Multi-Disease Classification For Retinal Diseases Using Deep Learning Technique (Record no. 608902)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02599nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 610 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Khan, Omar Salman |
| 245 ## - TITLE STATEMENT | |
| Title | Multi-Disease Classification For Retinal Diseases Using Deep Learning Technique |
| Statement of responsibility, etc. | Omar Salman Khan |
| 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 | 2022. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 55p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Diagnosis before the spread of retinal diseases is vital to prevent high level blindness<br/>and any sort of visual impairment. Many retinal diseases can be found via the fundus<br/>imaging which has a very important role in the observation and detection of various<br/>ophthalmic diseases. Most previous literature has focused their approaches on<br/>identifying individual diseases or a combination of 3-4 diseases like DR, MYA,<br/>ARMD, MH, ODC having major research. The eye is mostly affected by more than<br/>one underlying disease or disease marker, and uptil now most datasets had very few<br/>classes. Recently introduced RFMiD dataset, is one of the first datasets to provide 45<br/>different classes of ophthalmic diseases. Hence making it possible to work towards<br/>automated multi-disease classification models which would provide great help to<br/>highlight this issue via clinical decision support systems integrated in the medical<br/>image diagnosis. Our work aimed to achieve higher accuracy than previous literature<br/>and to create an CDS application from the model in understanding and predicting multi<br/>retinal diseases. Deep learning models are excellent and have proven to be extremely<br/>effective in solving complex image processing problems. In addition, ensemble<br/>learning yields high generalization performance by reducing variance. Therefore, a<br/>synthesis of transfer, ensemble, and deep learning was used in this work to create an<br/>accurate and reliable model for multi retinal disease classification. To create the Multi<br/>Retinal Disease Classification Model (MRDCM) we used ensemble of EfficientNetB4<br/>and EfficientNetV2S, with our final ensemble model giving promising results. In our<br/>evaluation, we scored an AUC of 0.973 which stands better than literature. Further our<br/>model selection is lighter than models used in literature. The model was tested on 27<br/>main classes of RFMiD dataset for comparison with literature. Index Terms—Deep<br/>iii<br/>Learning, Ensemble learning, Retinal Image Analysis, multi-Disease classification,<br/>transfer learning. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Biomedical Engineering (BME) |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Omer Gilani |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/31043">http://10.250.8.41:8080/xmlui/handle/123456789/31043</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 | 04/22/2024 | 610 | SMME-TH-775 | Thesis |