2025 ISAKOS Congress in Munich, Germany

2025 ISAKOS Biennial Congress Paper


Thessaly Graft Index (TGI): An Artificial Intelligence Based Index for the Assessment of Graft Integrity in ACL Reconstructed Knees

Georgios Paraskevas Chalatsis, MD, MSc, MSc, PhD(cand), Larisa, Thessaly GREECE
Vasileios Mitrousias, MD, PhD, Larissa, Europe GREECE
Athanasios Siouras, PhD, Larissa GREECE
Ilias Hantes, MD, Rotterdam NETHERLANDS
Serafeim Moustakidis, PhD, Talinn ESTONIA
Dimitris Tsaopoulos, PhD, Volos GREECE
Marianna Vlychou, Prof., Larissa GREECE
Michael E. Hantes, MD, PhD, Prof., Larissa GREECE

Department of Orthopaedic Surgery & Musculoskeletal Trauma, University Hospital of Larissa, School of Health Sciences, University of Thessaly, Larissa, Thessaly, GREECE

FDA Status Not Applicable

Summary

TGI index is the first artificial intelligence tool able to accurately recognize an ACL graft rupture. TGI also correlates with the KT-1000 postoperative values and the PROMs.

Abstract

Background

MRI has proven to be a valuable non-invasive tool for evaluating graft integrity after anterior cruciate ligament (ACL) reconstruction. However, MRI protocols and interpretation methodologies are quite diverse, preventing comparisons of signal intensity across subsequent scans and independent investigations. The purpose of this study is to create an artificial intelligence (AI) based index (Thessaly Graft Index - TGI) for the evaluation of graft integrity in ACL reconstructed knees.

Methods

The study included 24 patients with isolated ACL injury, treated with hamstring tendon (HT) autograft, and followed up for 1 year. MRI was performed pre-operatively and one year postoperatively. The clinical and functional evaluation was performed using the KT-1000 and the following patient-reported outcome measures (PROMs): the KOOS, the IKDC, the Lysholm score, and the Tegner Activity Scale (TAS). Based on YOLOv5 Nano version, an AI model was designed to compute the probability of accurately detecting, on sagittal plane, a healthy ACL on a percentage scale, and trained on healthy and injured knees from the KneeMRI-dataset. The model was used to assess the integrity of the ACL graft with a maximum score of 100. The results were compared with the MRI assessment from an independent radiologist and were correlated with PROMs and KT-1000.

Results

The mean preoperative and postoperative TGI scores were 64.21 and 82.37, respectively. A mean increase of 15% in the TGI between preoperative and postoperative images was observed. The minimum threshold for TGI to categorize a graft as healthy on the postoperative MRI was 79.21%. Twenty-two grafts were characterized as intact and two as re-ruptured, with post-op TGI scores of 71% and 42%, respectively. The radiologist's assessment was in total agreement with the TGI scores. The correlation of TGI ranged from moderate to very good for TAS (0.668), IKDC (0.516), Lysholm (0.521), KOOS total (0.594), and KT-1000 (0.561).

Conclusions

The TGI is an AI tool able to accurately recognize an ACL graft rupture. Moreover, the TGI was capable of correlating with the KT-1000 postoperative values and PROMs scores.