Yehyun Suh

2023

1. Label Augmentation Method for Medical Landmark Detection in Hip Radiograph Images

   Yehyun Suh, Peter Chan, J. Ryan Martin, and Daniel Moyer

   2023

   Abs Bib HTML PDF Code

   This work reports the empirical performance of an automated medical landmark detection method for predict clinical markers in hip radiograph images. Notably, the detection method was trained using a label-only augmentation scheme; our results indicate that this form of augmentation outperforms traditional data augmentation and produces highly sample efficient estimators. We train a generic U-Net-based architecture under a curriculum consisting of two phases: initially relaxing the landmarking task by enlarging the label points to regions, then gradually eroding these label regions back to the base task. We measure the benefits of this approach on six datasets of radiographs with gold-standard expert annotations.

   @misc{suh2023label,
     title = {Label Augmentation Method for Medical Landmark Detection in Hip Radiograph Images},
     author = {Suh, Yehyun and Chan, Peter and Martin, J. Ryan and Moyer, Daniel},
     year = {2023},
     eprint = {2309.16066},
     archiveprefix = {arXiv},
     primaryclass = {cs.LG},
   }

2. 

   Dilation-Erosion Methods for Radiograph Annotation in Total Knee Replacement

   Yehyun Suh, Aleksander Mika, J. Ryan Martin, and Daniel Moyer

   In Medical Imaging with Deep Learning, short paper track, 2023

   Abs Bib HTML PDF Code Poster

   In the present work we describe a novel training scheme for automated radiograph annotation, as used in post-surgical assessment of Total Knee Replacement. As we show experimentally, standard off-the-shelf methods fail to provide high accuracy image annotations for Total Knee Replacement annotation. We instead adopt a U-Net based segmentation style annotator, relax the task by dilating annotations into larger label regions, then progressively erode these label regions back to the base task on a schedule based on training epoch. We demonstrate the advantages of this scheme on a dataset of radiographs with gold-standard expert annotations, comparing against four baseline cases.

   @inproceedings{suh2023dilationerosion,
     title = {Dilation-Erosion Methods for Radiograph Annotation in Total Knee Replacement},
     author = {Suh, Yehyun and Mika, Aleksander and Martin, J. Ryan and Moyer, Daniel},
     booktitle = {Medical Imaging with Deep Learning, short paper track},
     year = {2023},
     url = {https://openreview.net/forum?id=bVC9bi_-t7Y},
   }