Dictionary-Driven Ischemia Detection From Cardiac Phase-Resolved Myocardial BOLD MRI at Rest

Accurate needle-free assessment of myocardial oxygenation for ischemic heart disease in canines using magnetic resonance imaging

Myocardial oxygenation-the ability of blood vessels to supply the heart muscle (myocardium) with oxygen-is a critical determinant of cardiac function. Impairment of myocardial oxygenation is a defining feature of ischemic heart disease (IHD), which is caused by pathological conditions that affect the blood vessels supplying oxygen to the heart muscle. Detecting altered myocardial oxygenation can help guide interventions and prevent acute life-threatening events such as heart attacks (myocardial infarction); however, current diagnosis of IHD relies on surrogate metrics and exogenous contrast agents for which many patients are contraindicated. An oxygenation-sensitive cardiac magnetic resonance imaging (CMR) approach used previously to demonstrate that CMR signals can be sensitized to changes in myocardial oxygenation showed limited ability to detect small changes in signals in the heart because of physiologic and imaging noise during data acquisition. Here, we demonstrate a CMR-based approach termed cfMRI [cardiac functional magnetic resonance imaging (MRI)] that detects myocardial oxygenation. cfMRI uses carbon dioxide for repeat interrogation of the functional capacity of the heart's blood vessels via a fast MRI approach suitable for clinical adoption without limitations of key confounders (cardiac/respiratory motion and heart rate changes). This method integrates multiple whole-heart images within a computational framework to reduce noise, producing confidence maps of alterations in myocardial oxygenation. cfMRI permits noninvasive monitoring of myocardial oxygenation without requiring ionizing radiation, contrast agents, or needles. This has the potential to broaden our ability to noninvasively identify IHD and a diverse spectrum of heart diseases related to myocardial ischemia.

Disentangled representation learning in cardiac image analysis

Typically, a medical image offers spatial information on the anatomy (and pathology) modulated by imaging specific characteristics. Many imaging modalities including Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) can be interpreted in this way. We can venture further and consider that a medical image naturally factors into some spatial factors depicting anatomy and factors that denote the imaging characteristics. Here, we explicitly learn this decomposed (disentangled) representation of imaging data, focusing in particular on cardiac images. We propose Spatial Decomposition Network (SDNet), which factorises 2D medical images into spatial anatomical factors and non-spatial modality factors. We demonstrate that this high-level representation is ideally suited for several medical image analysis tasks, such as semi-supervised segmentation, multi-task segmentation and regression, and image-to-image synthesis. Specifically, we show that our model can match the performance of fully supervised segmentation models, using only a fraction of the labelled images. Critically, we show that our factorised representation also benefits from supervision obtained either when we use auxiliary tasks to train the model in a multi-task setting (e.g. regressing to known cardiac indices), or when aggregating multimodal data from different sources (e.g. pooling together MRI and CT data). To explore the properties of the learned factorisation, we perform latent-space arithmetic and show that we can synthesise CT from MR and vice versa, by swapping the modality factors. We also demonstrate that the factor holding image specific information can be used to predict the input modality with high accuracy. Code will be made available at https://github.com/agis85/anatomy_modality_decomposition.

Learning Based Segmentation of CT Brain Images: Application to Postoperative Hydrocephalic Scans

OBJECTIVE

Hydrocephalus is a medical condition in which there is an abnormal accumulation of cerebrospinal fluid (CSF) in the brain. Segmentation of brain imagery into brain tissue and CSF [before and after surgery, i.e., preoperative (pre-op) versus postoperative (post-op)] plays a crucial role in evaluating surgical treatment. Segmentation of pre-op images is often a relatively straightforward problem and has been well researched. However, segmenting post-op computational tomographic (CT) scans becomes more challenging due to distorted anatomy and subdural hematoma collections pressing on the brain. Most intensity- and feature-based segmentation methods fail to separate subdurals from brain and CSF as subdural geometry varies greatly across different patients and their intensity varies with time. We combat this problem by a learning approach that treats segmentation as supervised classification at the pixel level, i.e., a training set of CT scans with labeled pixel identities is employed.

METHODS

Our contributions include: 1) a dictionary learning framework that learns class (segment) specific dictionaries that can efficiently represent test samples from the same class while poorly represent corresponding samples from other classes; 2) quantification of associated computation and memory footprint; and 3) a customized training and test procedure for segmenting post-op hydrocephalic CT images.

RESULTS

Experiments performed on infant CT brain images acquired from the CURE Children's Hospital of Uganda reveal the success of our method against the state-of-the-art alternatives. We also demonstrate that the proposed algorithm is computationally less burdensome and exhibits a graceful degradation against a number of training samples, enhancing its deployment potential.

Unsupervised Myocardial Segmentation for Cardiac BOLD

A fully automated 2-D+time myocardial segmentation framework is proposed for cardiac magnetic resonance (CMR) blood-oxygen-level-dependent (BOLD) data sets. Ischemia detection with CINE BOLD CMR relies on spatio-temporal patterns in myocardial intensity, but these patterns also trouble supervised segmentation methods, the de facto standard for myocardial segmentation in cine MRI. Segmentation errors severely undermine the accurate extraction of these patterns. In this paper, we build a joint motion and appearance method that relies on dictionary learning to find a suitable subspace. Our method is based on variational pre-processing and spatial regularization using Markov random fields, to further improve performance. The superiority of the proposed segmentation technique is demonstrated on a data set containing cardiac phase-resolved BOLD MR and standard CINE MR image sequences acquired in baseline and ischemic condition across ten canine subjects. Our unsupervised approach outperforms even supervised state-of-the-art segmentation techniques by at least 10% when using Dice to measure accuracy on BOLD data and performs at par for standard CINE MR. Furthermore, a novel segmental analysis method attuned for BOLD time series is utilized to demonstrate the effectiveness of the proposed method in preserving key BOLD patterns.

Comprehensive review on endonasal endoscopic sinus surgery

Endonasal endoscopic sinus surgery is the standard procedure for surgery of most paranasal sinus diseases. Appropriate frame conditions provided, the respective procedures are safe and successful. These prerequisites encompass appropriate technical equipment, anatomical oriented surgical technique, proper patient selection, and individually adapted extent of surgery. The range of endonasal sinus operations has dramatically increased during the last 20 years and reaches from partial uncinectomy to pansinus surgery with extended surgery of the frontal (Draf type III), maxillary (grade 3-4, medial maxillectomy, prelacrimal approach) and sphenoid sinus. In addition there are operations outside and beyond the paranasal sinuses. The development of surgical technique is still constantly evolving. This article gives a comprehensive review on the most recent state of the art in endoscopic sinus surgery according to the literature with the following aspects: principles and fundamentals, surgical techniques, indications, outcome, postoperative care, nasal packing and stents, technical equipment.