[Correlation of MRI and histopathology of bone marrow in patients with multiple myeloma]

PURPOSE

To compare MRI findings and histological plasmacellular infiltration of the bone marrow in patients with multiple myeloma (MM).

MATERIAL AND METHODS

Twenty-four patients with different stages of MM underwent 1.5T MRI of the pelvic bone before iliac crest punch biopsy. Precontrast T1wSE and STIR and postcontrast (Gd-DTPA) T1wSE-fatsat were acquired using axial slices. Immediately after the biopsy, T1wSE was repeated to locate the biopsy canal. The corresponding region in the examination before punch biopsy was assessed for bone marrow involvement using a three-point score (0: negative, 1: suspect, 2: definite).

RESULTS

Two patients were not included because the location of the biopsy canal was unclear. Of 7 patients without histological plasmacellular infiltration, MRI was false positive in one case (suspect). Of 15 patients with histological infiltration, MRI was positive in 10 cases (4 suspect, 6 definite). The T1wSE was positive in 9 cases, STIR in 8 cases, and postcontrast T1wSE-fatsat in 7 cases. In 10 of the 15 patients, the infiltration was histologically graded as low (5 - 20 % of bone marrow). In this group, MRI was only positive in 5 cases (3 suspect, 2 definite). Of five patients with the infiltration histologically graded as high (> 20 % of bone marrow), MRI was positive in all cases (1 suspect, 4 definite).

CONCLUSION

Only advanced bone marrow infiltration in MM can be reliably detected by MRI. None of the used sequences proved to be significantly superior or inferior.

Selbstorganisierende neuronale Netze zur automatischen Detektion und Klassifikation von Kontrast(mittel)-verstärkten Läsionen in der dynamischen MR-Mammographie

PURPOSE

Investigation and statistical evaluation of "Self-Organizing Maps," a special type of neural networks in the field of artificial intelligence, classifying contrast enhancing lesions in dynamic MR-mammography.

MATERIAL AND METHODS

176 investigations with proven histology after core biopsy or operation were randomly divided into two groups. Several Self-Organizing Maps were trained by investigations of the first group to detect and classify contrast enhancing lesions in dynamic MR-mammography. Each single pixel's signal/time curve of all patients within the second group was analyzed by the Self-Organizing Maps. The likelihood of malignancy was visualized by color overlays on the MR-images. At last assessment of contrast-enhancing lesions by each different network was rated visually and evaluated statistically.

RESULTS

A well balanced neural network achieved a sensitivity of 90.5 % and a specificity of 72.2 % in predicting malignancy of 88 enhancing lesions. Detailed analysis of false-positive results revealed that every second fibroadenoma showed a "typical malignant" signal/time curve without any chance to differentiate between fibroadenomas and malignant tissue regarding contrast enhancement alone; but this special group of lesions was represented by a well-defined area of the Self-Organizing Map.

DISCUSSION

Self-Organizing Maps are capable of classifying a dynamic signal/time curve as "typical benign" or "typical malignant." Therefore, they can be used as second opinion. In view of the now known localization of fibroadenomas enhancing like malignant tumors at the Self-Organizing Map, these lesions could be passed to further analysis by additional post-processing elements (e.g., based on T2-weighted series or morphology analysis) in the future.