Deep Learning-Based Image Registration in Dynamic Myocardial Perfusion CT Imaging

Registration of dynamic CT image sequences is a crucial preprocessing step for clinical evaluation of multiple physiological determinants in the heart such as global and regional myocardial perfusion. In this work, we present a deformable deep learning-based image registration method for quantitative myocardial perfusion CT examinations, which in contrast to previous approaches, takes into account some unique challenges such as low image quality with less accurate anatomical landmarks, dynamic changes of contrast agent concentration in the heart chambers and tissue, and misalignment caused by cardiac stress, respiration, and patient motion. The introduced method uses a recursive cascade network with a ventricle segmentation module, and a novel loss function that accounts for local contrast changes over time. It was trained and validated on a dataset of n = 118 patients with known or suspected coronary artery disease and/or aortic valve insufficiency. Our results demonstrate that the proposed method is capable of registering dynamic cardiac perfusion sequences by reducing local tissue displacements of the left ventricle (LV), whereas contrast changes do not affect the registration and image quality, in particular the absolute CT (HU) values of the entire CT sequence. In addition, the deep learning-based approach presented reveals a short processing time of a few seconds compared to conventional image registration methods, demonstrating its application potential for quantitative CT myocardial perfusion measurements in daily clinical routine.

Tuberculosis case-finding in Nicaragua: evaluation of routine activities in the control programme

SETTING

The new International Union against Tuberculosis and Lung Disease (IUATLD) tuberculosis strategy developed in the 1980s in Tanzania, Malawi and Mozambique, was simultaneously implemented in Nicaragua.

OBJECTIVE

Present results of case-finding, identify trends in incidence and limitations in case-finding and reporting.

DESIGN

Data are based upon the traditional reporting system until 1987, replaced as the programme was reorganized. Data were also collected directly from the Central Laboratory, Programme and Laboratory registers during supervision of health centres.

RESULTS

Quality control of sputum smears shows 1.8% discordance between peripheral and central laboratories. Notification rate of smear-positive tuberculosis declined 1.7% yearly 1983-1991 and 2.6% for all cases. Half of the patients are new smear-positive pulmonary cases, 40% smear-negative pulmonary cases. Relapses represent 11-13% of all smear-positive patients, children 7-30% of all cases. One-third of extrapulmonary tuberculosis cases are pleural effusions, another third lymphadenitis. 41% of adult patients entered as smear-negative in the programme had no smear reported in the laboratory.

CONCLUSIONS

Quality control of sputum smears was established and the reporting system improved in spite of adverse conditions. Notification rate declined gradually. Smears should be done in all patients classified as smear-negative pulmonary tuberculosis.