Soar, Peter ORCID: https://orcid.org/0000-0003-1745-9443, Palanca, Marco, Enrico, Dall'Ara and Tozzi, Gianluca (2024) D2IM prototype dataset: Porcine Vertebra Slices. [Dataset] (doi:10.34740/kaggle/ds/4500725)

	Image (TIFF) (D2IM Prototype Dataset - Porcine Vertebra Slices) D2IM_Data.zip - Supplemental Material Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (325MB)
	Other (D2IM Notebook File) d2im-prototype.ipynb - Supplemental Material Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (71kB)
	Other (Trained Convolutional Neural Network) D2IM_trained.h5 - Supplemental Material Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (437MB)
	Other (Trained Convolutional Neural Network with data augmentation) D2IM_trained_data_augmentation.h5 - Supplemental Material Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (437MB)
	Plain Text (README for dataset submission) README.txt - Supplemental Material Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1kB)
	Plain Text (Apache License - Version 2.0) 46150_SOAR_LICENSE-2.0.txt - Other Download (11kB)

Abstract

Supplementary data for the paper: Data-driven image mechanics (D2IM): a deep learning approach to predict displacement and strain fields from undeformed X-ray tomography images - Evaluation of bone mechanics. This submission contains the full dataset used for training and evaluating the D2IM model presented in the paper. The 'Input' folder contains two subdirectories, one containing the clinical scans (input 1 in the model) and the binary mask made from these scans (input 2 in the model). The 'Target' folder contains three subdirectories, which contain the ground truth images (obtained using DVC) corresponding to the full field displacement data for the three displacement components u, v and w. The 'Clinical' folder contains a few examples of clinical and resized images used (along with masks and other required imaging) used for testing the ability of the model to scale to lower resolution imaging. Also contained in this submission is an example notebook file (d2im-prototype.ipynb) showing the code used to train and evaluate the model, as well as generate the statistics and images presented in the paper. This is also accompanied with two examples of trained models(D2IM_trained.h5, D2IM_trained_data_augmentation.h5) that can be used to make predictions from the images.

Item Type:	Dataset
Additional Information:	This data was derived from the shared dataset of porcine vertebra under compressions with and without man made lesions obtained by Enrico Dall'Ara and Marco Palanca at the university of Sheffield: https://orda.shef.ac.uk/articles/dataset/Data_for_paper_MicroFE_models_of_porcine_vertebrae_with_induced_bone_focal_lesions_validation_of_predicted_displacements_with_Digital_Volume_Correlation_/16732441/1
Uncontrolled Keywords:	D2IM; Bone; X-ray computed tomography; digital volume correlation; deep learning; Convolutional Neural Network
Subjects:	Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty / School / Research Centre / Research Group:	Faculty of Engineering & Science Faculty of Engineering & Science > School of Computing & Mathematical Sciences (CMS)
Related URLs:	https://www.kaggle.com/ds/4500725 https://www.kaggle.com/code/petersoar/d2...
Last Modified:	10 Oct 2024 15:58
URI:	http://gala.gre.ac.uk/id/eprint/46150

Actions (login required)

View Item

Downloads