Corpus ID: 123746298

Efficient Prealignment of CT Scans for Registration through a Bodypart Regressor

  title={Efficient Prealignment of CT Scans for Registration through a Bodypart Regressor},
  author={Hans Meine and Alessa Hering},
Convolutional neural networks have not only been applied for classification of voxels, objects, or images, for instance, but have also been proposed as a bodypart regressor. We pick up this underexplored idea and evaluate its value for registration: A CNN is trained to output the relative height within the human body in axial CT scans, and the resulting scores are used for quick alignment between different timepoints. Preliminary results confirm that this allows both fast and robust… Expand
Self-supervised Learning of Pixel-wise Anatomical Embeddings in Radiological Images
Self-supervised Anatomical eMbedding is introduced, a pixel-level contrastive learning framework that generates semantic embeddings for each image pixel that describes its anatomical location or body part and outperforms supervised methods trained on 50 labeled images. Expand
Performance Comparison of Feature Generation Algorithms for Mosaic Photoacoustic Microscopy
  • Thanh Dat Le, Seong Young Kwon, Changho Lee
  • Computer Science
  • Photonics
  • 2021
The analytic results indicate the successful implementation of wide-field PAM images, realized by applying suitable methods to the mosaic PAM imaging process, compared to traditional and deep learning feature generation algorithms by estimating the processing time, the number of matches, good matching ratio, and matching efficiency. Expand


Unsupervised body part regression via spatially self-ordering convolutional neural networks
  • Ke Yan, Le Lu, R. Summers
  • Computer Science
  • 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018)
  • 2018
A convolutional neural network (CNN) based unsupervised body part regression (UBR) algorithm to address the problem of automatic body part recognition for CT slices and two inter-sample CNN loss functions are presented. Expand
Anatomy-specific classification of medical images using deep convolutional nets
It is demonstrated that deep learning can be used to train very reliable and accurate classifiers that could initialize further computer-aided diagnosis and a data augmentation approach can help to enrich the data set and improve classification performance. Expand
Self supervised deep representation learning for fine-grained body part recognition
This work is the first attempt studying the problem of robust body part recognition at a continuous level and can achieve high accuracy with a slice location estimation error of only a few slices on CT and MR data. Expand
Progressively growing convolutional networks for end-to-end deformable image registration
This work proposes a progressive training method for end-to-end image registration with convolutional neural networks that is able to learn larger deformations more quickly at the start of training, making pre-registration redundant. Expand
A deep learning framework for unsupervised affine and deformable image registration
For registration of cardiac cine MRI and registration of chest CT that performance of the DLIR framework is comparable to conventional image registration while being several orders of magnitude faster. Expand
Multi-Instance Deep Learning: Discover Discriminative Local Anatomies for Bodypart Recognition
  • Z. Yan, Y. Zhan, +5 authors X. Zhou
  • Computer Science, Medicine
  • IEEE Transactions on Medical Imaging
  • 2016
A multi-stage deep learning framework for image classification and apply it on bodypart recognition achieves better performances than state-of-the-art approaches, including the standard deep CNN. Expand
Deep Lesion Graphs in the Wild: Relationship Learning and Organization of Significant Radiology Image Findings in a Diverse Large-Scale Lesion Database
A triplet network is utilized to learn lesion embeddings with a sequential sampling strategy to depict their hierarchical similarity structure and results show promising qualitative and quantitative results on lesion retrieval, clustering, and classification. Expand
Unsupervised learning for large motion thoracic CT follow-up registration