| Proj No. | B3089-251 |
| Title | Adapting Large Language Model (LLM) in Medical Image Analysis |
| Summary | Building upon our previous FYP work on automatically generated spatial prompting for semi-supervised medical image segmentation, this FYP will develop a novel framework for adapting large language models (LLMs) to further enhance spatial prompting capabilities. The objective is to improve both the accuracy and efficiency of segmentation tasks across diverse imaging modalities. By incorporating domain-specific visual-language alignment mechanisms and fine-tuning strategies tailored to medical contexts, the proposed approach enables LLMs to interpret spatial cues and anatomical structures with greater precision. A hybrid prompting scheme is introduced, combining textual descriptions with spatial priors to guide segmentation more effectively, particularly in modalities such as X-ray and ultrasound imaging. Beyond technical contributions, this study serves as an exploration into the potential of LLM-driven prompting for AI-assisted medical image analysis, offering insights into its scalability, interpretability, and clinical relevance. |
| Supervisor | A/P Lin Zhiping (Loc:S2 > S2 B2A > S2 B2A 14, Ext: +65 67906857) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Information Systems (Loc: S2-B3a-06) |
| Single/Group: | Single |
| Area: | Intelligent Systems and Control Engineering |
| ISP/RI/SMP/SCP?: | ISP: Dr Lu Zhongkang Principal Scientist I2R zklu@i2r.a-star.edu.sg |