Generating 3D pseudo-healthy knee MR images to support trochleoplasty planning

被引:0
作者
Wehrli, Michael [1 ]
Durrer, Alicia [1 ]
Friedrich, Paul [1 ]
Buchakchiyskiy, Volodimir [1 ]
Mumme, Marcus [2 ]
Li, Edwin [2 ]
Lehoczky, Gyozo [2 ]
Hasler, Carol C. [2 ]
Cattin, Philippe C. [1 ]
机构
[1] Univ Basel, Dept Biomed Engn, Allschwil, Switzerland
[2] Univ Childrens Hosp Basel, Dept Orthoped, Basel, Switzerland
关键词
Pseudo-healthy; Trochlear dysplasia; Diffusion models; Inpainting; TROCHLEAR DYSPLASIA;
D O I
10.1007/s11548-025-03343-y
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
Purpose: Trochlear dysplasia (TD) is a common malformation in adolescents, leading to anterior knee pain and instability. Surgical interventions such as trochleoplasty require precise planning to correct the trochlear groove. However, no standardized preoperative plan exists to guide surgeons in reshaping the femur. This study aims to generate patient-specific, pseudo-healthy MR images of the trochlear region that should theoretically align with the respective patient's patella, potentially supporting the preoperative planning of trochleoplasty. Methods: We employ a wavelet diffusion model (WDM) to generate personalized pseudo-healthy, anatomically plausible MR scans of the trochlear region. We train our model using knee MR scans of healthy subjects. During inference, we mask out pathological regions around the patella in scans of patients affected by TD and replace them with their pseudo-healthy counterpart. An orthopedic surgeon measured the sulcus angle (SA), trochlear groove depth (TGD) and D & eacute;jour classification in MR scans before and after inpainting. The code is available at https://github.com/wehrlimi/Generate-Pseudo-Healthy-Knee-MRI. Results: The inpainting by our model significantly improves the SA, TGD and Dejour classification in a study with 49 knee MR scans. Conclusion: This study demonstrates the potential of WDMs in providing surgeons with patient-specific guidance. By offering anatomically plausible MR scans, the method could potentially enhance the precision and preoperative planning of trochleoplasty and pave the way to more minimally invasive surgeries.
引用
收藏
页码:1059 / 1066
页数:8
相关论文
共 26 条
[1]   Knee landmarks detection via deep learning for automatic imaging evaluation of trochlear dysplasia and patellar height [J].
Barbosa, Roberto M. ;
Serrador, Luis ;
da Silva, Manuel Vieira ;
Macedo, Carlos Sampaio ;
Santos, Cristina P. .
EUROPEAN RADIOLOGY, 2024, 34 (9) :5736-5747
[2]   Trochlear dysplasia: imaging and treatment options [J].
Batailler, Cecile ;
Neyret, Philippe .
EFORT OPEN REVIEWS, 2018, 3 (05) :240-247
[3]   Trochleoplasty in major trochlear dysplasia: Current concepts [J].
Philippe Beaufils ;
Mathieu Thaunat ;
Nicolas Pujol ;
Sven Scheffler ;
Roberto Rossi ;
Mike Carmont .
Sports Medicine, Arthroscopy, Rehabilitation, Therapy & Technology, 4 (1)
[4]   The patellotrochlear index: a new index for assessing patellar height [J].
Biedert, Roland M. ;
Albrecht, Silvia .
KNEE SURGERY SPORTS TRAUMATOLOGY ARTHROSCOPY, 2006, 14 (08) :707-712
[5]   Trochlear Shape and Patient-Reported Outcomes After Arthroscopic Deepening Trochleoplasty and Medial Patellofemoral Ligament Reconstruction: A Retrospective Cohort Study Including MRI Assessments of the Trochlear Groove [J].
Blond, Lars ;
Barfod, Kristoffer Weisskirchner .
ORTHOPAEDIC JOURNAL OF SPORTS MEDICINE, 2023, 11 (05)
[6]   Arthroscopic Deepening Trochleoplasty: The Technique [J].
Blond, Lars .
OPERATIVE TECHNIQUES IN SPORTS MEDICINE, 2015, 23 (02) :136-142
[7]   The Role of Trochlear Dysplasia in Patellofemoral Instability [J].
Bollier, Matthew ;
Fulkerson, John P. .
JOURNAL OF THE AMERICAN ACADEMY OF ORTHOPAEDIC SURGEONS, 2011, 19 (01) :8-16
[8]  
Dejour H, 1994, Knee Surg Sports Traumatol Arthrosc, V2, P19, DOI 10.1007/BF01552649
[9]  
Dirisamer F, 2023, ARTHROSKOPIE, V36, P387, DOI 10.1007/s00142-023-00651-w
[10]  
Durrer A, 2024, MICCAI WORKSH DEEP G, P87, DOI 10.1007/