Fig 2 - uploaded by Vassili Kovalev
Content may be subject to copyright.
Example slices of typical lung CT images of two patients with atelectasis (ATL) and malignant tumor (TUM). Patient 1 (left image) suffering from the cancer of middle bronchus with atelectasis of the right middle lobe of the lung. Patient 2 (right image) with the cancer of right upper bronchus and atelectasis of the back segment of the upper lung lobe.
Source publication
This paper presents a generalized approach for computing image gradient. It is predominantly aimed at detecting unclear and in certain circumstances even completely invisible borders in large 2D and 3D texture images. The method exploits the conventional approach of sliding window. Once two pixel/voxel sets are sub-sampled from orthogonal window ha...
Context in source publication
Context 1
... of 1.5 mm. The voxel size of 31 remaining tomograms was 0.68 mm in the axial image plane with the slice thickness equal to the inter- slice distance of 5.0 mm. No intravenous contrast agent was administered before the collec- tion of scan data what is a significant detail of present study. Typical examples of original CT image slices are shown in Fig. 2. ...
Similar publications
Type II diabetes is a chronic condition that affects the way our body metabolizes sugar. The body's important source of fuel is now becoming a chronic disease all over the world. It is now very necessary to identify the new potential targets for the drugs which not only control the disease but also can treat it. Support vector machines are the clas...
Background: Virtual reality simulators and machine learning have the potential to augment understanding, assessment and training of psychomotor performance in neurosurgery residents. Objective: This study outlines the first application of machine learning to distinguish "skilled" and "novice" psychomotor performance during a virtual reality neurosu...
Citations
... Accurate delineation of the tumor boundary is of great significance in tumor diagnosis, staging, and treatment [3,4]. Kovalev et al.'s study showed that statistical significance scores cannot effectively distinguish tumors from atelectasis regions on plain CT images, but methods such as generalized gradients can effectively enhance the distinction between tumor regions and atelectasis regions [5,6]. Flechsig et al. 's study showed that the density analysis of plain CT images has a reference value for distinguishing tumors from atelectasis [7]. ...
... In cancer-related radiomics studies, the 3D shape features of a tumor are commonly used [23][24][25][26]. Kovalev et al.'s study explored the significance of 3D generalized gradient in tumor imaging research [6]. Guan et al.'s study showed that 3D radiomics features have certain reference values in distinguishing difficult-to-recognize boundaries [27]. ...
... Their study lacks an objective evaluation of imaging features, and our study objectively evaluated the differentiation effect of various imaging features on tumors and atelectasis through IG. In addition, we have also built machine learning models that can automatically classify tumors and [5,6]. However, their study only involves one image feature, while we tested thousands of features. ...
Objectives:
To evaluate the utility of radiomics features in differentiating central lung cancers and atelectasis on contrast-enhanced computed tomography (CT) images. This study is retrospective.
Materials and methods:
In this study, 36 patients with central pulmonary cancer and atelectasis between July 2013 and June 2018 were identified. A total of 1,653 2D and 2,327 3D radiomics features were extracted from segmented lung cancers and atelectasis on contrast-enhanced CT. The refined features were investigated for usefulness in classifying lung cancer and atelectasis according to the information gain, and 10 models were trained based on these features. The classification model is trained and tested at the region level and pixel level, respectively.
Results:
Among all the extracted features, 334 2D features and 1,507 3D features had an information gain (IG) greater than 0.1. The highest accuracy (AC) of the region classifiers was 0.9375. The best Dice score, Hausdorff distance, and voxel AC were 0.2076, 45.28, and 0.8675, respectively.
Conclusions:
Radiomics features derived from contrast-enhanced CT images can differentiate lung cancers and atelectasis at the regional and voxel levels.
