Name
Title | ||
|---|---|---|
Learning Orientation Invariant Contextual Features For Nodule Detection In Lung Ct Scans |
Abstract | ||
|---|---|---|
This work combines model-based local shape analysis and data-driven local contextual feature learning for improved detection of pulmonary nodules in low dose computed tomography ( LDCT) chest scans. We reduce orientation-induced appearance variability by performing intensity-weighted principal component analysis ( PCA) to estimate the local orientation at each candidate location. Random comparison primitives defined in a local coordinate system are used to describe the local context around a nodule candidate. A random forest is trained to learn and combine a subset of these primitives into discriminative orientation invariant contextual features and classify nodule candidates. Validation using 99 CT scans from the publicly available Lung Image Database Consortium ( LIDC) demonstrates the benefit of combining geometric modeling and data-driven machine learning. The proposed method reduces more than 80% of false positives of the baseline model-based method consistently over a wide range of sensitivity levels (70%-90%). |
Year | Venue | Keywords |
|---|---|---|
2015 | 2015 IEEE 12TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI) | Nodule detection, lung CT, orientation invariance, contextual feature, random forest |
Field | DocType | ISSN |
Computer vision,Pattern recognition,Medical imaging,Computer science,Feature extraction,Artificial intelligence,Random forest,Discriminative model,Feature learning,Principal component analysis,Shape analysis (digital geometry),False positive paradox | Conference | 1945-7928 |
Citations | PageRank | References |
3 | 0.43 | 7 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Junjie Bai | 1 | 69 | 12.49 |
| Xiaojie Huang | 2 | 3 | 0.43 |
| Shubao Liu | 3 | 156 | 10.25 |
| Qi Song | 4 | 7 | 1.27 |
| Roshni Bhagalia | 5 | 26 | 4.58 |