Context-Aware Transformers For Spinal Cancer Detection and Radiological Grading

@inproceedings{Windsor2022ContextAwareTF,
  title={Context-Aware Transformers For Spinal Cancer Detection and Radiological Grading},
  author={Rhydian Windsor and Amir Jamaludin and Timor Kadir and Andrew Zisserman},
  booktitle={MICCAI},
  year={2022}
}
. This paper proposes a novel transformer-based model architecture for medical imaging problems involving analysis of vertebrae. It considers two applications of such models in MR images: (a) detection of spinal metastases and the related conditions of vertebral fractures and metastatic cord compression, (b) radiological grading of common degenerative changes in intervertebral discs. Our contributions are as follows: (i) We propose a Spinal Context Transformer (SCT), a deep-learning… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 35 REFERENCES

SpineNet: Automated classification and evidence visualization in spinal MRIs

A deep learning model for detection of cervical spinal cord compression in MRI scans

TLDR
A deep convolutional neural network is trained using images from the training/validation dataset and assessed model performance on the holdout dataset to improve the efficiency and objectivity of the interpretation of cervical spine MRI scans.

Discriminative Dictionary-Embedded Network for Comprehensive Vertebrae Tumor Diagnosis

TLDR
A discriminative dictionary-embedded network (DECIDE) that contains an elaborated enhanced-supervision recognition network (ERN) and a discerning diagnosis network (DDN) that integrates a novel label consistent dictionary learning layer into a classification network to obtain more discerning sparse codes for diagnosing performance improvement.

Deep Spine: Automated Lumbar Vertebral Segmentation, Disc-Level Designation, and Spinal Stenosis Grading using Deep Learning

TLDR
An efficient methodology is developed to leverage the subject-matter-expertise stored in large-scale archival reporting and image data for a deep-learning approach to fully-automated lumbar spinal stenosis grading and is expected to increase both radiology workflow efficiency and the perceived value of radiology reports for referring clinicians and patients.

SpineNetV2: Automated Detection, Labelling and Radiological Grading Of Clinical MR Scans

This technical paper presents SpineNetV2, an automated tool which: (i) detects and labels vertebral bodies in clinical spinal magnetic resonance (MR) scans across a range of commonly used sequences;

A Convolutional Approach to Vertebrae Detection and Labelling in Whole Spine MRI

TLDR
A novel convolutional method is proposed using a learnt vector field to group detected vertebrae corners together into individual vertebral bodies and Convolutional image-to-image translation followed by beam search to label vertebral levels in a self-consistent manner for whole spine MRIs.

Detection and Labeling of Vertebrae in MR Images Using Deep Learning with Clinical Annotations as Training Data

TLDR
Results show that clinically annotated image data from one image archive is sufficient to train a deep learning-based pipeline for accurate detection and labeling of MR images depicting the spine, and support using deep learning to assist radiologists in their work by providing highly accurate labels that only require rapid confirmation.

Vertebrae Localization in Pathological Spine CT via Dense Classification from Sparse Annotations

TLDR
A robust localization and identification algorithm which builds upon supervised classification forests and avoids an explicit parametric model of appearance is proposed which outperforms state-of-the-art on pathological cases and overcome the tedious requirement for dense annotations by a semi-automatic labeling strategy.

Self-supervised Learning for Spinal MRIs

TLDR
This work shows that longitudinal scans alone can be used as a form of “free” self-supervision for training a deep network, and shows that the performance of the pre-trained CNN on the supervised classification task is superior to that of a network trained from scratch.