In this thesis, topics relating to the optimization of high-throughput pipelines used for imaging are discussed. In particular, different levels of implementation, i.e., conceptual, software, and... Show moreIn this thesis, topics relating to the optimization of high-throughput pipelines used for imaging are discussed. In particular, different levels of implementation, i.e., conceptual, software, and hardware, are discussed and the thesis outlines how advances on each level need to be made to make gains in computationally demanding imaging applications. Chapter 2 concerns the implementation of real-time segmentation of X-ray computed tomography (CT). Chapter 3 concerns the end-to-end optimization of various CT workflows by using auto-differentiation frameworks. Chapter 4 concerns a novel pruning method for neural network to significantly increase the speed of convolutional neural networks (CNNs). Chapter 5 comprises a benchmark study of optimization algorithms for tuning GPU kernels, and introduces a novel graph-based approach to quantify search space difficulty. Chapter 6 introduces a novel model to improve the energy efficiency of GPUs. Show less
This thesis aims to improve the understanding and identification of the ventricular tachycardia substrate in patients with right ventricular tachycardia. An isolated epicardial right ventricular... Show moreThis thesis aims to improve the understanding and identification of the ventricular tachycardia substrate in patients with right ventricular tachycardia. An isolated epicardial right ventricular outflow tract scar is described in high level endurance athletes. Novel parameters such as endocardial unipolar voltage, transmural activation time and CT heterogeneity may help to guide substrate mapping and ablation. Implementing these techniques in current clinical practice may improve the identification and treatment of ventricular tachycardia substrates in right ventricular cardiomyopathies. Show less
Radiography is an important technique to inspect objects, with applications in airports and hospitals. X-ray imaging is also essential in industry, for instance in food safety checks for the... Show moreRadiography is an important technique to inspect objects, with applications in airports and hospitals. X-ray imaging is also essential in industry, for instance in food safety checks for the presence of foreign objects. Computed tomography (CT) enables more accurate visualizations of an object in 3D, but requires more computation time. Spectral X-ray imaging is an important recent development to optimize these conflicting goals of speed and accuracy. This technique enables separation of detected X-ray photons in terms of energy. More information can be extracted from spectral images, which allows for better separation of materials. Deep learning is another important recent technique enabling machines to quickly carry out processing tasks, by training these with large volumes of data for these specific tasks.In this dissertation we present new processing methods that use spectral imaging and machine learning, with a special focus on industrial processes. We design a workflow using CT to efficiently generate large volumes of machine learning training data. In addition, we develop a compression method for efficient processing of large volumes of spectral data and two new spectral CT methods to produce more accurate reconstructions. The presented methods are designed for effective use in industry. Show less
A chronic subdural hematoma (CSDH) is an intracranial bleeding between the outer two meninges of the brain due to rupture of cerebral veins or an inflammatory response in the subdural space.... Show moreA chronic subdural hematoma (CSDH) is an intracranial bleeding between the outer two meninges of the brain due to rupture of cerebral veins or an inflammatory response in the subdural space. Elderly patients using anti-thrombotic therapy are at higher risk for hematoma development. A rise in CSDH incidence is expected because of the aging population and increase in anti-thrombotic therapy use due to cardiovascular disease. To date, no treatment guideline exists regarding optimal CSDH treatment. Surgery with subdural drainage is the mainstay treatment. However, due to relevant surgical complications, a recurrence risk up to 30% and increased mortality in this vulnerable patient population, corticosteroid therapy is being administered as an alternative or adjuvant treatment modality.In this thesis we have shown that surgical treatment results in significantly better treatment outcome than medicinal approach by the corticosteroid dexamethasone in a retrospective study (chapter 2) as well as in a randomized controlled trial (chapter 3 and 4). Furthermore, we revealed radiological markers that are of prognostic value to predict treatment outcome after surgery (chapter 5) and dexamethasone therapy (chapter 6) in symptomatic CSDH patients. Show less
With the rising global health burden of aortic valve diseas and growing awareness of the consequences of severe AS, more patients are expected to be referred for aortic valve replacement.... Show moreWith the rising global health burden of aortic valve diseas and growing awareness of the consequences of severe AS, more patients are expected to be referred for aortic valve replacement. Multimodality imaging remains of paramount importance for proper patient selection, determining optimal timing of intervention and in the evaluation of therapy. For risk stratification and defining optimal timing of intervention, conventional and advanced echocardiography and computed tomography are crucial. Conventional echocardiography can be used to assess extra-aortic valvular cardiac damage in patients with severe AS. On top of conventional echocardiography, advanced echocardiography can provide additional insights. Left ventricular GLS by speckle tracking echocardiography has been suggested as a more sensitive marker of LV systolic dysfunction. LV GLS may be of help to define more optimal timing of intervention in asymptomatic patients with severe AS. Also, LV GLS may be of incremental value on top of conventional echocardiographic parameters for the assessment of cardiac injury. For the evaluation of prothesis function and durability after aortic valve implantation and detection of possible (late) complications, echocardiography is the mainstay imaging modality. Also, both conventional and advanced echocardiography can provide additional information on the effects of therapy on LV function and remodelling. Show less
The aim of this thesis is to determine diagnostic performance of machine learning in differentiating between atypical cartilaginous tumor (ACT) and high-grade chondrosarcoma (CS) based on radiomic... Show moreThe aim of this thesis is to determine diagnostic performance of machine learning in differentiating between atypical cartilaginous tumor (ACT) and high-grade chondrosarcoma (CS) based on radiomic features derived from magnetic resonance imaging (MRI) and computed tomography (CT). In chapter 2, the concept of radiomics of musculoskeletal sarcomas is introduced and a systematic review on radiomic feature reproducibility and validation strategies is conducted. In chapter 3, a preliminary study is performed to investigate the performance of MRI radiomics-based machine learning in discriminating ACT from high-grade CS, using a single-center cohort, in comparison with an expert radiologist. In chapter 4, the influence of interobserver segmentation variability on the reproducibility of CT and MRI radiomic features of cartilaginous bone tumors is assessed. In chapter 5, the performance of CT radiomics-based machine learning in discriminating ACT from high-grade CS of long bones is determined and validated using independent data from a multicenter cohort, compared to an expert radiologist. In chapter 6, the performance of MRI radiomics-based machine learning in differentiating between ACT and grade II CS of long bones is determined and validated using independent data from a multicenter cohort, in comparison with an expert radiologist. Finally, in chapter 7, the main results and implications of this thesis are summarized and discussed. Show less
Venous thromboembolism (VTE) encompasses pulmonary embolism (PE) and deep vein thrombosis (DVT). DVT most commonly occurs in the deep veins of the lower extremity but can also occur in the veins of... Show moreVenous thromboembolism (VTE) encompasses pulmonary embolism (PE) and deep vein thrombosis (DVT). DVT most commonly occurs in the deep veins of the lower extremity but can also occur in the veins of upper extremity, abdomen and cerebrum. As symptoms of VTE are nonspecific, the diagnosis of VTE is based on diagnostic tests, including clinical decision rules (CDR), D-dimer tests and imaging. Although the diagnostic management of VTE has greatly advanced in recent years with the introduction of novel CDRs and high-sensitive D-dimer tests, the diagnosis may still be challenging in certain settings. The latter is mainly caused by the indirect way of thrombus visualisation by current imaging tests, such as by showing incompressibility with compression ultrasonography (CUS) or a filling defect on contrast-enhanced computed tomography (CT) or magnetic resonance imaging (MRI).This thesis focuses on challenging settings for diagnosing VTE, including suspected recurrent ipsilateral DVT, upper extremity DVT, cerebral vein thrombosis and portal vein thrombosis. We studied a novel imaging technique called Magnetic Resonance Non-Contrast Thrombus Imaging (MR-NCTI) and its application in these different VTE settings. Show less
The objectives of this thesis were to elucidate the pathogenesis of metabolic heart disease, evaluate the associated changes in myocardial structure and contractile function, and determine the long... Show moreThe objectives of this thesis were to elucidate the pathogenesis of metabolic heart disease, evaluate the associated changes in myocardial structure and contractile function, and determine the long-term prognostic implications of subclinical myocardial dysfunction on all-cause mortality. Show less
This thesis showed that cardiac computed tomography may provide additional geometrical insights in valvular heart disease and cardiac remodeling. Further, computed tomography provides accurate... Show moreThis thesis showed that cardiac computed tomography may provide additional geometrical insights in valvular heart disease and cardiac remodeling. Further, computed tomography provides accurate anatomical images of the heart that may assist the planning of minimal invasive transcatheter cardiac procedures. Show less
Cardiovascular diseases are the leading cause of mortality and morbidity in the current era. Current guidelines base their recommendations for diagnosis and management of cardiovascular diseases on... Show moreCardiovascular diseases are the leading cause of mortality and morbidity in the current era. Current guidelines base their recommendations for diagnosis and management of cardiovascular diseases on several important parameters such as left ventricular (LV) dimension and function, presence of coronary artery disease (CAD) and valve function. Accurate assessment of these parameters is therefore essential for patients with or at risk of cardiovascular diseases and requires the use of invasive and non-invasive testing. Non-invasive testings are in principle preferable, especially for a first-line approach, being safer and generally widely available and easy to perform. The present thesis highlights the use of non-invasive imaging modalities, namely cardiac computed tomography and advanced echocardiography analysis (speckle tracking and calibrated integrated backscatter) to diagnosis and guide the treatment of various cardiovascular diseases. Show less
This thesis examines how computer software can be used to analyse medical images of an aseptically loosening hip prosthesis, and subsequently to plan and guide a minimally invasive cement injection... Show moreThis thesis examines how computer software can be used to analyse medical images of an aseptically loosening hip prosthesis, and subsequently to plan and guide a minimally invasive cement injection procedure to stabilize the prosthesis. We addressed the detection and measurement of periprosthetic bone lesions from CT image volumes. Post-operative CTs of patients treated at our institution were analysed. We developed tissue classification algorithms that automatically label periprosthetic bone, cement and fibrous interface tissue. An existing particle-based multi-material meshing algorithm was adapted for improved Finite Element model creation. We then presented HipRFX, a proof-of-concept software tool for planning and guidance during percutaneous cement refixation procedures. Show less
The role of computed tomography in the development of transcatheter aortic valve implantation (TAVI)has been crucial. Post-TAVI computed tomography data has helped us to understand the underlying... Show moreThe role of computed tomography in the development of transcatheter aortic valve implantation (TAVI)has been crucial. Post-TAVI computed tomography data has helped us to understand the underlying mechanisms of specific complications related to TAVI. The future of TAVI is promising in subgroups of patients that would intialy have been excluded from this procedure. In this future, the role of imaging is pivotal Show less
The primary objective of this dissertation is to determine the diagnostic performance of 320-row CTA for cardiac applications, particularly in the assessment of significant coronary stenosis in... Show moreThe primary objective of this dissertation is to determine the diagnostic performance of 320-row CTA for cardiac applications, particularly in the assessment of significant coronary stenosis in patients with known or suspected CAD. It was shown that 320-row CTA allows accurate, non-invasive assessment of significant CAD and global left ventricular function in patients with suspected CAD, as well as in patients with a history of revascularization. Furthermore, the prognostic value of CTA and its role in clinical management of patients with suspected CAD were investigated. The potential of CTA to serve as a gatekeeper prior to CTA was explored. It was shown that CTA has the potential to serve as a gatekeeper for invasive coronary angiography in patients with a low-to-intermediate pre-test likelihood of obstructive CAD. Subsequently, it was shown that the assessment of left ventricular function analysis on CTA may further enhance risk stratification beyond the assessment of degree of stenosis. Finally, in patients with type 2 diabetes mellitus, the combined presence of increased waist circumference and elevated plasma triglyceride levels was shown to translate into an increased likelihood of CAD on CTA and may therefore serve as a practical clinical biomarker to improve risk stratification. Show less
The presence of a decreased left ventricular (LV) function after myocardial infarction has demonstrated to be of considerable clinical importance. In this thesis, the role of 2D echocardiography to... Show moreThe presence of a decreased left ventricular (LV) function after myocardial infarction has demonstrated to be of considerable clinical importance. In this thesis, the role of 2D echocardiography to evaluate LV function in ischemic heart disease was investigated. In the first part of the thesis, recently introduced echocardiographic parameters to describe LV function were studied and their importance for prognosis after myocardial infarction was evaluated. In addition, in the second part of the thesis, the role for echocardiography in the decision making around advanced treatment options in heart failure such as cardiac resynchronization therapy (CRT) and cardiac surgery was explored. Show less
The Lambert-Eaton myasthenic syndrome (LEMS) is a rare autoimmune disorder in which patients have muscle weakness and autonomic dysfunction. Half of the patients have small cell lung cancer (SCLC).... Show moreThe Lambert-Eaton myasthenic syndrome (LEMS) is a rare autoimmune disorder in which patients have muscle weakness and autonomic dysfunction. Half of the patients have small cell lung cancer (SCLC). SCLC is a very aggressive lung tumour with a median survival of only 9 months. Quick discovery and treatment is of uttermost importance for both patient and physician to improve the chance of cure. SCLC-LEMS is related to smoking, a higher age at onset and weight loss. The clinical symptoms develop more quickly and more severely if the LEMS is related to SCLC. The discovery of SOX antibodies is described specific for SCLC-LEMS. Based on simple epidemiological and clinical parameters, we created the DELTA-P score and validated it in an independent second cohort. The DELTA-P score predicts already shortly after onset of symptoms with 95% accuracy who has or will have an SCLC. The reliability of imaging to detect SCLC is analyzed in 100 patients, creating a new screening protocol. For other paraneoplastic syndromes, screening guidelines are updated. SOX and Hu antibodies are also found in 43% of SCLC patients (without LEMS). Combination of different antibodies might lead to reliable screening strategies in high-risk patients. Show less
Cochlear implants (CIs) are a well accepted treatment for hearing impaired people. In pre- and postoperative assessment of CI-candidates imaging plays an important role to analyze anatomy, rule out... Show moreCochlear implants (CIs) are a well accepted treatment for hearing impaired people. In pre- and postoperative assessment of CI-candidates imaging plays an important role to analyze anatomy, rule out pathology and determine intracochlear positioning and integrity of the implant. Developments in CI-design, differences in surgical approach and broadening of treatment indications have raised new questions to radiologists, which were the subject of several studies described in this thesis. For optimal, a-traumatic positioning of a CI precise information about the inner ear anatomy is mandatory. We describe the development, validation and application of a method for 3-dimensional medical image exploration of the inner ear. This renders a tool to obtain cochlear dimensions on clinical computer tomography (CT) images. This will be useful for patientspecific implantplanning. It also shows an anatomical substrate for cochlear trauma during insertion. For postoperative imaging we studied the value of multislice-CT for optimal visualization of the implant within the cochlea. Its role to evaluate operation technique and electrode design, to study frequency mapping and to assess cochlear trauma is discussed. Moreover an international consensus for an objective cochlear framework is presented, forming a common ground for clear and easy exchange of findings in scientific and clinical studies. Show less
In this thesis the assessment of ultrasonography (US) and Computed Tomography (CT) in the diagnostic strategy of suspected appendicitis is presented. The first study showed that focused single... Show moreIn this thesis the assessment of ultrasonography (US) and Computed Tomography (CT) in the diagnostic strategy of suspected appendicitis is presented. The first study showed that focused single-detector helical CT as well as graded compression US performed in a general community teaching hospital by both body imaging radiologists and general radiology staff members have a similar accuracy for the diagnosis of acute appendicitis. A second study showed that in interpreting CT images the expertise of the attending radiologist should be considered. A third study showed that gender seems to affect the accuracy of US and CT in patients suspected of acute appendicitis. A fourth study showed that US as a sole imaging tool is of limited value both in women with unequivocal and in women with equivocal signs of appendicitis. A fifth study showed that US and CT implemented in a diagnostic pathway yields a high diagnostic accuracy for acute appendicitis without adverse events due to delay in treatment. A sixth study showed that for a majority of the surgeons, the diagnosis of acute appendicitis is based on clinical signs and symptoms. US and CT can be valuable in diagnosing appendicitis but further cooperation between surgeons and radiologists is required. Show less
Current non-invasive detection of coronary artery disease (CAD) is based on demonstration of ischemia using stress-rest imaging: this is an indirect way of identifying CAD by demonstration of the... Show moreCurrent non-invasive detection of coronary artery disease (CAD) is based on demonstration of ischemia using stress-rest imaging: this is an indirect way of identifying CAD by demonstration of the hemodynamic consequences rather than direct visualization of the obstructive lesions in the coronary arteries. Multi-slice computed tomography (MSCT) has recently emerged as an extremely rapidly developing non-invasive imaging modality, which allows anatomical imaging of the coronary arteries, or non-invasive coronary angiography. In addition, total plaque burden, plaque morphology and (to some extent) plaque constitution can be assessed by MSCT. The technique also provides information on resting left ventricular systolic function, and possibly resting perfusion. Ideally, stress function and perfusion should also be evaluated, since this would allow detection of ischemia and would complete the picture on CAD. However, this is not routinely performed, since sequential acquisitions are associated with high radiation doses and thus pose a limitation for cardiovascular applications of MSCT. It is anticipated that, with reduction in radiation, MSCT may become an important player in the diagnostic and prognostic workup of patients with known or suspected CAD. Show less
Various non-invasive imaging techniques are available for the diagnosis of coronary artery disease (CAD). Multi-slice computed tomography (MSCT) is an upcoming technique that allows direct... Show moreVarious non-invasive imaging techniques are available for the diagnosis of coronary artery disease (CAD). Multi-slice computed tomography (MSCT) is an upcoming technique that allows direct visualization of the coronary arteries. Apart from the assessment of atherosclerosis, MSCT can also provide important information on the global and regional left ventricular (LV) function. However, it should be realized that the hemodynamic consequences of atherosclerosis can not be obtained by MSCT imaging, and that functional testing, with for example nuclear imaging, will remain necessary to determine therapeutic strategy. CAD is the most common cause of chronic heart failure. Recently, cardiac resynchronization therapy (CRT) has become implemented in the treatment of patients with severe heart failure. Although the improvement in systolic function after CRT implantation can be considerable, 20% to 30% of patients do not respond to CRT. It has been shown that the presence of LV dyssynchrony is an important predictor of response to CRT. Gated SPECT allows not only the assessment of myocardial perfusion (scar tissue and viable myocardium) but also the evaluation of LV dyssynchrony. As many patients with heart failure undergo nuclear imaging with SPECT, integrated assessment of LV dyssynchrony, viability and scar tissue may be an attractive option. Show less