Derek Merck

Training models of anatomic shape variability

Learning probability distributions of the shape of anatomic structures requires fitting shape representations to human expert segmentations from training sets of medical images. The quality of statistical segmentation and registration methods is directly related to the quality of this initial shape fitting, yet the subject is largely overlooked or described in an ad hoc way. This article presents a set of general principles to guide such training. Our novel method is to jointly estimate both the best geometric model for any given image and the shape distribution for the entire population of training images by iteratively relaxing purely geometric constraints in favor of the converging shape probabilities as the fitted objects converge to their target segmentations. The geometric constraints are carefully crafted both to obtain legal, nonself-interpenetrating shapes and to impose the model-to-model correspondences required for useful statistical analysis. The paper closes with example applications of the method to synthetic and real patient CT image sets, including same patient male pelvis and head and neck images, and cross patient kidney and brain images. Finally, we outline how this shape training serves as the basis for our approach to IGRT/ART.

Geometrically proper models in statistical training

In deformable model segmentation, the geometric training process plays a crucial role in providing shape statistical priors and appearance statistics that are used as likelihoods. Also, the geometric training process plays a crucial role in providing shape probability distributions in methods finding significant differences between classes. The quality of the training seriously affects the final results of segmentation or of significant difference finding between classes. However, the lack of shape priors in the training stage itself makes it difficult to enforce shape legality, i.e., making the model free of local self-intersection or creases. Shape legality not only yields proper shape statistics but also increases the consistency of parameterization of the object volume and thus proper appearance statistics. In this paper we propose a method incorporating explicit legality constraints in training process. The method is mathematically sound and has proved in practice to lead to shape probability distributions over only proper objects and most importantly to better segmentation results.

Experimental measurement of microwave ablation heating pattern and comparison to computer simulations.

Abstract Introduction: For computational models of microwave ablation (MWA), knowledge of the antenna design is necessary, but the proprietary design of clinical applicators is often unknown. We characterised the specific absorption rate (SAR) during MWA experimentally and compared to a multi-physics simulation. Methods: An infrared (IR) camera was used to measure SAR during MWA within a split ex vivo liver model. Perseon Medical’s short-tip (ST) or long-tip (LT) MWA antenna were placed on top of a tissue sample (n = 6), and microwave power (15 W) was applied for 6 min, while intermittently interrupting power. Tissue surface temperature was recorded via IR camera (3.3 fps, 320 × 240 resolution). SAR was calculated intermittently based on temperature slope before and after power interruption. Temperature and SAR data were compared to simulation results. Results: Experimentally measured SAR changed considerably once tissue temperatures exceeded 100 °C, contrary to simulation results. The ablation zone diameters were 1.28 cm and 1.30 ± 0.03 cm (transverse), and 2.10 cm and 2.66 ± −0.22 cm (axial), for simulation and experiment, respectively. The average difference in temperature between the simulation and experiment were 5.6 °C (ST) and 6.2 °C (LT). Dice coefficients for 1000 W/kg SAR iso-contour were 0.74 ± 0.01 (ST) and 0.77 (± 0.03) (LT), suggesting good agreement of SAR contours. Conclusion: We experimentally demonstrated changes in SAR during MWA ablation, which were not present in simulation, suggesting inaccuracies in dielectric properties. The measured SAR may be used in simplified computer simulations to predict tissue temperature when the antenna geometry is unknown.

Quantitative ultrasound texture analysis for clinical decision making support

We propose a general ultrasound (US) texture-analysis and machine-learning framework for detecting the presence of disease that is suitable for clinical application across clinicians, disease types, devices, and operators. Its stages are image selection, image filtering, ROI selection, feature parameterization, and classification. Each stage is modular and can be replaced with alternate methods. Thus, this framework is adaptable to a wide range of tasks. Our two preliminary clinical targets are hepatic steatosis and adenomyosis diagnosis. For steatosis, we collected US images from 288 patients and their pathology-determined values of steatosis (%) from biopsies. Two radiologists independently reviewed all images and identified the region of interest (ROI) most representative of the hepatic echotexture for each patient. To parameterize the images into comparable quantities, we filter the US images at multiple scales for various texture responses. For each response, we collect a histogram of pixel features within the ROI, and parameterize it as a Gaussian function using its mean, standard deviation, kurtosis, and skew to create a 36-feature vector. Our algorithm uses a support vector machine (SVM) for classification. Using a threshold of 10%, we achieved 72.81% overall accuracy, 76.18% sensitivity, and 65.96% specificity in identifying steatosis with leave-ten-out cross-validation (p<0.0001). Extending this framework to adenomyosis, we identified 38 patients with MR-confirmed findings of adenomyosis and previous US studies and 50 controls. A single rater picked the best US-image and ROI for each case. Using the same processing pipeline, we obtained 76.14% accuracy, 86.00% sensitivity, and 63.16% specificity with leave-one-out cross-validation (p<0.0001).

Exploratory Application of Augmented Reality/Mixed Reality Devices for Acute Care Procedure Training

Introduction Augmented reality (AR), mixed reality (MR), and virtual reality devices are enabling technologies that may facilitate effective communication in healthcare between those with information and knowledge (clinician/specialist; expert; educator) and those seeking understanding and insight (patient/family; non-expert; learner). Investigators initiated an exploratory program to enable the study of AR/MR use-cases in acute care clinical and instructional settings. Methods Academic clinician educators, computer scientists, and diagnostic imaging specialists conducted a proof-of-concept project to 1) implement a core holoimaging pipeline infrastructure and open-access repository at the study institution, and 2) use novel AR/MR techniques on off-the-shelf devices with holoimages generated by the infrastructure to demonstrate their potential role in the instructive communication of complex medical information. Results The study team successfully developed a medical holoimaging infrastructure methodology to identify, retrieve, and manipulate real patients’ de-identified computed tomography and magnetic resonance imagesets for rendering, packaging, transfer, and display of modular holoimages onto AR/MR headset devices and connected displays. Holoimages containing key segmentations of cervical and thoracic anatomic structures and pathology were overlaid and registered onto physical task trainers for simulation-based “blind insertion” invasive procedural training. During the session, learners experienced and used task-relevant anatomic holoimages for central venous catheter and tube thoracostomy insertion training with enhanced visual cues and haptic feedback. Direct instructor access into the learner’s AR/MR headset view of the task trainer was achieved for visual-axis interactive instructional guidance. Conclusion Investigators implemented a core holoimaging pipeline infrastructure and modular open-access repository to generate and enable access to modular holoimages during exploratory pilot stage applications for invasive procedure training that featured innovative AR/MR techniques on off-the-shelf headset devices.

Developing an open platform for evidence-based microwave ablation treatment planning and validation

The clinical utility of current thermal ablation planning tools is severely limited by treatment variability. We discuss the development of an open platform for evidence-based thermal ablation treatment planning and validation. Improved predictive treatment modeling and consistent outcome analysis are crucial components for useful planning and guidance tools.

Computational modeling of 915 MHz microwave ablation: comparative assessment of temperature-dependent tissue dielectric models

Purpose The objective of this study is to develop a computational model for simulating 915 MHz microwave ablation (MWA), and verify the simulation predictions of transient temperature profiles against experimental measurements. Due to the limited experimental data characterizing temperature‐dependent changes of tissue dielectric properties at 915 MHz, we comparatively assess two temperature‐dependent approaches of modeling of dielectric properties: model A‐ piecewise linear temperature dependencies based on existing, but limited, experimental data, and model B‐ similar to model A, but augmented with linear decrease in electrical conductivity above 95 °C, as guided by our experimental measurements. Methods The finite element method was used to simulate MWA procedures in liver with a clinical 915 MHz ablation applicator. A coupled electromagnetic‐thermal solver incorporating temperature‐dependent tissue biophysical properties of liver was implemented. Predictions of the transient temperature profiles and ablation zone dimensions for both model A and model B were compared against experimental measurements in ex vivo bovine liver tissue. Broadband dielectric properties of tissue within different regions of the ablation zone were measured and reported at 915 MHz and 2.45 GHz. Results Model B yielded peak tissue temperatures in closer agreement with experimental measurements, attributed to the inclusion of decrease in electrical conductivity at elevated temperature. The simulated transverse diameters of the ablation zone predicted by both models were greater than experimental measurements, which may be in part due to the lack of a tissue shrinkage model. At both considered power levels, predictions of transverse ablation zone diameters were in closer agreement with measurements for model B (max. discrepancy of 5 mm at 60 W, and 3 mm at 30 W), compared to model A (max. discrepancy of 9 mm at 60 W, and 6 mm at 30 W). Ablation zone lengths with both models were within 2 mm at 30 W, but overestimated by up to 10 mm at 60 W. Conclusions The inclusion of decreased electrical conductivity above 95 °C, implemented with model B as guided by our experimental measurements, may be a good approach for approximating the dynamic changes that occur during MWA at 915 MHz. Although a step toward more effectively modeling MWA at 915 MHz, further investigation of the transition in dielectric properties with temperature and tissue shrinkage, especially at high temperatures is needed for more accurate simulations.

Quantitative analysis of ultrasound images for computer-aided diagnosis

Abstract. We propose an adaptable framework for analyzing ultrasound (US) images quantitatively to provide computer-aided diagnosis using machine learning. Our preliminary clinical targets are hepatic steatosis, adenomyosis, and craniosynostosis. For steatosis and adenomyosis, we collected US studies from 288 and 88 patients, respectively, as well as their biopsy or magnetic resonanceconfirmed diagnosis. Radiologists identified a region of interest (ROI) on each image. We filtered the US images for various texture responses and use the pixel intensity distribution within each ROI as feature parameterizations. Our craniosynostosis dataset consisted of 22 CT-confirmed cases and 22 age-matched controls. One physician manually measured the vectors from the center of the skull to the outer cortex at every 10 deg for each image and we used the principal directions as shape features for parameterization. These parameters and the known diagnosis were used to train classifiers. Testing with cross-validation, we obtained 72.74% accuracy and 0.71 area under receiver operating characteristics curve for steatosis (p<0.0001), 77.27% and 0.77 for adenomyosis (p<0.0001), and 88.63% and 0.89 for craniosynostosis (p=0.0006). Our framework is able to detect a variety of diseases with high accuracy. We hope to include it as a routinely available support system in the clinic.

A methodology to analyze treatment zone geometry and variability of percutaneous thermal ablation

A major challenge for image guided tumor ablation is the high treatment variability due to heterogeneous tissue characteristics and thermal sinks. In this work, we present a methodology to analyze the geometry of the treatment zones and treatment zone variability. Our first contribution is an applicator centric co-ordinate system which enables us to compare treatment zones and vendor specifications across patients. Our second contribution is the analysis of the shape of the ablation zone using applicator centric longitudinal 2D cross sections. We present initial results of applying this methodology to analyze the geometry and variability in synthetic examples like ellipsoid, sphere and real microwave ablation zones in lung and liver.

SU-E-J-18: A Thermal Simulation Model and Validation for Percutaneous Cancer Ablation

PURPOSE Image-guided percutaneous ablation is an effective, inexpensive, and accessible treatment for liver, lung, and kidney cancers. However, because of its relatively high recurrence rate, percutaneous ablation is usually considered to be palliative only. We hypothesize that the high recurrence rate is due in part to poor margin control resulting from inaccurate treatment models in procedure planning. To address this shortcoming, we are developing a thermal simulation model for percutaneous cancer ablation from first principles. METHODS Our model uses finite element methods to solve Pennes Heat Equation and Maxwells equations for electromagnetic energy transfer in matter over time. The simulation accounts for applicator geometry and materials as taken from actual clinical devices, and incorporates appropriate density, thermal conductivity properties, dielectric properties, power dissipation, and the relative water content for a homogeneous liver tissue domain. RESULTS The solution generated is a continuous 3D thermal profile over time. The simulated 60 degree Celsius isotherm at 60 watts for 10 minutes in homogenous liver tissue is accurate to within approximately 5% (i.e., an average 2mm variance from a 36mm expected width) of the vendor specification and within 12% (5mm) of our own ex vivo ablation procedures as measured by 4D CT and visual inspection of the coagulation zone. Simulations at other input settings give similar results within 5%-15% of expected and empirically observed results. CONCLUSION This promising initial model forms the basis of ongoing work in principled thermal simulation for ablation planning. Our next goals are to incorporate heterogeneous tissue types and heat sinks in the solution domain and validate the resulting simulation against our ongoing clinical data collection.