This paper introduces a network for volumetric segmentation that learns from sparsely annotated volumetric images. We outline two attractive use cases of this method: (1) In a semi-automated setup, the user annotates some slices in the volume to be segmented. The network learns from these sparse annotations and provides a dense 3D segmentation. (2) In a fully-automated setup, we assume that a representative, sparsely annotated training set exists. Trained on this data set, the network densely segments new volumetric images. The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts. The implementation performs on-the-fly elastic deformations for efficient data augmentation during training. It is trained end-to-end from scratch, i.e., no pre-trained network is required. We test the performance of the proposed method on a complex, highly variable 3D structure, the Xenopus kidney, and achieve good results for both use cases.

/pdf/3d-u-net-learning-dense-volumetric-segmentation-from-sparse-4yrx1x4zn2.pdf

3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation

ImageJ is an image analysis program extensively used in the biological sciences and beyond. Due to its ease of use, recordable macro language, and extensible plug-in architecture, ImageJ enjoys contributions from non-programmers, amateur programmers, and professional developers alike. Enabling such a diversity of contributors has resulted in a large community that spans the biological and physical sciences. However, a rapidly growing user base, diverging plugin suites, and technical limitations have revealed a clear need for a concerted software engineering effort to support emerging imaging paradigms, to ensure the software’s ability to handle the requirements of modern science. We rewrote the entire ImageJ codebase, engineering a redesigned plugin mechanism intended to facilitate extensibility at every level, with the goal of creating a more powerful tool that continues to serve the existing community while addressing a wider range of scientific requirements. This next-generation ImageJ, called “ImageJ2” in places where the distinction matters, provides a host of new functionality. It separates concerns, fully decoupling the data model from the user interface. It emphasizes integration with external applications to maximize interoperability. Its robust new plugin framework allows everything from image formats, to scripting languages, to visualization to be extended by the community. The redesigned data model supports arbitrarily large, N-dimensional datasets, which are increasingly common in modern image acquisition. Despite the scope of these changes, backwards compatibility is maintained such that this new functionality can be seamlessly integrated with the classic ImageJ interface, allowing users and developers to migrate to these new methods at their own pace. Scientific imaging benefits from open-source programs that advance new method development and deployment to a diverse audience. ImageJ has continuously evolved with this idea in mind; however, new and emerging scientific requirements have posed corresponding challenges for ImageJ’s development. The described improvements provide a framework engineered for flexibility, intended to support these requirements as well as accommodate future needs. Future efforts will focus on implementing new algorithms in this framework and expanding collaborations with other popular scientific software suites.

/pdf/imagej2-imagej-for-the-next-generation-of-scientific-image-41ybjcosb6.pdf

ImageJ2: ImageJ for the next generation of scientific image data

The multiscale second order local structure of an image (Hessian) is examined with the purpose of developing a vessel enhancement filter. A vesselness measure is obtained on the basis of all eigenvalues of the Hessian. This measure is tested on two dimensional DSA and three dimensional aortoiliac and cerebral MRA data. Its clinical utility is shown by the simultaneous noise and background suppression and vessel enhancement in maximum intensity projections and volumetric displays.

/pdf/muliscale-vessel-enhancement-filtering-3g7prwx990.pdf

Muliscale Vessel Enhancement Filtering

A reproducible evaluation of ANTs similarity metric performance in brain image registration.

Radiomics aims to quantify phenotypic characteristics on medical imaging through the use of automated algorithms. Radiomic artificial intelligence (AI) technology, either based on engineered hard-coded algorithms or deep learning methods, can be used to develop noninvasive imaging-based biomarkers. However, lack of standardized algorithm definitions and image processing severely hampers reproducibility and comparability of results. To address this issue, we developed PyRadiomics, a flexible open-source platform capable of extracting a large panel of engineered features from medical images. PyRadiomics is implemented in Python and can be used standalone or using 3D Slicer. Here, we discuss the workflow and architecture of PyRadiomics and demonstrate its application in characterizing lung lesions. Source code, documentation, and examples are publicly available at www.radiomics.io With this platform, we aim to establish a reference standard for radiomic analyses, provide a tested and maintained resource, and to grow the community of radiomic developers addressing critical needs in cancer research. Cancer Res; 77(21); e104-7. ©2017 AACR.

/pdf/computational-radiomics-system-to-decode-the-radiographic-qdly99paxt.pdf

Computational Radiomics System to Decode the Radiographic Phenotype

We are developing three-dimensional imaging methods to portray vascular anatomy better, including noise-free display of vessels extracted from 3-D data sets, tree-based display, and reconstruction of angiographic data (preliminary work has resulted in the successful reconstruction of aneurysms from angiographic data). Fast, interactive display permits real-time manipulation of viewing orientation.

http://www.ajnr.org/content/ajnr/18/3/417.full.pdf

Methods for displaying intracerebral vascular anatomy

Response of the autonomic nervous system can be assessed by quantifying the dilation of the pupil of a human placed in darkness. When the intensity of the surrounding light is low, human's pupil dilates to capture a maximum number of photons. This type of dilation is known as dark adaptation. The aim of this study is to test the hypothesis that dark adaptation is slowed proportional to the amount of stress that an individual has experienced. We have developed a new tool for automatic quantification of pupil dilation. Our system uses statistics of the color of the pupil and the iris as well as model-to-image registration and region growing segmentation techniques. Our system has been tested on several images and shows high correlation with hand segmentation.

/pdf/automatic-quantification-of-pupil-dilation-under-stress-1030tdigjc.pdf

Automatic quantification of pupil dilation under stress

When the projection of a collection of samples onto a subset of basis feature vectors has a Gaussian distribution, those samples have a generalized projective Gaussian distribution (GPGD). GPGDs arise in a variety of medical images as well as some speech recognition problems. We will demonstrate that GPGDs are better represented by continuous Gaussian mixture models (CGMMs) than finite Gaussian mixture models (FGMMs).

/pdf/continuous-gaussian-mixture-modeling-29n041u5ob.pdf

Continuous Gaussian Mixture Modeling

We propose a novel method for the validation of vascular segmentations. Our technique combines morphological operators and the STAPLE algorithm to obtain ground truth of centerline extractions as well as a measure of accuracy of the methods to be compared. Moreover, our method can be extended to the validation of any open-curves. We also present a comparison study of three vascular segmentation methods: ridge traversal, statistical and curves level set. They are compared with manual segmentations from five experts.

/pdf/comparison-of-vessel-segmentations-using-staple-1131rsvdnj.pdf

Stephen R. Aylward

Papers

Methods for displaying intracerebral vascular anatomy

Automatic quantification of pupil dilation under stress

Continuous Gaussian Mixture Modeling

Comparison of vessel segmentations using STAPLE

Teaching medical image analysis with the Insight Toolkit.