Mediastinal lymph node malignancy detection in computed tomography images using fully convolutional network

2020 ◽  
Vol 40 (1) ◽  
pp. 187-199 ◽  
Author(s):  
Hitesh Tekchandani ◽  
Shrish Verma ◽  
Narendra D. Londhe
Keyword(s):  
Computed Tomography ◽  
Lymph Node ◽  
Mediastinal Lymph Node ◽  
Convolutional Network ◽  
Fully Convolutional Network ◽  
Computed Tomography Images

Assessment of cervical lymph node metastases using indirect computed tomography lymphography with iopamidol in a tongue VX2 carcinoma model

2011 ◽  
Vol 125 (8) ◽  
pp. 820-828 ◽  
Author(s):  
Y Shu ◽  
X Xu ◽  
Z Wang ◽  
W Dai ◽  
Y Zhang ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lymph Node ◽  
Lymph Nodes ◽  
Lymph Node Metastases ◽  
Cervical Lymph Node ◽  
Cervical Lymph Nodes ◽  
Cervical Lymph Node Metastases ◽  
Computed Tomography Images ◽  
Vx2 Carcinoma ◽  
Node Metastases

AbstractObjective:To investigate the performance of indirect computed tomography lymphography with iopamidol for detecting cervical lymph node metastases in a tongue VX2 carcinoma model.Materials and methods:A metastatic cervical lymph node model was created by implanting VX2 carcinoma suspension into the tongue submucosa of 21 rabbits. Computed tomography images were obtained 1, 3, 5, 10, 15 and 20 minutes after iopamidol injection, on days 11, 14, 21 (six rabbits each) and 28 (three rabbits) after carcinoma transplantation. Computed tomography lymphography was performed, and lymph node filling defects and enhancement characteristics evaluated.Results:Indirect computed tomography lymphography revealed bilateral enhancement of cervical lymph nodes in all animals, except for one animal imaged on day 28. There was significantly slower evacuation of contrast in metastatic than non-metastatic nodes. A total of 41 enhanced lymph nodes displayed an oval or round shape, or local filling defects. One lymph node with an oval shape was metastatic (one of 11, 9.1 per cent), while 21 nodes with filling defects were metastatic (21/30, 70 per cent). The sensitivity, specificity, accuracy, and positive and negative predictive values when using a filling defect diameter of 1.5 mm as a diagnostic criterion were 86.4, 78.9, 82.9, 82.6 and 83.3 per cent, respectively.Conclusion:When using indirect computed tomography lymphography to detect metastatic lymph nodes, filling defects and slow evacuation of contrast agent are important diagnostic features.

Computed Tomography and Mediastinoscopy in the Assessment of Resectability of Lung Cancer

1989 ◽  
Vol 30 (2) ◽  
pp. 169-173 ◽  
Author(s):  
S. Lähde ◽  
K. Hyrynkangas ◽  
J. Merikanto ◽  
R. Pokela ◽  
K. Jokinen ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Lymph Node ◽  
Mediastinal Lymph Node ◽  
Lymph Node Involvement ◽  
Superior Mediastinum ◽  
Mediastinal Tumour ◽  
Tumour Spread ◽  
Tumour Extension ◽  
Mediastinal Involvement

In order to assess the potential of computed tomography (CT) of the mediastinum and mediastinoscopy in the staging of lung cancer, 125 patients were examined. Of these, 104 underwent thoracotomy, at which there was no evidence of mediastinal tumour involvement in 79 while 25 patients had signs of tumour spread. The sensitivity and specificity of CT were 87.0 per cent and 95.8 per cent, respectively, in the detection of direct tumour extension with a mediastinal mass. When lymph node enlargement was the sole finding, CT did not provide any differentiation between benign and malignant lymphadenopathy. The mediastinal involvement was inaccessible on mediastinoscopy in 18 cases (72%). Despite the surperior sensitivity of CT it was often difficult to determine whether direct tumour infiltratin of mediastinal structures had occurred. It was concluded that CT is necessary for screening the entire mediastinum and, when it reveals no evidence of mediastinal tumour spread, mediastinoscopy will yield no further information. Mediastinoscopy will help to correctly identify accessible mediastinal lymph node involvement of the superior mediastinum and to define the mediastinal tumour invasion in doubtful cases.

scholarly journals From Raw Pixels to Recurrence Image for Deep Learning of Benign and Malignant Mediastinal Lymph Nodes on Computed Tomography

2020 ◽  
Author(s):  
Tuan Pham
Keyword(s):  
Computed Tomography ◽  
Lung Cancer ◽  
Deep Learning ◽  
Lymph Node ◽  
Lymph Nodes ◽  
Mediastinal Lymph Node ◽  
Survival Rates ◽  
Primary Lung Cancer ◽  
Lymph Node Status ◽  
Mediastinal Lymph Nodes

<div>Lung cancer causes the most cancer deaths worldwide and has one of the lowest five-year survival rates of all cancer types. It is reported that more than half of patients with lung cancer die within one year of being diagnosed. Because mediastinal lymph node status is the most important factor for the treatment and prognosis of lung cancer, the aim of this study is to improve the predictive value in assessing the computed tomography (CT) of mediastinal lymph-node malignancy in patients with primary lung cancer. This paper introduces a new method for creating pseudo-labeled images of CT regions of mediastinal lymph nodes by using the concept of recurrence analysis in nonlinear dynamics for the transfer learning. Pseudo-labeled images of original CT images are used as input into deep-learning models. Three popular pretrained convolutional neural networks (AlexNet, SqueezeNet, and DenseNet-201) were used for the implementation of the proposed concept for the classification of benign and malignant mediastinal lymph nodes using a public CT database. In comparison with the use of the original CT data, the results show the high performance of the transformed images for the task of classification. The proposed method has the potential for differentiating benign from malignant mediastinal lymph nodes on CT, and may provide a new way for studying lung cancer using radiology imaging. </div><div><br></div>

Sign in / Sign up

Export Citation Format

Share Document