A machine learning technique is presented for assessing brain tumor progression by exploring six patients' complete
MRI records scanned during their visits in the past two years. There are ten MRI series, including diffusion tensor image
(DTI), for each visit. After registering all series to the corresponding DTI scan at the first visit, annotated normal and
tumor regions were overlaid. Intensity value of each pixel inside the annotated regions were then extracted across all of
the ten MRI series to compose a 10 dimensional vector. Each feature vector falls into one of three categories:normal,
tumor, and normal but progressed to tumor at a later time. In this preliminary study, we focused on the trend of brain
tumor progression during three consecutive visits, i.e., visit A, B, and C. A machine learning algorithm was trained using
the data containing information from visit A to visit B, and the trained model was used to predict tumor progression from
visit A to visit C. Preliminary results showed that prediction for brain tumor progression is feasible. An average of
80.9% pixel-wise accuracy was achieved for tumor progression prediction at visit C.
Respiratory motion causes problems of tumour localisation in radiotherapy treatment planning for lung cancer patients. We have developed a novel method of building patient specific motion models, which model the movement and non-rigid deformation of a lung tumour and surrounding lung tissue over the respiratory cycle. Free-breathing (FB) CT scans are acquired in cine mode, using 3 couch positions to acquire contiguous 'slabs' of 16 slices covering the region of interest. For each slab, 20 FB volumes are acquired over approx 20s. A reference volume acquired at Breath Hold (BH) and covering the whole lung, is non-rigidly registered to each of the FB volumes. The FB volumes are assigned a position in the respiratory cycle (PRC) calculated from the displacement of the chest wall. A motion model is then constructed for each slab, by fitting functions that temporally interpolate the registration results over the respiratory cycle. This can produce a prediction of the lung and tumour within the slab at any arbitrary PRC. The predictions for each of the slabs are then combined to produce a volume covering the whole region of interest. Results indicate that the motion modelling method shows considerable promise, offering significant improvement over current clinical practice, and potential advantages over alternative 4D CT imaging techniques. Using this framework, we examined and evaluated several different functions for performing the temporal interpolation. We believe the results of these comparisons will aid future model building for this and other applications.
Intensity based registration algorithms have proved to be accurate and robust for 3D-3D registration tasks. However, these methods utilise the information content within an image, and therefore their performance is hindered for image data that is sparse. This is the case for the registration of a single image slice to a 3D image volume. There are some important applications that could benefit from improved slice-to-volume registration, for example, the planning of magnetic resonance (MR) scans or cardiac MR imaging, where images are acquired as stacks of single slices. We have developed and validated an information based slice-to-volume registration algorithm that uses vector valued probabilistic images of tissue classification that have been derived from the original intensity images. We believe that using such methods inherently incorporates into the registration framework more information about the images, especially in images containing severe partial volume artifacts. Initial experimental results indicate that the suggested method can achieve a more robust registration compared to standard intensity based methods for the rigid registration of a single thick brain MR slice, containing severe partial volume artifacts in the through-plane direction, to a complete 3D MR brain volume.