Nuclear morphometric analysis of non-Hodgkin's lymphoma

Deep Learning-Based Nuclear Morphometry Reveals an Independent Prognostic Factor in Mantle Cell Lymphoma

Blastoid/pleomorphic morphology is associated with short survival in mantle cell lymphoma (MCL), but its prognostic value is overridden by Ki-67 in multivariate analysis. Herein, a nuclear segmentation model was developed using deep learning, and nuclei of tumor cells in 103 MCL cases were automatically delineated. Eight nuclear morphometric attributes were extracted from each nucleus. The mean, variance, skewness, and kurtosis of each attribute were calculated for each case, resulting in 32 morphometric parameters. Compared with those in classic MCL, 17 morphometric parameters were significantly different in blastoid/pleomorphic MCL. Using univariate analysis, 16 morphometric parameters (including 14 significantly different between classic and blastoid/pleomorphic MCL) emerged as significant prognostic factors. Using multivariate analysis, Biologic MCL International Prognostic Index (bMIPI) risk group (P = 0.025), low skewness of nuclear irregularity (P = 0.020), and high mean of nuclear irregularity (P = 0.047) emerged as independent adverse prognostic factors. Additionally, a morphometric score calculated from the skewness and mean of nuclear irregularity (P = 0.0038) was an independent prognostic factor in addition to bMIPI risk group (P = 0.025), and a summed morphometric bMIPI score was useful for risk stratification of patients with MCL (P = 0.000001). These results demonstrate, for the first time, that a nuclear morphometric score is an independent prognostic factor in MCL. It is more robust than blastoid/pleomorphic morphology and can be objectively measured.

Working formulation of the non-Hodgkin's lymphomas: a study of cell size and mitotic indices in cytologic subtypes

Cell size and mitotic indices were studied in 243 non-Hodgkin's lymphomas (NHL) diagnosed cytologically and classified according to the Working Formulation. Low-, intermediate-, and high-grade lymphomas constituted 14.8%, 18.9%, and 61.7% of the cases, respectively. Measurement of the diameter of 100 lymphoid cells in each case showed that in most of the low-grade malignant lymphomas, 50-80% of the cells were small (less than 10 microns). A majority of the cells (an average of 45-60%) in intermediate- and high-grade lymphomas were in the range of 11-15 microns. Only the intermediate-grade large noncleaved and high-grade immunoblastic lymphomas had a majority of their cells (greater than 50%) larger than 15 microns. The mitotic indices (number of mitotic figures per 500 lymphoid cells) showed a highly significant difference between low- (0.7 +/- 1.14), intermediate- (3.0 +/- 2.67), and high-grade (5.4 +/- 3.40) lymphomas using the Wilcoxon's signed rank test (P less than 0.0001). Nearly two-thirds of the cases in each grade were within specific ranges of mitotic indices, i.e., less than 1 for low-, 1-3 for intermediate-, and greater than 3 for high-grade lymphomas.