A Framework for Automatic Morphological Feature Extraction and Analysis of Abdominal Organs in MRI Volumes

Liver shape analysis using statistical parametric maps at population scale

BACKGROUND

Morphometric image analysis enables the quantification of differences in the shape and size of organs between individuals.

METHODS

Here we have applied morphometric methods to the study of the liver by constructing surface meshes from liver segmentations from abdominal MRI images in 33,434 participants in the UK Biobank. Based on these three dimensional mesh vertices, we evaluated local shape variations and modelled their association with anthropometric, phenotypic and clinical conditions, including liver disease and type-2 diabetes.

RESULTS

We found that age, body mass index, hepatic fat and iron content, as well as, health traits were significantly associated with regional liver shape and size. Interaction models in groups with specific clinical conditions showed that the presence of type-2 diabetes accelerates age-related changes in the liver, while presence of liver fat further increased shape variations in both type-2 diabetes and liver disease.

CONCLUSIONS

The results suggest that this novel approach may greatly benefit studies aiming at better categorisation of pathologies associated with acute and chronic clinical conditions.

Maximally stable extremal regions-based algorithm for automatic interpretation of disc-diffusion antibiotic sensitivity test

Antibiotic resistance causes a major threat to patients suffering from infectious diseases. Accurate and timely assessment of Antibiotic Susceptibility Test (AST) is of great importance to ensure adequate treatment for patients and for epidemiological monitoring. Disc Diffusion Test (DDT) is a standard and widely used method for AST. Manual interpretation of DDT results is a tedious task and susceptible to human errors. Computer vision-based automated interpretation of DDT results will speed up the process and reduces the manpower requirement. This would assist the physician to initiate the antibiotic treatment for the patients on time and results in saving the patient's life. The crucial step in automatic interpretation of DDT result is to measure and present the diameter of zone of inhibition without manual intervention. The existing methods require manual interventions at various stages during inhibition zone diameter measurement for some typical cases. This issue is addressed in the present work through maximally stable extremal regions (MSER) based algorithm. Dataset consisting of 60 agar plate images that includes different agar medium, images having different resolution and visual quality is used to validate the proposed method. Experimental results demonstrated that there is a strong correlation between standard method and the proposed method.

Improving Automatic Renal Segmentation in Clinically Normal and Abnormal Paediatric DCE-MRI via Contrast Maximisation and Convolutional Networks for Computing Markers of Kidney Function

There is a growing demand for fast, accurate computation of clinical markers to improve renal function and anatomy assessment with a single study. However, conventional techniques have limitations leading to overestimations of kidney function or failure to provide sufficient spatial resolution to target the disease location. In contrast, the computer-aided analysis of dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) could generate significant markers, including the glomerular filtration rate (GFR) and time-intensity curves of the cortex and medulla for determining obstruction in the urinary tract. This paper presents a dual-stage fully modular framework for automatic renal compartment segmentation in 4D DCE-MRI volumes. (1) Memory-efficient 3D deep learning is integrated to localise each kidney by harnessing residual convolutional neural networks for improved convergence; segmentation is performed by efficiently learning spatial-temporal information coupled with boundary-preserving fully convolutional dense nets. (2) Renal contextual information is enhanced via non-linear transformation to segment the cortex and medulla. The proposed framework is evaluated on a paediatric dataset containing 60 4D DCE-MRI volumes exhibiting varying conditions affecting kidney function. Our technique outperforms a state-of-the-art approach based on a GrabCut and support vector machine classifier in mean dice similarity (DSC) by 3.8% and demonstrates higher statistical stability with lower standard deviation by 12.4% and 15.7% for cortex and medulla segmentation, respectively.

3D Deep Learning for Anatomical Structure Segmentation in Multiple Imaging Modalities

Accurate, quantitative segmentation of anatomical structures in radiological scans, such as Magnetic Resonance Imaging (MRI) and Computer Tomography (CT), can produce significant biomarkers and can be integrated into computer-aided assisted diagnosis (CADx) systems to support the interpretation of medical images from multi-protocol scanners. However, there are serious challenges towards developing robust automated segmentation techniques, including high variations in anatomical structure and size, the presence of edge-based artefacts, and heavy un-controlled breathing that can produce blurred motion-based artefacts. This paper presents a novel computing approach for automatic organ and muscle segmentation in medical images from multiple modalities by harnessing the advantages of deep learning techniques in a two-part process. (1) a 3D encoder-decoder, Rb-UNet, builds a localisation model and a 3D Tiramisu network generates a boundary-preserving segmentation model for each target structure; (2) the fully trained Rb-UNet predicts a 3D bounding box encapsulating the target structure of interest, after which the fully trained Tiramisu model performs segmentation to reveal detailed organ or muscle boundaries. The proposed approach is evaluated on six different datasets, including MRI, Dynamic Contrast Enhanced (DCE) MRI and CT scans targeting the pancreas, liver, kidneys and psoas-muscle and achieves quantitative measures of mean Dice similarity coefficient (DSC) that surpass or are comparable with the state-of-the-art. A qualitative evaluation performed by two independent radiologists verified the preservation of detailed organ and muscle boundaries.