Development and validation of an AI-enabled digital breast cancer assay to predict early-stage breast cancer recurrence within 6 years.

BACKGROUND: Breast cancer (BC) grading plays a critical role in patient management despite the considerable inter- and intra-observer variability, highlighting the need for decision support tools to improve reproducibility and prognostic accuracy for use in clinical practice. The objective was to evaluate the ability of a digital artificial intelligence (AI) assay (PDxBr) to enrich BC grading and improve risk categorization for predicting recurrence. METHODS: In our population-based longitudinal clinical development and validation study, we enrolled 2075 patients from Mount Sinai Hospital with infiltrating ductal carcinoma of the breast. With 3:1 balanced training and validation cohorts, patients were retrospectively followed for a median of 6 years. The main outcome was to validate an automated BC phenotyping system combined with clinical features to produce a binomial risk score predicting BC recurrence at diagnosis. RESULTS: The PDxBr training model (n = 1559 patients) had a C-index of 0.78 (95% CI, 0.76-0.81) versus clinical 0.71 (95% CI, 0.67-0.74) and image feature models 0.72 (95% CI, 0.70-0.74). A risk score of 58 (scale 0-100) stratified patients as low or high risk, hazard ratio (HR) 5.5 (95% CI 4.19-7.2, p < 0.001), with a sensitivity 0.71, specificity 0.77, NPV 0.95, and PPV 0.32 for predicting BC recurrence within 6 years. In the validation cohort (n = 516), the C-index was 0.75 (95% CI, 0.72-0.79) versus clinical 0.71 (95% CI 0.66-0.75) versus image feature models 0.67 (95% CI, 0.63-071). The validation cohort had an HR of 4.4 (95% CI 2.7-7.1, p < 0.001), sensitivity of 0.60, specificity 0.77, NPV 0.94, and PPV 0.24 for predicting BC recurrence within 6 years. PDxBr also improved Oncotype Recurrence Score (RS) performance: RS 31 cutoff, C-index of 0.36 (95% CI 0.26-0.45), sensitivity 37%, specificity 48%, HR 0.48, p = 0.04 versus Oncotype RS plus AI-grade C-index 0.72 (95% CI 0.67-0.79), sensitivity 78%, specificity 49%, HR 4.6, p < 0.001 versus Oncotype RS plus PDxBr, C-index 0.76 (95% CI 0.70-0.82), sensitivity 67%, specificity 80%, HR 6.1, p < 0.001. CONCLUSIONS: PDxBr is a digital BC test combining automated AI-BC prognostic grade with clinical-pathologic features to predict the risk of early-stage BC recurrence. With future validation studies, we anticipate the PDxBr model will enrich current gene expression assays and enhance treatment decision-making.

Antemortem detection of Parkinson's disease pathology in peripheral biopsies using artificial intelligence.

The diagnosis of Parkinson's disease (PD) is challenging at all stages due to variable symptomatology, comorbidities, and mimicking conditions. Postmortem assessment remains the gold standard for a definitive diagnosis. While it is well recognized that PD manifests pathologically in the central nervous system with aggregation of α-synuclein as Lewy bodies and neurites, similar Lewy-type synucleinopathy (LTS) is additionally found in the peripheral nervous system that may be useful as an antemortem biomarker. We have previously found that detection of LTS in submandibular gland (SMG) biopsies is sensitive and specific for advanced PD; however, the sensitivity is suboptimal especially for early-stage disease. Further, visual microscopic assessment of biopsies by a neuropathologist to identify LTS is impractical for large-scale adoption. Here, we trained and validated a convolutional neural network (CNN) for detection of LTS on 283 digital whole slide images (WSI) from 95 unique SMG biopsies. A total of 8,450 LTS and 35,066 background objects were annotated following an inter-rater reliability study with Fleiss Kappa = 0.72. We used transfer learning to train a CNN model to classify image patches (151 × 151 pixels at 20× magnification) with and without the presence of LTS objects. The trained CNN model showed the following performance on image patches: sensitivity: 0.99, specificity: 0.99, precision: 0.81, accuracy: 0.99, and F-1 score: 0.89. We further tested the trained network on 1230 naïve WSI from the same cohort of research subjects comprising 42 PD patients and 14 controls. Logistic regression models trained on features engineered from the CNN predictions on the WSI resulted in sensitivity: 0.71, specificity: 0.65, precision: 0.86, accuracy: 0.69, and F-1 score: 0.76 in predicting clinical PD status, and 0.64 accuracy in predicting PD stage, outperforming expert neuropathologist LTS density scoring in terms of sensitivity but not specificity. These findings demonstrate the practical utility of a CNN detector in screening for LTS, which can translate into a computational tool to facilitate the antemortem tissue-based diagnosis of PD in clinical settings.

Spatiotemporal changes in diffusivity and anisotropy in fetal brain tractography.

Population averaged diffusion atlases can be utilized to characterize complex microstructural changes with less bias than data from individual subjects. In this study, a fetal diffusion tensor imaging (DTI) atlas was used to investigate tract-based changes in anisotropy and diffusivity in vivo from 23 to 38 weeks of gestational age (GA). Healthy pregnant volunteers with typically developing fetuses were imaged at 3 T. Acquisition included structural images processed with a super-resolution algorithm and DTI images processed with a motion-tracked slice-to-volume registration algorithm. The DTI from individual subjects were used to generate 16 templates, each specific to a week of GA; this was accomplished by means of a tensor-to-tensor diffeomorphic deformable registration method integrated with kernel regression in age. Deterministic tractography was performed to outline the forceps major, forceps minor, bilateral corticospinal tracts (CST), bilateral inferior fronto-occipital fasciculus (IFOF), bilateral inferior longitudinal fasciculus (ILF), and bilateral uncinate fasciculus (UF). The mean fractional anisotropy (FA) and mean diffusivity (MD) was recorded for all tracts. For a subset of tracts (forceps major, CST, and IFOF) we manually divided the tractograms into anatomy conforming segments to evaluate within-tract changes. We found tract-specific, nonlinear, age related changes in FA and MD. Early in gestation, these trends appear to be dominated by cytoarchitectonic changes in the transient white matter fetal zones while later in gestation, trends conforming to the progression of myelination were observed. We also observed significant (local) heterogeneity in within-tract developmental trajectories for the CST, IFOF, and forceps major.

Retrospective Distortion and Motion Correction for Free-Breathing DW-MRI of the Kidneys Using Dual-Echo EPI and Slice-to-Volume Registration.

BACKGROUND: Diffusion-weighted MRI (DW-MRI) of the kidneys is a technique that provides information about the microstructure of renal tissue without requiring exogenous contrasts such as gadolinium, and it can be used for diagnosis in cases of renal disease and assessing response-to-therapy. However, physiological motion and large geometric distortions due to main B0 field inhomogeneities degrade the image quality, reduce the accuracy of quantitative imaging markers, and impede their subsequent clinical applicability. PURPOSE: To retrospectively correct for geometric distortion for free-breathing DW-MRI of the kidneys at 3T, in the presence of a nonstatic distortion field due to breathing and bulk motion. STUDY TYPE: Prospective. SUBJECTS: Ten healthy volunteers (ages 29-38, four females). FIELD STRENGTH/SEQUENCE: 3T; DW-MR dual-echo echo-planar imaging (EPI) sequence (10 b-values and 17 directions) and a T2 volume. ASSESSMENT: The distortion correction was evaluated subjectively (Likert scale 0-5) and numerically with cross-correlation between the DW images at b = 0 s/mm2 and a T2 volume. The intravoxel incoherent motion (IVIM) and diffusion tensor (DTI) model-fitting performance was evaluated using the root-mean-squared error (nRMSE) and the coefficient of variation (CV%) of their parameters. STATISTICAL TESTS: Statistical comparisons were done using Wilcoxon tests. RESULTS: The proposed method improved the Likert scores by 1.1 ± 0.8 (P < 0.05), the cross-correlation with the T2 reference image by 0.13 ± 0.05 (P < 0.05), and reduced the nRMSE by 0.13 ± 0.03 (P < 0.05) and 0.23 ± 0.06 (P < 0.05) for IVIM and DTI, respectively. The CV% of the IVIM parameters (slow and fast diffusion, and diffusion fraction for IVIM and mean diffusivity, and fractional anisotropy for DTI) was reduced by 2.26 ± 3.98% (P = 6.971 × 10-2 ), 11.24 ± 26.26% (P = 6.971 × 10-2 ), 4.12 ± 12.91% (P = 0.101), 3.22 ± 0.55% (P < 0.05), and 2.42 ± 1.15% (P < 0.05). DATA CONCLUSION: The results indicate that the proposed Di + MoCo method can effectively correct for time-varying geometric distortions and for misalignments due to breathing motion. Consequently, the image quality and precision of the DW-MRI model parameters improved. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 1.

PAIP 2019: Liver cancer segmentation challenge.

Pathology Artificial Intelligence Platform (PAIP) is a free research platform in support of pathological artificial intelligence (AI). The main goal of the platform is to construct a high-quality pathology learning data set that will allow greater accessibility. The PAIP Liver Cancer Segmentation Challenge, organized in conjunction with the Medical Image Computing and Computer Assisted Intervention Society (MICCAI 2019), is the first image analysis challenge to apply PAIP datasets. The goal of the challenge was to evaluate new and existing algorithms for automated detection of liver cancer in whole-slide images (WSIs). Additionally, the PAIP of this year attempted to address potential future problems of AI applicability in clinical settings. In the challenge, participants were asked to use analytical data and statistical metrics to evaluate the performance of automated algorithms in two different tasks. The participants were given the two different tasks: Task 1 involved investigating Liver Cancer Segmentation and Task 2 involved investigating Viable Tumor Burden Estimation. There was a strong correlation between high performance of teams on both tasks, in which teams that performed well on Task 1 also performed well on Task 2. After evaluation, we summarized the top 11 team's algorithms. We then gave pathological implications on the easily predicted images for cancer segmentation and the challenging images for viable tumor burden estimation. Out of the 231 participants of the PAIP challenge datasets, a total of 64 were submitted from 28 team participants. The submitted algorithms predicted the automatic segmentation on the liver cancer with WSIs to an accuracy of a score estimation of 0.78. The PAIP challenge was created in an effort to combat the lack of research that has been done to address Liver cancer using digital pathology. It remains unclear of how the applicability of AI algorithms created during the challenge can affect clinical diagnoses. However, the results of this dataset and evaluation metric provided has the potential to aid the development and benchmarking of cancer diagnosis and segmentation.

In vivo characterization of emerging white matter microstructure in the fetal brain in the third trimester.

The third trimester of pregnancy is a period of rapid development of fiber bundles in the fetal white matter. Using a recently developed motion-tracked slice-to-volume registration (MT-SVR) method, we aimed to quantify tract-specific developmental changes in apparent diffusion coefficient (ADC), fractional anisotropy (FA), and volume in third trimester healthy fetuses. To this end, we reconstructed diffusion tensor images from motion corrected fetal diffusion magnetic resonance imaging data. With an approved protocol, fetal MRI exams were performed on healthy pregnant women at 3 Tesla and included multiple (2-8) diffusion scans of the fetal head (1-2 b = 0 s/mm2 images and 12 diffusion-sensitized images at b = 500 s/mm2 ). Diffusion data from 32 fetuses (13 females) with median gestational age (GA) of 33 weeks 4 days were processed with MT-SVR and deterministic tractography seeded by regions of interest corresponding to 12 major fiber tracts. Multivariable regression analysis was used to evaluate the association of GA with volume, FA, and ADC for each tract. For all tracts, the volume and FA increased, and the ADC decreased with GA. Associations reached statistical significance for: FA and ADC of the forceps major; volume and ADC for the forceps minor; FA, ADC, and volume for the cingulum; ADC, FA, and volume for the uncinate fasciculi; ADC of the inferior fronto-occipital fasciculi, ADC of the inferior longitudinal fasciculi; and FA and ADC for the corticospinal tracts. These quantitative results demonstrate the complex pattern and rates of tract-specific, GA-related microstructural changes of the developing white matter in human fetal brain.

BACH: Grand challenge on breast cancer histology images.

Breast cancer is the most common invasive cancer in women, affecting more than 10% of women worldwide. Microscopic analysis of a biopsy remains one of the most important methods to diagnose the type of breast cancer. This requires specialized analysis by pathologists, in a task that i) is highly time- and cost-consuming and ii) often leads to nonconsensual results. The relevance and potential of automatic classification algorithms using hematoxylin-eosin stained histopathological images has already been demonstrated, but the reported results are still sub-optimal for clinical use. With the goal of advancing the state-of-the-art in automatic classification, the Grand Challenge on BreAst Cancer Histology images (BACH) was organized in conjunction with the 15th International Conference on Image Analysis and Recognition (ICIAR 2018). BACH aimed at the classification and localization of clinically relevant histopathological classes in microscopy and whole-slide images from a large annotated dataset, specifically compiled and made publicly available for the challenge. Following a positive response from the scientific community, a total of 64 submissions, out of 677 registrations, effectively entered the competition. The submitted algorithms improved the state-of-the-art in automatic classification of breast cancer with microscopy images to an accuracy of 87%. Convolutional neuronal networks were the most successful methodology in the BACH challenge. Detailed analysis of the collective results allowed the identification of remaining challenges in the field and recommendations for future developments. The BACH dataset remains publicly available as to promote further improvements to the field of automatic classification in digital pathology.

Fetal brain growth portrayed by a spatiotemporal diffusion tensor MRI atlas computed from in utero images.

Altered structural fetal brain development has been linked to neuro-developmental disorders. These structural alterations can be potentially detected in utero using diffusion tensor imaging (DTI). However, acquisition and reconstruction of in utero fetal brain DTI remains challenging. Until now, motion-robust DTI methods have been employed for reconstruction of in utero fetal DTIs. However, due to the unconstrained fetal motion and permissible in utero acquisition times, these methods yielded limited success and have typically resulted in noisy DTIs. Consequently, atlases and methods that could enable groupwise studies, multi-modality imaging, and computer-aided diagnosis from in utero DTIs have not yet been developed. This paper presents the first DTI atlas of the fetal brain computed from in utero diffusion-weighted images. For this purpose an algorithm for computing an unbiased spatiotemporal DTI atlas, which integrates kernel-regression in age with a diffeomorphic tensor-to-tensor registration of motion-corrected and reconstructed individual fetal brain DTIs, was developed. Our new algorithm was applied to a set of 67 fetal DTI scans acquired from healthy fetuses each scanned at a gestational age between 21 and 39 weeks. The neurodevelopmental trends in the fetal brain, characterized by the atlas, were qualitatively and quantitatively compared with the observations reported in prior ex vivo and in utero studies, and with results from imaging gestational-age equivalent preterm infants. Our major findings revealed early presence of limbic fiber bundles, followed by the appearance and maturation of projection pathways (characterized by an age related increase in FA) during late 2nd and early 3rd trimesters. During the 3rd trimester association fiber bundles become evident. In parallel with the appearance and maturation of fiber bundles, from 21 to 39 gestational weeks gradual disappearance of the radial coherence of the telencephalic wall was qualitatively identified. These results and analyses show that our DTI atlas of the fetal brain is useful for reliable detection of major neuronal fiber bundle pathways and for characterization of the fetal brain reorganization that occurs in utero. The atlas can also serve as a useful resource for detection of normal and abnormal fetal brain development in utero.

Motion-robust diffusion compartment imaging using simultaneous multi-slice acquisition.

PURPOSE: To achieve motion-robust diffusion compartment imaging (DCI) in near continuously moving subjects based on simultaneous multi-slice, diffusion-weighted brain MRI. METHODS: Simultaneous multi-slice (SMS) acquisition enables fast and dense sampling of k- and q-space. We propose to achieve motion-robust DCI via slice-level motion correction by exploiting the rigid coupling between simultaneously acquired slices. This coupling provides 3D coverage of the anatomy that substantially constraints the slice-to-volume alignment problem. This is incorporated into an explicit model of motion dynamics that handles continuous and large subject motion in robust DCI reconstruction. RESULTS: We applied the proposed technique, called Motion Tracking based on Simultanous Multislice Registration (MT-SMR) to multi b-value SMS diffusion-weighted brain MRI of healthy volunteers and motion-corrupted scans of 20 pediatric subjects. Quantitative and qualitative evaluation based on fractional anisotropy in unidirectional fiber regions, and DCI in crossing-fiber regions show robust reconstruction in the presence of motion. CONCLUSION: The proposed approach has the potential to extend routine use of SMS DCI in very challenging populations, such as young children, newborns, and non-cooperative patients.

Temporal slice registration and robust diffusion-tensor reconstruction for improved fetal brain structural connectivity analysis.

Diffusion weighted magnetic resonance imaging, or DWI, is one of the most promising tools for the analysis of neural microstructure and the structural connectome of the human brain. The application of DWI to map early development of the human connectome in-utero, however, is challenged by intermittent fetal and maternal motion that disrupts the spatial correspondence of data acquired in the relatively long DWI acquisitions. Fetuses move continuously during DWI scans. Reliable and accurate analysis of the fetal brain structural connectome requires careful compensation of motion effects and robust reconstruction to avoid introducing bias based on the degree of fetal motion. In this paper we introduce a novel robust algorithm to reconstruct in-vivo diffusion-tensor MRI (DTI) of the moving fetal brain and show its effect on structural connectivity analysis. The proposed algorithm involves multiple steps of image registration incorporating a dynamic registration-based motion tracking algorithm to restore the spatial correspondence of DWI data at the slice level and reconstruct DTI of the fetal brain in the standard (atlas) coordinate space. A weighted linear least squares approach is adapted to remove the effect of intra-slice motion and reconstruct DTI from motion-corrected data. The proposed algorithm was tested on data obtained from 21 healthy fetuses scanned in-utero at 22-38 weeks gestation. Significantly higher fractional anisotropy values in fiber-rich regions, and the analysis of whole-brain tractography and group structural connectivity, showed the efficacy of the proposed method compared to the analyses based on original data and previously proposed methods. The results of this study show that slice-level motion correction and robust reconstruction is necessary for reliable in-vivo structural connectivity analysis of the fetal brain. Connectivity analysis based on graph theoretic measures show high degree of modularity and clustering, and short average characteristic path lengths indicative of small-worldness property of the fetal brain network. These findings comply with previous findings in newborns and a recent study on fetuses. The proposed algorithm can provide valuable information from DWI of the fetal brain not available in the assessment of the original 2D slices and may be used to more reliably study the developing fetal brain connectome.

Motion-Robust Spatially Constrained Parameter Estimation in Renal Diffusion-Weighted MRI by 3D Motion Tracking and Correction of Sequential Slices.

In this work, we introduce a novel motion-robust spatially constrained parameter estimation (MOSCOPE) technique for kidney diffusion-weighted MRI. The proposed motion compensation technique does not require a navigator, trigger, or breath-hold but only uses the intrinsic features of the acquired data to track and compensate for motion to reconstruct precise models of the renal diffusion signal. We have developed a technique for physiological motion tracking based on robust state estimation and sequential registration of diffusion sensitized slices acquired within 200ms. This allows a sampling rate of 5Hz for state estimation in motion tracking that is sufficiently faster than both respiratory and cardiac motion rates in children and adults, which range between 0.8 to 0.2Hz, and 2.5 to 1Hz, respectively. We then apply the estimated motion parameters to data from each slice and use motion-compensated data for 1) robust intra-voxel incoherent motion (IVIM) model estimation in the kidney using a spatially constrained model fitting approach, and 2) robust weighted least squares estimation of the diffusion tensor model. Experimental results, including precision of IVIM model parameters using bootstrap-sampling and in-vivo whole kidney tractography, showed significant improvement in precision and accuracy of these models using the proposed method compared to models based on the original data and volumetric registration.

Motion-Robust Diffusion-Weighted Brain MRI Reconstruction Through Slice-Level Registration-Based Motion Tracking.

This work proposes a novel approach for motion-robust diffusion-weighted (DW) brain MRI reconstruction through tracking temporal head motion using slice-to-volume registration. The slice-level motion is estimated through a filtering approach that allows tracking the head motion during the scan and correcting for out-of-plane inconsistency in the acquired images. Diffusion-sensitized image slices are registered to a base volume sequentially over time in the acquisition order where an outlier-robust Kalman filter, coupled with slice-to-volume registration, estimates head motion parameters. Diffusion gradient directions are corrected for the aligned DWI slices based on the computed rotation parameters and the diffusion tensors are directly estimated from the corrected data at each voxel using weighted linear least squares. The method was evaluated in DWI scans of adult volunteers who deliberately moved during scans as well as clinical DWI of 28 neonates and children with different types of motion. Experimental results showed marked improvements in DWI reconstruction using the proposed method compared to the state-of-the-art DWI analysis based on volume-to-volume registration. This approach can be readily used to retrieve information from motion-corrupted DW imaging data.

Motion-Robust Reconstruction based on Simultaneous Multi-Slice Registration for Diffusion-Weighted MRI of Moving Subjects.

Simultaneous multi-slice (SMS) echo-planar imaging has had a huge impact on the acceleration and routine use of diffusion-weighted MRI (DWI) in neuroimaging studies in particular the human connectome project; but also holds the potential to facilitate DWI of moving subjects, as proposed by the new technique developed in this paper. We present a novel registration-based motion tracking technique that takes advantage of the multi-plane coverage of the anatomy by simultaneously acquired slices to enable robust reconstruction of neural microstructure from SMS DWI of moving subjects. Our technique constitutes three main components: 1) motion tracking and estimation using SMS registration, 2) detection and rejection of intra-slice motion, and 3) robust reconstruction. Quantitative results from 14 volunteer subject experiments and the analysis of motion-corrupted SMS DWI of 6 children indicate robust reconstruction in the presence of continuous motion and the potential to extend the use of SMS DWI in very challenging populations.

Elastic registration of prostate MR images based on estimation of deformation states.

Magnetic resonance imaging (MRI) is being used increasingly for image-guided targeted biopsy and focal therapy of prostate cancer. In this paper, a combined rigid and deformable registration technique is proposed to register pre-treatment diagnostic 3T magnetic resonance (MR) images of the prostate, with the identified target tumor(s), to intra-treatment 1.5T MR images. The pre-treatment T2-weighted MR images were acquired with patients in a supine position using an endorectal coil in a 3T scanner, while the intra-treatment T2-weighted MR images were acquired in a 1.5T scanner before insertion of the needle with patients in the semi-lithotomy position. Both the rigid and deformable registration algorithms employ an intensity-based distance metric defined based on the modality independent neighborhood descriptors (MIND) between images. The optimization routine for estimating the rigid transformation parameters is initialized using four pairs of manually selected approximate corresponding points on the boundaries of the prostate. In this paper, the problem of deformable image registration is approached from the perspective of state estimation for dynamical systems. The registration algorithm employs a rather generic dynamic linear elastic model of the tissue deformation discretized by the finite element method (FEM). We use the model in a classical state estimation framework to estimate the deformation of the prostate based on the distance metric between pre- and intra-treatment images. Our deformable registration results using 17 sets of prostate MR images showed that the proposed method yielded a target registration error (TRE) of 1.87 ± 0.94 mm,2.03 ± 0.94 mm, and 1.70 ± 0.93 mm for the whole gland (WG), central gland (CG), and peripheral zone (PZ), respectively, using 76 manually-identified fiducial points. This was an improvement over the 2.67 ± 1.31 mm, 2.95 ± 1.43 mm, and 2.34 ± 1.11 mm, respectively for the WG, CG, and PZ after rigid registration alone. Dice similarity coefficients (DSC) in the WG, CG and PZ were 88.2 ± 5.3, 85.6 ± 7.6 and 68.7 ± 6.9 percent, respectively. Furthermore, the mean absolute distances (MAD) between surfaces was 1.26 ± 0.56 mm and 1.27 ± 0.55 mm in the WG and CG, after deformable registration. These results indicate that the proposed registration technique has sufficient accuracy for localizing prostate tumors in MRI-guided targeted biopsy or focal therapy of clinically localized prostate cancer.

Non-rigid registration of medical images based on estimation of deformation states.

A unified framework for automatic non-rigid 3D-3D and 3D-2D registration of medical images with static and dynamic deformations is proposed in this paper. The problem of non-rigid image registration is approached as a classical state estimation problem using a generic deformation model for the soft tissue. The registration technique employs a dynamic linear elastic continuum mechanics model of the tissue deformation, which is discretized using the finite element method. In the proposed method, the registration is achieved through a Kalman-like filtering process, which incorporates information from the deformation model and a vector of observation prediction errors computed from an intensity-based similarity/distance metric between images. With this formulation, single and multiple-modality, 3D-3D and 3D-2D image registration problems can all be treated within the same framework. The performance of the proposed registration technique was evaluated in a number of different registration scenarios. First, 3D magnetic resonance (MR) images of uncompressed and compressed breast tissue were co-registered. 3D MR images of the uncompressed breast tissue were also registered to a sequence of simulated 2D interventional MR images of the compressed breast. Finally, the registration algorithm was employed to dynamically track a target sub-volume inside the breast tissue during the process of the biopsy needle insertion based on registering pre-insertion 3D MR images to a sequence of real-time simulated 2D interventional MR images. Registration results indicate that the proposed method can be effectively employed for the registration of medical images in image-guided procedures, such as breast biopsy in which the tissue undergoes static and dynamic deformations.

Model-Based Deformable Registration of Preoperative 3D to Intraoperative Low-Resolution 3D and 2D Sequences of MR Images

We have developed an automatic model-based deformable registration method applicable to MR soft-tissue imaging. The registration algorithm uses a dynamic finite element (FE) continuum mechanics model of the tissue deformation to register its 3D preoperative images with intraoperative 1) 3D low-resolution or 2) 2D MR images. The registration is achieved through a filtering process that combines information from the deformation model and observation errors based on correlation ratio, mutual information or sum of square differences between images. Experimental results with a breast phantom show that the proposed method converges in few iterations in the presence of very large deformations, similar to those typically observed in breast biopsy applications.

Model-based 3D/2D deformable registration of MR images.

A method is proposed for automatic registration of 3D preoperative magnetic resonance images of deformable tissue to a sequence of its 2D intraoperative images. The algorithm employs a dynamic continuum mechanics model of the deformation and similarity (distance) measures such as correlation ratio, mutual information or sum of squared differences for registration. The registration is solely based on information present in the 3D preoperative and 2D intraoperative images and does not require fiducial markers, feature extraction or image segmentation. Results of experiments with a biopsy training breast phantom show that the proposed method can perform well in the presence of large deformations. This is particularly useful for clinical applications such as MR-based breast biopsy where large tissue deformations occur.

GPU implementation of a deformable 3D image registration algorithm.

We present a parallel implementation of a new deformable image registration algorithm using the Computer Unified Device Architecture (CUDA). The algorithm co-registers preoperative and intraoperative 3-dimensional magnetic resonance (MR) images of a deforming organ. It employs a linear elastic dynamic finite-element model of the deformation and distance measures such as mutual information and sum of squared differences to align volumetric image data sets. Computationally intensive elements of the method such as interpolation, displacement and force calculation are significantly accelerated using a Graphics Processing Unit (GPU). The result of experiments carried out with a realistic breast phantom tissue shows a 37 fold speedup for the GPU-based implementation compared with an optimized CPU-based implementation in high resolution MR image registration. The GPU implementation is capable of registering 512 × 512 × 136 image sets in just over 2 seconds, making it suitable for clinical applications requiring fast and accurate processing of medical images.