A convolutional neural network for high throughput screening of femoral stem taper corrosion.

Corrosion at the modular head-neck taper interface of total and hemiarthroplasty hip implants (trunnionosis) is a cause of implant failure and clinical concern. The Goldberg corrosion scoring method is considered the gold standard for observing trunnionosis, but it is labor-intensive to perform. This limits the quantity of implants retrieval studies typically analyze. Machine learning, particularly convolutional neural networks, have been used in various medical imaging applications and corrosion detection applications to help reduce repetitive and tedious image identification tasks. 725 retrieved modular femoral stem arthroplasty devices had their trunnion imaged in four positions and scored by an observer. A convolutional neural network was designed and trained from scratch using the images. There were four classes, each representing one of the established Goldberg corrosion classes. The composition of the classes were as follows: class 1 (n = 1228), class 2 (n = 1225), class 3 (n = 335), and class 4 (n = 102). The convolutional neural network utilized a single convolutional layer and RGB coloring. The convolutional neural network was able to distinguish no and mild corrosion (classes 1 and 2) from moderate and severe corrosion (classes 3 and 4) with an accuracy of 98.32%, a class 1 and 2 sensitivity of 0.9881, a class 3 and 4 sensitivity of 0.9556 and an area under the curve of 0.9740. This convolutional neural network may be used as a screening tool to identify retrieved modular hip arthroplasty device trunnions for further study and the presence of moderate and severe corrosion with high reliability, reducing the burden on skilled observers.

What Patient and Implant Factors Affect Trunnionosis Severity? An Implant Retrieval Analysis of 664 Femoral Stems.

BACKGROUND: Corrosion at the modular head-neck taper interface of total and hemiarthroplasty hip implants (trunnionosis) is a cause of implant failure and thus a clinical concern. Patient and device factors contributing to the occurrence of trunnionosis have been investigated in prior implant retrieval studies but generally with limited sample sizes and a narrow range of models. The purpose of the present investigation was to determine which patient and device factors were associated with corrosion damage on the femoral stem taper across a large collection of different implant models retrieved following revision hip arthroplasty. METHODS: A retrieval study of 664 hip arthroplasty modular stem components was performed. Patient and device information was collected. Trunnions were imaged under digital microscopy and scored for corrosion damage using a scaling system. Damage was related to patient and device factors using regression analyses. RESULTS: Greater duration of implantation (P = .005) and larger head size (P < .001) were associated with an elevated corrosion class. Older age at index surgery (P = .035), stainless steel stem material (P = .022), indication for revision as bone or periprosthetic fracture (P = .017), and infection (P = .018) and certain larger taper geometries were associated with a decreased corrosion class. CONCLUSION: Factors identified as contributing to a higher or lower risk of more severe corrosion are consistent with most prior smaller retrieval studies. Surgeons should be aware of these risk factors when selecting implants for their patients and when diagnosing trunnionosis in symptomatic hip arthroplasty patients.