Osteoarthritis (OA) is primarily characterized by progressive degeneration of structure and composition articular cartilage (AC), along with the sclerotic changes in subchondral bone. These changes in the microstructure of AC and subchondral bone can be visualized in three-dimensions (3D) using µCT. However, direct µCT imaging of soft tissues, such us AC, is not possible. This model tackles the problem of automatic tidemark segmentation in phosphotungstic acid (PTA) stained osteochondral samples using Deep Learning. The model also presents a data acquisition protocol base that allowes to obtain the segmentation masks without their explicit annotation by a human expert. The model is shown to perform better than UNet model which is primarily used in practice.
Input variables : CT Image
Output Variables : Micro CT images of articular cartilage
| Statistical | : | Somers D | Accuracy | Precision and Recall | Confusion Matrix | F1 Score | Roc and Auc | Prevalence | Detection Rate | Balanced Accuracy | Cohen's Kappa | Concordance | Gini Coefficent | KS Statistic | Youden's J Index |
| Infrastructure | : | Log Bytes | Logging/User/IAMPolicy | Logging/User/VPN | CPU Utilization | Memory Usage | Error Count | Prediction Count | Prediction Latencies | Private Endpoint Prediction Latencies | Private Endpoint Response Count |
Visit Model : github.com
Additional links : arxiv.org
| Model Category | : | Public |
| Date Published | : | July, 2019 |
| Healthcare Domain | : | Provider |
| Code | : | github.com |
| Health Risk Management |
| Chronic Care Management |