Classification of in vivo 1H MR spectra from breast tissue using artificial neural networks.

BACKGROUND

The study was designed in order to investigate whether artificial neural networks could be used for analysis of in vivo magnetic resonance (MR) spectra from breast cancer patients.

MATERIALS AND METHODS

In vivo 1H MR spectra with three different echo times (TE 135, 350 and 450 msec) were acquired from patients with benign and malignant breast lesions and from healthy volunteers, of whom some were breast-feeding. A spectral region (4.0-1.5 ppm) was used as input for artificial neural network analysis, for the attempted classification of the data into different groups.

RESULTS

Data recorded at all three echo times were necessary to obtain the best results. Furthermore, malignant tissue was differentiated from benign tumours using this approach, whereas benign tumours were poorly separated from healthy tissue.

CONCLUSION

The results presented here indicate that in vivo MR spectroscopy in conjunction with neural network analysis might be useful for the evaluation of breast lesions.