Dual-Stream Attention-Based Classification Network for Tibial Plateau Fractures via Diffusion Model Augmentation and Segmentation Map Integration

Abstract

Objective

This study aimed to explore a novel method that integrates the segmentation guidance classification and the diffusion model augmentation to realize the automatic classification for tibial plateau fractures (TPFs).

Methods

YOLOv8n-cls was used to construct a baseline model on the data of 3781 patients from the Orthopedic Trauma Center of Wuhan Union Hospital. Additionally, a segmentation-guided classification approach was proposed. To enhance the dataset, a diffusion model was further demonstrated for data augmentation.

Results

The novel method that integrated the segmentation-guided classification and diffusion model augmentation significantly improved the accuracy and robustness of fracture classification. The average accuracy of classification for TPFs rose from 0.844 to 0.896. The comprehensive performance of the dual-stream model was also significantly enhanced after many rounds of training, with both the macro-area under the curve (AUC) and the micro-AUC increasing from 0.94 to 0.97. By utilizing diffusion model augmentation and segmentation map integration, the model demonstrated superior efficacy in identifying Schatzker I, achieving an accuracy of 0.880. It yielded an accuracy of 0.898 for Schatzker II and III and 0.913 for Schatzker IV; for Schatzker V and VI, the accuracy was 0.887; and for intercondylar ridge fracture, the accuracy was 0.923.

Conclusion

The dual-stream attention-based classification network, which has been verified by many experiments, exhibited great potential in predicting the classification of TPFs. This method facilitates automatic TPF assessment and may assist surgeons in the rapid formulation of surgical plans.

Keywords

Artificial intelligence / YOLOv8 / Tibial plateau fracture / Diffusion model augmentation / Segmentation map

© The Author(s), under exclusive licence to Huazhong University of Science and Technology 2025

Authors’ Contributions All authors listed have made a substantial, direct, and intellectual contribution to the work, and approved it for publication.

Data Availability Not applicable.

Declarations

Conflict of Interest All authors declare that there are no competing financial interests.

Ethics Approval and Consent to Participate Not applicable.

Consent for Publication Not applicable.

References

[1] Khan K, Mushtaq M, Rashid M, et al. Management of tibial plateau fractures: a fresh review. Acta Orthop Belg. 2023; 89(2):265-273.

[2] Xie X, Zhan Y, Wang Y, et al. Comparative Analysis of Mechanism-Associated 3-Dimensional Tibial Plateau Fracture Patterns. J Bone Joint Surg Am. 2020; 102(5):410-418.

[3] Kfuri M, Schatzker J. Revisiting the Schatzker classification of tibial plateau fractures. Injury. 2018; 49(12):2252-2263.

[4] Liu PR, Zhang JY, Xue MD, et al. Artificial Intelligence to Diagnose Tibial Plateau Fractures: An Intelligent Assistant for Orthopedic Physicians. Curr Med Sci. 2021; 41(6):1158-1164.

[5] Hill BG, Krogue JD, Jevsevar DS, et al. Deep Learning and Imaging for the Orthopaedic Surgeon: How Machines "Read" Radiographs. J Bone Joint Surg Am. 2022; 104(18):1675-1686.

[6] Yoon AP, Lee YL, Kane RL, et al. Development and Validation of a Deep Learning Model Using Convolutional Neural Networks to Identify Scaphoid Fractures in Radiographs. JAMA Netw Open. 2021; 4(5):e216096.

[7] Senanayake D, Seneviratne S, Imani M, et al. Classification of Fracture Risk in Fallers Using Dual-Energy X-Ray Absorptiometry (DXA) Images and Deep Learning-Based Feature Extraction. JBMR Plus. 2023; 7(12):e10828.

[8] Xu F, Xiong Y, Ye G, et al. Deep learning-based artificial intelligence model for classification of vertebral compression fractures: A multicenter diagnostic study. Front Endocrinol (Lausanne). 2023; 14:1025749.

[9] Liu XS, Nie R, Duan AW, et al. YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons. Chin J Traumatol. 2024; 23:1087-1092.

[10] Zhang J, Xia L, Liu J, et al. Exploring deep learning radiomics for classifying osteoporotic vertebral fractures in X-ray images. Front Endocrinol (Lausanne). 2024; 15:1370838.

[11] Ono Y, Suzuki N, Sakano R, et al. A Deep Learning-Based Model for Classifying Osteoporotic Lumbar Vertebral Fractures on Radiographs: A Retrospective Model Development and Validation Study. J Imaging. 2023; 9(9):187.

[12] Chung SW, Han SS, Lee JW, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018; 89(4):468-473.

[13] Mutasa S, Varada S, Goel A, et al. Advanced deep learning techniques applied to automated femoral neck fracture detection and classification. J Digit Imaging. 2020; 33(5):1209-1217.

[14] Wang H, Cao P, Yang J, et al. MCA-UNet: multi-scale cross coattentional U-Net for automatic medical image segmentation. Health Inf Sci Syst. 2023; 11(1):10.

[15] Chen C, Liu B, Zhou K, et al. CSR-Net: Cross-Scale Residual Network for multi-objective scaphoid fracture segmentation. Comput Biol Med. 2021; 137:104776.

[16] Guo J, Mu Y, Xue D, et al. Automatic analysis system of calcaneus radiograph: Rotation-invariant landmark detection for calcaneal angle measurement, fracture identification and fracture region segmentation. Comput Methods Programs Biomed. 2021; 206:106124.

[17] Zeng B, Wang H, Joskowicz L, et al. Fragment distance-guided dualstream learning for automatic pelvic fracture segmentation. Comput Med Imaging Graph. 2024; 116:102412.

[18] Huang Y, Yang X, Liu L, et al. Med Image Anal. Segment anything model for medical images? 2024; 92:103061.

[19] Chen Y, Yang XH, Wei Z, et al. Generative Adversarial Networks in Medical Image augmentation: A review. Comput Biol Med. 2022; 144:105382.

[20] Kebaili A, Lapuyade-Lahorgue J, Ruan S. Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review. J Imaging. 2023; 9(4):81.

[21] Wu S, Kurugol S, Tsai A. Improving the radiographic image analysis of the classic metaphyseal lesion via conditional diffusion models. Med Image Anal. 2024; 97:103284.

[22] Kazerouni A, Aghdam EK, Heidari M, et al. Diffusion models in medical imaging: A comprehensive survey. Med Image Anal. 2023; 88:102846.

[23] Hao R, Namdar K, Liu L, et al. A Comprehensive Study of Data Augmentation Strategies for Prostate Cancer Detection in DiffusionWeighted MRI Using Convolutional Neural Networks. J Digit Imaging. 2021; 34(4):862-876.

[24] Abedeen I, Rahman MA, Prottyasha FZ, et al. FracAtlas: A Dataset for Fracture Classification, Localization and Segmentation of Musculoskeletal Radiographs. Sci Data. 2023; 10(1):521.

[25] Yao X, Zhou K, Lv B, et al. 3D mapping and classification of tibial plateau fractures. Bone Joint Res. 2020; 9(6):258-267.

[26] Aly GH, Marey M, El-Sayed SA, et al. YOLO Based Breast Masses Detection and Classification in Full-Field Digital Mammograms. Comput Methods Programs Biomed. 2021; 200:105823.

[27] Jeon YD, Kang MJ, Kuh SU, et al. Deep Learning Model Based on You Only Look Once Algorithm for Detection and Visualization of Fracture Areas in Three-Dimensional Skeletal Images. Diagnostics (Basel). 2023; 14(1):11.

[28] Ju RY, Cai W. Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm. Sci Rep. 2023; 13(1):20077.

[29] Cheng J, Tian S, Yu L, et al. Fully convolutional attention network for biomedical image segmentation. Artif Intell Med. 2020; 107:101899.

[30] Zhuo M, Chen X, Guo J, et al. Deep Learning-Based Segmentation and Risk Stratification for Gastrointestinal Stromal Tumors in Transabdominal Ultrasound Imaging. J Ultrasound Med. 2024; 43(9):1661-1672.

[31] Das N, Das S. Attention-UNet architectures with pretrained backbones for multi-class cardiac MR image segmentation. Curr Probl Cardiol. 2024; 49(1):102129.

[32] Bian X, Wang G, Wu Y, et al. TCI-UNet: transformer-CNN interactive module for medical image segmentation. Biomed Opt Express. 2023; 14(11):5904-5920.

[33] Xu Y, Gong M, Xie S, et al. Semi-Implicit Denoising Diffusion Models (SIDDMs). Adv Neural Inf Process Syst. 2023; 36:17383-17394.

[34] Hung ALY, Zhao K, Zheng H, et al. Med-cDiff: Conditional Medical Image Generation with Diffusion Models. Bioengineering (Basel). 2023; 10(11):1258.

[35] Daher R, Vasconcelos F, Stoyanov D. A Temporal Learning Approach to Inpainting Endoscopic Specularities and Its Effect on Image Correspondence. Med Image Anal. 2023; 90:102994.

[36] Xiao L, Wu J. Image inpainting algorithm based on double curvature-driven diffusion model with P-Laplace operator. PLoS One. 2024; 19(7):e0305470.

[37] Leiñena J, Saiz FA, Barandiaran I. Latent Diffusion Models to Enhance the Performance of Visual Defect Segmentation Networks in Steel Surface Inspection. Sensors (Basel). 2024; 24(18):6016.

[38] Hinton GE, Salakhutdinov RR. Reducing the dimensionality of data with neural networks. Science. 2006; 313(5786):504-507.

[39] Lin J, Xie X, Wu W, et al. Model transfer from 2D to 3D study for boxing pose estimation. Front Neurorobot. 2023; 17:1148545.

[40] Kuo RYL, Harrison C, Curran TA, et al. Artificial Intelligence in Fracture Detection: A Systematic Review and Meta-Analysis. Radiology. 2022; 304(1):50-62.

[41] Oakden-Rayner L, Gale W, Bonham TA, et al. Validation and algorithmic audit of a deep learning system for the detection of proximal femoral fractures in patients in the emergency department: a diagnostic accuracy study. Lancet Digit Health. 2022; 4(5):e351-e358.

[42] Qiu Z, Xie Z, Lin H, et al. Learning co-plane attention across MRI sequences for diagnosing twelve types of knee abnormalities. Nat Communication. 2024; 15:7637.

Funding

the National Natural Science Foundation of China(81974355)

the National Natural Science Foundation of China(82172524)

Key Research and Development Program of Hubei Province(2021BEA161)

National Innovation Platform Development Program(2020021105012440)

Open Project Funding of the Hubei Key Laboratory of Big Data Intelligent Analysis and Application, Hubei University(2024BDIAA03)

Free Innovation Preliminary Research Fund of Wuhan Union Hospital(2024XHYN047)