Computer-aided localisation, segmentation and quantification of focal liver lesions in contrast-enhanced ultrasound

The research presented in this thesis focuses on applications of Contrast Enhanced Ultrasound (CEUS) imaging and is coordinated to address current clinical requirements in the assessment, quantification and evaluation of liver cancer and in particular focal liver lesions (FLLs). The main outcomes of this research are methods to assist radiologists with automating these routinely performed manual image interpretation tasks, with the intention of supporting them to make their diagnostic decisions faster, more easily and with greater confidence. Such automatic analysis is challenging mainly because of the relative motion between the ultrasound transducer and the liver, the physiological motion of the patient and the dramatic intensity changes over time caused by the contrast-enhancing agents intravenously injected during a CEUS examination. The work described in this thesis can be divided into three principal themes. These are addressed in turn below. Firstly, a set of methods are proposed to assist in automating initialisation tasks required for the offline assessment of data acquired during CEUS liver scans. These tasks relate to the delineation of the area comprising the ultrasonographic image, the identification of the optimal reference frame for initialising an FLL, as well as the segmentation of the FLL boundaries on this frame. The potential clinical value of the proposed methods is that they can lead to easier and faster assessment of FLLs, whilst producing results less dependent on the human initialisation and hence improving the repeatability and reproducibility of the assessment of the examination and increasing the confidence of radiologists when making a diagnosis. Secondly, a variety of methods are investigated to estimate the motion observed within the ultrasonographic image of CEUS screening recordings and then compensate for this, allowing for an accurate quantification of the perfusion of tissue regions. Obtaining a perfusion curve for an image region, without compensating for the observed motion, may lead to erroneous diagnostic results as the specified image region may correspond to different tissue along the video sequence. Quantitative evaluation of the presented methods demonstrates their potential as reliable real-time motion compensation methods for such recordings. Finally, an alternative fully automatic method for the identification and localisation of potential malignancies is proposed. For such identification, and hence distinction between cases that include potentially malignant and benign lesions, an innovative assessment of the global spatial configuration of local variations of perfusion curves is presented. For the localisation of tissue regions of potential malignancy, a novel feature is proposed that encompasses spatio-temporal information (Le. the combination of both the variation in these local perfusion curves and the location they relate to) to cluster together neighbouring regions with similar dynamic behaviour. The clinical value of the identification part is the early diagnosis of an FLL's type and the possibility for the discharge of patients with benign FLLs, leading to less distress to the patients and their families, as well as reduced healthcare costs. Additionally, the localisation part assists in enhancing the radiologist's awareness of tissue regions with potentially malignant behaviour, as well as providing effortless localisation of such regions allowing for an objective initialisation of computer-aided segmentation methods improving the repeatability and reproducibility of the assessment of CEUS data. The key findings of this research indicate that: i) the optimal reference frame can be reliably identified in a fully automatic and deterministic manner, ii) the segmentation of an F LL can be performed in a rapid semi-automatic manner, which produces results that are, at worst, of comparable consistency as different manual annotations, iii) the apparent observed motion can be compensated in real-time, either locally or globally, and a simple translation is sufficient to achieve this, iv) the distinction between benign and malignant lesions can be performed in a fully automatic and deterministic manner, without missing a single malignancy, and v) potential malignancies can be localised reliably in a fully automatic manner. Quantitative analysis of all results on real clinical data, from a multi-centre study, is used to evaluate the level of confidence of the decision of the proposed methods and demonstrates the value of these methods in a diverse dataset acquired using the protocol of current standard care. A system incorporating the proposed methods could improve the current clinical practice for assessing, quantifying and evaluating FLLs in CEUS recordings. Specifically, it would be beneficial to radiologists, for cancer research, providing easier and faster assessment of FLLs whilst producing results less dependent on the human initialisation and therefore increasing the confidence of radiologists in their diagnostic decisions.