Skin Lesion Correspondence Localization in Total Body Photography.

Longitudinal tracking of skin lesions - finding correspondence, changes in morphology, and texture - is beneficial to the early detection of melanoma. However, it has not been well investigated in the context of full-body imaging. We propose a novel framework combining geometric and texture information to localize skin lesion correspondence from a source scan to a target scan in total body photography (TBP). Body landmarks or sparse correspondence are first created on the source and target 3D textured meshes. Every vertex on each of the meshes is then mapped to a feature vector characterizing the geodesic distances to the landmarks on that mesh. Then, for each lesion of interest (LOI) on the source, its corresponding location on the target is first coarsely estimated using the geometric information encoded in the feature vectors and then refined using the texture information. We evaluated the framework quantitatively on both a public and a private dataset, for which our success rates (at 10 mm criterion) are comparable to the only reported longitudinal study. As full-body 3D capture becomes more prevalent and has higher quality, we expect the proposed method to constitute a valuable step in the longitudinal tracking of skin lesions.

A Complete Electron Microscopy Volume of the Brain of Adult Drosophila melanogaster.

Drosophila melanogaster has a rich repertoire of innate and learned behaviors. Its 100,000-neuron brain is a large but tractable target for comprehensive neural circuit mapping. Only electron microscopy (EM) enables complete, unbiased mapping of synaptic connectivity; however, the fly brain is too large for conventional EM. We developed a custom high-throughput EM platform and imaged the entire brain of an adult female fly at synaptic resolution. To validate the dataset, we traced brain-spanning circuitry involving the mushroom body (MB), which has been extensively studied for its role in learning. All inputs to Kenyon cells (KCs), the intrinsic neurons of the MB, were mapped, revealing a previously unknown cell type, postsynaptic partners of KC dendrites, and unexpected clustering of olfactory projection neurons. These reconstructions show that this freely available EM volume supports mapping of brain-spanning circuits, which will significantly accelerate Drosophila neuroscience. VIDEO ABSTRACT.

Spring level sets: a deformable model representation to provide interoperability between meshes and level sets.

A new type of deformable model is presented that merges meshes and level sets into one representation to provide interoperability between methods designed for either. This includes the ability to circumvent the CFL time step restriction for methods that require large step sizes. The key idea is to couple a constellation of disconnected triangular surface elements (springls) with a level set that tracks the moving constellation. The target application for Spring Level Sets (SpringLS) is to implement comprehensive imaging pipelines that require a mixture of deformable model representations to achieve the best performance. We demonstrate how to implement key components of a comprehensive imaging pipeline with SpringLS, including image segmentation, registration, tracking, and atlasing.

The Open Connectome Project Data Cluster: Scalable Analysis and Vision for High-Throughput Neuroscience.

We describe a scalable database cluster for the spatial analysis and annotation of high-throughput brain imaging data, initially for 3-d electron microscopy image stacks, but for time-series and multi-channel data as well. The system was designed primarily for workloads that build connectomes- neural connectivity maps of the brain-using the parallel execution of computer vision algorithms on high-performance compute clusters. These services and open-science data sets are publicly available at openconnecto.me. The system design inherits much from NoSQL scale-out and data-intensive computing architectures. We distribute data to cluster nodes by partitioning a spatial index. We direct I/O to different systems-reads to parallel disk arrays and writes to solid-state storage-to avoid I/O interference and maximize throughput. All programming interfaces are RESTful Web services, which are simple and stateless, improving scalability and usability. We include a performance evaluation of the production system, highlighting the effec-tiveness of spatial data organization.

Multi-object spring level sets (MUSCLE).

A new data structure is presented for geometrically modeling multi-objects. The model can exhibit elastic and fluid-like behavior to enable interpretability between tasks that require both deformable registration and active contour segmentation. The data structure consists of a label mask, distance field, and springls (a constellation of disconnected triangles). The representation has sub-voxel precision, is parametric, re-meshes, tracks point correspondences, and guarantees no self-intersections, air-gaps, or overlaps between adjacent structures. In this work, we show how to apply existing registration algorithms and active contour segmentation to the data structure; and as a demonstration, the data structure is used to segment cortical and subcortical structures (74 total) in the human brain.

Multi-object geodesic active contours (MOGAC).

An emerging topic is to build image segmentation systems that can segment hundreds to thousands of objects (i.e. cell segmentation\tracking, full brain parcellation, full body segmentation, etc.). Multi-object Level Set Methods (MLSM) perform this task with the benefit of sub-pixel precision. However, current implementations of MLSM are not as computationally or memory efficient as their region growing and graph cut counterparts which lack sub-pixel precision. To address this performance gap, we present a novel parallel implementation of MLSM that leverages the sparse properties of the algorithm to minimize its memory footprint for multiple objects. The new method, Multi-Object Geodesic Active Contours (MOGAC), can represent N objects with just two functions: a label mask image and unsigned distance field. The time complexity of the algorithm is shown to be O((M (power)d)/P) for M (power)d pixels and P processing units in dimension d = {2,3}, independent of the number of objects. Results are presented for 2D and 3D image segmentation problems.

Increased organ sparing using shape-based treatment plan optimization for intensity modulated radiation therapy of pancreatic adenocarcinoma.

PURPOSE: To develop a model to assess the quality of an IMRT treatment plan using data of prior patients with pancreatic adenocarcinoma. METHODS: The dose to an organ at risk (OAR) depends in large part on its orientation and distance to the planning target volume (PTV). A database of 33 previously treated patients with pancreatic cancer was queried to find patients with less favorable PTV-OAR configuration than a new case. The minimal achieved dose among the selected patients should also be achievable for the OAR of the new case. This way the achievable doses to the OARs of 25 randomly selected pancreas cancer patients were predicted. The patients were replanned to verify if the predicted dose could be achieved. The new plans were compared to their original clinical plans. RESULTS: The predicted doses were achieved within 1 and 2 Gy for more than 82% and 94% of the patients, respectively, and were a good approximation of the minimal achievable doses. The improvement after replanning was 1.4 Gy (range 0-4.6 Gy) and 1.7 Gy (range 0-6.3 Gy) for the mean dose to the liver and the kidneys, respectively, without compromising target coverage or increasing radiation dose to the bowel, cord or stomach. CONCLUSIONS: The model could accurately predict the achievable doses, leading to a considerable decrease in dose to the OARs and an increase in treatment planning efficiency.

SpringLS: a deformable model representation to provide interoperability between meshes and level sets.

A new type of deformable model is presented that merges meshes and level sets into one representation to provide interoperability between methods designed for either. The key idea is to use a constellation of triangular surface elements (springls) to define a level set. A Spring Level Set (SpringLS) can be interpreted as a mesh or level set and used in place of them in many instances. There is no loss of shape information in the transformation from triangle mesh or level set into SpringLS. As examples, we present results for joint segmentation/spherical mapping of a human brain cortex and atlas/non-atlas segmentation of a pelvis.

A user-assisted approach to visualizing multidimensional images.

We present a new technique for fusing together an arbitrary number of aligned images into a single color or intensity image. We approach this fusion problem from the context of Multidimensional Scaling (MDS) and describe an algorithm that preserves the relative distances between pairs of pixel values in the input (vectors of measurements) as perceived differences in a color image. The two main advantages of our approach over existing techniques are that it can incorporate user constraints into the mapping process and allows adaptively compressing or exaggerating features in the input in order to make better use of the output's limited dynamic range. We demonstrate these benefits by showing applications in various scientific domains and comparing our algorithm to previously proposed techniques.

Data-driven approach to generating achievable dose-volume histogram objectives in intensity-modulated radiotherapy planning.

PURPOSE: To propose a method of intensity-modulated radiotherapy (IMRT) planning that generates achievable dose-volume histogram (DVH) objectives using a database containing geometric and dosimetric information of previous patients. METHODS AND MATERIALS: The overlap volume histogram (OVH) is used to compare the spatial relationships between the organs at risk and targets of a new patient with those of previous patients in a database. From the OVH analysis, the DVH objectives of the new patient were generated from the database and used as the initial planning goals. In a retrospective OVH-assisted planning demonstration, 15 patients were randomly selected from a database containing clinical plans (CPs) of 91 previous head-and-neck patients treated by a three-level IMRT-simultaneous integrated boost technique. OVH-assisted plans (OPs) were planned in a leave-one-out manner by a planner who had no knowledge of CPs. Thus, DVH objectives of an OP were generated from a subdatabase containing the information of the other 90 patients. Those DVH objectives were then used as the initial planning goals in IMRT optimization. Planning efficiency was evaluated by the number of clicks of the "Start Optimization" button in the course of planning. Although the Pinnacle(3) treatment planning system allows planners to interactively adjust the DVH parameters during optimization, planners in our institution have never used this function in planning. RESULTS: The average clicks required for completing the CP and OP was 27.6 and 1.9, respectively (p <.00001); three OPs were finished within a single click. Ten more patient's cord + 4 mm reached the sparing goal D(0.1cc) <44 Gy (p <.0001), where D(0.1cc) represents the dose corresponding to 0.1 cc. For planning target volume uniformity, conformity, and other organ at risk sparing, the OPs were at least comparable with the CPs. Additionally, the averages of D(0.1cc) to the cord + 4 mm decreased by 6.9 Gy (p <.0001); averages of D(0.1cc) to the brainstem decreased by 7.7 Gy (p <.005). The averages of V(30 Gy) to the contralateral parotid decreased by 8.7% (p <.0001), where V(30 Gy) represents the percentage volume corresponding to 30 Gy. CONCLUSION: The method heralds the possibility of automated IMRT planning.

A statistical approach for achievable dose querying in IMRT planning.

The task of IMRT planning, particularly in head-and-neck cancer, is a difficult one, often requiring days of work from a trained dosimetrist. One of the main challenges is the prescription of achievable target doses that will be used to optimize a treatment plan. This work explores a data-driven approach in which effort spent on past plans is used to assist in the planning of new patients. Using a database of treated patients, we identify the features of patient geometry that are correlated with received dose and use these to prescribe target dose levels for new patients. We incorporate our approach in a quality-control system, identifying patients with organs that received a dose significantly higher than the one recommended by our method. For all these patients, we have found that a replan using our predicted dose results in noticeable sparing of the organ without compromising dose to other treatment volumes.

A shape relationship descriptor for radiation therapy planning.

In this paper we address the challenge of matching patient geometry to facilitate the design of patient treatment plans in radiotherapy. To this end we propose a novel shape descriptor, the Overlap Volume Histogram, which provides a rotation and translation invariant representation of a patient's organs at risk relative to the tumor volume. Using our descriptor, it is possible to accurately identify database patients with similar constellations of organ and tumor geometries, enabling the transfer of treatment plans between patients with similar geometries, We demonstrate the utility of our method for such tasks by outperforming state of the art shape descriptors in the retrieval of patients with similar treatment plans. We also preliminarily show its potential as a quality control tool by demonstrating how it is used to identify an organ at risk whose dose can be significantly reduced.

An approximate and efficient method for optimal rotation alignment of 3D models.

In many shape analysis applications, the ability to find the best rotation that aligns two models is an essential first step in the analysis process. In the past, methods for model alignment have either used normalization techniques, such as PCA alignment, or have performed an exhaustive search over the space of rotation to find the best optimal alignment. While normalization techniques have the advantage of efficiency, providing a quick method for registering two shapes, they are often imprecise and can give rise to poor alignments. Conversely, exhaustive search is guaranteed to provide the correct answer, but, even using efficient signal processing techniques, this type of approach can be prohibitively slow. In this paper, we present a new method for aligning two 3D shapes. We show that the method is markedly faster than existing approaches based on efficient signal processing and we provide registration results demonstrating that the alignments obtained using our method have a high degree of precision and are markedly better than those obtained using normalization.