Treatment and Outcomes of Missed Perilunate Dislocations: A Case Series

We read Pelrine et al's[1] article with interest and share their view that perilunate dislocations, although rare, are devastating injuries, and 25% of these injuries go undetected at initial assessment, even though they could be treated quickly and successfully with ligament and bone repair. In their series, eight perilunate dislocations were diagnosed late, on average 133 days after the date of injury.

The main reason for this delay in diagnosis is that most of the time, frontal radiographs are difficult to be interpreted by nonspecialists unfamiliar with Gilula's arches. For this reason, we have developed an artificial intelligence algorithm[2] that automatically detects perilunate dislocations on frontal radiographs of the wrist by identifying normal and pathological patterns of Gilula's arches II and III that we have termed Gilula's “crescent” ([Fig. 1]).

Fig. 1 Front wrist radiograph. Left: Gilula's arches in yellow on a normal wrist. Middle: Gilula's crescent in yellow on a normal wrist. Right, Gilula's crescent in red on a pathological wrist with perilunate dislocation.

We hope that this artificial intelligence algorithm will soon be integrated into the automatic fracture and dislocation detection software used in the radiology departments of emergency care facilities.

All in all, we congratulate Pelrine et al[1] on their very interesting article, which is yet another reminder of the importance of managing perilunate dislocations as quickly as possible.

Publication History

Article published online:
18 July 2024

• References

• 1 Pelrine E, Larson E, Freilich A, Dacus AR, Deal N. Treatment and outcomes of missed perilunate dislocations: a case series. J Wrist Surg 2023; 13 (02) 171-175
• 2 Majzoubi N, Allègre R, Wemmert C, Liverneaux P. A deep-learning-based algorithm for automatic detection of perilunate dislocation in frontal wrist radiographs. Hand Surg Rehabil 2024; 101742