A Novel Projection Based Approach for Medical Image Registration. In: Pluim JPW, Likar B, Gerritsen FA, editors. Biomedical Image Registration. Berlin: Springer Berlin Heidelberg; 2006. pp. 247-56. [DOI: 10.1007/11784012_30]

Autonomous Detection and Classification of PI-RADS Lesions in an MRI Screening Population Incorporating Multicenter-Labeled Deep Learning and Biparametric Imaging: Proof of Concept

Background: Opportunistic prostate cancer (PCa) screening is a controversial topic. Magnetic resonance imaging (MRI) has proven to detect prostate cancer with a high sensitivity and specificity, leading to the idea to perform an image-guided prostate cancer (PCa) screening; Methods: We evaluated a prospectively enrolled cohort of 49 healthy men participating in a dedicated image-guided PCa screening trial employing a biparametric MRI (bpMRI) protocol consisting of T2-weighted (T2w) and diffusion weighted imaging (DWI) sequences. Datasets were analyzed both by human readers and by a fully automated artificial intelligence (AI) software using deep learning (DL). Agreement between the algorithm and the reports—serving as the ground truth—was compared on a per-case and per-lesion level using metrics of diagnostic accuracy and k statistics; Results: The DL method yielded an 87% sensitivity (33/38) and 50% specificity (5/10) with a k of 0.42. 12/28 (43%) Prostate Imaging Reporting and Data System (PI-RADS) 3, 16/22 (73%) PI-RADS 4, and 5/5 (100%) PI-RADS 5 lesions were detected compared to the ground truth. Targeted biopsy revealed PCa in six participants, all correctly diagnosed by both the human readers and AI. Conclusions: The results of our study show that in our AI-assisted, image-guided prostate cancer screening the software solution was able to identify highly suspicious lesions and has the potential to effectively guide the targeted-biopsy workflow.

Sparse 3D Radon Space Rigid Registration of CT Scans: Method and Validation Study

We present a new method for rigid registration of CT datasets in 3D Radon space based on sparse sampling of scanning projections. The inputs are the two 3D Radon transforms of the CT scans, one densely sampled and the other sparsely sampled (limited number of scan angles/ranges). The output is the rigid transformation that best matches them. The method first finds the best matching between each projection direction vector in the sparse transform and the corresponding direction vector in the dense transform. It then solves a system of linear equations derived from the direction vector pairs (parallel-beam projections) or finds a solution by non-linear optimization (fan-beam and cone-beam projections). Experimental studies show that our method for 3D parallel beam registration outperforms image space registration in terms of convergence range with significantly reduced X-ray dose compared to a full conventional CT scan.

Rigid registration of medical images using 1D and 2D binary projections

Image registration is a necessary procedure in everyday clinical practice. Several techniques for rigid and non-rigid registration have been developed and tested and the state-of-the-art is evolving from the research setting to incorporate image registration techniques into clinically useful tools. In this paper, we develop a novel rigid medical image registration technique which incorporates binary projections. This technique is tested and compared to the standard mutual information (MI) methods. Results show that the method is significantly more accurate and robust compared to MI methods. The accuracy is well below 0.5° and 0.5 mm. This method introduces two more improvements over MI methods: (1)for 2D registration with the use of 1D binary projections, we use minimal interpolation; and (2) for 3D registration with the use of 2D binary projections the method converges to stable final positions, independent of the initial misregistration.

3-D brain MRI tissue classification on FPGAs

Many automatic algorithms have been proposed for analyzing magnetic resonance imaging (MRI) data sets. With the increasingly large data sets being used in brain mapping, there has been a significant rise in the need for accelerating these algorithms. Partial volume estimation (PVE), a brain tissue classification algorithm for MRI, was implemented on a field-programmable gate array (FPGA)-based high performance reconfigurable computer using the Mitrion-C high-level language (HLL). This work develops on prior work in which we conducted initial studies on accelerating the prior information estimation algorithm. In this paper, we extend the work to include probability density estimation and present new results and additional analysis. We used several simulated and real human brain MR images to evaluate the accuracy and performance improvement of the proposed algorithm. The FPGA-based probability density estimation and prior information estimation implementation achieved an average speedup over an Itanium 2 CPU of 2.5 x and 9.4 x , respectively. The overall performance improvement of the FPGA-based PVE algorithm was 5.1 x with four FPGAs.

Standardized platform for coregistration of nonconcurrent diffuse optical and magnetic resonance breast images obtained in different geometries

We present a novel methodology for combining breast image data obtained at different times, in different geometries, and by different techniques. We combine data based on diffuse optical tomography (DOT) and magnetic resonance imaging (MRI). The software platform integrates advanced multimodal registration and segmentation algorithms, requires minimal user experience, and employs computationally efficient techniques. The resulting superposed 3-D tomographs facilitate tissue analyses based on structural and functional data derived from both modalities, and readily permit enhancement of DOT data reconstruction using MRI-derived a-priori structural information. We demonstrate the multimodal registration method using a simulated phantom, and we present initial patient studies that confirm that tumorous regions in a patient breast found by both imaging modalities exhibit significantly higher total hemoglobin concentration (THC) than surrounding normal tissues. The average THC in the tumorous regions is one to three standard deviations larger than the overall breast average THC for all patients.

Computer assistance for MR based diagnosis of breast cancer: present and future challenges

MR based methods have gained an important role for the clinical detection and diagnosis of breast cancer. Dynamic contrast-enhanced MRI of the breast has become a robust and successful method, especially for diagnosis of high-risk cases due to its higher sensitivity compared to X-ray mammography. The application of MR based imaging methods depends on various automated image processing routines. The combination of techniques for preprocessing, quantification and visualization of datasets is necessary to achieve fast and solid assessment of valuable parameters for diagnosis. In this paper, different aspects such as registration methods for the reduction of motion artifacts, segmentation issues, as well as morphologic and dynamic lesion analysis will be reviewed with a focus on breast MRI, MR spectroscopy and MR guided biopsies of the breast, their implications and technical challenges from a computer assistance point of view.