Aggarwal, Preeti and Vig, Renu and Sardana, H.K. (2013) Patient-Wise Versus Nodule-Wise Classification of Annotated Pulmonary Nodules using Pathologically Confirmed Cases. Journal of Computers, 8 (9). pp. 2245-2255. ISSN 1796-203X
Full text not available from this repository.Abstract
This paper presents a novel framework for combining well known shape, texture, size and resolution informatics descriptor of solitary pulmonary nodules (SPNs) detected using CT scan. The proposed methodology evaluates the performance of classifier in differentiating benign, malignant as well as metastasis SPNs with 246 chests CT scan of patients. Both patient-wise as well as nodule-wise available diagnostic report of 80 patients was used in differentiating the SPNs and the results were compared. For patient-wise data, generated a model with efficiency of 62.55% with labeled nodules and using semi-supervised approach, labels of rest of the unknown nodules were predicted and finally classification accuracy of 82.32% is achieved with all labeled nodules. For nodule-wise data, ground truth database of labeled nodules is expanded from a very small ground truth using content based image retrieval CBIR) method and achieved a precision of 98%. Proposed methodology not only avoids unnecessary biopsies but also efficiently label unknown nodules using pre-diagnosed cases which can certainly help the physicians in diagnosis.
| Item Type: | Article |
|---|---|
| Uncontrolled Keywords: | Computer aided diagnosis; lung cancer; CT; SPNs; Haralick; Gabor; classification; SVM; PCA. |
| Subjects: | CSIO > Computational Instrumentation CSIO > Medical Instrumentation |
| Divisions: | Computational Instrumentation |
| Depositing User: | Ms. Jyotsana |
| Date Deposited: | 13 Jan 2015 10:21 |
| Last Modified: | 13 Jan 2015 10:21 |
| URI: | http://csioir.csio.res.in/id/eprint/444 |
Actions (login required)
 |
View Item |
