Cluster Analysis of Biomedical Image Time-Series Wismüller, Axel; Lange, Oliver; Dersch, Dominik R ...
International journal of computer vision,
02/2002, Letnik:
46, Številka:
2
Journal Article
Recenzirano
In this paper, we present neural network clustering by deterministic annealing as a powerful strategy for self-organized segmentation of biomedical image time-series data identifying groups of pixels ...sharing common properties of local signal dynamics. After introducing the theoretical concept of minimal free energy vector quantization and related clustering techniques, we discuss its potential to serve as a multi-purpose computer vision strategy to image time-series analysis and visualization for many fields of medicine ranging from biomedical basic research to clinical assessment of patient data. In particular, we present applications to (i) functional MRI data analysis for human brain mapping, (ii) dynamic contrast-enhanced perfusion MRI for the diagnosis of cerebrovascular disease, and (iii) magnetic resonance mammography for the analysis of suspicious lesions in patients with breast cancer. This wide scope of completely different medical applications illustrates the flexibility and conceptual power of neural network vector quantization in this context. Although there are obvious methodological similarities, each application requires specific careful consideration w.r.t. data preprocessing, postprocessing and interpretation. This challenge can only be managed by close interdisciplinary cooperation of medical doctors, engineers, and computer scientists. Hence, this field of research can serve as an example for lively cross-fertilization between computer vision and related research.PUBLICATION ABSTRACT
To determine the response to treatment and the long-term outcome of patients with the antisynthetase syndrome associated with anti-Jo-1-antibodies.
A total of 12 patients with histologically proven ...myositis and anti-Jo-1-autoantibodies were evaluated over a mean follow-up period of 66.4 months. In all patients neuromuscular function tests, electromyographic examinations, pulmonary function tests and high-resolution-computed tomography of the lungs were performed regularly.
Muscle function improved in all patients with treatment, and a complete clinical response was achieved in 5 patients. Pulmonary function worsened in 1 patient, who died from respiratory failure, but normalised in 4 patients. Arthropathy progressed despite improvement of myositis and pulmonary status in 2 patients. Discontinuation of treatment was facilitated in 1 patient, although long-term therapy was required in 10 patients. In 2 patients with refractory disease, treatment with intravenous immunoglobulins was successful. Severe side effects of treatment occurred in 7 patients and overall mortality rate was one of 12 (8 %).
The antisynthetase syndrome associated with anti-Jo-1-antibodies requires long-term immunosuppressive therapy in most patients. Whereas a complete clinical response of muscular symptoms is frequent, continued deterioration of the pulmonary system may occur despite immunosuppressive treatment, and may lead to fatal outcome. An interdisciplinary therapeutic approach is necessary for best possible results in these patients.
Increased prevalence of cavum septi pellucidi (CSP) in schizophrenic patients in comparison to healthy subjects was reported previously. Our purpose was to evaluate the prevalence of variants of the ...septum pellucidum in healthy subjects in three different age groups.
151 healthy subjects, including 46 children (age 6 +/- 4 years), 72 young adults (age 31 +/- 8 years) and 33 elderly adults (age 59 +/- 7 years) were examined with high-resolution MRI. Three observers analysed the images using a standardised protocol. We evaluated the incidences of CSP, cavum vergae (CV) and their length.
CSP was detected in 80% of the cases in the paediatric group and 68% of young adults and in 72% of the elderly adults. A cavum vergae (CV) was noted in 22% of the children, in 39% of the young adults and in 36% of the elderly subjects. There was no significant difference between the age-related groups.
We detected a high prevalence of cavum septi pellucidi without a significant age dependence. Enlarged cava septi pellucidi are rare in healthy subjects.
Abstract Objective While dimension reduction has been previously explored in computer aided diagnosis (CADx) as an alternative to feature selection, previous implementations of its integration into ...CADx do not ensure strict separation between training and test data required for the machine learning task. This compromises the integrity of the independent test set, which serves as the basis for evaluating classifier performance. Methods and materials We propose, implement and evaluate an improved CADx methodology where strict separation is maintained. This is achieved by subjecting the training data alone to dimension reduction; the test data is subsequently processed with out-of-sample extension methods. Our approach is demonstrated in the research context of classifying small diagnostically challenging lesions annotated on dynamic breast magnetic resonance imaging (MRI) studies. The lesions were dynamically characterized through topological feature vectors derived from Minkowski functionals. These feature vectors were then subject to dimension reduction with different linear and non-linear algorithms applied in conjunction with out-of-sample extension techniques. This was followed by classification through supervised learning with support vector regression. Area under the receiver-operating characteristic curve (AUC) was evaluated as the metric of classifier performance. Results Of the feature vectors investigated, the best performance was observed with Minkowski functional ‘perimeter’ while comparable performance was observed with ‘area’. Of the dimension reduction algorithms tested with ‘perimeter’, the best performance was observed with Sammon's mapping (0.84 ± 0.10) while comparable performance was achieved with exploratory observation machine (0.82 ± 0.09) and principal component analysis (0.80 ± 0.10). Conclusions The results reported in this study with the proposed CADx methodology present a significant improvement over previous results reported with such small lesions on dynamic breast MRI. In particular, non-linear algorithms for dimension reduction exhibited better classification performance than linear approaches, when integrated into our CADx methodology. We also note that while dimension reduction techniques may not necessarily provide an improvement in classification performance over feature selection, they do allow for a higher degree of feature compaction.
Purpose:
Topological texture features were compared in their ability to classify “honeycombing,” a morphological pattern that is considered indicative for the presence of fibrotic interstitial lung ...disease in high-resolution computed tomography (HRCT) images.
Methods:
For 14 patients with known occurrence of honeycombing, a stack of 70 axial, lung kernel reconstructed images was acquired from HRCT chest exams. A set of 964 regions of interest of both healthy and pathological (356) lung tissue was identified by an experienced radiologist. Texture features were extracted using statistical features (Stat), six properties calculated from gray-level co-occurrence matrices (GLCMs), Minkowski dimensions (MDs), and three Minkowski functionals (MFs) (e.g., MF.Euler). A naïve Bayes (NB) and
k
-nearest-neighbor (
k
-NN) classifier, a multilayer radial basis functions network (RBFN), and a support vector machine with a radial basis function (SVMrbf) kernel were optimized in a tenfold cross-validation for each texture vector, and the classification accuracy was calculated on independent test sets as a quantitative measure of automated tissue characterization. A Wilcoxon signed-rank test was used to compare two accuracy distributions and the significance thresholds were adjusted for multiple comparisons by the Bonferroni correction.
Results:
The best classification results were obtained by the MF features, which performed significantly better than all the standard Stat, GLCM, and MD features
(
p
<
0.001
)
for both classifiers. The highest accuracies were found for MF.Euler (93.6%, 94.9%, 94.2%, and 95.0% for NB,
k
-NN, RBFN, and SVMrbf, respectively). The best groups of standard texture features were a Stat and GLCM (“homogeneity”) feature set (up to 91.8%).
Conclusions:
The results indicate that advanced topological texture features derived from MFs can provide superior classification performance in computer-assisted diagnosis of fibrotic interstitial lung disease patterns when compared to standard texture analysis methods.
Characterizing the dignity of breast lesions as benign or malignant is specifically difficult for
small
lesions; they do not exhibit typical characteristics of malignancy and are harder to segment ...since margins are harder to visualize. Previous attempts at using dynamic or morphologic criteria to classify small lesions (mean lesion diameter of about 1 cm) have not yielded satisfactory results. The goal of this work was to improve the classification performance in such small diagnostically challenging lesions while concurrently eliminating the need for precise lesion segmentation. To this end, we introduce a method for topological characterization of lesion enhancement patterns over time. Three Minkowski Functionals were extracted from all five post-contrast images of 60 annotated lesions on dynamic breast MRI exams. For each Minkowski Functional, topological features extracted from each post-contrast image of the lesions were combined into a high-dimensional texture feature vector. These feature vectors were classified in a machine learning task with support vector regression. For comparison, conventional Haralick texture features derived from gray-level co-occurrence matrices (GLCM) were used. A new method for extracting thresholded GLCM features was also introduced and investigated here. The best classification performance was observed with Minkowski Functionals
area
and
perimeter
, thresholded GLCM features f8 and f9, and conventional GLCM features f4 and f6. However, both Minkowski Functionals and thresholded GLCM achieved such results
without lesion segmentation
while the performance of GLCM features significantly deteriorated when lesions were not segmented (
). This suggests that such advanced spatio-temporal characterization can improve the classification performance achieved in such small lesions, while simultaneously eliminating the need for precise segmentation.
Previous work suggests that patients with unipolar depression may have structural as well as functional abnormalities in limbic-thalamic-cortical networks, which are hypothesized to modulate human ...mood states. A core area in these networks is the hippocampus. In the present study, differences in volumes of hippocampal gray and white matter between patients with a first episode of major depression and healthy comparison subjects were examined.
Thirty patients with a first episode of major depression and 30 healthy comparison subjects who were matched for age, gender, handedness, and education were examined with high-resolution magnetic resonance imaging.
Male patients with a first episode of major depression had significantly smaller hippocampal total and gray matter volumes than healthy male comparison subjects. Both male and female patients showed significant alterations of left-right asymmetry and significant reductions of left and right hippocampal white matter fibers in relation to healthy comparison subjects. Hippocampal measurements were not significantly correlated with clinical variables, such as age at onset of illness, illness duration, or severity of depression.
These results are consistent with findings of structural abnormalities of the hippocampal formation in patients with major depression that were more pronounced in male patients. The authors' findings support the hypothesis that the hippocampus and its connections within limbic-cortical networks may play a crucial role in the pathogenesis of major depression.
We present a complete system for image-based 3D vocal tract analysis ranging from MR image acquisition during phonation, semi-automatic image processing, quantitative modeling including model-based ...speech synthesis, to quantitative model evaluation by comparison between recorded and synthesized phoneme sounds. For this purpose, six professionally trained speakers, age 22-34y, were examined using a standardized MRI protocol (1.5 T, T1w FLASH, ST 4mm, 23 slices, acq. time 21s). The volunteers performed a prolonged (> or = 21s) emission of sounds of the German phonemic inventory. Simultaneous audio tape recording was obtained to control correct utterance. Scans were made in axial, coronal, and sagittal planes each. Computer-aided quantitative 3D evaluation included (i) automated registration of the phoneme-specific data acquired in different slice orientations, (ii) semi-automated segmentation of oropharyngeal structures, (iii) computation of a curvilinear vocal tract midline in 3D by nonlinear PCA, (iv) computation of cross-sectional areas of the vocal tract perpendicular to this midline. For the vowels /a/,/e/,/i/,/o/,/ø/,/u/,/y/, the extracted area functions were used to synthesize phoneme sounds based on an articulatory-acoustic model. For quantitative analysis, recorded and synthesized phonemes were compared, where area functions extracted from 2D midsagittal slices were used as a reference. All vowels could be identified correctly based on the synthesized phoneme sounds. The comparison between synthesized and recorded vowel phonemes revealed that the quality of phoneme sound synthesis was improved for phonemes /a/, /o/, and /y/, if 3D instead of 2D data were used, as measured by the average relative frequency shift between recorded and synthesized vowel formants (p < 0.05, one-sided Wilcoxon rank sum test). In summary, the combination of fast MRI followed by subsequent 3D segmentation and analysis is a novel approach to examine human phonation in vivo. It unveils functional anatomical findings that may be essential for realistic modelling of the human vocal tract during speech production.
Dysfunction of neuronal plasticity or remodelling seems to contribute to the pathopysiology of major depression and may cause the well-documented hippocampal changes in depression. We aimed to ...investigate whether reduced hippocampal volumes correlate with executive dysfunctioning or memory dysfunctioning or with depression severity.
We recruited 34 inpatients with a previous or current episode of major depression from the department of psychiatry at the Ludwig-Maximilians University of Munich, Germany. We examined the 34 patients and 34 healthy control subjects with structural high resolution MRI. We assessed cognitive functions with the Wisconsin Card Sorting Test (WCST) and the Rey Auditory Verbal Learning Test (RAVLT) and severity of depression with the Hamilton Depression Rating Scale.
Hippocampal volumes and frontal lobe volumes were significantly smaller in patients, compared with healthy control subjects. Furthermore, lower hippocampal volumes were correlated with poorer performance in the WCST. No significant correlations were found between hippocampal volumes and RAVLT performance or severity of depression.
The present findings emphasize that patients with reduced hippocampal volumes show more executive dysfunctions than their counterparts. Thus, the mechanisms resulting in reduced hippocampal volumes seem to be related to the development of major depression.