EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

High accuracy in lower limb alignment analysis using convolutional neural networks, with improvements needed for joint‐level metrics

Christof Hoffmann, Fatih Göksu, Isabella Klöpfer-Krämer, Julius Watrinet, Philipp Blum, Sven Hungerer, Steffen Schröter, Fabian Stuby, Peter Augat, Julian Fürmetz

Knee Surgery, Sports Traumatology, Arthroscopy · 2025-06 · 33 (6) · 1975-1981

DOI: 10.1002/ksa.12481 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Knee Surgery, Sports Traumatology, Arthroscopy, online erschienen am 22.09.2024. Verfasst von Christof Hoffmann und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Trauma Surgery, BG Trauma Center Murnau, Murnau, Germany. Hauptthemen laut MEDLINE: Convolutional Neural Networks, Knee Joint, Lower Extremity, Osteoarthritis, Knee. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: mediCAD.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Evaluation of long‐leg standing radiographs (LSR) is a standardised procedure for analysis of primary or secondary deformities of the lower limbs. Deep‐learning convolutional neural networks (CNN) offer the potential to enhance radiological measurement by increasing reproducibility and accuracy. This study aims to evaluate the measurement accuracy of an automated CNN‐based planning tool (mediCAD® 7.0; mediCAD Hectec GmbH) of lower limb deformities.

Methods

In a retrospective single‐centre study, 164 pre‐ and postoperative bilateral LSRs with uni‐ or bilateral posttraumatic knee arthritis undergoing total knee arthroplasty (TKA) were enroled. Alignment parameters relevant to knee arthroplasty and deformity correction were analysed independently by two observers and a CNN. The intraclass correlation coefficient (ICC) was used to evaluate the accuracy between observers and the CNN, which was further evaluated using absolute deviations, limits of agreement (LoA) and root mean square error (RMSE).

Results

CNN evaluation demonstrated high consistency in measuring leg length (ICC > 0.99) and overall lower limb alignment measures of mechanical tibio‐femoral angle (mTFA) (ICC > 0.97; RMSE < 1.1°). The mean absolute difference between angular measurements were low for overall lower limb alignment (mTFA 0.49–0.61°) and high for specific joint angles (aMPFA 3.86–4.50°). Accuracy at specific joint angles like the mechanical proximal tibial angle (MPTA) and the mechanical lateral distal femur angle (mLDFA) varied between lower limbs with deformity, with and without TKA with greatest difference for TKA (ICC 0.22–0.85; RMSE 1.72–3.65°).

Conclusion

Excellent accuracy was observed between manual and automated measurements for overall alignment and leg length, but joint‐level metrics need further improvement especially in case of TKA similar to other existing algorithms. Despite the observed deviations, the time‐efficient nature of the algorithm improves the efficiency of the preoperative planning process. Level of Evidence Level IV.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Convolutional Neural NetworksKnee JointLower ExtremityOsteoarthritis, KneeAgedFemaleHumansMaleMiddle AgedArthroplasty, Replacement, KneeRadiographyReproducibility of ResultsRetrospective Studies

Stichwörter der Autor:innen

deep learning convolutional neural networkleg deformitylong leg standing radiographsosteotomytotal knee arthroplasty

Autor:innen und Institutionen

  • Department of Trauma Surgery, BG Trauma Center Murnau, Murnau, Germany.
  • Department of Orthopedics and Reconstructive Surgery, Diakonie Klinikum, GmbH Jung-Stilling-Krankenhaus, Siegen, Germany.
  • Institute for Biomechanics, Paracelsus University Salzburg, Salzburg, Austria.
  • Department of Orthopaedic Sports Medicine, Technical University, Munich, Germany.
  • Department of Orthopedics and Trauma Surgery, Musculoskeletal University Center Munich (MUM), University Hospital, LMU Munich, Munich, Germany.

Förderung

  • mediCAD

Zitieren

APA

Hoffmann, C., Göksu, F., Klöpfer-Krämer, I., Watrinet, J., Blum, P., Hungerer, S., Schröter, S., Stuby, F., Augat, P., & Fürmetz, J. (2025). High accuracy in lower limb alignment analysis using convolutional neural networks, with improvements needed for joint‐level metrics. Knee Surgery, Sports Traumatology, Arthroscopy, 33(6), 1975-1981. https://doi.org/10.1002/ksa.12481

Vancouver

Hoffmann C, Göksu F, Klöpfer-Krämer I, Watrinet J, Blum P, Hungerer S, et al. High accuracy in lower limb alignment analysis using convolutional neural networks, with improvements needed for joint‐level metrics. Knee Surgery, Sports Traumatology, Arthroscopy. 2025;33(6):1975-1981. doi:10.1002/ksa.12481

BibTeX
@article{Hoffmann2025,
  author = {Hoffmann, Christof and Göksu, Fatih and Klöpfer-Krämer, Isabella and Watrinet, Julius and Blum, Philipp and Hungerer, Sven and Schröter, Steffen and Stuby, Fabian and Augat, Peter and Fürmetz, Julian},
  title = {High accuracy in lower limb alignment analysis using convolutional neural networks, with improvements needed for joint‐level metrics},
  journal = {Knee Surgery, Sports Traumatology, Arthroscopy},
  year = {2025},
  volume = {33},
  number = {6},
  pages = {1975--1981},
  doi = {10.1002/ksa.12481}
}
Kostenlos starten →