Comparative analysis of alignment algorithms for macular optical coherence tomography imaging

BACKGROUND

Optical coherence tomography (OCT) is the most important and commonly utilized imaging modality in ophthalmology and is especially crucial for the diagnosis and management of macular diseases. Each OCT volume is typically only available as a series of cross-sectional images (B-scans) that are accessible through proprietary software programs which accompany the OCT machines. To maximize the potential of OCT imaging for machine learning purposes, each OCT image should be analyzed en bloc as a 3D volume, which requires aligning all the cross-sectional images within a particular volume.

METHODS

A dataset of OCT B-scans obtained from 48 age-related macular degeneration (AMD) patients and 50 normal controls was used to evaluate five registration algorithms. After alignment of B-scans from each patient, an en face surface map was created to measure the registration quality, based on an automatically generated Laplace difference of the surface map-the smoother the surface map, the smaller the average Laplace difference. To demonstrate the usefulness of B-scan alignment, we trained a 3D convolutional neural network (CNN) to detect age-related macular degeneration (AMD) on OCT images and compared the performance of the model with and without B-scan alignment.

RESULTS

The mean Laplace difference of the surface map before registration was 27 ± 4.2 pixels for the AMD group and 26.6 ± 4 pixels for the control group. After alignment, the smoothness of the surface map was improved, with a mean Laplace difference of 5.5 ± 2.7 pixels for Advanced Normalization Tools Symmetric image Normalization (ANTs-SyN) registration algorithm in the AMD group and a mean Laplace difference of 4.3 ± 1.4.2 pixels for ANTs in the control group. Our 3D CNN achieved superior performance in detecting AMD, when aligned OCT B-scans were used (AUC 0.95 aligned vs. 0.89 unaligned).

CONCLUSIONS

We introduced a novel metric to quantify OCT B-scan alignment and compared the effectiveness of five alignment algorithms. We confirmed that alignment could be improved in a statistically significant manner with readily available alignment algorithms that are available to the public, and the ANTs algorithm provided the most robust performance overall. We further demonstrated that alignment of OCT B-scans will likely be useful for training 3D CNN models.

Nanoparticle size and 3D shape measurement by electron tomography: An Inter-Laboratory Comparison

Electron tomography (ET) has been used for quantitative measurement of shape and size of objects in three dimensions (3D) for many years. However, systematic investigation of repeatability and reproducibility of ET has not been evaluated in detail. To assess the reproducibility and repeatability of a protocol for measuring size and three-dimensional (3D) shape parameters for nanoparticles (NPs) by ET, an inter-laboratory comparison (ILC) has been performed. The ILC included six laboratories and six instruments models from three instrument manufacturers following a standard measurement protocol. A technical specification describing the normative steps of the protocol is published by the International Standards Organization (ISO). Gold NPs with 30 nm nominal diameter contained within a rod-shaped carbon support were measured. The use of a rod-shaped sample support eliminated the missing wedge effect in the experimental tilt series of projected images for improved quantification. A total of 443 NPs were initially measured by NRC-NANO and then 115 out of the 443 NPs were measured by five other labs to compare measurands such as the Volume (V), maximum Feret diameter (F_max), minimum Feret diameter (F_min), volume-equivalent diameter (D_eq) and aspect ratio (F_rat) of the NPs. The results of the five labs were compared with the results obtained at NRC-NANO. The maximum disagreement in measurements of F_min and F_max obtained by the participating labs did not exceed 7 %. The measured D_eq was between 27.5 nm and 30.3 nm in agreement with the NP manufacturer's specification (28 nm-32 nm). In addition to the above, the influence of the missing wedge effect and beam-induced NP movement was quantified based on the differences of the results between labs.

Synchronization and Alignment of Follow-up Examinations: a Practical and Educational Approach Using the DICOM Reference Coordinate System

This work presents an approach for synchronization and alignment of Digital Imaging and Communications in Medicine (DICOM) series from different studies that allows, e.g., easier reading of follow-up examinations. The proposed concept developed within the DICOM's patient-based reference coordinate system allows to synchronize all image data of two different studies/examinations based on a single registration. The most suitable DICOM series for registration could be set as default per protocol. Necessary basics regarding the DICOM standard and the used mathematical transformations are presented in an educative way to allow straightforward implementation in Picture Archiving And Communications Systems (PACS) and other DICOM tools. The proposed method for alignment of DICOM images is potentially also useful for various scientific tasks and machine-learning applications.

Iterative simulations to estimate the elastic properties from a series of MRI images followed by MRI-US validation

The modeling of breast deformations is of interest in medical applications such as image-guided biopsy, or image registration for diagnostic purposes. In order to have such information, it is needed to extract the mechanical properties of the tissues. In this work, we propose an iterative technique based on finite element analysis that estimates the elastic modulus of realistic breast phantoms, starting from MRI images acquired in different positions (prone and supine), when deformed only by the gravity force. We validated the method using both a single-modality evaluation in which we simulated the effect of the gravity force to generate four different configurations (prone, supine, lateral, and vertical) and a multi-modality evaluation in which we simulated a series of changes in orientation (prone to supine). Validation is performed, respectively, on surface points and lesions using as ground-truth data from MRI images, and on target lesions inside the breast phantom compared with the actual target segmented from the US image. The use of pre-operative images is limited at the moment to diagnostic purposes. By using our method we can compute patient-specific mechanical properties that allow compensating deformations. Graphical Abstract Workflow of the proposed method and comparative results of the prone-to-supine simulation (red volumes) validated using MRI data (blue volumes).

Survey of Non-Rigid Registration Tools in Medicine

We catalogue available software solutions for non-rigid image registration to support scientists in selecting suitable tools for specific medical registration purposes. Registration tools were identified using non-systematic search in Pubmed, Web of Science, IEEE Xplore® Digital Library, Google Scholar, and through references in identified sources (n = 22). Exclusions are due to unavailability or inappropriateness. The remaining (n = 18) tools were classified by (i) access and technology, (ii) interfaces and application, (iii) living community, (iv) supported file formats, and (v) types of registration methodologies emphasizing the similarity measures implemented. Out of the 18 tools, (i) 12 are open source, 8 are released under a permissive free license, which imposes the least restrictions on the use and further development of the tool, 8 provide graphical processing unit (GPU) support; (ii) 7 are built on software platforms, 5 were developed for brain image registration; (iii) 6 are under active development but only 3 have had their last update in 2015 or 2016; (iv) 16 support the Analyze format, while 7 file formats can be read with only one of the tools; and (v) 6 provide multiple registration methods and 6 provide landmark-based registration methods. Based on open source, licensing, GPU support, active community, several file formats, algorithms, and similarity measures, the tools Elastics and Plastimatch are chosen for the platform ITK and without platform requirements, respectively. Researchers in medical image analysis already have a large choice of registration tools freely available. However, the most recently published algorithms may not be included in the tools, yet.

Automatic hemolysis identification on aligned dual-lighting images of cultured blood agar plates

BACKGROUND AND OBJECTIVE

The recent introduction of Full Laboratory Automation systems in clinical microbiology opens to the availability of streams of high definition images representing bacteria culturing plates. This creates new opportunities to support diagnostic decisions through image analysis and interpretation solutions, with an expected high impact on the efficiency of the laboratory workflow and related quality implications. Starting from images acquired under different illumination settings (top-light and back-light), the objective of this work is to design and evaluate a method for the detection and classification of diagnostically relevant hemolysis effects associated with specific bacteria growing on blood agar plates. The presence of hemolysis is an important factor to assess the virulence of pathogens, and is a fundamental sign of the presence of certain types of bacteria.

METHODS

We introduce a two-stage approach. Firstly, the implementation of a highly accurate alignment of same-plate image scans, acquired using top-light and back-light illumination, enables the joint spatially coherent exploitation of the available data. Secondly, from each segmented portion of the image containing at least one bacterial colony, specifically designed image features are extracted to feed a SVM classification system, allowing detection and discrimination among different types of hemolysis.

RESULTS

The fine alignment solution aligns more than 98.1% images with a residual error of less than 0.13 mm. The hemolysis classification block achieves a 88.3% precision with a recall of 98.6%.

CONCLUSIONS

The results collected from different clinical scenarios (urinary infections and throat swab screening) together with accurate error analysis demonstrate the suitability of our system for robust hemolysis detection and classification, which remains feasible even in challenging conditions (low contrast or illumination changes).

Robust image alignment for cryogenic transmission electron microscopy

Cryo-electron microscopy recently experienced great improvements in structure resolution due to direct electron detectors with improved contrast and fast read-out leading to single electron counting. High frames rates enabled dose fractionation, where a long exposure is broken into a movie, permitting specimen drift to be registered and corrected. The typical approach for image registration, with high shot noise and low contrast, is multi-reference (MR) cross-correlation. Here we present the software package Zorro, which provides robust drift correction for dose fractionation by use of an intensity-normalized cross-correlation and logistic noise model to weight each cross-correlation in the MR model and filter each cross-correlation optimally. Frames are reliably registered by Zorro with low dose and defocus. Methods to evaluate performance are presented, by use of independently-evaluated even- and odd-frame stacks by trajectory comparison and Fourier ring correlation. Alignment of tiled sub-frames is also introduced, and demonstrated on an example dataset. Zorro source code is available at github.com/CINA/zorro.

Electron Tomography Methods for C. elegans

Methods for electron tomography of the nematode C. elegans are explained in detail, including a brief introduction to specimen preparation, methods for image collection, and a comparison of several general methods for producing dual-axis tomograms, with or without external fiducial reference objects. New electron tomograms highlight features in software for data display, annotation, and analysis. This chapter discusses the ultrastructural analysis of cells and tissues, rather than molecular studies.

Landmark matching based retinal image alignment by enforcing sparsity in correspondence matrix

Retinal image alignment is fundamental to many applications in diagnosis of eye diseases. In this paper, we address the problem of landmark matching based retinal image alignment. We propose a novel landmark matching formulation by enforcing sparsity in the correspondence matrix and offer its solutions based on linear programming. The proposed formulation not only enables a joint estimation of the landmark correspondences and a predefined transformation model but also combines the benefits of the softassign strategy (Chui and Rangarajan, 2003) and the combinatorial optimization of linear programming. We also introduced a set of reinforced self-similarities descriptors which can better characterize local photometric and geometric properties of the retinal image. Theoretical analysis and experimental results with both fundus color images and angiogram images show the superior performances of our algorithms to several state-of-the-art techniques.