Bimodal Automated Carotid Ultrasound Segmentation Using Geometrically Constrained Deep Neural Networks.

For asymptomatic patients suffering from carotid stenosis, the assessment of plaque morphology is an important clinical task which allows monitoring of the risk of plaque rupture and future incidents of stroke. Ultrasound Imaging provides a safe and non-invasive modality for this, and the segmentation of media-adventitia boundaries and lumen-intima boundaries of the Carotid artery form an essential part in this monitoring process. In this paper, we propose a novel Deep Neural Network as a fully automated segmentation tool, and its application in delineating both the media-adventitia boundary and the lumen-intima boundary. We develop a new geometrically constrained objective function as part of the Network's Stochastic Gradient Descent optimisation, thus tuning it to the problem at hand. Furthermore, we also apply a bimodal fusion of amplitude and phase congruency data proposed by us in previous work, as an input to the network, as the latter provides an intensity-invariant data source to the network. We finally report the segmentation performance of the network on transverse sections of the carotid. Tests are carried out on an augmented dataset of 81,000 images, and the results are compared to other studies by reporting the DICE coefficient of similarity, modified Hausdorff Distance, sensitivity and specificity. Our proposed modification is shown to yield improved results on the standard network over this larger dataset, with the advantage of it being fully automated. We conclude that Deep Neural Networks provide a reliable trained manner in which carotid ultrasound images may be automatically segmented, using amplitude data and intensity invariant phase congruency maps as a data source.

Thermographic patterns of the upper and lower limbs: baseline data.

Objectives. To collect normative baseline data and identify any significant differences between hand and foot thermographic distribution patterns in a healthy adult population. Design. A single-centre, randomized, prospective study. Methods. Thermographic data was acquired using a FLIR camera for the data acquisition of both plantar and dorsal aspects of the feet, volar aspects of the hands, and anterior aspects of the lower limbs under controlled climate conditions. Results. There is general symmetry in skin temperature between the same regions in contralateral limbs, in terms of both magnitude and pattern. There was also minimal intersubject temperature variation with a consistent temperature pattern in toes and fingers. The thumb is the warmest digit with the temperature falling gradually between the 2nd and the 5th fingers. The big toe and the 5th toe are the warmest digits with the 2nd to the 4th toes being cooler. Conclusion. Measurement of skin temperature of the limbs using a thermal camera is feasible and reproducible. Temperature patterns in fingers and toes are consistent with similar temperatures in contralateral limbs in healthy subjects. This study provides the basis for further research to assess the clinical usefulness of thermography in the diagnosis of vascular insufficiency.

Carotid ultrasound segmentation using radio-frequency derived phase information and gabor filters.

Ultrasound image segmentation is a field which has garnered much interest over the years. This is partially due to the complexity of the problem, arising from the lack of contrast between different tissue types which is quite typical of ultrasound images. Recently, segmentation techniques which treat RF signal data have also become popular, particularly with the increasing availability of such data from open-architecture machines. It is believed that RF data provides a rich source of information whose integrity remains intact, as opposed to the loss which occurs through the signal processing chain leading to Brightness Mode Images. Furthermore, phase information contained within RF data has not been studied in much detail, as the nature of the information here appears to be mostly random. In this work however, we show that phase information derived from RF data does elicit structure, characterized by texture patterns. Texture segmentation of this data permits the extraction of rough, but well localized, carotid boundaries. We provide some initial quantitative results, which report the performance of the proposed technique.

Hidden dangers revealed by misdiagnosed peripheral arterial disease using ABPI measurement.

AIM: The aim of this study was to compare ankle brachial indices (APBI) with pedal waveforms utilizing the continuous wave Doppler in a population with diabetes mellitus. METHODS: A prospective study design was employed to investigate the ABPI in a cohort of 49 people with type 2 diabetes mellitus. ABPI assessment was completed using a portable handheld Doppler and ankle pressures of <0.9 were taken as suggestive of peripheral arterial disease (PAD). Arterial spectral waveforms in each foot were also recorded and compared to the ABPI readings. RESULTS: Inconsistencies were identified between ABPIs and waveform interpretations in the study population. Approximately 35% of subjects had inconsistencies between their ABPI result and waveform interpretation in their right or left foot. CONCLUSIONS: Both ABPIs and Doppler waveforms should be used in the assessment of people with diabetes in order to screen for PAD. This would ensure an accurate assessment of PAD and would allow initiation of appropriate secondary risk factor control measures.

Exploiting gastrointestinal anatomy for organ classification in capsule endoscopy using locality preserving projections.

Capsule Endoscopy is a technique designed to wirelessly image the small intestine within the gastrointestinal (GI) tract. Its main drawback is the vast amount of images it generates per patient, necessitating long screening sessions by the clinician. Previous studies have proposed to partially facilitate this process by automatically segmenting the GI tract into its constituent organs, thus identifying the region of interest. In this work, we propose to exploit the anatomical structure of the GI tract when carrying out dimensionality reduction on visual feature vectors that describe the capsule images. To this end, we suggest a novel adaptation of a technique called Locality Preserving Projections, and results show that this achieves an improved performance in organ classification and segmentation, at no additional computational or memory cost.

Investigating linear superposition of multi-species neurotransmitter voltammetric measurements in-vitro.

Fast-Scan Cyclic Voltammetry (FSCV) is frequently used to monitor the concentrations of neurotransmitters in real-time. However, few studies have examined the issue of monitoring the concentration of multiple neurotransmitters at the same time, despite their coexistence at brain synapses. This stems from the fact that some neurotransmitters have relatively similar electrochemical profiles. In this work we use Factor Spaces to analyze the current signals obtained using FSCV for both individual and mixed solutions of neurotransmitters. It is shown that the behavior of the current signals during the interaction between the neurotransmitter species approaches the principle of superposition. This potentially results in a significant simplification in the way combined voltammetric data is interpreted. The performance of Principal Component Analysis in extracting suitable Factor Spaces is evaluated.