her lungs. After 4 more courses of nivolumab, the ground-glass nodules increased in size, and cystic air spaces appeared in their centers. The patient did not have any symptoms. Laboratory tests showed no evidence of infection or nivolumab-induced pneumonitis. Sialyl Lewis X-i antigen increased, and positron emission tomography showed abnormal uptake of 18F-fluorodeoxyglucose in these lesions. Considering this evidence, the cystic lesions were diagnosed as multiple lung metastases. Various differential diagnoses should be considered when diffuse cystic lesions are found in the lungs after the administration of immune checkpoint inhibitors.

scholarly journals Enlarged inflammatory multiple ground-glass nodules of the lung over five years' follow-up: A surgical case report

2015 ◽  
Vol 29 (7) ◽  
pp. 890-895
Author(s):  
Naoya Yokomakura ◽  
Hiroo Nishijima ◽  
Masakazu Yanagi ◽  
Kazuhiro Wakida ◽  
Aya Harada ◽  
...  
Keyword(s):  
Case Report ◽  
Ground Glass ◽  
Surgical Case ◽  
Ground Glass Nodules

scholarly journals Significance of intra-nodular vessel sign in differentiating benign and malignant pulmonary ground-glass nodules

2021 ◽  
Vol 12 (1) ◽  
Author(s):  
Bin-jie Fu ◽  
Fa-jin Lv ◽  
Wang-jia Li ◽  
Rui-yu Lin ◽  
Yi-neng Zheng ◽  
...  
Keyword(s):  
Differential Diagnosis ◽  
Pulmonary Veins ◽  
Ground Glass ◽  
Occurrence Rate ◽  
Pathological Examination ◽  
Common Occurrence ◽  
Vascular Changes ◽  
Distance Ratio ◽  
Pulmonary Vessels ◽  
Ground Glass Nodules

Abstract Background The presence of pulmonary vessels inside ground-glass nodules (GGNs) of different nature is a very common occurrence. This study aimed to reveal the significance of pulmonary vessels displayed in GGNs in their diagnosis and differential diagnosis. Results A total of 149 malignant and 130 benign GGNs confirmed by postoperative pathological examination were retrospectively enrolled in this study. There were significant differences in size, shape, nodule-lung interface, pleural traction, lobulation, and spiculation (each p < 0.05) between benign and malignant GGNs. Compared with benign GGNs, intra-nodular vessels were more common in malignant GGNs (67.79% vs. 54.62%, p = 0.024), while the vascular categories were similar (p = 0.663). After adjusting the nodule size and the distance between the nodule center and adjacent pleura [radius–distance ratio, RDR], the occurrences of internal vessels between them were similar. The number of intra-nodular vessels was positively correlated with nodular diameter and RDR. Vascular changes were more common in malignant than benign GGNs (52.48% vs. 18.31%, p < 0.0001), which mainly manifested as distortion and/or dilation of pulmonary veins (61.19%). The occurrence rate, number, and changes of internal vessels had no significant differences among all the pre-invasive and invasive lesions (each p > 0.05). Conclusions The incidence of internal vessels in GGNs is mainly related to their size and the distance between nodule and pleura rather than the pathological nature. However, GGNs with dilated or distorted internal vessels, especially pulmonary veins, have a higher possibility of malignancy.

Effect of Lung Volume and Gravity on the Attenuation and Size of a Pure Ground-Glass Nodule

2012 ◽  
Vol 27 (1) ◽  
pp. W15-W17 ◽  
Author(s):  
Gilbert R. Ferretti ◽  
François Arbib ◽  
Jean François Roux ◽  
Vincent Bland ◽  
Sylvie Lantuejoul
Keyword(s):  
Lung Volume ◽  
Ground Glass ◽  
Ground Glass Nodule

scholarly journals Research on Generation Method of Grasp Strategy Based on DeepLab V3+ for Three-Finger Gripper

Information ◽  
2021 ◽  
Vol 12 (7) ◽  
pp. 278
Author(s):  
Sanlong Jiang ◽  
Shaobo Li ◽  
Qiang Bai ◽  
Jing Yang ◽  
Yanming Miao ◽  
...  
Keyword(s):  
Field Of View ◽  
Convolution Kernel ◽  
Parallel Connection ◽  
Multi Scale ◽  
Spatial Pyramid Pooling ◽  
The Stability ◽  
Parameter Values ◽  
Filter Layer ◽  
Complex Dataset ◽  
Better Than

A reasonable grasping strategy is a prerequisite for the successful grasping of a target, and it is also a basic condition for the wide application of robots. Presently, mainstream grippers on the market are divided into two-finger grippers and three-finger grippers. According to human grasping experience, the stability of three-finger grippers is much better than that of two-finger grippers. Therefore, this paper’s focus is on the three-finger grasping strategy generation method based on the DeepLab V3+ algorithm. DeepLab V3+ uses the atrous convolution kernel and the atrous spatial pyramid pooling (ASPP) architecture based on atrous convolution. The atrous convolution kernel can adjust the field-of-view of the filter layer by changing the convolution rate. In addition, ASPP can effectively capture multi-scale information, based on the parallel connection of multiple convolution rates of atrous convolutional layers, so that the model performs better on multi-scale objects. The article innovatively uses the DeepLab V3+ algorithm to generate the grasp strategy of a target and optimizes the atrous convolution parameter values of ASPP. This study used the Cornell Grasp dataset to train and verify the model. At the same time, a smaller and more complex dataset of 60 was produced according to the actual situation. Upon testing, good experimental results were obtained.

Sign in / Sign up

Export Citation Format

Share Document