Quantitative imaging for oncology is emerging as an important clinical and pre-clinical technique. The basic idea in quantitative imaging is to extract numerical features from medical images, and use these features for clinical decision making, for example to assess whether a patient with cancer is responding to therapy.

Our objectives are to develop new methods for improving quantitative imaging for oncology. An area of major focus is quantitative imaging biomarkers for predicting and prognosticating therapy response. Quantitative metrics derived from functional imaging modalities such as PET, SPECT, and diffusion MRI has shown tremendous promise for early non-invasive detection of cancer therapy response in comparison to anatomical modalities. However, images obtained using these modalities often have high noise and limited spatial resolution, which can lead to unreliable quantification of these metrics, degrading their predictive ability and limiting their clinical value. This is a major challenge in clinical assessment and application of these metrics as biomarkers. To address this challenge, we are developing rigorous image-science and statistical estimation theory-based image analysis and quantification approaches. We are also developing methods to clinically assess these metrics as biomarkers. We also actively collaborate with oncologists and radiologists to translate these methods to the clinic, in the process demonstrating the value of our methods.

In another recent project, methods developed by us for quantitative diffusion MRI were evaluated in a prospective trial, where it was observed that the developed methods were important for quantitative diffusion MRI to serve as a restrictive predictive biomarker of therapy response. More here.

In another project, we are developing deep-learning-based methods to segment patient images. The potential to extract quantitative features from PET images and use these features as biomarkers for cancer is highly significant. However, for clinical application, it is essential that these features are measured reliably, which requires the development of improved image analysis and quantification methods.  One key image-analysis step is tumor segmentation. Currently, this segmentation is typically performed manually, which is erroneous and may lead to significant inter and intra-reader variability. Conventional semi-automated segmentation methods also suffer from limited reliability. Thus, there is a need to develop reliable segmentation methods. For this purpose, we have developed machine-learning-based approaches, including those based on deep learning.

References:

  • Z. Liu, J. Mhlanga, R. Laforest, P. DerenoncourtB. A. Siegel, and A. K. Jha, “A Bayesian approach to tissue-fraction estimation for oncological PET segmentation”,  Phys. Med. Biol. 66 124002 (link) (WashU press release) (NIH press release)
  • F Yousefirizi, A K Jha, J Brosch-Lenz, B Saboury, A Rahmim, “Toward High-Throughput Artificial Intelligence-Based Segmentation in Oncological PET Imaging”, PET Clin. 2021 Oct;16(4):577-596 (link)
  • Leung, W. Marashdeh, S. Ashrafinia, A. Rahmim, M. Pomper, and A. K. Jha, “A physics-guided modular deep-learning based automated framework for tumor segmentation in PET”,  Phys. Med. Biol. (link) (arxiv) (press release)
  • E. Mena, S. Sheikhbahaei, M. Taghipour, A. K. Jha, J. Xiao, E. Vicente, R. M. Subramaniam, “18F-FDG PET/CT Metabolic Tumor Volume and intra-tumoral heterogeneity in pancreatic adenocarcinomas: Impact of Dual-Time-Point and Segmentation Methods”, Clin. Nuc. Med., 2016.
  • Mena, M. Taghipour, S. Sheikhbahaei, A. K. Jha, A. Yanamadala, R. M. Subramaniam, “Value of intra-tumoral metabolic heterogeneity and quantitative 18F-FDG PET/CT parameters to predict prognosis in patients with HPV-positive primary oropharyngeal squamous cell carcinoma”, Clin. Nucl. Med. 2016
  • Leung, W. Marashdeh, S. Ashrafinia, M. Pomper. A. Rahmim, A. K. Jha, “A Modular Deep-Learning Based Fully Automated Framework for Tumor Segmentation in PET Images”, Phys. Med. Biol (link)
  • A. K. Jha, E. Mena, B. Caffo, S. Ashrafinia, A. Rahmim, E. C. Frey and R. Subramaniam, “Practical no-gold-standard framework to evaluate quantitative imaging methods: Application to lesion segmentation in PET”, J. Med. Imag. (Special Section on PET imaging), 4(1), 2017 (pdf).
  • E. Mena, M. Taghipour, S. Sheikhbahaei, A. K. Jha, L. Solnes, R. M. Subramaniam, “Value of intra-tumoral metabolic heterogeneity and quantitative 18F-FDG PET/CT parameters to predict prognosis, in patients with HPV-positive primary oropharyngeal squamous cell carcinoma”, Clin. Nuc. Med., 42(5); e227-34, 2017 (pdf)
  • E. Mena, S. Sheikhbahaei, M. Taghipour, A. K. Jha, J. Xiao, E. Vicente, R. M. Subramaniam, “18F-FDG PET/CT Metabolic Tumor Volume and intra-tumoral heterogeneity: Impact of Dual-Time-Point and Segmentation Methods”, Clin. Nuc. Med., 42(1), e16-e21, 2017 (link)
  • A. K. Jha, J. J. Rodriguez, A. T. Stopeck, “A maximum-likelihood method to estimate a single ADC value of lesions using diffusion MRI”, Mag. Res. Med., 76(6), 2016 (pdf)
  • A. K. Jha, B. Caffo, E. Frey, “A no-gold-standard technique for objective assessment of quantitative nuclear-medicine imaging methods”, Phys. Med. Biol., 61(7), 2780-2800, 2016 (pdf)
  • R. M. Stephen, A. K. Jha, D. J. Roe, et al., “Diffusion MRI with Semi-Automated Segmentation Can Serve as a Restricted Predictive Biomarker of the Therapeutic Response of Liver Metastasis”, Magn. Res. Imag., 33(10), 1267-33, 2015 (pdf)
  • A. K. Jha, M. A. Kupinski, J. J. Rodriguez, R. Stephen, A. Stopeck, “Task-based evaluation of segmentation algorithms for diffusion-weighted MRI without using a gold standard”, Phys. Med. Biol., 57(13) 4425-46, 2012 (link)
  • A. K. Jha, M. A. Kupinski, J. J. Rodriguez, R. M. Stephen, A. T. Stopeck, “Evaluating segmentation algorithms for diffusion-weighted MR images: a task-based approach”, Proc. SPIE 7627,76270L1-8, 2010 (Best Student Paper Award) (link)