Multilabel Classification and Localization of Rare Pulmonary Diseases using Deep Learning / (Record no. 608658)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 01838nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 610 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Khaliq, Fariha |
| 245 ## - TITLE STATEMENT | |
| Title | Multilabel Classification and Localization of Rare Pulmonary Diseases using Deep Learning / |
| Statement of responsibility, etc. | Fariha Khaliq |
| 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 | 52p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Chest radiography is the most common radiological examination used for the<br/>diagnosis of thoracic diseases. Currently, automated classification of radiological images<br/>is abundantly used in clinical diagnosis. However, each pathology has its own response<br/>characteristic receptive field regions, which is a key problem during the classification of<br/>chest diseases. In addition to extreme class imbalance, cases labelled as uncertain in the<br/>dataset further complicate this task. To solve this problem, we propose a semi-supervised<br/>learning approach known as U-SelfTrained. In this scheme, uncertain labels are left<br/>unlabeled in the dataset; first, the model is trained on labelled instances and then on<br/>unlabeled instances relabeling them with labels having a higher probability.<br/>Comprehensive experimentation was carried out on the CheXpert dataset, which consists<br/>of 223,816 frontal and lateral view CXR images of 64,740 patients with 14 diseases. The<br/>testing accuracy is 0.877 on the CheXpert dataset, which is currently the highest score<br/>achieved to date. This validates the effectiveness of this method for chest radiography<br/>classification. The practical significance of this study is the implementation of AI<br/>algorithms to assist radiologists in improving their diagnostic accuracy. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Biomedical Sciences (BMS) |
| 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/123456789/31146">http://10.250.8.41:8080/xmlui/handle/123456789/31146</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 | 03/11/2024 | 610 | SMME-TH-788 | Thesis |