Medical image analysis
-
In Magnetic Resonance Imaging, image resolution is limited by several factors such as hardware or time constraints. In many cases, the acquired images have to be upsampled to match a specific resolution. In such cases, image interpolation techniques have been traditionally applied. ⋯ In this paper, a new upsampling method is proposed to recover some of this high frequency information by using a data-adaptive patch-based reconstruction in combination with a subsampling coherence constraint. The proposed method has been evaluated on synthetic and real clinical cases and compared with traditional interpolation methods. The proposed method is shown to outperform classical interpolation methods compared in terms of quantitative measures and visual observation.
-
In this paper, a new object-based method to estimate noise in magnitude MR images is proposed. The main advantage of this object-based method is its robustness to background artefacts such as ghosting. The proposed method is based on the adaptation of the Median Absolute Deviation (MAD) estimator in the wavelet domain for Rician noise. ⋯ The impact of the accuracy of noise estimation on the performance of a denoising filter is also studied. The results obtained on synthetic images show the accuracy and the robustness of the proposed method. Within the validation on real data, the proposed method obtained very competitive results compared to the methods under study.
-
Medical image analysis · Jun 2010
A new computationally efficient CAD system for pulmonary nodule detection in CT imagery.
Early detection of lung nodules is extremely important for the diagnosis and clinical management of lung cancer. In this paper, a novel computer aided detection (CAD) system for the detection of pulmonary nodules in thoracic computed tomography (CT) imagery is presented. The paper describes the architecture of the CAD system and assesses its performance on a publicly available database to serve as a benchmark for future research efforts. ⋯ The mean overlap between the nodule regions delineated by three or more radiologists and the ones segmented by the proposed segmentation algorithm is approximately 63%. Overall, with a specificity of 3 false positives (FPs) per case/patient on average, the CAD system is able to correctly identify 80.4% of the nodules (115/143) using 40 selected features. A 7-fold cross-validation performance analysis using the LIDC database only shows CAD sensitivity of 82.66% with an average of 3 FPs per CT scan/case.
-
Medical image analysis · Jun 2010
Evaluation of brain atrophy estimation algorithms using simulated ground-truth data.
A number of analysis tools have been developed for the estimation of brain atrophy using MRI. Since brain atrophy is being increasingly used as a marker of disease progression in many neuro-degenerative diseases such as Multiple Sclerosis and Alzheimer's disease, the validation of these tools is an important task. However, this is complex, in the real scenario, due to the absence of gold standards for comparison. ⋯ Using these gold standards, an evaluation of the performance of three standard brain atrophy estimation methods (SIENA, SIENAX and BSI-UCD), on the basis of their robustness to various sources of error (bias-field inhomogeneity, noise, geometrical distortions, interpolation artefacts and presence of lesions), is presented. Our evaluation shows that, in general, bias-field inhomogeneity and noise lead to larger errors in the estimated atrophy than geometrical distortions and interpolation artefacts. Experiments on 18 different anatomical models of the brain after simulating whole brain atrophies in the range of 0.2-1.5% indicate that, in the presence of bias-field inhomogeneity and noise, a mean error of 0.64+/-0.53%,4.00+/-2.41% and 1.79+/-0.97% may be expected in the atrophy estimated by SIENA, SIENAX and BSI-UCD, respectively.
-
Medical image analysis · Apr 2010
Combining atlas based segmentation and intensity classification with nearest neighbor transform and accuracy weighted vote.
In this paper, different methods to improve atlas based segmentation are presented. The first technique is a new mapping of the labels of an atlas consistent with a given intensity classification segmentation. This new mapping combines the two segmentations using the nearest neighbor transform and is especially effective for complex and folded regions like the cortex where the registration is difficult. ⋯ This weighting is derived from statistical classification theory and is computed offline using the atlases as a training dataset. Concretely, the accuracy map of each atlas is computed and the vote is weighted by the accuracy of the atlases. Numerical experiments have been performed on publicly available in vivo datasets and show that, when used together, the two techniques provide an important improvement of the segmentation accuracy.