FinalPresentation_Group_1_ComputerAided.pptx

Computer-aided Diagnosis Group 1 slides

1. MISSING FINGER PREDICTION By Group 1 Instructor: Dr. Tan-Nhu Nguyen CAD PROJECT

2. Tran Dao Quang BEBEIU20266 Nguyen Huu Trong Pham BEBEIU21 Bui Minh Duc BEBEIU21053 Vo Hoang Viet BEBEIU20266 GROUP MEMBER

3. 1. Introduction 2. Method & Result 3. Discussion 4. Conlcusion CONTENT

4. 1. Introduction Clinical needs: Restores functionality and improves prosthetics by predicting the exact shape of missing fingers. Enables personalized solutions, enhancing fit and comfort. Assists surgeons with preoperative planning for better outcomes. Social needs: Improves understanding of hand anatomy and relationships between finger structures Establishes a framework for future anatomical modeling studies.

5. 1. Introduction Project requirements: Algorithm Development : Using PCA for dimension reduction and implementing statistical shape modeling techniques using tools like Trimesh and regression analysis for accurate missing finger prediction. GUI: Develop a user-friendly interface for clinicians to input partial hand data and visualize the predicted shape.

6. 2. Method & Result DATA GENERATION DATA PROCESSING MODEL CREATION MODEL TRAINING MODEL VALIDATION TEST INFERENCE Hand meshes Missing-finger hand meshes Finger meshes PCA missing-finger hand meshes Optimal number of components for PCA Accuracy A software predicting missing finger Linear regreson model Overall processing method:

7. Data generation LOAD MANO MODEL HAND MESHES RANDOM HAND SIZE

8. Data processing HAND MESHES REGISTER CORRESPONDING POINTS IN OTHER MESH VERTICES OF INDEX FINGER OF FIRST MESH Finger meshes Missing-finger hand meshes

9. Model creation & training INPUT: MISSING-FINGER HAND PCA: DIMENSION REDUCTION TRAIN LINEAR REGRESSION MODEL DATASET: 70-20-10 (TRAIN – VALIDATION – TEST) LINEAR REGRESSION MODEL PREDICTING IN TESTING SET PCA MODEL MISSING FINGER PARAMETRS OUTPUT: MISSING FINGER

10. Validation COMPUTING ERROR BETWEEN GROUND TRUTH SET AND PREDICTED SET OPTIMIZED N COMPONENT

11. Test and GUI

12. Test and GUI

13. Test and GUI

14. 4. Discussion Drawback: Model Assumptions Real-World Integration Challenges Perspectives Expanding Data Diversity Adopting Advanced Models Future Research Directions

15. 5. Conclusion The missing finger prediction model offers a promising solution to address critical clinical and social needs by leveraging advanced statistical and computational techniques. Through the use of PCA and regression analysis, the model demonstrates its potential in restoring hand functionality and improving the design of prosthetic devices.

16. Reference Sung, P. C., Hsu, C. C., Lee, C. L., Chiu, Y. S. P., & Chen, H. L. (2015). Formulating grip strength and key pinch strength prediction models for Taiwanese: a comparison between stepwise regression and artificial neural networks. Journal of Ambient Intelligence and Humanized Computing, 6, 37-46. Castellini, C., Passig , G., & Zarka , E. (2012). Using ultrasound images of the forearm to predict finger positions. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 20(6), 788-797. Belić , J. J., & Faisal, A. A. (2015). Decoding of human hand actions to handle missing limbs in neuroprosthetics . Frontiers in computational neuroscience, 9, 27. Alazrai , R., Khalifeh, A., Alnuman , N., Alabed , D., & Mowafi , Y. (2016, August). An ensemble-based regression approach for continuous estimation of wrist and fingers movements from surface electromyography. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 319-322). IEEE. Chang, J. H., Wu, M., Lee, C. L., Guo, Y. L., & Chiu, H. Y. (2011). Correlation of return to work outcomes and hand impairment measures among workers with traumatic hand injury. Journal of occupational rehabilitation, 21, 9-16. Noyce, A. J., R'Bibo , L., Peress, L., Bestwick, J. P., Adams‐Carr, K. L., Mencacci , N. E., ... & Schrag, A. (2017). PREDICT‐PD: An online approach to prospectively identify risk indicators of Parkinson's disease. Movement Disorders, 32(2), 219-226. Bell, P. M., & Heng, W. (1997). Fuzzy linear regression models for assessing risks of cumulative trauma disorders. Fuzzy Sets and Systems, 92(3), 317-340.

17. THANK YOU