A Deep Learning Method for Quantification of Femoral Head Necrosis Based on Routine Hip MRI for Improved Surgical Decision Making

Ruckli, Adrian C.; Nanavati, Andreas K.; Meier, Malin K.; Lerch, Till D.; Steppacher, Simon D.; Vuilleumier, Sébastian; Boschung, Adam; Vuillemin, Nicolas; Tannast, Moritz; Siebenrock, Klaus A.; Gerber, Nicolas; Schmaranzer, Florian (2023). A Deep Learning Method for Quantification of Femoral Head Necrosis Based on Routine Hip MRI for Improved Surgical Decision Making. Journal of personalized medicine, 13(1), p. 153. MDPI 10.3390/jpm13010153

[img]
Preview
Text
jpm-13-00153-v2.pdf - Published Version
Available under License Creative Commons: Attribution (CC-BY).

Download (5MB) | Preview

(1) Background: To evaluate the performance of a deep learning model to automatically segment femoral head necrosis (FHN) based on a standard 2D MRI sequence compared to manual segmentations for 3D quantification of FHN. (2) Methods: Twenty-six patients (thirty hips) with avascular necrosis underwent preoperative MR arthrography including a coronal 2D PD-w sequence and a 3D T1 VIBE sequence. Manual ground truth segmentations of the necrotic and unaffected bone were then performed by an expert reader to train a self-configuring nnU-Net model. Testing of the network performance was performed using a 5-fold cross-validation and Dice coefficients were calculated. In addition, performance across the three segmentations were compared using six parameters: volume of necrosis, volume of unaffected bone, percent of necrotic bone volume, surface of necrotic bone, unaffected femoral head surface, and percent of necrotic femoral head surface area. (3) Results: Comparison between the manual 3D and manual 2D segmentations as well as 2D with the automatic model yielded significant, strong correlations (Rp > 0.9) across all six parameters of necrosis. Dice coefficients between manual- and automated 2D segmentations of necrotic- and unaffected bone were 75 ± 15% and 91 ± 5%, respectively. None of the six parameters of FHN differed between the manual and automated 2D segmentations and showed strong correlations (Rp > 0.9). Necrotic volume and surface area showed significant differences (all p < 0.05) between early and advanced ARCO grading as opposed to the modified Kerboul angle, which was comparable between both groups (p > 0.05). (4) Conclusions: Our deep learning model to automatically segment femoral necrosis based on a routine hip MRI was highly accurate. Coupled with improved quantification for volume and surface area, as opposed to 2D angles, staging and course of treatment can become better tailored to patients with varying degrees of AVN.

Item Type:

Journal Article (Original Article)

Division/Institute:

04 Faculty of Medicine > Department of Orthopaedic, Plastic and Hand Surgery (DOPH) > Clinic of Orthopaedic Surgery
04 Faculty of Medicine > Department of Radiology, Neuroradiology and Nuclear Medicine (DRNN) > Institute of Diagnostic, Interventional and Paediatric Radiology
08 Faculty of Science > School of Biomedical and Precision Engineering (SBPE)
08 Faculty of Science > School of Biomedical and Precision Engineering (SBPE) > Personalised Medicine

Graduate School:

Graduate School for Cellular and Biomedical Sciences (GCB)

UniBE Contributor:

Ruckli, Adrian Cyrill, Meier, Malin Kristin, Lerch, Till, Steppacher, Simon Damian, Vuillemin, Nicolas Sébastien, Tannast, Moritz, Siebenrock, Klaus-Arno, Gerber, Nicolas, Schmaranzer, Florian

Subjects:

600 Technology > 610 Medicine & health

ISSN:

2075-4426

Publisher:

MDPI

Funders:

[4] Swiss National Science Foundation

Language:

English

Submitter:

Nicolas Gerber

Date Deposited:

20 Jan 2023 14:43

Last Modified:

12 Jul 2023 12:23

Publisher DOI:

10.3390/jpm13010153

BORIS DOI:

10.48350/177510

URI:

https://boris.unibe.ch/id/eprint/177510

Actions (login required)

Edit item Edit item
Provide Feedback