Many research questions in dysphagia research require frame-by-frame annotation of anatomical landmarks visible in videofluorographs as part of the research workflow, which can be a tedious and error prone process. Such annotation is done manually using image analysis tools, is error prone, and characterized by poor rater reliability. In this thesis, a computer-assisted workflow that uses a point tracking technique based on the Kanade-Lucas-Tomasi tracker to semi-automate the annotation process, is developed and evaluated. Techniques to semi-automate the annotation process have been explored but none have had their research value demonstrated. To demonstrate the research value of a workflow based on point tracking in enhancing the annotation process, the developed workflow was used to perform an enhanced version of the recently published Coordinate Mapping swallowing study annotation technique to determine several swallowing parameters. Evaluation was done on eight swallow studies obtained from a variety of clinical sources and showed that the workflow produced annotation results with clinically insignificant spatial errors. The workflow has the potential to significantly enhance research processes that require frame-by-frame annotation of anatomical landmarks in videofluorographs as part of their data preparation steps, by reducing the total time required to annotate clinical cases

As computer technologies are developed rapidly in recent years, the ways to diagnose diseases also alter in clinical practice. Picture Archiving and Communication System (PACS) is an example that makes the diagnostic way for medical images change from view box to monitor. All types of medical images tend to be digitized and this makes it practical for helping doctor diagnose medical images via computer technologies. In this thesis, we propose a systemic approach to screen abnormalities in chest radiographs. First, a preprocess step identifying the view of chest radiographs is introduced. Second, a method is proposed for automated detection of gross abnormal opacity in chest radiographs. Third, computation time reduction is performed by subsampling. Finally, a computer-aided diagnosis system is implemented and evaluated in a clinical environment. Major technique used in this thesis is to analyze the projection profile obtained by projecting a chest image on to the mediolateral axis. The discriminant performance for each method is evaluated by using receiver operating characteristic (ROC) analysis. The results indicate that the proposed methods are potentially useful for screening abnormalities in chest radiographs.

Inflammatory muscle disease (myositis) is characterised by inflammation and a gradual increase in muscle weakness. Diagnosis typically requires a range of clinical tests, including magnetic resonance imaging of the thigh muscles to assess the disease severity. In the past, this has been measured by manually counting the number of muscles affected. In this work, a computer-aided analysis of inflammatory muscle disease is presented to help doctors diagnose and monitor the disease. Methods to quantify the level of oedema and fat infiltration from magnetic resonance scans are proposed and the disease quantities determined are shown to have positive correlation against expert medical opinion. The methods have been designed and tested on a database of clinically acquired T1 and STIR sequences, and are proven to be robust despite suboptimal image quality. General background information is first introduced, giving an overview of the medical, technical, and theoretical topics necessary to understand the problem domain. Next, a detailed introduction to the physics of magnetic resonance imaging is given. A review of important literature from similar and related domains is presented, with valuable insights that are utilised at a later stage. Scans are carefully pre-processed to bring all slices in to a common frame of reference and the methods to quantify the level of oedema and fat infiltration are defined and shown to have good positive correlation with expert medical opinion. A number of validation tests are performed with re-scanned subjects to indicate the level of repeatability. The disease quantities, together with statistical features from the T1-STIR joint histogram, are used for automatic classification of the disease severity. Automatic classification is shown to be successful on out of sample data for both the oedema and fat infiltration problems.

Le diagnostic assisté par ordinateur du cancer du sein devient de plus en plus une nécessité vu la croissance exponentielle du nombre de mammographies effectuées chaque année. En particulier, le diagnostic des masses mammaires et leur classification suscitent actuellement un grand intérêt. En effet, la complexité des formes traitées et la difficulté rencontrée afin de les discerner nécessitent l'usage de descripteurs appropriés. Dans ce travail, des méthodes de caractérisation adaptées aux pathologies mammaires sont proposées ainsi que l'étude de différentes méthodes de classification est abordée. Afin de pouvoir analyser les formes des masses, une étude concernant les différentes techniques de segmentation est réalisée. Cette étude nous a permis de nous orienter vers le modèle du level set basé sur la minimisation de l'énergie de la région évolutive. Une fois les images sont segmentées, une étude des différents descripteurs proposés dans la littérature est menée. Cependant, ces propositions présentent certaines limites telles que la sensibilité au bruit, la non invariance aux transformations géométriques et la description générale et imprécise des lésions. Dans ce contexte, nous proposons un nouveau descripteur intitulé les points terminaux du squelette (SEP) afin de caractériser les spiculations du contour des masses tout en respectant l'invariance à l'échelle. Un deuxième descripteur nommé la sélection des protubérances (PS) est proposé. Il assure de même le critère d'invariance et la description précise de la rugosité du contour. Toutefois, le SEP et le PS sont sensibles au bruit. Une troisième proposition intitulée le descripteur des masses spiculées (SMD) assurant une bonne robustesse au bruit est alors réalisée. Dans l'objectif de comparer différents descripteurs, une étude comparative entre différents classifieurs est effectuée. Les séparateurs à vaste marge (SVM) fournissent pour tous les descripteurs considérés le meilleur résultat de classification. Finalement, les descripteurs proposés ainsi que d'autres couramment utilisés dans le domaine du cancer du sein sont comparés afin de tester leur capacité à caractériser convenablement le contour des masses en question. La performance des trois descripteurs proposés et notamment le SMD est mise en évidence à travers les comparaisons effectuées. / The computer-aided diagnosis of breast cancer is becoming increasingly a necessity given the exponential growth of performed mammograms. In particular, the breast mass diagnosis and classification arouse nowadays a great interest. Indeed, the complexity of processed forms and the difficulty to distinguish between them require the use of appropriate descriptors. In this work, characterization methods suitable for breast pathologies are proposed and the study of different classification methods is addressed. In order to analyze the mass shapes, a study about the different segmentation techniques in the context of breast mass detection is achieved. This study allows to adopt the level set model based on minimization of region-scalable fitting energy. Once the images are segmented, a study of various descriptors proposed inthe literature is conducted. Nevertheless, these proposals have some limitations such as sensitivity to noise, non invariance to geometric transformations and imprecise and general description of lesions. In this context, we propose a novel descriptor entitled the Skeleton End Points descriptor (SEP) in order to better characterize spiculations in mass contour while respecting the scale invariance. A second descriptor named the Protuberance Selection (PS) is proposed. It ensures also the same invariance criterion and the accurate description of the contour roughness. However, SEP and PS proposals are sensitive to noise. A third proposal entitled Spiculated Mass Descriptor (SMD) which has good robustness to noise is then carried out. In order to compare different descriptors, a comparative study between different classifiers is performed. The Support Vector Machine (SVM) provides for all considered descriptors the best classification result. Finally, the proposed descriptors and others commonly used in the breast cancer field are compared to test their ability to characterize the considered mass contours.

Computed tomography (CT) imagery is an important weapon in the fight against lung cancer; various forms of lung cancer are routinely diagnosed from CT imagery. The growth of the suspect nodule is known to be a prognostic factor in the diagnosis of pulmonary cancer, but the change in other aspects of the nodule, such as its aspect ratio, density, spiculation, or other features usable for machine learning, may also provide prognostic information. We hypothesized that adding combined feature information from multiple CT image sets separated in time could provide a more accurate determination of nodule malignancy. To this end, we combined data from multiple CT images for individual patients taken from the National Lung Screening Trial. The resulting dataset was compared to equivalent datasets featuring single CT images for each patient. Feature reduction and normalization was performed as is standard. The highest accuracy achieved was 83.71% on a subset of features chosen by a combination of manual feature stability testing and the Correlation-based Feature Selection algorithm and classified by the Random Forests algorithm. The highest accuracy achieved with individual CT images was 81.00%, on a feature set consisting solely of the volume of the nodule in cubic centimeters.

Several computer-aided diagnostic (CAD) methods for solitary pulmonary nodules (SPNs) have been proposed, which can be divided into two major categories: (1) the morphometric CT method, and (2) the perfusion CT method. The first goal of this work is to introduce a neural network-based CAD method of lung nodule diagnosis by combining morphometry and perfusion characteristics by perfusion CT. The proposed approach has the following distinctive features. Firstly, this work develops a very efficient semi-automatic procedure to segment entire nodules. Secondly, reliable nodule classification can be achieved by using only two time-point perfusion CT feature measures (precontrast and 90 s). This greatly reduces the amount of radiation exposure to patients and the data processing time. As demonstrated in previous work, classification tuberculomas from malignancies has been considered to be a challenging task. However the diagnosis accuracy for tuberculomas reaches 92.9% by applying the proposed CAD method. Another goal of this work is, by investigating the relative merits of 2D and 3D methods, to develop a two-stage approach that combines the simplicity of 2D and the accuracy of 3D methods. Experimental results show statistically significant differences between the diagnostic accuracy of 2D and 3D methods. The results also show that with a very minor drop in diagnostic performance the two-stage approach can significantly reduce the number of nodules needed to be processed by the 3D method and thus alleviates the computational demand.

Coronary atherosclerosis is one of the leading cause of mortality in developed countries, and is increasingly diagnosed via X-ray computed tomography. Due to the large resulting volume of data, recent research has been directed towards developing automated methods of screening CT scans for coronary atherosclerosis. This task typically consists of lumen extraction, plaque detection, plaque quantification, and material discrimination. In this paper, we describe a novel set of techniques for accomplishing the first three steps, which aim to provide higher precision than previous efforts. We also discuss how such a high-precision detection and quantification system could be used to significantly improve on the state of the art in material discrimination. Our methods extract lumen for 71.2% of centreline points, detect plaque with a detection sensitivity of 67% on CTA reference data, and quantify plaque with a linear weighted kappa coefficient of 0.08.

No description available.

No description available.

This paper examines the use of convolutional neural networks to classify Covid-19 in chest radiographs. Three network architectures are compared: VGG16, ResNet-50, and DenseNet-121 along with preprocessing methods which include contrast limited adaptive histogram equalization and non-local means denoising. Chest radiographs from patients with healthy lungs, lung cancer, non-Covid pneumonia, tuberculosis, and Covid-19 were used for training and testing. Networks trained using radiographs that were preprocessed using contrast limited adaptive histogram equalization and non-local means denoising performed better than those trained on the original radiographs. DenseNet-121 performed slightly better in terms of accuracy, performance, and F1 score than all other networks but was not found to be statistically better performing than VGG16.