YAPAY ZEKA TABANLI OTONOM SOKET ÖNERME PROGRAMI: KLİNİK KARAR DESTEK SİSTEMİ İÇİN ÖN ÇALIŞMA

Öz

Amaç: Bu çalışmanın amacı, protez ihtiyacı olan engelli bireylerle çalışan profesyonellerin (klinisyenler ve/veya akademisyenler) kullanabileceği yapay zeka tabanlı arayüzler geliştirmek ve bu alanda çalışan profesyoneller için örnek bir veri seti oluşturmaktır. Yöntem: Amputasyon cerrahisi geçiren toplam 101 hasta çalışmaya dahil edildi. Tüm hastaların güdükleri üç boyutlu tarayıcı kullanılarak tarandı ve bilgisayara kaydedildi. Çalışmaya dahil edilen hastaların geleneksel yöntemlerle üretilen protez soketleri de aynı tarayıcıyla taranarak elde edilen üç boyutlu modelleri de bilgisayara kaydedildi. Üç boyutlu tarayıcılarla elde edilen nokta bulutu verileri kullanılarak güdük-protez soket eşleşmeleri elde edildi ve derin sinir ağı (DNN) tabanlı bir karar destek sistemi geliştirildi. Sonuçlar: 101 hastaya ait nokta bulutu veri setleri ile yapılan simülasyon çalışmalarında %86 oranında eğitim başarı oranı elde edildi. DNN modeli %78'lik bir genelleme başarı oranı sergiledi. Tartışma: Bu çalışma ile geliştirilen yapay zeka tabanlı otonom soket önerme ara yüzü protez ihtiyacı olan hastalar için uygun 3 boyutlu soket modeli önererek profesyonellere yardımcı olabilir. Daha sonraki çalışmalarda modelin doğruluğunu artırmak için daha fazla hastanın verilerinin kullanılması planlanmaktadır.

Anahtar Kelimeler

• Amputasyon
• Yapay Zeka
• Karar Destek Sistemi

ARTIFICIAL INTELLIGENCE–BASED AUTONOMOUS SOCKET PROPOSAL PROGRAM: A PRELIMINARY STUDY FOR CLINICAL DECISION SUPPORT SYSTEM

Abstract

Purpose: The aim of this study is to develop artificial intelligence-based interfaces that can be used by professionals (clinicians and/or academics) working with disabled individuals who need prosthetics and to create a sample data set for professionals working in this field. Methods: 101 patients who had undergone amputation were enrolled. The residual limbs of all patients were scanned using a three-dimensional (3D) scanner and saved on the computer. The prosthetic sockets, fabricated using traditional methods, were also scanned with the same scanner and saved as a 3D model. Residual limb–prosthetic socket matches were obtained using data points and a deep neural network (DNN)-based decision support system was developed. Results: Simulation studies conducted with the point cloud data sets of 101 patients yielded a training success rate of 86%. The DNN model exhibited a generalization success rate of 78%. Conclusion: The artificial intelligence–based software interface has potential and could assist professionals by suggesting a suitable 3D socket model for patients in need of a prosthesis. Further studies will benefit from additional sample data to enhance the accuracy of the model.

Keywords

• Amputation
• Artificial Intelligence
• Decision Support System

References

1. Ribeiro D, Cimino SR, Mayo AL, Ratto M, Hitzig SL. 3D printing and amputation: a scoping review. Disabil Rehabil Assist Technol. 2021;16(2):221-240.
2. Abbady H, Klinkenberg ET, de Moel L, Nicolai N, Van der Stelt M, Verhulst AC, et al. 3D-printed prostheses in developing countries: A systematic review. Prosthet Orthot Int. 2022;46(1):19-30.
3. Anderson CB, Kittelson AJ, Wurdeman SR, Miller MJ, Stoneback JW, Christiansen CL, et al. Understanding decision-making in prosthetic rehabilitation by prosthetists and people with lower limb amputation: a qualitative study. Disabil Rehabil. 2023;45(4): 723-732.
4. Cuellar JS, Smit G, Zadpoor AA, Breedveld P. Ten guidelines for the design of non-assembly mechanisms: the case of 3D-printed prosthetic hands. Proc Inst Mech Eng H. 2018;232(9):962-971.
5. Schwartz JK, Fermin A, Fine K, Iglesias N, Pivarnik D, Struck, et al. Methodology and feasibility of a 3D printed assistive technology intervention. Disabil Rehabil Assist Technol. 2020;15(2):141-147.
6. Seminati E, Young M, Talamas DC, Twiste M, Dhokia V, Bilzon J. Reliability of three different methods for assessing amputee residuum shape and volume: 3D scanners vs. circumferential measurements. Prosthet Orthot Int. 2022;46(4):327-334.
7. Seminati E, Talamas DC, Young M, Twiste M, Dhokia V, Bilzon JLJ. Validity and reliability of a novel 3D scanner for assessment of the shape and volume of amputees’ residual limb models. PloS One. 2017;12(9), e0184498.
8. Goal-tech [Internet]. Success Stories, Artec Eva (stories); [Updated 2022, cited 2023 Nov 23]. Available from: https://goal-tech.com.mx/en/2022/09/13/creating-a-one-of-a-kind-prosthesis-with-artec-eva-and-geomagic-freeform/.

9. Koçak Ç, Yiğit T, Anitha J, Mustafayeva A. Topic modeling analysis of tweets on the twitter hashtags with LDA and creating a new dataset. 2021 3rd International Conference on Artificial Intelligence and Applied Mathematics in Engineering, October 1-3, Antalya. ECPSCI; 2021;551-565.
10. Xiao A, Huang J, Guan D, Zhang X, Lu S, Shao L. Unsupervised point cloud representation learning with deep neural networks: A survey. IEEE Trans Pattern Anal Mach Intell. 2023;45(9):11321-11339.
11. Li Y, Ma L, Zhong Z, Liu F, Chapman MA, Cao D, et al. Deep learning for lidar point clouds in autonomous driving: A review. IEEE Trans Neural Netw Learn Syst. 2020;32(8):3412-3432.
12. Cheng Q, Sun P, Yang C, Yang Y, Liu PX. A morphing-based 3D point cloud reconstruction framework for medical image processing. Comput Methods Programs Biomed. 2020;193:105495.
13. Li J, Zhang H, Yin P, Su X, Zhao Z, Zhou J. A new measurement technique of the characteristics of nutrient artery canals in tibias using Materialise’s interactive medical image control system software. Biomed Res Int. 2015; 2015:171672.
14. Chen T, Que YT, Zhang YH, Long FY, Li Y, Huang X, et al. Using Materialise's interactive medical image control system to reconstruct a model of a patient with rectal cancer and situs inversus totalis: A case report. World J Clin Cases. 2020;8(4):806.
15. Guo Y, Wang H, Hu Q, Liu H, Liu L, Bennamoun M. Deep learning for 3d point clouds: A survey. IEEE Trans Pattern Anal Mach Intell. 2020;43(12):4338-4364.
16. Qiu K, Haghiashtiani G, McAlpine MC. 3D printed organ models for surgical applications. Annu Rev Anal Chem. 2018;11:287-306.
17. Popov VV, Muller-Kamskii G, Kovalevsky A, Dzhenzhera G, Strokin E, Kolomiets A, et al. Design and 3D-printing of titanium bone implants: brief review of approach and clinical cases. Biomed Eng Lett. 2018;8(4):337-344.
18. Wang J, Huang Z, Wang F, Yu X, Li D. Materialise’s interactive medical image control system (MIMICS) is feasible for volumetric measurement of urinary calculus. Urolithiasis. 2020;48(5):443-446.
19. Li J, Zhang H, Yin P, Su X, Zhao Z, Zhou J, et al. A new measurement technique of the characteristics of nutrient artery canals in tibias using Materialise’s interactive medical image control system software. Biomed Res Int. 2015; 2015:171672.
20. Chen T, Que YT, Zhang YH, Long FY, Li Y, Huang X, et al.. Using Materialise's interactive medical image control system to reconstruct a model of a patient with rectal cancer and situs inversus totalis: A case report. World J Clin Cases. 2020;8(4):806.
21. Colombo G, Facoetti G, Regazzoni D, Rizzi C. A full virtual approach to design and test lower limb prosthesis: This paper reports a software platform for design and validation of lower limb prosthesis in a completely virtual environment, potentially replacing current manual process. Virtual and Physical Prototyping. 2013;8(2):97-111.
22. Seminati E, Young M, Talamas DC, Twiste M, Dhokia V, Bilzon J. Reliability of three different methods for assessing amputee residuum shape and volume: 3D scanners vs. circumferential measurements. Prosthet Orthot Int. 2022; 46(4):327-334.
23. Lu Y, Wang X, Yang B, Xu Z, Zhang B, Jia B, et al. Application of SolidWorks software in preoperative planning of high tibial osteotomy. Front Surg. 2023; 9:951820.
24. Piot N, Barry F, Schlund M, Ferri J, Demondion X, Nicot R. 3D printing for orbital volume anatomical measurement. Surg Radiol Anat.2022;44(7):991-998.
25. Giacomini GO, Dotto GN, Mello WM, Dutra V, Liedke GS. Three‐Dimensional printed model for preclinical training in oral radiology. Eur J Dent Educ.2023;27(2):280-286.
26. Moser N, Santander P, Quast A. From 3D imaging to 3D printing in dentistry-a practical guide. Int J Comput Dent.2018;21(4):345-356.