Development and validation of a deep learning model for radiographic classification of pediatric femoral neck fractures.
Authors
Affiliations (24)
Affiliations (24)
- The fourth Clinical Medical College of Guangzhou University of Chinese Medicine, ShenZhen, GuangDong, China. [email protected].
- Department of Orthopedics, Shenzhen Traditional Chinese Medicine Hospital, 1st FuHua Road, FuTian District, ShenZhen, 518033, GuangDong, China. [email protected].
- The fourth Clinical Medical College of Guangzhou University of Chinese Medicine, ShenZhen, GuangDong, China.
- Department of Orthopedics, Shenzhen Traditional Chinese Medicine Hospital, 1st FuHua Road, FuTian District, ShenZhen, 518033, GuangDong, China.
- School of Integrated Circuits (International School of Microelectronics), Dongguan University of Technology, 1st DaXue Road, SongShanHu District, DongGuan, 523808, GuangDong, China.
- Orthopedic and Traumatology Department, IRCCS Istituto Giannina Gaslini, Via Gerolamo Gaslini 5, Genoa, Italy.
- DISC-Dipartimento di Scienze Chirurgiche e Diagnostiche Integrate, University of Genova, Viale Benedetto XV No 6, Genoa, Italy.
- Department of Pediatric Orthopedics, Vittore Buzzi Children's Hospital, Milan, Italy.
- Hand and Microsurgery Unit, IRCCS Istituto Giannina Gaslini, Via Gerolamo Gaslini 5, Genoa, Italy.
- Orthopedic and Traumatology Department, Alto Vicentino Hospital, Via Garziere 42, Santorso, Italy.
- Department of Radiology, IRCCS Istituto Giannina Gaslini, Via Gerolamo Gaslini 5, Genoa, Italy.
- Department of General Surgery and Medical Surgical Specialties, Section of Orthopaedics and Trarumatology, Policlinico Rodolico-San Marco, University of Catania, Catania, Italy.
- Deaprtment of Pediatric Orthopaedics, Orthochildren Center, Bologna, Italy.
- Department of Precision Medicine in Medical, Surgical and Critical Care (Me.Pre.C.C.), University of Palermo, Palermo, Italy.
- Department of Orthopedics, Azienda Ospedaliera Universitaria "Luigi Vanvitelli", University of Campania "Luigi Vanvitelli" School of Medicine, Naples, Italy.
- Department of Life Science, Health and Health Professions, Link Campus University, Rome, Italy.
- Department of Orthopedics, Wuhan Children's Hospital (Wuhan Maternal and Child Healthcare Hospital), Tongji Medical College, Huazhong University of Science & Technology, Wuhan, China.
- Department of Pediatric Orthopedics, Foshan Hospital of Traditional Chinese Medicine, FoShan, GuangDong, China.
- Department of Orthopedics, Mindong Hospital of Ningde City, NingDe, FuJian, China.
- Department of Pediatric Orthopedics, Children's Hospital of Chongqing Medical University, ChongQing, China.
- Department of Pediatric Orthopedics, Children's Hospital of Fudan University, National Children's Medical Center, ShangHai, China.
- Department of Pediatric Orthopedics, Fuzhou Second General Hospital, 47th ShangTeng Road, CangShan District, FuZhou, 350007, FuJian, China. [email protected].
- School of Integrated Circuits (International School of Microelectronics), Dongguan University of Technology, 1st DaXue Road, SongShanHu District, DongGuan, 523808, GuangDong, China. [email protected].
- Department of Pediatric Orthopedics, Shenzhen Children's Hospital, 7019th YiTian Road, FuTian District, ShenZhen, 518026, GuangDong, China. [email protected].
Abstract
The Delbet-Colonna (DC) classification guides treatment of pediatric femoral neck fractures (PFNFs) but relies on clinical experience. No deep learning (DL) model has been developed and validated to differentiate between PFNFs and proximal femoral growth plates (PFGPs) and classify PFNFs via DC classification, in order to overcome this limitation. X-ray data including the annotations of 5555 PFGPs, 1306 PFNFs with various DC types, and 257 pediatric subtrochanteric femoral fractures (PSFFs), were prepared to construct a DL model based on the you-only-look-once (YOLO) model with wavelet transform (WT) and attention mechanism (AM) architectures. Two senior-level pediatric orthopedic surgeons (POS) performed the annotations independently by referring to the postoperative X-rays. The annotations were finalized if there were no differences. Otherwise, the two POS discussed and determined the final annotation. Thirty-one POS with different experience assessed the external testing dataset twice, without (first) and with (second) YOLO-WTAM model assistance. The rating performances of the YOLO-WTAM model and POS were evaluated. The kappa value reflecting reliability was obtained using a Fleiss kappa analysis. According to the internal testing dataset, the area under the curve for different annotations ranged from 0.94 to 0.99. According to the external testing dataset, in the second round, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were greater than those in the first (P < 0.001): 79.17-87.16%, 83.30-87.47%, 94.68-96.57%, 74.62-79.44%, and 92.97-95.55%, respectively. Senior-level POS exhibited superior accuracy (P = 0.021), sensitivity (P = 0.013), specificity (P = 0.039), PPV (P = 0.004), and NPV (P = 0.025) in the first round but not in the second. The kappa value improved among residents (+27.36%), junior-level (+17.03%), mid-level (+26.66%), and senior-level (+17.07%) POS. The YOLO-WTAM model can accurately differentiate between PFNFs and PFGPs and classify different DC types of PFNFs. This improves POSs' rating performance and reduces the need for experience in classifying PFNFs. Level III.