Multi Locale Bone Fracture Radiographs and Localization

Abedeen, Iftekharul; Rahman, MD Ashiqur; Prottyasha, Fatema Zohra

dc.contributor.author	Abedeen, Iftekharul
dc.contributor.author	Rahman, MD Ashiqur
dc.contributor.author	Prottyasha, Fatema Zohra
dc.date.accessioned	2023-03-16T05:57:02Z
dc.date.available	2023-03-16T05:57:02Z
dc.date.issued	2022-05-30
dc.identifier.citation	Basha, M. A. A., Ismail, A. A. A., & Imam, A. H. F. (2018). Does radiography still have a significant diagnostic role in evaluation of acute traumatic wrist injuries? a prospective comparative study. Emergency Radiology, 25(2), 129– 138 (cit. on p. 4). Bochkovskiy, A., Wang, C.-Y., & Liao, H.-Y. M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (cit. on p. 7). Bodla, N., Singh, B., Chellappa, R., & Davis, L. (2017). Improving object detection with one line of code. 2017. CoRR, abs/1704.04503. http://arxiv.org/abs/ 1704.04503 (cit. on pp. 17, 25) De Putter, C., Selles, R., Polinder, S., Panneman, M., Hovius, S., & van Beeck, E. F. (2012). Economic impact of hand and wrist injuries: Health-care costs and productivity costs in a population-based study. Jbjs, 94(9), e56 (cit. on p. 4). Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. 2009 IEEE conference on computer vision and pattern recognition, 248–255 (cit. on p. 1). Eksi, Z., & Cakiroglu, M. (2012). Performance evaluation of the popular segmentation algorithms for bone fracture detection. Global Journal on Technology, 1 (cit. on p. 9). He, K., Gkioxari, G., Dollar, P., & Girshick, R. ( ´ 2017). Mask r-cnn. Proceedings of the IEEE international conference on computer vision, 2961–2969 (cit. on pp. 7, 8, 19, 20). HHS, N. (2016). Medpix. https://medpix.nlm.nih.gov/search?allen=false& allt=false&alli=true&query=fracture. (Cit. on p. 12) Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., NanoCode012, Kwon, Y., TaoXie, Fang, J., imyhxy, Michael, K., Lorna, V, A., Montes, D., Nadar, J., Laughing, tkianai, yxNONG, Skalski, P., Wang, Z., . . . Minh, M. T. (2022). ultralytics/yolov5: v6.1 - TensorRT, TensorFlow Edge TPU and OpenVINO Export and Inference (Version v6.1). Zenodo. https://doi.org/10.5281/zenodo.6222936. (Cit. on p. 7) Karl, J. W., Olson, P. R., & Rosenwasser, M. P. (2015). The epidemiology of upper extremity fractures in the united states, 2009. Journal of orthopaedic trauma, 29(8), e242–e244 (cit. on p. 4). Kim, D., & MacKinnon, T. (2018). Artificial intelligence in fracture detection: Transfer learning from deep convolutional neural networks. Clinical radiology, 73(5), 439–445 (cit. on p. 9). 31 Bibliography Kositbowornchai, S., Nuansakul, R., Sikram, S., Sinahawattana, S., & Saengmontri, S. (2001). Root fracture detection: A comparison of direct digital radiography with conventional radiography. Dentomaxillofacial Radiology, 30(2), 106–109 (cit. on pp. 1, 9). Lin, T.-Y., Goyal, P., Girshick, R., He, K., & Dollar, P. ( ´ 2017). Focal loss for dense object detection. Proceedings of the IEEE international conference on computer vision, 2980–2988 (cit. on pp. 7, 8, 20, 21). Outram, A. K. (2002). Bone fracture and within-bone nutrients: An experimentally based method for investigating levels of marrow extraction. McDonald Institute for Archaeological Research. (Cit. on p. 4). Radiopaedia. (2006). https://radiopaedia.org/search?lang=us&q=fracture. (Cit. on p. 12) Raisuddin, A. M., Vaattovaara, E., Nevalainen, M., Nikki, M., Jarvenp ¨ a¨a, E., Makko- ¨ nen, K., Pinola, P., Palsio, T., Niemensivu, A., Tervonen, O., et al. (2021). Critical evaluation of deep neural networks for wrist fracture detection. Scientific reports, 11(1), 1–11 (cit. on pp. 4, 10, 11). Rajpurkar, P., Irvin, J., Bagul, A., Ding, D., Duan, T., Mehta, H., Yang, B., Zhu, K., Laird, D., Ball, R. L., et al. (2017). Mura: Large dataset for abnormality detection in musculoskeletal radiographs. arXiv preprint arXiv:1712.06957 (cit. on p. 11). Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE conference on computer vision and pattern recognition, 779–788 (cit. on pp. 5, 6). Redmon, J., & Farhadi, A. (2017). Yolo9000: Better, faster, stronger. Proceedings of the IEEE conference on computer vision and pattern recognition, 7263–7271 (cit. on p. 6). Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (cit. on p. 7). S.Gornale, S., U.Patravali. (2020). A comprehensive digital knee x-ray image dataset for the assessment of osteoarthritis. IEEE Transactions on Biomedical Engineering, 56(2), 407–415 (cit. on p. 12). Skalski, P. (2019). Make sense. https://www.makesense.ai/. (Cit. on pp. 14, 18) Solawetz, J. (2020). Yolov5 new version - improvements and evaluation. https: //blog.roboflow.com/yolov5-improvements - and - evaluation/. (Cit. on pp. 18, 19) Tan, M., Pang, R., & Le, Q. V. (2020). Efficientdet: Scalable and efficient object detection. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 10781–10790 (cit. on pp. 20, 21). Tentori, F., McCullough, K., Kilpatrick, R. D., Bradbury, B. D., Robinson, B. M., Kerr, P. G., & Pisoni, R. L. (2014). High rates of death and hospitalization follow bone fracture among hemodialysis patients. Kidney international, 85(1), 166–173 (cit. on p. 4). Thatte, A. V. (2020). Evolution of yolo-yolo version 1. https://towardsdatascience. com/evolution-of-yolo-yolo-version-1-afb8af302bd2. (Cit. on p. 5) 32 Bibliography Thian, Y. L., Li, Y., Jagmohan, P., Sia, D., Chan, V. E. Y., & Tan, R. T. (2019). Convolutional neural networks for automated fracture detection and localization on wrist radiographs. Radiology: Artificial Intelligence, 1(1), e180001 (cit. on p. 10). Thuan, D. (2021). Evolution of yolo algorithm and yolov5: The state-of-the-art object detection algorithm (cit. on pp. 5, 6). Ubaidillah, S. H. S. A., Sallehuddin, R., & Ali, N. A. (2013). Cancer detection using aritifical neural network and support vector machine: A comparative study. Jurnal Teknologi, 65(1) (cit. on p. 1). Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017). Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE conference on computer vision and pattern recognition, 2097–2106 (cit. on p. 12). Welling, R. D., Jacobson, J. A., Jamadar, D. A., Chong, S., Caoili, E. M., & Jebson, P. J. (2008). Mdct and radiography of wrist fractures: Radiographic sensitivity and fracture patterns. American Journal of Roentgenology, 190(1), 10–16 (cit. on p. 8). Yadav, D., & Rathor, S. (2020). Bone fracture detection and classification using deep learning approach. 2020 International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC), 282–285 (cit. on p. 12).	en_US
dc.identifier.uri	http://hdl.handle.net/123456789/1772
dc.description	Supervised by Mr. Tareque Mohmud Chowdhury & Mr. Tasnim Ahmed, Department of Computer Science and Engineering(CSE), Islamic University of Technology (IUT) Board Bazar, Gazipur-1704, Bangladesh. This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2022.	en_US
dc.description.abstract	We introduce MLBFR, a varied radiographs dataset of human bone fractures. The dataset contains 2,583 radiographs, among which 410 have 575 fracture points. A radiologist manually labelled the dataset as ”fractured” and ”non-fractured” with masks for the fracture locations. The dataset was verified and approved by an expert medical officer to evaluate the radiologist’s performance further. To precisely detect and localize the fracture areas, we experimented with several state- of-the-art object detection models, YOLOv5, maskRCNN, efficientDet and more, along with their ensemble. The trained models fell under two criteria, one being the full dataset and the other being only the fractured radiographs. The trained models managed to achieve a precision of 78.9% and 91.65% on combined and only fractured radiographs, respectively. The model performances were comparable to that of radiologists in detecting major abnormalities in the arm and shinbone area. With falling slightly behind in detecting fractures in the hip, thigh, and finger fractures. It is our belief that the task of improving this performance will be a good challenge for future research. To further encourage advancement in this area, we intend to make this dataset freely available in the future.	en_US
dc.language.iso	en	en_US
dc.publisher	Department of Computer Science and Engineering(CSE), Islamic University of Technology(IUT), Board Bazar, Gazipur, Bangladesh	en_US
dc.subject	MLFBR, Radiographs, maskRCNN, YOLO	en_US
dc.title	Multi Locale Bone Fracture Radiographs and Localization	en_US
dc.type	Thesis	en_US