A Robust Scheme of Vertebrae Segmentation for Medical Diagnosis / (Record no. 610613)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 04101nam a22001457a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 629.8 |
| 245 ## - TITLE STATEMENT | |
| Title | A Robust Scheme of Vertebrae Segmentation for Medical Diagnosis / |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2019. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 114p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Automated vertebrae analysis from medical images plays an important role in computer<br/>aided diagnosis (CAD). It provides an initial and early identification of various vertebral<br/>abnormalities to doctors and radiologists. Vertebrae segmentation and classification are<br/>important but difficult tasks in medical imaging due to low contrasts in image, noise and high<br/>topological shape variations in radiological scans. It becomes even more challenging when<br/>dealing with various deformities and pathologies present in the vertebral scans like osteoporotic<br/>vertebral fractures.<br/>In this work, we want to address the challenging problem of vertebral image analysis for<br/>vertebra segmentation and classification. In the past, various traditional imagery techniques were<br/>employed to address these problems. Recently, deep learning techniques have been introduced in<br/>biomedical image processing for segmentation and characterization of several abnormalities.<br/>These techniques are becoming popular in solving various medical image analysis problems due<br/>to their robustness and accuracy.<br/>In this research, we present a solution of vertebrae segmentation and classification<br/>problem with the help of deep learning approach. We present a novel combination of traditional<br/>region based level-set with deep learning framework in order to extract the shape of vertebral<br/>bones accurately; which would be able to handle the deformities in the vertebral bones precisely<br/>and efficiently. After vertebrae segmentation, we further extend the work to abnormal vertebrae<br/>classification with the help of deep learning approach. This novel framework would be able to<br/>help the medical doctors and radiologists with better visualization of vertebral bones and<br/>providing the initial automated classification of vertebrae to be normal or abnormal.<br/>The proposed method of vertebrae segmentation was successfully tested on different<br/>datasets with various fields of views. The first dataset comprises of 173 CT scans of<br/>thoracolumbar (thoracic and lumbar) vertebrae in sagittal view, collected from a local hospital.<br/>The second dataset comprises 73 CT scans of cervical vertebrae in sagittal view, also collected<br/>from a local hospital. The third dataset comprises 20 CT scans of thoracolumbar (thoracic and<br/>lumbar) vertebrae in sagittal view collected from spine segmentation challenge CSI 2014. The<br/>forth dataset comprises 25 CT scans of lumbar vertebrae in sagittal view collected from spine<br/>segmentation challenge CSI 2016. Lastly, we have utilized the same locally collected set of 173<br/>iii<br/>CT scans of thoracolumbar (thoracic and lumbar) vertebrae and extracted in axial view to<br/>perform the segmentation task.<br/>For classification purpose, we have utilized the locally collected set of 173 CT scans of<br/>thoracolumbar (thoracic and lumbar) vertebrae as these include osteoporotic vertebral fractures<br/>in it. The details of these datasets have been presented in respective sections.<br/>We have achieved promising results on our proposed techniques. The evaluation of the<br/>segmentation performance on the datasets with various machines and field of views helped us to<br/>ensure the robustness of our proposed method. On validation sets of these datasets, we have<br/>achieved an average dice score of around 95% for vertebrae segmentation; and accuracy of<br/>above 80% for the vertebrae classification. The detailed results have been presented in the results<br/>section. These results reveal that our proposed techniques are competitive over the other state of<br/>the arts in terms of accuracy, efficiency, flexibility and time |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | PhD Robotics and Intelligent Machine Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Syed Irtiza Ali Shah |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/13182">http://10.250.8.41:8080/xmlui/handle/123456789/13182</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 07/29/2024 | 629.8 | SMME-Phd-6 | Thesis |