Classification of Small Contrast Enhancing Breast Lesions in Dynamic Magnetic Resonance Imaging Using a Combination of Morphological Criteria and Dynamic Analysis Based on Unsupervised Vector-Quantization

Schlossbauer, Thomas; Leinsinger, Gerda; Wismüller, Axel; Lange, Oliver; Scherr, Martin; Meyer‐Baese, Anke; Reiser, Maximilian

doi:10.1097/rli.0b013e3181559932

Cited by 47 publications

(23 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, in a clinical study on 85 small mammographically indetermintate lesions, it could be demonstrated that dynamic analysis using our vector quantization approach alone resulted in a higher diagnostic accuracy when compared to a combined morphologic and dynamic analysis [128].…”

Section: Dynamic Mr Image Time-series Analysis In Breast Cancer Diagnmentioning

confidence: 96%

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Wismüller

2010

Comput Sci Res Dev

View full text Add to dashboard Cite

Technical innovations in radiology, such as advanced cross-sectional imaging methods, have opened up new vistas for the exploration of structure and function of the human body enabling both high spatial and temporal resolution. However, these techniques have led to vast amounts of data whose precise and reliable visual analysis by radiologists requires a considerable amount of human intervention and expertise, thus resulting in a cost factor of substantial economic relevance. Hence, the computer-assisted analysis of biomedical image data has moved into the focus of interest as an issue of high priority research efforts. In this context, innovative approaches to exploratory analysis of huge complex spatio-temporal patterns play a key role to improve computer-assisted signal and image processing in radiology. Examples of such approaches are various unsupervised vector quantization methods or supervised function approximation techniques, such as Generalized RadialBasis-Functions-(GRBF-) neural networks. Recent developments motivated by concepts of computational intelligence are the 'Deformable Feature Map' (DM) as an algorithm for self-organized model adaptation, the 'Mutual Connectivity Analysis' (MCA) as an instrument for the analysis of large time-series ensembles and the 'Exploratory Observation Machine' (XOM) as a novel general framework for learning by self-organization-three methods that the author has invented and applied to biomedical real-world applications. This contribution covers both conceptual foundations A. Wismüller ( )

show abstract

Section: Dynamic Mr Image Time-series Analysis In Breast Cancer Diagnmentioning

confidence: 96%

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Wismüller

2010

Comput Sci Res Dev

View full text Add to dashboard Cite

show abstract

“…However, not many studies have focused on evaluating the value of DCE-MRI in small lesions which may not exhibit typical characteristics of benign and malignant tumors [13]. Accurate diagnosis of such small lesions is clinically important for improving disease management in patients, where evaluating the dignity of breast lesions as being benign or malignant is specifically challenging.…”

Section: Introductionmentioning

confidence: 99%

Classification of small lesions in dynamic breast MRI: eliminating the need for precise lesion segmentation through spatio-temporal analysis of contrast enhancement

Nagarajan

Huber

Schlossbauer

et al. 2012

Machine Vision and Applications

Self Cite

View full text Add to dashboard Cite

Characterizing the dignity of breast lesions as benign or malignant is specifically difficult for small lesions; they don’t 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 sixty 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 also 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 (p < 0.05). 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.

show abstract

“…The best hyperplane is the one that maximizes the distance (margin) of the two parallel hyperplanes defined in Equation 14. Since the distance of a hyperplane to the origin is b w , we want to maximize 2 w .…”

Section: Support Vector Machinesmentioning

confidence: 99%

“…, n in their d dimensional domain in two classes v i ∈ {M, B}. First, let us assume that our data set is linearly separable and that we can find a pair ( w, b) that fulfills 14) http://asp.eurasipjournals.com/content/2013/1/157…”

Section: Support Vector Machinesmentioning

confidence: 99%

Computer-aided diagnosis for diagnostically challenging breast lesions in DCE-MRI based on image registration and integration of morphologic and dynamic characteristics

Retter¹,

Plant

Burgeth³

et al. 2013

EURASIP J. Adv. Signal Process.

Self Cite

View full text Add to dashboard Cite

Diagnostically challenging lesions comprise both foci (small lesions) and non-mass-like enhancing lesions and pose a challenge to current computer-aided diagnosis systems. Motion-based artifacts lead in dynamic contrast-enhanced breast magnetic resonance to diagnostic misinterpretation; therefore, motion compensation represents an important prerequisite to automatic lesion detection and diagnosis. In addition, the extraction of pertinent kinetic and morphologic features as lesion descriptors is an equally important task. In the present paper, we evaluate the performance of a computer-aided diagnosis system consisting of motion correction, lesion segmentation, and feature extraction and classification. We develop a new feature extractor, the radial Krawtchouk moment, which guarantees rotation invariance. Many novel feature extraction techniques are proposed and tested in conjunction with lesion detection. Our simulation results have shown that motion compensation combined with Minkowski functionals and Bayesian classifier can improve lesion detection and classification.

show abstract

Classification of Small Contrast Enhancing Breast Lesions in Dynamic Magnetic Resonance Imaging Using a Combination of Morphological Criteria and Dynamic Analysis Based on Unsupervised Vector-Quantization

Cited by 47 publications

References 33 publications

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Computational intelligence in biomedical imaging: multidimensional analysis of spatio-temporal patterns

Classification of small lesions in dynamic breast MRI: eliminating the need for precise lesion segmentation through spatio-temporal analysis of contrast enhancement

Computer-aided diagnosis for diagnostically challenging breast lesions in DCE-MRI based on image registration and integration of morphologic and dynamic characteristics

Contact Info

Product

Resources

About