| Proj No. | B3089-251 |
| Title | Adapting Large Language Model (LLM) in Medical Image Analysis |
| Summary | Abstract: Large Language Models (LLMs) are increasingly being explored for their potential to enhance medical image analysis, a crucial task for accurate diagnostic imaging. Recently open-sourced Deepseek Janus-Pro model makes it possible for us to explore the potential of adapting LLMs in CTCA image analysis with limited computing power. During the last three years, we have developed several AI models for CTCA image analysis, such as whole-heart segmentation, coronary artery segmentation, auto-labeling and stenosis/plaque grading, in APOLLO platform. In APOLLO platform, we also have patients' MR information and radiology report. In this FYP project, we will use the above-mentioned AI models as pre-trained vision tokenizer, MR information as inputs, and radiology report as ground truth to fine-tune LLMs. The integration methods and model performance will be analyzed. |
| Supervisor | A/P Lin Zhiping (Loc:S2 > S2 B2A > S2 B2A 14, Ext: +65 67906857) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Information System Research Lab (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 |