PET-CT scans using 18F-FDG are increasingly used to detect cancer, but interpretation can be challenging due to non-specific uptake and complex anatomical structures nearby. To aide this process, we investigate the potential of automated detection of lesions in 18F-FDG scans using deep learning tools. A 5-layer convolutional neural network (CNN) with 2x2 kernels, rectified linear unit (ReLU) activations and two dense layers was trained to detect cancerous lesions in 2D axial image segments from PET scans. Pre-contoured scans from a retrospective cohort study of 480 oesophageal cancer patients were split 80:10:10 into training, validation and test sets. These were then used to generate a total of ~14000 45×45 pixel image segments, where tumor present segments were centered on the marked lesion, and tumor absent segments were randomly located outside the marked lesion. ROC curves generated from the training and validation datasets produced an average AUC of ~<95%.
Accurate, Respiratory Motion Modelling of the abdominal-thoracic organs serves as a pre-requisite for motion correction of Nuclear Medicine (NM) Images. Many respiratory motion models to date build a static correspondence between a parametrized external surrogate signal and internal motion. Mean drifts in respiratory motion, changes in respiratory style and noise conditions of the external surrogate signal motivates a more adaptive approach to capture non-stationary behavior. To this effect we utilize the application of our novel Kalman model with an incorporated expectation maximization step to allow adaptive learning of model parameters with changing respiratory observations. A comparison is made with a popular total least squares (PCA) based approach. It is demonstrated that in the presence of noisy observations the Kalman framework outperforms the static PCA model, however, both methods correct for respiratory motion in the computational anthropomorphic phantom to < 2mm. Motion correction performed on 3 dynamic MRI patient datasets using the Kalman model results in correction of respiratory motion to ≈ 3mm.
Nuclear Medicine (NM) imaging serves as a powerful diagnostic tool for imaging of biochemical and physiological
processes in vivo. The degradation in spatial image resolution caused by the often irregular respiratory motion
must be corrected to achieve high resolution imaging. In order perform motion correction more accurately, it
is proposed that patient motion obtained from 4D MRI can be used to analyse respiratory motion. To extract
motion from the dynamic MRI dataset an organ wise intensity based affine registration framework is proposed
and evaluated. Comparison of the resultant motion obtained within selected organs is made against an open
source free form deformation algorithm. For validation, the correlation of the results of both techniques to a
previous study of motion in 20 patients is found. Organwise affine registration correlates very well (r≈0:9)
with a previous study (Segars et al., 2007)1 whilst free form deformation shows little correlation (r ≈ 0:3). This
increases the confidence of the organ wise affine registration framework being an effective tool to extract motion
from dynamic anatomical datasets.