ITK is one of the most powerful image segmentation and registration libraries available as an open source toolkit. Motivated by the recent popularization of the iPhone, iPod touch, and iPad, in this work, we describe the set of required steps for integrating the ITK framework into Apple’s iOS mobile operating system. Our focus in this paper is on the process of importing the C++ based ITK to the Objective-C based iOS, and creating a simple application that demonstrates the ITK libraries are integrated. This paper brings to the reader a user-manual on how to integrate the ITK libraries into iOS applications and code. We present here the series of steps we performed in order to import the ITK libraries as well as report the results of importing them under different versions of the iOS and under different architectures (the Simulator and Device architecture).

ITK on the iOS

This document describes the use and implementation of first and second order spatial derivatives of coordinate transformations in the Insight Toolkit url{www.itk.org}). Spatial derivatives are useful for many types of regularising or penalty terms frequently used in image registration. These derivatives are dubbed 'SpatialJacobian' and 'SpatialHessian' to distinguish with the derivative to the transformation parameters themselves, which is called `Jacobian' in the ITK.

In addition to the spatial derivatives, we derived and implemented the derivatives to the registration/transform parameters of these spatial derivatives, required for gradient descent type optimisation routines. These derivatives are implemented in a sparse manner, reducing the computation time for transformations which have local support. All of these derivatives are implemented for the most common ITK coordinate transformation, such as the rigid, affine and B-spline transformation. In addition we derive formulae and code for arbitrary compositions of transformations. The spatial derivatives were subsequently exploited by implementing the bending energy penalty term.

This paper is accompanied with the source code, input data, parameters and output data that the authors used for validating the algorithm described in this paper. This adheres to the fundamental principle that scientific publications must facilitate reproducibility of the reported results.


Itk::Transforms supporting spatial derivatives

In this paper, we analyze the relationship between parameters of brain tumors obtained through in vivo magnetic resonance imaging (MRI), in vivo magneticnresonance spectroscopy (MRS), and ex vivo immunohistochemistry (IHC). The goal of our project is to provide a quantitative definition of tumor cellularity based on the in vivo parameters. Biopsy samples obtained from previously untreated patients with a diagnosis of GBM are used to find the link between imaging parameters at the specific biopsy locations and IHC parameters from the corresponding tissue samples. A functional tree (FT) model of tumor cellularity is learned from the in vivo parameters and the remaining histological parameters. The tumor cellularity model is then tested on examples which contain only in vivo parameters, by first estimating the remaining IHC parameters by applying the Expectation Maximization (EM) algorithm, and then using the complete parameter vector for classification.

Modeling Tumor Cellularity in Newly Diagnosed GBMs using MR Imaging and Spectroscopy

This paper presents a technique for immunostaining biomarker detection in digital slides. We treat immunostaining detection as a color image analysis problem and build statistical color models using a large number of labeled positive and negative immunostaining pixels. We have implemented the statistical models in different color spaces and show that the opponent chromaticity signals effectively characterize the color distributions of the immunostaining biomarkers and that the luminance is an unreliable and distractive signal. We have applied the technique to the detection of positive P53 immunostaining in digital slides of oesophagitis and colorectal biopsies. We present experimental results and show that the technique can achieve a biomarker detection rate of over 98% with 5% false positives. 

Biomarker Detection in Whole Slide Imaging based on Statistical Color Models

This paper presents a method for nonlinear registration of images, where there exists no one-to-one correspondence in parts of the image. Such a situation occurs for instance in the case where an atlas of normal anatomy shall be matched to pathological data, such as tumors, resections or lesions. Our idea is to use local confidence weights and to model pathological regions with zero confidence. We integrate this concept into the efficient and publicly available diffeomorphic demons registration framework. Finally, we show that this process better captures deformations in high-confidence regions than without using the proposed modification. Furthermore, it is easy to implement and runs faster than previous approaches.

Atlas to Image-with-Tumor Registration Based on Demons and Deformation Inpainting

We have recently detailed the procedure for building ITK on the iOS. In this work, we contribute itkiOSImageIO , the necessary ITK class that provides the input/output (IO) interface with the repository of images stored on iOS Apple devices, such as the iPod touch, iPhone, or iPad. The proposed classes provide the ITK programmer with the facility to read or write iOS images. Along with contributing the source code for these classes, we provide examples of reading and writing different types of gray 
level and color iOS images, as well as ﬁltering the images using ITK ﬁlters. 

ITK Image IO interface with Apple iOS

ITK has a powerful and flexible image IO framework. Reading and writing different types of image file is straightforward. The image IO could be easily extended by writing a specific image IO class for a new image file format. Whereas, there is no such framework for easily reading and writing itk::Mesh/itk::QuadEdgeMesh, At the moment, only a few specific classes to read vtk polydata format and is not easily to be extended. This paper describes our contribution to itk for providing a mesh IO framework which could be used for reading and writing some commonly used mesh file formats. The mesh IO classes worked well for both itk::Mesh and itk::QuadEdgeMesh.

ITK Mesh IO Framework

This documents is about the filter itkQuadEdgeMeshSimilarityCalculator. It takes inputs of two meshes and gives the similarity of the labels on them in two types of similarity measurements – Dice Similarity and Jaccard Similarity.
This paper is accompanied with the source code, input data, parameters and output data that we used for validating the algorithm described in this paper. This adheres to the fundamental principle that scientific publications must facilitate reproducibility of the reported results.

Mesh Similarity Calculator

This documents is about the filter itk::WarpQuadEdgeMeshFilter. It takes two input meshes (fixed and moving meshes) and one deformation field. It produces one output mesh. Each point on the fixed mesh is warped according to the displacement vector saved in the deformation field and gets a scalar value assigned by interpolating the scalar value from the moving mesh. An interpolator is needed to apply this filter.
This paper is accompanied with the source code, input data, parameters and output data that we used for validating the algorithm described in this paper. This adheres to the fundamental principle that scientific publications must facilitate reproducibility of the reported results.

Warp Mesh Filter

Expectation maximization (EM) is a common technique for estimating the parameters of a model after having collected observations of data generated by the model. We first explain the algorithm, then present our impelementation. We focus on estimation of the parameters of a Gaussian Mixture Model (GMM). The implementation is written in the VTK framework and is provided as a new class, vtkExpectationMaximization.

The code is hosted here: http://github.com/daviddoria/ExpectationMaximization for the time being.