Marker controlled watershed transform for intra-retinal cysts segmentation from optical coherence tomography B-scans
| Autor: | Jeny Rajan, Abhishek R. Kothari, G. N. Girish |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Ground truth
Watershed Correlation coefficient medicine.diagnostic_test business.industry Computer science k-means clustering 01 natural sciences 030218 nuclear medicine & medical imaging 010309 optics 03 medical and health sciences 0302 clinical medicine Optical coherence tomography Artificial Intelligence 0103 physical sciences Signal Processing medicine Computer vision Segmentation Computer Vision and Pattern Recognition Artificial intelligence Cluster analysis Precision and recall business Software |
| Zdroj: | Pattern Recognition Letters. 139:86-94 |
| ISSN: | 0167-8655 |
| Popis: | Retinal cysts have pathological significance in several eye disorders. Detecting and quantifying such cysts from optical coherence tomography (OCT) scans is currently tedious and requires expertise. To aid the diagnostic process, an automatic intra-retinal cyst segmentation method using marker-controlled watershed transform on OCT B-scans is proposed in this paper. The proposed method is based on two stages – k-means clustering technique is used to identify cysts in the form of markers, followed by topographical based watershed transform for final segmentation. Qualitative and quantitative evaluation of proposed method was carried out against ground truth obtained from two graders on OPTIMA cyst segmentation challenge dataset. This method efficiently segments cystic structures with mean recall and precision rate 0.67 and 0.78, respectively, while preserving high correlation coefficient of 0.95 against ground truth obtained from both graders. Obtained results show that the proposed method outperformed other existing methods. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect