While the AIAI lab is involved in many research projects, there are several overarching themes that have tied much of the research together. Some of these major themes are listed below:
.
Machine/Deep Learning in Imaging
Machine learning is finding widespread application including imaging applications. In particular, we are interested in learned approaches that can be applied as part of the image formation process. Moreover, we seek machine learning solutions that leverage physics and domain knowledge about imaging performance and clinical tasks as part of their design and training. Similarly, we are interested in the rigorous assessment of machine learning approaches in terms of task-based performance, robustness, and generalization. Applications are broad but include: Parameterized neural networks that can provide task-optimized performance or a range of image properties with a user-tunable “knob” to permit, e.g., the level of noise reduction; Networks that use radiomics supervision to create realistic anatomy for virtual clinical trials and algorithm assessments; Networks that combine rigorous physics models with deep learned priors of human anatomy; Perturbation analysis of machine learning denoising approaches. Selected publications include:
- Generative Adversarial Networks with Radiomics Supervision for Lung Lesion Generation. In: IEEE Trans. Biomedical Engineering, Forthcoming.
- End-to-end deep learning restoration of GLCM features from blurred and noisy images. Proc SPIE Medical Imaging, vol. 12927, 2024.
- Strategies for CT Reconstruction using Diffusion Posterior Sampling with a Nonlinear Model . In: TBD, Forthcoming.
- Diffusion Posterior Sampling for Nonlinear CT Reconstruction. In: Journal of Medical Imaging, vol. 11, iss. 4, pp. 043504 , 2024, (** Featured on Cover **).
- Control of variance and bias in CT image processing with variational training of deep neural networks. In: SPIE Medical Imaging, 2022, (Wagner Award Finalist and 2nd Place Best Student Paper).
- A CT denoising neural network with image properties parameterization and control. In: SPIE Medical Imaging, pp. 115950K, International Society for Optics and Photonics, 2021.
- Performance analysis for nonlinear tomographic data processing. In: SPIE Proceedings, 15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, pp. 110720W-1-5, 2019.
.
Spectral Computed Tomography
Standard computed tomography does not leverage energy-dependent attenuation of materials; however, there is growing use of this information for spectral CT which permits material identification and decomposition with quantitative density estimates. While several dual-energy approaches have found clinical application including kV-switching, dual-layer detectors, and dual-source systems, there is room for additional strategies. We have developed several novel strategies including spatial-spectral filtration, grating-based filtration, as well as combination approaches for improved performance. Enabling these new data acquisition methods and their combinations are model-based material decomposition methods (e.g. so-called “one-step” approaches) that implicitly handle highly varied measurement models, sparsity, etc. Optimization and control of such algorithms is potentially complex and has necessitated studies on how to control not only the standard noise-resolution trade-offs but also the cross-response and correlations between channels for optimal regularization and system design. Selected publications include:
- Multi-Material Decomposition Using Spectral Diffusion Posterior Sampling . In: Forthcoming.
- A prototype spatial–spectral CT system for material decomposition with energy‐integrating detectors. In: Medical Physics, vol. 48, iss. 10, pp. 6401-6411, 2021.
- Spectral CT using a fine grid structure and varying x‐ray incidence angle. In: Medical Physics, 2021.
- High-Resolution Model-based Material Decomposition for Multi-Layer Flat-Panel Detectors. In: International Conference on Image Formation in X-Ray Computed Tomography, 2020.
- Multi-Contrast CT Imaging with a Prototype Spatial-Spectral Filter . In: International Conference on Image Formation in X-Ray Computed Tomography, 2020.
- Combining spectral CT acquisition methods for high-sensitivity material decomposition. In: SPIE Medical Imaging, pp. 1131218, International Society for Optics and Photonics, 2020.
- Prospective prediction and control of image properties in model-based material decomposition for spectral CT. In: SPIE Medical Imaging, pp. 113121Z, International Society for Optics and Photonics, 2020.
.
Virtual Clinical Trials and Phantom Studies
Testing new medical imaging technologies can be very costly when it involves patient studies. Thus, the ability to conduct simulation studies and physical phantom experiments is often a critical initial step in the introduction of new technologies. This is particularly true for new system design and algorithm development. Morever, there is growing agreement that systematic evaluation of imaging systems needs to involve performance metrics that quantify the clinical task that is being conducted. Thus, for realistic studies, virtual clinical trials and phantom experiments should represent actual clinical tasks and realistic anatomical structures. Towards this end, we have developed a number of simulation tools and processes for phantom construction of realistic anthropomorphic targets. Selected publications include:
- Generative adversarial networks and radiomics supervision for lung lesion synthesis. In: SPIE Medical Imaging, pp. 115950O, International Society for Optics and Photonics, 2021, (Robert F. Wagner All-conference Best Student Paper Award ).
- Three-dimensional printing of patient-specific lung phantoms for CT imaging: emulating lung tissue with accurate attenuation profiles and textures. In: Medical Physics, pp. Submitted, 2021.Note that this technology is a joint collaboration with LACTI at the University of Pennsylvania, and is available to other researchers via PixelPrint.
- Performance assessment of texture reproduction in high-resolution CT. In: SPIE Medical Imaging, pp. 113160R, International Society for Optics and Photonics, 2020.
Task-Driven Imaging
Traditional image quality metrics like noise variance and RMS error often fail to capture details of imaging performance. More sophisticated performance metric integrate a mathematical formulation of the diagnostic task to quantify the expected task-based performance. Such metrics have been used extensively for system design and evaluation; however, one can go a step further and use such metrics to prospectively predict imaging performance under different acquisition and reconstruction settings. Thus, it is possible to perform task-driven imaging that is optimized for the particular diagnostic test and patient anatomy. We have developed a optimization framework that can predict imaging performance using detectability index to drive customized acquisitions and image formation for both traditional filtered-backprojection and model-based reconstruction methods. Such optimization can lead to novel acquisition strategies. For example, for computed tomography with tube current modulation (TCM) we find scenarios where current TCM strategies can degrade task performance when model-based reconstruction is applied. In cone-beam CT applications we have demonstrated that if one breaks free from traditional circular or helical orbits, dramatic image quality improvement can be made when more general non-circular source-detector trajectories are chosen. Selected publications include:
- Universal orbit design for metal artifact elimination. In: Physics in Medicine and Biology, vol. 67, iss. 11, 2022.
- Metal-Tolerant Noncircular Orbit Design and Implementation on Robotic C-Arm Systems. In: International Conference on Image Formation in X-Ray Computed Tomography, 2020.
- Task-driven source–detector trajectories in cone-beam computed tomography: I. Theory and methods. In: Journal of Medical Imaging, vol. 6, no. 2, pp. 025002, 2019.
- Task-driven source–detector trajectories in cone-beam computed tomography: II. Application to neuroradiology. In: Journal of Medical Imaging, vol. 6, no. 2, pp. 025004, 2019.
- Task-driven tube current modulation and regularization design in computed tomography with penalized-likelihood reconstruction. In: Kontos, Despina; Flohr, Thomas G.; Lo, Joseph Y. (Ed.): SPIE Medical Imaging, pp. 978324, International Society for Optics and Photonics 2016.
- Task-Based Design of Fluence Field Modulation in CT for Model-Based Iterative Reconstruction. In: 4th International Conference on Image Formation in X-Ray Computed Tomography, pp. 407–410, Bamberg, Germany, 2016.
- Task-driven image acquisition and reconstruction in cone-beam CT.. In: Physics in medicine and biology, vol. 60, no. 8, pp. 3129–50, 2015, ISSN: 1361-6560.
- Task-Based Trajectories in Iteratively Reconstructed Interventional Cone-Beam CT. In: Proceedings of the International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, pp. 257–260, 2013.
.
Patient-Specific Data Acquisition
With the capability to optimize patient imaging through the task-driven imaging framework discussed above, we have sought flexibility in imaging system designs. Thus, we have built imaging platforms with expanded capabilities to customize the data acquisition. This includes a modified cone-beam CT test-bench with the capability to perform frame-to-frame fluence modulation up to a dynamic range of about 60 (in contrast, most modern clinical CT scanners are capable of dynamic tube current modulation of around a factor of three). Similarly, the AIAI lab has developed fluence-field modulation strategies (analogous to dynamic bowtie filters) that permit varying spatial modulations of the x-ray beam during an acquisition. Alternate strategies using similar technology have allow for customization of the x-ray spectrum. Additionally, we have developed and investigated test-bench and clinical systems that are capable of generalized non-circular orbits (in contrast to traditional CT universally uses a circular orbit). Such systems have much more flexibility in selecting what information is collected during a patient scan and how much and where x-ray exposure is delivered – permitting highly patient-specific data acquisition where imaging performance is maximized while minimizing radiation exposure. Selected publications include:
- Spectral CT using a fine grid structure and varying x‐ray incidence angle. In: Medical Physics, 2021.
- Fluence-field modulated x-ray CT using multiple aperture devices. In: Kontos, Despina; Flohr, Thomas G.; Lo, Joseph Y. (Ed.): SPIE Medical Imaging, pp. 97830X, International Society for Optics and Photonics 2016.
- Design of dual multiple aperture devices for dynamical fluence field modulated CT. In: 4th International Conference on Image Formation in X-Ray Computed Tomography, pp. 29–32, 2016.
- Self-calibration of cone-beam CT geometry using 3D-2D image registration.. In: Physics in medicine and biology, vol. 61, no. 7, pp. 2613–32, 2016, ISSN: 1361-6560.
- Task-Based Optimization of Source-Detector Orbits in Interventional Cone-beam CT. In: International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, vol. 13, 2015.
.
High-Fidelity System Modeling
Model-based Iterative Reconstruction (MBIR) has been widely adopted in tomographic applications due to its ability to model imaging system details and measurement noise. The limits of imaging performance using such methods rely on accurate imaging system models – in effect, the higher the fidelity of the system model, the better the imaging performance that can be achieved. Many MBIR methods have been applied to imaging systems without careful consideration of the underlying physical models. This has been particularly true for flat-panel-based cone-beam CT systems where traditional assumptions about the physical model are violated. For example, conventional MBIR methods presume independent measurement and no blur between detector elements; whereas such effects can be prominent in high-resolution flat-panel CT systems. We have developed MBIR models that integrate high-fidelity models to demonstrate improved imaging performance. Related work has consider other variations in the noise model based on various corrections that are applied to CBCT projection data which also change the noise structure. Selected publications include:
- High-resolution Model-based Material Decomposition in Dual-layer Flat-panel CBCT. In: Medical Physics, vol. 48, iss. 10, pp. 6375-6387, 2021.
- Nonlinear statistical reconstruction for flat-panel cone-beam CT with blur and correlated noise models. In: Kontos, Despina; Flohr, Thomas G.; Lo, Joseph Y. (Ed.): SPIE Medical Imaging, pp. 97830R, International Society for Optics and Photonics 2016, (Errata: The calculation for the upper bound (11) is incorrect.).
- Model-based iterative reconstruction for flat-panel cone-beam CT with focal spot blur, detector blur, and correlated noise.. In: Physics in medicine and biology, vol. 61, no. 1, pp. 296–319, 2016, ISSN: 1361-6560, (Errata: [1] The fidelity terms in equations 10 and 12 are missing a multiplication by 0.5. [2] Equation 14 should be mu(x_j) = a + b erf (2 sqrt( log(2) (x_j-d) / FWHM ). [3] In section 3.2 a reference to Figure 10(e) should be 9(f).).
- Statistical reconstruction for cone-beam CT with a post-artifact-correction noise model: application to high-quality head imaging.. In: Physics in medicine and biology, vol. 60, no. 16, pp. 6153–75, 2015, ISSN: 1361-6560.
.
Prior-Image-Based Reconstruction
There are numerous scenarios where patients undergo a series of imaging studies. For example, sequential studies are often obtained over the course of a disease diagnosis, treatment, and follow-up. Specific clinical scenarios include dynamic imaging studies (perfusion imaging, image-guided surgery with intraoperative imaging, image-guided radiotherapy with on-board imaging, etc.) Such sequential studies share a great wealth of shared anatomical information that can potentially be used to reduce data fidelity requirements in subsequent scans (permitting faster, lower exposure, etc. acquisitions). We have developed a number of reconstruction methods that utilize this highly specific prior image information as part of the image formation process. Clinical examples have included very low exposure lung nodule surveillance using sparse acquisitions, and improved onboard CBCT imaging for radiation therapy using CT planning data. Some methods like Reconstruction of Difference (RoD) have focused on imaging the change between studies; whereas the PIRPLE (Prior Image Registration Penalized Likelihood Estimation) approach has concentrated on visualization of the current anatomy. These prior image methods utilize high-fidelity physical models including measurement statistics for optimal performance and have been used jointly with both rigid and deformable registration of the prior image to better integrate prior information. Selected publications include:
- Integration of Prior CT into CBCT Reconstruction for Improved Image Quality via Reconstruction of Difference: First Patient Studies. In: Flohr, Thomas G.; Lo, Joseph Y.; Schmidt, Taly Gilat (Ed.): SPIE Medical Imaging, pp. 1013211-1–6, 2017.
- Reconstruction of difference in sequential CT studies using penalized likelihood estimation.. In: Physics in medicine and biology, vol. 61, no. 5, pp. 1986–2002, 2016, ISSN: 1361-6560.
- Prospective regularization design in prior-image-based reconstruction.. In: Physics in medicine and biology, vol. 60, no. 24, pp. 9515–36, 2015, ISSN: 1361-6560.
- dPIRPLE: a joint estimation framework for deformable registration and penalized-likelihood CT image reconstruction using prior images.. In: Physics in medicine and biology, vol. 59, no. 17, pp. 4799–826, 2014, ISSN: 1361-6560.
- PIRPLE: a penalized-likelihood framework for incorporation of prior images in CT reconstruction.. In: Physics in medicine and biology, vol. 58, no. 21, pp. 7563–82, 2013, ISSN: 1361-6560.
.
Known-Component Reconstruction
Interventional imaging presents a number of opportunities to integrate additional knowledge into the image formation process. This is particularly true in 3D imaging of implants within a patient. In CT, metal implants can cause significant artifacts including noise and streaking that degrade the image. Moreover, the image quality tends to worst nearest the implant – which is typically where image quality requirements are greatest (i.e., diagnostic tasks are typically close to the implant/tissue boundary). However, if the shape and material composition of the implant is known a priori (e.g., from a CAD model), one may integrate this information into image formation – effectively creating a joint reconstruction problem (of the anatomical background) and a registration of the known component(s). We have applied such methodologies for a number of styles of implant and generalized the approach for deformable and other generalized registrations; eliminated the requirement for prior knowledge of beam quality and material composition through joint estimation of spectral effects; and removed the limitation of needing a shape model by deriving shape information directly from the projection data. Selected publications include:
- Model-based dual-energy tomographic image reconstruction of objects containing known metal components. In: Physics in Medicine and Biology, vol. 65, no. 24, pp. 245046, 2020.
- Known-component model-based material decomposition for dual energy imaging of bone compositions in the presence of metal implant. In: International Meeting on Fully Three-Dimensional Image Reconstruction, Proc. SPIE , pp. 1107213, 2019.
- Improved intraoperative imaging in spine surgery: clinical translation of known-component 3D image reconstruction on the O-arm system. In: Proc. SPIE Medical Imaging, pp. 1095103-1-8, 2019.
- Polyenergetic known-component reconstruction without prior shape models. In: Flohr, Thomas G.; Lo, Joseph Y.; Schmidt, Taly Gilat (Ed.): SPIE Medical Imaging, pp. 101320O-1–6, 2017.
- Polyenergetic known-component CT reconstruction with unknown material compositions and unknown x-ray spectra. In: Physics in medicine and biology, vol. 62, no. 8, pp. 3352-3374, 2017.
- Integration of Component Knowledge in Penalized-Likelihood Reconstruction with Morphological and Spectral Uncertainties. In: Conference proceedings/International Conference on Image Formation in X-Ray Computed Tomography. International Conference on Image Formation in X-Ray Computed Tomography, pp. 111, NIH Public Access 2014.
- Overcoming nonlinear partial volume effects in known-component reconstruction of Cochlear implants. In: Nishikawa, Robert M.; Whiting, Bruce R. (Ed.): SPIE Medical Imaging, pp. 86681L, International Society for Optics and Photonics 2013.
- Model-based tomographic reconstruction of objects containing known components.. In: IEEE transactions on medical imaging, vol. 31, no. 10, pp. 1837–48, 2012, ISSN: 1558-254X.