added a research item
Medical Image Segmentation
100+ 2D US Images and Tumor Segmentation Masks. Please cite this paper if you use these in your work: A. Hann, L. Bettac, M. M. Haenle, T. Graeter, A. W. Berger, J. Dreyhaupt, D. Schmalstieg, W. G. Zoller, J. Egger. “Algorithm guided outlining of 105 pancreatic cancer liver metastases in Ultrasound“. In: Sci. Rep. 7, 12779, 2017. https://www.nature.com/articles/s41598-017-12925-z
Non-contrast and contrast-enhanced t1-weighted MRI scans from a healthy subject. Non-contrast scan acquired 2010 and contrast-enhanced scan acquired 2015 (Note: the contrast-enhanced scan has been registered to the non-contrast scan). If you use anything for your own research, please give credits to: J. Egger "non-contrast and contrast-enhanced t1-weighted MRI scans", ResearchGate, January 2018. and L. Lindner, B. Pfarrkirchner, C. Gsaxner, D. Schmalstieg, J. Egger. "TuMore: Generation of Synthetic Brain Tumor MRI Data for Deep Learning Based Segmentation Approaches". SPIE Medical Imaging, Machine Learning and Artificial Intelligence, Paper 10579-63, February 2018.
Spinal diseases are very common; for example, the risk of osteoporotic fracture is 40% for White women and 13% for White men in the United States during their lifetime. Hence, the total number of surgical spinal treatments is on the rise with the aging population, and accurate diagnosis is of great importance to avoid complications and a reappearance of the symptoms. Imaging and analysis of a vertebral column is an exhausting task that can lead to wrong interpretations. The overall goal of this contribution is to study a cellular automata-based approach for the segmentation of vertebral bodies between the compacta and surrounding structures yielding to time savings and reducing interpretation errors. To obtain the ground truth, T2-weighted magnetic resonance imaging acquisitions of the spine were segmented in a slice-by-slice procedure by several neurosurgeons. Subsequently, the same vertebral bodies have been segmented by a physician using the cellular automata approach GrowCut. Manual and GrowCut segmentations have been evaluated against each other via the Dice Score and the Hausdorff distance resulting in 82.99% ± 5.03% and 18.91 ± 7.2 voxel, respectively. Moreover, the times have been determined during the slice-by-slice and the GrowCut course of actions, indicating a significantly reduced segmentation time (5.77 ± 0.73 min) of the algorithmic approach. In this contribution, we used the GrowCut segmentation algorithm publicly available in three-dimensional Slicer for three-dimensional segmentation of vertebral bodies. To the best of our knowledge, this is the first time that the GrowCut method has been studied for the usage of vertebral body segmentation. In brief, we found that the GrowCut segmentation times were consistently less than the manual segmentation times. Hence, GrowCut provides an alternative to a manual slice-by-slice segmentation process.
This software framework brings a set of input volumes from pediatric brains into alignment. Therefore, the notion of pair-wise image registration is extended to group-wise alignment, which allows to find correspondence among a whole group of data sets instead of just two of them. Moreover, it simultaneously brings the set of input volumes into alignment, with every member of the population approaching the group’s central tendency at the same time.
The manual outlining of hepatic metastasis in (US) ultrasound acquisitions from patients suffering from pancreatic cancer is common practice. However, such pure manual measurements are often very time consuming, and the results repeatedly differ between the raters. In this contribution, we study the in-depth assessment of an interactive graph-based approach for the segmentation for pancreatic metastasis in US images of the liver with two specialists in Internal Medicine. Thereby, evaluating the approach with over one hundred different acquisitions of metastases. The two physicians or the algorithm had never assessed the acquisitions before the evaluation. In summary, the physicians first performed a pure manual outlining followed by an algorithmic segmentation over one month later. As a result, the experts satisfied in up to ninety percent of algorithmic segmentation results. Furthermore, the algorithmic segmentation was much faster than manual outlining and achieved a median Dice Similarity Coefficient (DSC) of over eighty percent. Ultimately, the algorithm enables a fast and accurate segmentation of liver metastasis in clinical US images, which can support the manual outlining in daily practice.