Early MRI-based quantitative outcomes are associated with a positive functional performance trajectory from 6 to 24 months post-ACL surgery

Lower extremity return to sport testing: A systematic review

BACKGROUND

Lower extremity injuries account for an enormous portion of sports medicine cases in the United States each year. Unfortunately, there are no uniform criteria for athletes to complete prior to returning to sport (RTS) following a lower extremity injury. Therefore, the purpose of this systematic review is to review current literature for joint-specific and global lower extremity testing to determine the most valid functional test that can be utilized to reduce the risk of re-injury as athletes RTS.

METHODS

A systematic search of PubMed, PubMed Central, Cochrane Library, OVID, and Embase databases was conducted for studies prior to May 2024 following PRISMA guidelines. ROBINS-I Tool was utilized for the risk of bias assessment.

RESULTS

Of 19,189 studies, 114 (0.6%) studies published prior to May of 2024 met inclusion criteria and were analyzed. Eighty five percent of articles discussed RTS for individuals with knee pathology. Furthermore, 82% specifically analyzed RTS following ACL reconstruction. The most common RTS test was isokinetic dynamometry testing which is seen in 73% of studies. Only 6.2% of studies analyzed RTS for individuals with hip pathology and only two studies analyzed RTS for patients with ankle injuries.

CONCLUSION

Even with the enormous amount of literature that exists regarding ACL injuries and testing there is no standardized criterion for RTS clearance. The suggested test batteries from this review can serve as a framework for future research and validation for joint-specific RTS functional testing.

Reinjury Following Return to Play

Radiologists are frequently called on for guidance regarding return to play (RTP) for athletes and active individuals after sustaining a musculoskeletal injury. Avoidance of reinjury is of particular importance throughout the rehabilitative process and following resumption of competitive activity. Understanding reinjury risk estimation, imaging patterns, and correlation of clinical and surgical findings will help prepare the radiologist to identify reinjuries correctly on diagnostic imaging studies and optimize management for a safe RTP.

Postoperative Return to Play and the Role of Imaging

Return to play (RTP) following surgery is a complex subject at the interface of social and internal pressures experienced by the athlete, psychological readiness, and intrinsic healing of the surgically repaired structures. Although functional testing, time from surgery, clinical examination, and scoring metrics can help clarify an athlete's readiness to return to sport, imaging can allow for a more direct assessment of the structures in question. Because imaging is often included in the diagnostic work-up of pain following surgery, the radiologist must be familiar with the expected postsurgical imaging appearance, as well as the associated complications. We briefly review such findings following anterior cruciate ligament reconstruction, Achilles tendon repair, syndesmotic fixation, and ulnar collateral ligament reconstruction in the context of the athlete, highlighting issues related to RTP.

Assessment of ultrashort echo time (UTE) T2* mapping at 3T for the whole knee: repeatability, the effects of fat suppression, and knee position

Background

Knee tissues such as tendon, ligament and meniscus have short T2* relaxation times and tend to show little to no signal in conventional magnetic resonance acquisitions. An ultrashort echo time (UTE) technique offers a unique tool to probe fast-decaying signals in these tissues. Clinically relevant factors should be evaluated to quantify the sensitivity needed to distinguish diseased from control tissues. Therefore, the objectives of this study were to (I) quantify the repeatability of UTE-T2* relaxation time values, and (II) evaluate the effects of fat suppression and (III) knee positioning on UTE-T2* relaxation time quantification.

Methods

A dual-echo, three-dimensional center-out radially sampling UTE and conventional gradient echo sequences were utilized to image gadolinium phantoms, one ex-vivo specimen, and five in-vivo subjects on a clinical 3T scanner. Scan-rescan images from the phantom and in-vivo experiments were used to evaluate the repeatability of T2* relaxation time values. Fat suppressed and non-suppressed images were acquired for phantoms and the ex-vivo specimen to evaluate the effect of fat suppression on T2* relaxation time quantifications. The effect of knee positioning was evaluated by imaging in-vivo subjects in extended and flexed positions within the knee coil and comparing T2* relaxation times quantified from tissues in each position.

Results

Phantom and in-vivo measurements demonstrated repeatable T2* mapping, where the percent difference between T2* relaxation time quantified from scan-rescan images was less than 8% for the phantom and knee tissues. The coefficient of variation across fat suppressed and non-suppressed images was less than 5% for the phantoms and ex-vivo knee tissues, showing that fat suppression had a minimal effect on T2* relaxation time quantification. Knee position introduced variability to T2* quantification of the anterior cruciate ligament, posterior cruciate ligament, and patellar tendon, with percent differences exceeding 20%, but the meniscus showed a percent difference less than 10%.

Conclusions

The 3D radial UTE sequence presented in this study could potentially be used to detect clinically relevant changes in mean T2* relaxation time, however, reproducibility of these values is impacted by knee position consistency between scans.

LigaNET: A multi-modal deep learning approach to predict the risk of subsequent anterior cruciate ligament injury after surgery

Anterior cruciate ligament (ACL) injuries are a common cause of soft tissue injuries in young active individuals, leading to a significant risk of premature joint degeneration. Postoperative management of such injuries, in particular returning patients to athletic activities, is a challenge with immediate and long-term implications including the risk of subsequent injury. In this study, we present LigaNET, a multi-modal deep learning pipeline that predicts the risk of subsequent ACL injury following surgical treatment. Postoperative MRIs (n=1,762) obtained longitudinally between 3 to 24 months after ACL surgery from a cohort of 159 patients along with 11 non-imaging outcomes were used to train and test: 1) a 3D CNN to predict subsequent ACL injury from segmented ACLs, 2) a 3D CNN to predict injury from the whole MRI, 3) a logistic regression classifier predict injury from non-imaging data, and 4) a multi-modal pipeline by fusing the predictions of each classifier. The CNN using the segmented ACL achieved an accuracy of 77.6% and AUROC of 0.84, which was significantly better than the CNN using the whole knee MRI (accuracy: 66.6%, AUROC: 0.70; P<.001) and the non-imaging classifier (accuracy: 70.1%, AUROC: 0.75; P=.039). The fusion of all three classifiers resulted in highest classification performance (accuracy: 80.6%, AUROC: 0.89), which was significantly better than each individual classifier (P<.001). The developed multi-modal approach had similar performance in predicting the risk of subsequent ACL injury from any of the imaging sequences (P>.10). Our results demonstrate that a deep learning approach can achieve high performance in identifying patients at high risk of subsequent ACL injury after surgery and may be used in clinical decision making to improve postoperative management (e.g., safe return to sports) of ACL injured patients.

Predicting anterior cruciate ligament failure load with T2* relaxometry and machine learning as a prospective imaging biomarker for revision surgery

Non-invasive methods to document healing anterior cruciate ligament (ACL) structural properties could potentially identify patients at risk for revision surgery. The objective was to evaluate machine learning models to predict ACL failure load from magnetic resonance images (MRI) and to determine if those predictions were related to revision surgery incidence. It was hypothesized that the optimal model would demonstrate a lower mean absolute error (MAE) than the benchmark linear regression model, and that patients with a lower estimated failure load would have higher revision incidence 2 years post-surgery. Support vector machine, random forest, AdaBoost, XGBoost, and linear regression models were trained using MRI T2* relaxometry and ACL tensile testing data from minipigs (n = 65). The lowest MAE model was used to estimate ACL failure load for surgical patients at 9 months post-surgery (n = 46) and dichotomized into low and high score groups via Youden's J statistic to compare revision incidence. Significance was set at alpha = 0.05. The random forest model decreased the failure load MAE by 55% (Wilcoxon signed-rank test: p = 0.01) versus the benchmark. The low score group had a higher revision incidence (21% vs. 5%; Chi-square test: p = 0.09). ACL structural property estimates via MRI may provide a biomarker for clinical decision making.