Cluster analysis of signal-intensity time course in dynamic breast MRI: does unsupervised vector quantization help to evaluate small mammographic lesions?
- First Online:
We examined whether neural network clustering could support the characterization of diagnostically challenging breast lesions in dynamic magnetic resonance imaging (MRI). We examined 88 patients with 92 breast lesions (51 malignant, 41 benign). Lesions were detected by mammography and classified Breast Imaging and Reporting Data System (BIRADS) III (median diameter 14 mm). MRI was performed with a dynamic T1-weighted gradient echo sequence (one precontrast and five postcontrast series). Lesions with an initial contrast enhancement ≥50% were selected with semiautomatic segmentation. For conventional analysis, we calculated the mean initial signal increase and postinitial course of all voxels included in a lesion. Secondly, all voxels within the lesions were divided into four clusters using minimal-free-energy vector quantization (VQ). With conventional analysis, maximum accuracy in detecting breast cancer was 71%. With VQ, a maximum accuracy of 75% was observed. The slight improvement using VQ was mainly achieved by an increase of sensitivity, especially in invasive lobular carcinoma and ductal carcinoma in situ (DCIS). For lesion size, a high correlation between different observers was found (R2 = 0.98). VQ slightly improved the discrimination between malignant and benign indeterminate lesions (BIRADS III) in comparison with a standard evaluation method.
KeywordsBreast cancer MR mammography Vector quantization
- 4.Heywang-Kobrunner SH, Bick U, Bradley WG Jr, Bone B, Casselman J, Coulthard A, Fischer U, Muller-Schimpfle M, Oellinger H, Patt R, Teubner J, Friedrich M, Newstead G, Holland R, Schauer A, Sickles EA, Tabar L, Waisman J, Wernecke KD (2001) International investigation of breast MRI: results of a multicentre study (11 sites) concerning diagnostic parameters for contrast-enhanced MRI based on 519 histopathologically correlated lesions. Eur Radiol 11(4): 531–546CrossRefPubMedGoogle Scholar
- 6.Wismueller A, Dersch DR, Lipinski B, Hahn K, Auer D (1998) A neural network approach to functional MRI pattern analysis—clustering of time-series by hierarchical vector quantization. In: Niklasson L, Boden M, Ziemke T (eds) Perspectives in neural computing. Springer, Berlin Heidelberg New York, pp 123–128Google Scholar
- 10.Dersch DR. Eigenschaften neuronaler Vektorquantisierer und ihre Anwendung in der Sprachverarbeitung. Verlag Harri Deutsch, Reihe Physik 1996 (54). ISBN 3–8171–1492–3Google Scholar
- 15.Harms SE, Flamig DP, Hesley KL, Meiches MD, Jensen RA , Evans WP, Savino DA, Wells RV (1993). MR imaging of the breast with rotating delivery of excitation off resonance: clinical experience with pathologic correlation. Radiology 87:493–501Google Scholar
- 26.Mussurakis S, Buckley DL, Bowsley SJ, Carleton PJ, Fox JN, Turnbull LW, Horsman A (1995) Dynamic contrast-enhanced magnetic resonance imaging of the breast combined with pharmacokinetic analysis of gadolinium-DTPA uptake in the diagnosis of local recurrence of early stage breast carcinoma. Invest Radiol 30(11):650–662PubMedCrossRefGoogle Scholar