Deep Geometric Supervision Improves Spatial Generalization in Orthopedic Surgery Planning

Kordon F, Maier A, Swartman B, Privalov M, El Barbari JS, Kunze H (2022)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2022

Publisher: Springer

City/Town: Cham

Book Volume: 13437 LNCS

Pages Range: 615-625

Conference Proceedings Title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2022

Event location: Singapore SG

ISBN: 978-3-031-16449-1

DOI: 10.1007/978-3-031-16449-1_59

Abstract

Careful surgical planning facilitates the precise and safe placement of implants and grafts in reconstructive orthopedics. Current attempts to (semi-)automatic planning separate the extraction of relevant anatomical structures on X-ray images and perform the actual positioning step using geometric post-processing. Such separation requires optimization of a proxy objective different from the actual planning target, limiting generalization to complex image impressions and the positioning accuracy that can be achieved. We address this problem by translating the geometric steps to a continuously differentiable function, enabling end-to-end gradient flow. Combining this companion objective function with the original proxy formulation improves target positioning directly while preserving the geometric relation of the underlying anatomical structures. We name this concept Deep Geometric Supervision. The developed method is evaluated for graft fixation site identification in medial patellofemoral ligament (MPFL) reconstruction surgery on (1) 221 diagnostic and (2) 89 intra-operative knee radiographs. Using the companion objective reduces the median Euclidean Distance error for MPFL insertion site localization from (1) 2.29mm" role="presentation">2.29mm to 1.58mm" role="presentation">1.58mm and (2) 8.70px" role="presentation">8.70px to 3.44px" role="presentation">3.44px, respectively. Furthermore, we empirically show that our method improves spatial generalization for strongly truncated anatomy.

Authors with CRIS profile

Florian Kordon Lehrstuhl für Informatik 5 (Mustererkennung) Andreas Maier Lehrstuhl für Informatik 5 (Mustererkennung) Holger Kunze

Additional Organisation(s)

Lehrstuhl für Informatik 5 (Mustererkennung) Erlangen Graduate School in Advanced Optical Technologies (SAOT)

Related research project(s)

Deep-Learning basierte Segmentierung und Landmarkendetektion auf Röntgenbildern für unfallchirurgische Eingriffe May 6, 2019 - May 6, 2022

Involved external institutions

BG Unfallklinik Ludwigshafen (BGU) / BG Hospital Ludwigshafen DE Germany (DE) Siemens Healthineers DE Germany (DE)

How to cite

APA:

Kordon, F., Maier, A., Swartman, B., Privalov, M., El Barbari, J.S., & Kunze, H. (2022). Deep Geometric Supervision Improves Spatial Generalization in Orthopedic Surgery Planning. In Wang L, Dou Q, Fletcher PT, Speidel S, Li S (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2022 (pp. 615-625). Singapore, SG: Cham: Springer.

MLA:

Kordon, Florian, et al. "Deep Geometric Supervision Improves Spatial Generalization in Orthopedic Surgery Planning." Proceedings of the Medical Image Computing and Computer Assisted Intervention – MICCAI 2022, Singapore Ed. Wang L, Dou Q, Fletcher PT, Speidel S, Li S, Cham: Springer, 2022. 615-625.

BibTeX: Download