Analysis of OCT Scanning Parameters in AMD and RVO.

Optical coherence tomography (OCT) is an extensively used imaging tool for disease monitoring in both age-related macular degeneration (AMD) and retinal vein occlusion (RVO). However, there is limited literature on minimum requirements of OCT settings for reliable biomarker detection. This study systematically investigates both the influence of scan size and interscan distance (ISD) on disease activity detection. We analyzed 80 OCT volumes of AMD patients and 12 OCT volumes of RVO patients for the presence of subretinal fluid (SRF), intraretinal fluid (IRF), and pigment epithelium detachment (PED). All volume scans had a scan size of 6 × 6 mm and an ISD of 125 µm. We analyzed both general fluid distribution and how biomarker detection sensitivity decreases when reducing scan size or density. We found that in AMD patients, all fluids were nearly normally distributed, with most occurrences in the foveal center and concentric decrease towards the periphery. When reducing the scan size to 3 × 3 and 2 × 2 mm, disease activity detection was still high (0.98 and 0.96). Increasing ISD only slightly can already compromise biomarker detection sensitivity (0.9 for 250 µm ISD against 125 µm ISD).

Image registration and appearance adaptation in non-correspondent image regions for new MS lesions detection.

Manual detection of newly formed lesions in multiple sclerosis is an important but tedious and difficult task. Several approaches for automating the detection of new lesions have recently been proposed, but they tend to either overestimate the actual amount of new lesions or to miss many lesions. In this paper, an image registration convolutional neural network (CNN) that adapts the baseline image to the follow-up image by spatial deformations and simulation of new lesions is proposed. Simultaneously, segmentations of new lesions are generated, which are shown to reliably estimate the real new lesion load and to separate stable and progressive patients. Several applications of the proposed network emerge: image registration, detection and segmentation of new lesions, and modeling of new MS lesions. The modeled lesions offer the possibility to investigate the intensity profile of new lesions.

Deep learning-based simultaneous registration and unsupervised non-correspondence segmentation of medical images with pathologies.

PURPOSE: The registration of medical images often suffers from missing correspondences due to inter-patient variations, pathologies and their progression leading to implausible deformations that cause misregistrations and might eliminate valuable information. Detecting non-corresponding regions simultaneously with the registration process helps generating better deformations and has been investigated thoroughly with classical iterative frameworks but rarely with deep learning-based methods. METHODS: We present the joint non-correspondence segmentation and image registration network (NCR-Net), a convolutional neural network (CNN) trained on a Mumford-Shah-like functional, transferring the classical approach to the field of deep learning. NCR-Net consists of one encoding and two decoding parts allowing the network to simultaneously generate diffeomorphic deformations and segment non-correspondences. The loss function is composed of a masked image distance measure and regularization of deformation field and segmentation output. Additionally, anatomical labels are used for weak supervision of the registration task. No manual segmentations of non-correspondences are required. RESULTS: The proposed network is evaluated on the publicly available LPBA40 dataset with artificially added stroke lesions and a longitudinal optical coherence tomography (OCT) dataset of patients with age-related macular degeneration. The LPBA40 data are used to quantitatively assess the segmentation performance of the network, and it is shown qualitatively that NCR-Net can be used for the unsupervised segmentation of pathologies in OCT images. Furthermore, NCR-Net is compared to a registration-only network and state-of-the-art registration algorithms showing that NCR-Net achieves competitive performance and superior robustness to non-correspondences. CONCLUSION: NCR-Net, a CNN for simultaneous image registration and unsupervised non-correspondence segmentation, is presented. Experimental results show the network's ability to segment non-correspondence regions in an unsupervised manner and its robust registration performance even in the presence of large pathologies.

Self-Examination Low-Cost Full-Field Optical Coherence Tomography (SELFF-OCT) for neovascular age-related macular degeneration: a cross-sectional diagnostic accuracy study.

OBJECTIVES: Self-Examination Low-Cost Full-Field Optical Coherence Tomography (SELFF-OCT) is a novel OCT technology that was specifically designed for home monitoring of neovascular age-related macular degeneration (AMD). First clinical findings have been reported before. This trial investigates an improved prototype for patients with AMD and focusses on device operability and diagnostic accuracy compared with established spectral-domain OCT (SD-OCT). DESIGN: Prospective single-arm diagnostic accuracy study. SETTING: Tertiary care centre (University Eye Clinic). PARTICIPANTS: 46 patients with age-related macular degeneration. INTERVENTIONS: Patients received short training in device handling and then performed multiple self-scans with the SELFF-OCT according to a predefined protocol. Additionally, all eyes were examined with standard SD-OCT, performed by medical personnel. All images were graded by at least 2 masked investigators in a reading centre. PRIMARY OUTCOME MEASURE: Rate of successful self-measurements. SECONDARY OUTCOME MEASURES: Sensitivity and specificity of SELFF-OCT versus SD-OCT for different biomarkers and necessity for antivascular endothelial growth factor (anti-VEGF) treatment. RESULTS: In 86% of all examined eyes, OCT self-acquisition resulted in interpretable retinal OCT volume scans. In these patients, the sensitivity for detection of anti-VEGF treatment necessity was 0.94 (95% CI 0.79 to 0.99) and specificity 0.95 (95% CI 0.82 to 0.99). CONCLUSIONS: SELFF-OCT was used successfully for retinal self-examination in most patients, and it could become a valuable tool for retinal home monitoring in the future. Improvements are in progress to reduce device size and to improve handling, image quality and success rates. TRIAL REGISTRATION NUMBER: DRKS00013755, CIV-17-12-022384.

Segmentation of mouse skin layers in optical coherence tomography image data using deep convolutional neural networks.

Optical coherence tomography (OCT) enables the non-invasive acquisition of high-resolution three-dimensional cross-sectional images at micrometer scale and is mainly used in the field of ophthalmology for diagnosis as well as monitoring of eye diseases. Also in other areas, such as dermatology, OCT is already well established. Due to its non-invasive nature, OCT is also employed for research studies involving animal models. Manual evaluation of OCT images of animal models is a challenging task due to the lack of imaging standards and the varying anatomy among models. In this paper, we present a deep learning algorithm for the automatic segmentation of several layers of mouse skin in OCT image data using a deep convolutional neural network (CNN). The architecture of our CNN is based on the U-net and is modified by densely connected convolutions. We compared our adapted CNN with our previous algorithm, a combination of a random forest classification and a graph-based refinement, and a baseline U-net. The results showed that, on average, our proposed CNN outperformed our previous algorithm and the baseline U-net. In addition, a reduction of outliers could be observed through the use of densely connected convolutions.

MRI FLAIR lesion segmentation in multiple sclerosis: Does automated segmentation hold up with manual annotation?

INTRODUCTION: Magnetic resonance imaging (MRI) has become key in the diagnosis and disease monitoring of patients with multiple sclerosis (MS). Both, T2 lesion load and Gadolinium (Gd) enhancing T1 lesions represent important endpoints in MS clinical trials by serving as a surrogate of clinical disease activity. T2- and fluid-attenuated inversion recovery (FLAIR) lesion quantification - largely due to methodological constraints - is still being performed manually or in a semi-automated fashion, although strong efforts have been made to allow automated quantitative lesion segmentation. In 2012, Schmidt and co-workers published an algorithm to be applied on FLAIR sequences. The aim of this study was to apply the Schmidt algorithm on an independent data set and compare automated segmentation to inter-rater variability of three independent, experienced raters. METHODS: MRI data of 50 patients with RRMS were randomly selected from a larger pool of MS patients attending the MS Clinic at the Brain and Mind Centre, University of Sydney, Australia. MRIs were acquired on a 3.0T GE scanner (Discovery MR750, GE Medical Systems, Milwaukee, WI) using an 8 channel head coil. We determined T2-lesion load (total lesion volume and total lesion number) using three versions of an automated segmentation algorithm (Lesion growth algorithm (LGA) based on SPM8 or SPM12 and lesion prediction algorithm (LPA) based on SPM12) as first described by Schmidt et al. (2012). Additionally, manual segmentation was performed by three independent raters. We calculated inter-rater correlation coefficients (ICC) and dice coefficients (DC) for all possible pairwise comparisons. RESULTS: We found a strong correlation between manual and automated lesion segmentation based on LGA SPM8, regarding lesion volume (ICC = 0.958 and DC = 0.60) that was not statistically different from the inter-rater correlation (ICC = 0.97 and DC = 0.66). Correlation between the two other algorithms (LGA SPM12 and LPA SPM12) and manual raters was weaker but still adequate (ICC = 0.927 and DC = 0.53 for LGA SPM12 and ICC = 0.949 and DC = 0.57 for LPA SPM12). Variability of both manual and automated segmentation was significantly higher regarding lesion numbers. CONCLUSION: Automated lesion volume quantification can be applied reliably on FLAIR data sets using the SPM based algorithm of Schmidt et al. and shows good agreement with manual segmentation.

Performance of Hippocampus Volumetry with FSL-FIRST for Prediction of Alzheimer's Disease Dementia in at Risk Subjects with Amnestic Mild Cognitive Impairment.

MRI-based hippocampus volume, a core feasible biomarker of Alzheimer's disease (AD), is not yet widely used in clinical patient care, partly due to lack of validation of software tools for hippocampal volumetry that are compatible with routine workflow. Here, we evaluate fully-automated and computationally efficient hippocampal volumetry with FSL-FIRST for prediction of AD dementia (ADD) in subjects with amnestic mild cognitive impairment (aMCI) from phase 1 of the Alzheimer's Disease Neuroimaging Initiative. Receiver operating characteristic analysis of FSL-FIRST hippocampal volume (corrected for head size and age) revealed an area under the curve of 0.79, 0.70, and 0.70 for prediction of aMCI-to-ADD conversion within 12, 24, or 36 months, respectively. Thus, FSL-FIRST provides about the same power for prediction of progression to ADD in aMCI as other volumetry methods.

Atlas based brain volumetry: How to distinguish regional volume changes due to biological or physiological effects from inherent noise of the methodology.

Fully-automated regional brain volumetry based on structural magnetic resonance imaging (MRI) plays an important role in quantitative neuroimaging. In clinical trials as well as in clinical routine multiple MRIs of individual patients at different time points need to be assessed longitudinally. Measures of inter- and intrascanner variability are crucial to understand the intrinsic variability of the method and to distinguish volume changes due to biological or physiological effects from inherent noise of the methodology. To measure regional brain volumes an atlas based volumetry (ABV) approach was deployed using a highly elastic registration framework and an anatomical atlas in a well-defined template space. We assessed inter- and intrascanner variability of the method in 51 cognitively normal subjects and 27 Alzheimer dementia (AD) patients from the Alzheimer's Disease Neuroimaging Initiative by studying volumetric results of repeated scans for 17 compartments and brain regions. Median percentage volume differences of scan-rescans from the same scanner ranged from 0.24% (whole brain parenchyma in healthy subjects) to 1.73% (occipital lobe white matter in AD), with generally higher differences in AD patients as compared to normal subjects (e.g., 1.01% vs. 0.78% for the hippocampus). Minimum percentage volume differences detectable with an error probability of 5% were in the one-digit percentage range for almost all structures investigated, with most of them being below 5%. Intrascanner variability was independent of magnetic field strength. The median interscanner variability was up to ten times higher than the intrascanner variability.