Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques |
| |
| Institution: | 1. Department of Computer Science and Information Engineering, National Central University, Jhongli County, Taoyuan City, Taiwan;2. Department of Mechanical Engineering, National Central University, Jhongli County, Taoyuan City, Taiwan;3. Pervasive Artificial Intelligence (PAIR) Labs, Taipei City, Taiwan;4. Orthopedic Department, Show Chwan Memorial Hospital, Changhua City, Taiwan;5. Institute of Cognitive Neuroscience, National Central University, No. 300, Jhongda Rd., Jhongli County, Taoyuan City 32001, Taiwan;1. Department of Orthopaedic Surgery, Canberra Hospital, Yamba Drive, Garran, ACT 2605, Australia;2. Trauma and Orthopaedic Research Unit, Canberra Hospital and Australian National University Medical School, Building 6, Level 1, Canberra Hospital, Yamba Drive, Garran, ACT 2605, Australia;1. Division of Orthopaedic Trauma;2. Department of Orthopaedics and Traumatology, Taipei Veterans General Hospital, 201, Sec.2, Shih-Pai Rd. Taipei 112, Taiwan;3. Department of Orthopaedics, School of Medicine, National Yang-Ming University;4. Division of Medical Imaging for Health Management, Cheng-Hsin General Hospital;5. Department of Radiology, School of Medicine, National Yang-Ming University;1. Orthopedic Surgery Resident, Department of Orthopedic Surgery, Albert Einstein Medical Center, Philadelphia, PA;2. Ear Nose and Throat Resident, Icahn School of Medicine at Mount Sinai, New York, NY;3. Orthopedic Surgeon, Department of Orthopedic Surgery, Albert Einstein Medical Center, Philadelphia, PA;1. Resident Surgery, Trauma Unit, Academic Medical Center location AMC, Amsterdam, the Netherlands;2. Trauma Surgeon, Trauma Unit, Academic Medical Center location AMC, Amsterdam, the Netherlands |
| |
| Abstract: | BackgroundClassification of the type of calcaneal fracture on CT images is essential in driving treatment. However, human-based classification can be challenging due to anatomical complexities and CT image constraints. The use of computer-aided classification system in standard practice is additionally hindered by the availability of training images. The aims of this study is to 1) propose a deep learning network combined with data augmentation technique to classify calcaneal fractures on CT images into the Sanders system, and 2) assess the efficiency of such approach with differential training methods.MethodsIn this study, the Principle component analysis (PCA) network was selected for the deep learning neural network architecture for its superior performance. CT calcaneal images were processed through PCA filters, binary hashing, and a block-wise histogram. The Augmentor pipeline including rotation, distortion, and flips was applied to generate artificial calcaneus fractured images. Two types of training approaches and five data sample sizes were investigated to evaluate the performance of the proposed system with and without data augmentation.ResultsCompared to the original performance, use of augmented images during training improved network performance accuracy by almost twofold in classifying Sanders fracture types for all dataset sizes. A fivefold increase in the number of augmented training images improved network classification accuracy by 35%. The proposed deep CNN model achieved 72% accuracy in classifying CT calcaneal images into the four Sanders categories when trained with sufficient augmented artificial images.ConclusionThe proposed deep-learning algorithm coupled with data augmentation provides a feasible and efficient approach to the use of computer-aided system in assisting physicians in evaluating calcaneal fracture types. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
