Name
Abstract | ||
|---|---|---|
We present a machine learning tool for automatic texton-based joint classification and segmentation of mitochondria in MNT-1 cells imaged using ion-abrasion scanning electron microscopy (IA-SEM). For diagnosing signatures that may be unique to cellular states such as cancer, automatic tools with minimal user intervention need to be developed for analysis and mining of high-throughput data from these large volume data sets (typically ~2GB/cell). Challenges for such a tool in 3D electron microscopy arise due to low contrast and signal-to-noise ratios (SNR) inherent to biological imaging. Our approach is based on block-wise classification of images into a trained list of regions. Given manually labeled images, our goal is to learn models that can localize novel instances of the regions in test datasets. Since datasets obtained using electron microscopes are intrinsically noisy, we improve the SNR of the data for automatic segmentation by implementing a 2D texture-preserving filter on each slice of the 3D dataset. We investigate texton-based region features in this work. Classification is performed by k-nearest neighbor (k-NN) classifier, support vector machines (SVMs), adaptive boosting (AdaBoost) and histogram matching using a NN classifier. In addition, we study the computational complexity vs. segmentation accuracy tradeoff of these classifiers. Segmentation results demonstrate that our approach using minimal training data performs close to semi-automatic methods using the variational level-set method and manual segmentation carried out by an experienced user. Using our method, which we show to have minimal user intervention and high classification accuracy, we investigate quantitative parameters such as volume of the cytoplasm occupied by mitochondria, differences between the surface area of inner and outer membranes and mean mitochondrial width which are quantities potentially relevant to distinguishing cancer cells from normal cells. To test the accuracy of our approach, these quantities are compared against manually computed counterparts. We also demonstrate extension of these methods to segment 3D images obtained using electron tomography. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1016/j.patcog.2008.08.009 | Pattern Recognition |
Keywords | Field | DocType |
automatic joint classification,automatic texton-based joint classification,minimal user intervention,electron tomography,segmentation result,mitochondria,segmentation accuracy tradeoff,whole cell,manual segmentation,automated techniques,electron microscope,classification,automatic segmentation,texture features,segmentation,cancer detection,block-wise classification,machine learning,electron microscopy,3d imaging,support vector machine,k nearest neighbor,scanning electron microscopy,level set method,outer membrane,computational complexity,high throughput,signal to noise ratio,surface area | Computer vision,AdaBoost,Scale-space segmentation,Pattern recognition,Segmentation,Texton,Support vector machine,Image segmentation,Boosting (machine learning),Artificial intelligence,Contextual image classification,Mathematics | Journal |
Volume | Issue | ISSN |
42 | 6 | Pattern Recognition |
Citations | PageRank | References |
15 | 1.39 | 18 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rajesh Narasimha | 1 | 30 | 6.18 |
| Hua Ouyang | 2 | 187 | 11.60 |
| Alexander G. Gray | 3 | 990 | 80.16 |
| Steven W. McLaughlin | 4 | 343 | 41.18 |
| Subramaniam Sriram | 5 | 64 | 5.84 |