Computer-Assisted Diagnostics Interventions (CADI)

Research members: Ruhan Sa, Subarna Gosh, Jaehan Koh, Raja Alomari, Taruna Seth

Automatic landmark detection in spine medical images


Evaluating spine biomechanical parameters, such as spine curvatures, vertebral body rotations, etc, are important to diagnose spine diseases as well as improving clinical outcomes by performing corrective actions to the affected area for a conservative treatment. For example, 75% of patients injured in motor vehicle accidents are suffered from ligament instability and injury, which can be diagnosed through calculation of specific osseous landmarks on spinal radiograph. However, evaluating these biomechanical parameters manually in clinical treatment is not pragmatic as it leads to prolonged diagnostic process. Furthermore, to ensure the accuracy of the evaluations, one needs to be involved in extensive and specialized trainings. Due to the above barriers, biomechanical analysis is not being used clinically despite the numerous benefits it can bring to improve clinical outcomes. In order to overcome the current clinical barrier, we propose to automatically analyze spine parameters using the latest techniques in machine learning and computer vision field.

Related Publications

  • Ruhan Sa, William Owens Jr, Raymond Wiegand, Mark Studin, Donald Capoferri, Kenneth Bahoora, Alexander Greaux, Robbrey Rattray, Adam Hutton, John Cintineo, Vipin Chaudhary, “Intervertebral Disc Detection in X-Ray Images using Faster R-CNN”, 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Jeju Island, South Korea, July 2017.  pdf poster
  • R. Sa, W. Owens, R. Wiegand,and V. Chaudhary, “Towards an affordable Deep Learning system: automated intervertebral disc detection in x-ray images”, SPIE Medical Imaging (ORAL presentation), February 11-16, 2017, Orlando, FL. pdf poster
  • R. Sa, W. Owens, R. Wiegand, and V. Chaudhary, “Fast scale-invariant lateral lumbar vertebrae detection and segmentation in X-ray images”, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Orlando, FL, 17-20, August 2016. pdf poster

Lumbar spine disc herniation diagnosis

Lower Back Pain (LBP) is the second most common neurological ailment in the United States after the headache. It costs over $100 billion annually in treatment and related rehabilitation costs including worker compensation. In fact, it is the most common reason for lost wages and missed work days. Degenerative Disc Disease (DDD) is the major abnormality that causes LBP. Moreover, Magnetic Resonance Imaging (MRI) test is the main clinically approved non-invasive imaging modality for the diagnosis of DDD. However, there is over 50 % inter- and intra-observer variability in the MRI interpretation that urges the need for standardized mechanisms in MRI interpretation. In this chapter, we propose a Computer Aided Diagnosis (CAD) System for Disc Degenerative Disease detection from clinical Magnetic Resonance Imaging (MRI).
Related Publications

  • Raja S Alomari, Jason J Corso, Vipin Chaudhary, Gurmeet Dhillon , “Lumbar spine disc herniation diagnosis with a joint shape model” In Computational Methods and Clinical Applications for Spine Imaging, pp. 87-98. Springer, Cham, 2014. pdf
  • Ghosh, Subarna, and Vipin Chaudhary. “Supervised methods for detection and segmentation of tissues in clinical lumbar MRI.” Computerized medical imaging and graphics 38, no. 7 (2014): 639-649.pdf
  • Raja’S, Alomari, Jason J. Corso, and Vipin Chaudhary. “Labeling of lumbar discs using both pixel-and object-level features with a two-level probabilistic model.” IEEE transactions on medical imaging 30, no. 1 (2011): 1-10. pdf
  • Ghosh, Subarna, Alomari Raja’S, Vipin Chaudhary, and Gurmeet Dhillon. “Computer-aided diagnosis for lumbar mri using heterogeneous classifiers.” In Biomedical Imaging: From Nano to Macro, 2011 IEEE International Symposium on, pp. 1179-1182. IEEE, 2011.pdf
  • Ghosh, Subarna, Alomari Raja’S, Vipin Chaudhary, and Gurmeet Dhillon. “Composite features for automatic diagnosis of intervertebral disc herniation from lumbar MRI.” In Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE, pp. 5068-5071. IEEE, 2011.pdf
  • Raja’S, Alomari, Jason J. Corso, Vipin Chaudhary, and Gurmeet Dhillon. “Toward a clinical lumbar CAD: herniation diagnosis.” International journal of computer assisted radiology and surgery 6, no. 1 (2011): 119-126.pdf
  • Raja’S, Alomari, Jason J. Corso, Vipin Chaudhary, and Gurmeet Dhillon. “Automatic diagnosis of lumbar disc herniation with shape and appearance features from MRI.” In Medical Imaging 2010: Computer-Aided Diagnosis, vol. 7624, p. 76241A. International Society for Optics and Photonics, 2010.pdf
  • Raja’S, Alomari, Jason J. Corso, Vipin Chaudhary, and Gurmeet Dhillon. “Computer-aided diagnosis of lumbar disc pathology from clinical lower spine MRI.” International journal of computer assisted radiology and surgery 5, no. 3 (2010): 287-293. pdf
  • Corso, Jason J., Alomari Raja’S, and Vipin Chaudhary. “Lumbar disc localization and labeling with a probabilistic model on both pixel and object features.” In International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 202-210. Springer, Berlin, Heidelberg, 2008. pdf
  • Raja’S, Alomari, Jason J. Corso, Vipin Chaudhary, and Gurmeet Dhillon. “Abnormality detection in lumbar discs from clinical MR images with a probabilistic model.” injury 4 (2009): 3.pdf

Lumbar wedge compression fractures diagnosis

Lumbar vertebral fractures vary greatly in types and causes and usually result from severe
trauma or pathological conditions such as osteoporosis. Lumbar wedge compression
fractures are amongst the most common ones where the vertebra is severely compressed
forming a wedge shape and causing pain and pressure on the nerve roots and the spine.
Since vertebral segmentation is the first step in any automated diagnosis task, we present a
fully automated method for robustly localizing and segmenting the vertebrae for preparation
of vertebral fracture diagnosis.

Related Publications

  • Ghosh, Subarna, Alomari Raja’S, Vipin Chaudhary, and Gurmeet Dhillon. “Automatic lumbar vertebra segmentation from clinical CT for wedge compression fracture diagnosis.” In Medical Imaging 2011: Computer-Aided Diagnosis, vol. 7963, p. 796303. International Society for Optics and Photonics, 2011.pdf
  • Al-Helo, Samah, Raja S. Alomari, Subarna Ghosh, Vipin Chaudhary, Gurmeet Dhillon, Al-Zoubi Moh’d B, Hazem Hiary, and Thair M. Hamtini. “Compression fracture diagnosis in lumbar: a clinical CAD system.” International journal of computer assisted radiology and surgery 8, no. 3 (2013): 461-469.pdf