Cell image staining and analysis using robust AI
Accurate diagnosis of blood-related disorders in the field of hematology relies on the precise analysis of white blood cells (WBCs), a task that requires a detailed examination of cell attributes associated with it to classify it properly. While traditional methods are accurate and effective, they c...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/176742 |
| _version_ | 1811683073278869504 |
|---|---|
| author | Tan, Qin Xiong |
| author2 | Wen Bihan |
| author_facet | Wen Bihan Tan, Qin Xiong |
| author_sort | Tan, Qin Xiong |
| collection | NTU |
| description | Accurate diagnosis of blood-related disorders in the field of hematology relies on the precise analysis of white blood cells (WBCs), a task that requires a detailed examination of cell attributes associated with it to classify it properly. While traditional methods are accurate and effective, they can be time-consuming and subject to human error depending on the laboratory technician’s skills. On the other hand, automatic methods like flow cytometers are expensive and require highly trained specialists to operate and be constantly maintained by service engineers.
While there are studies into the categorization of WBC using AI, they are often lacking in necessary morphological details to explain their decision process. This project is supported by Sysmex Corporation and carried out in collaboration with an NTU project team and pathologists, who have developed an innovative approach. It involves identifying 11 morphological attributes for each cell and coupled with introducing comprehensive annotations for a Peripheral Blood Cells (PBC) dataset. Additionally, they have developed a deep learning (DL) model to predict these morphological attributes from cell images. The developed model aims to aid medical laboratory staff in making more informed decisions with explainable artificial intelligence (XAI), enabling quicker and more accurate diagnosis of blood-related disorders. However, the current model has some ongoing issues with predicting nucleus shape correctly.
Therefore, this final year project will focus on improving nucleus shape prediction accuracy and experiment with various techniques like image-preprocessing and attention mechanisms. Any improvement in prediction accuracy will be valuable for medical diagnostics, contributing to the development of a fully functional XAI for healthcare application. |
| first_indexed | 2024-10-01T04:06:56Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/176742 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T04:06:56Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1767422024-05-24T15:51:32Z Cell image staining and analysis using robust AI Tan, Qin Xiong Wen Bihan School of Electrical and Electronic Engineering National Supercomputing Centre (NSCC) Singapore Rapid-Rich Object Search (ROSE) Lab bihan.wen@ntu.edu.sg Engineering Accurate diagnosis of blood-related disorders in the field of hematology relies on the precise analysis of white blood cells (WBCs), a task that requires a detailed examination of cell attributes associated with it to classify it properly. While traditional methods are accurate and effective, they can be time-consuming and subject to human error depending on the laboratory technician’s skills. On the other hand, automatic methods like flow cytometers are expensive and require highly trained specialists to operate and be constantly maintained by service engineers. While there are studies into the categorization of WBC using AI, they are often lacking in necessary morphological details to explain their decision process. This project is supported by Sysmex Corporation and carried out in collaboration with an NTU project team and pathologists, who have developed an innovative approach. It involves identifying 11 morphological attributes for each cell and coupled with introducing comprehensive annotations for a Peripheral Blood Cells (PBC) dataset. Additionally, they have developed a deep learning (DL) model to predict these morphological attributes from cell images. The developed model aims to aid medical laboratory staff in making more informed decisions with explainable artificial intelligence (XAI), enabling quicker and more accurate diagnosis of blood-related disorders. However, the current model has some ongoing issues with predicting nucleus shape correctly. Therefore, this final year project will focus on improving nucleus shape prediction accuracy and experiment with various techniques like image-preprocessing and attention mechanisms. Any improvement in prediction accuracy will be valuable for medical diagnostics, contributing to the development of a fully functional XAI for healthcare application. Bachelor's degree 2024-05-23T07:23:18Z 2024-05-23T07:23:18Z 2024 Final Year Project (FYP) Tan, Q. X. (2024). Cell image staining and analysis using robust AI. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/176742 https://hdl.handle.net/10356/176742 en A3239-231 application/pdf Nanyang Technological University |
| spellingShingle | Engineering Tan, Qin Xiong Cell image staining and analysis using robust AI |
| title | Cell image staining and analysis using robust AI |
| title_full | Cell image staining and analysis using robust AI |
| title_fullStr | Cell image staining and analysis using robust AI |
| title_full_unstemmed | Cell image staining and analysis using robust AI |
| title_short | Cell image staining and analysis using robust AI |
| title_sort | cell image staining and analysis using robust ai |
| topic | Engineering |
| url | https://hdl.handle.net/10356/176742 |
| work_keys_str_mv | AT tanqinxiong cellimagestainingandanalysisusingrobustai |