top of page

Deep Learning-Based Nuclear Morphometry Reveals an Independent Prognostic Factor in MCL

Published by the American Journal of Pathology

Vol. 192, No. 12, Dec. 2022

Mantle cell lymphoma (MCL) is a rare type of B-cell lymphoma with a largely aggressive clinical course. The median survival of patients with MCL is about 3 to 5 years. Identification of patients with poor prognosis would aid in consideration of more aggressive treatment, such as hematopoietic stem cell transplant.

Blastoid/pleomorphic morphology has long been known to correlate with worse prognosis in patients with MCL. However, the identification of these morphologic variants could be challenging for general pathologists with less experience.

This study analyzed the disease prognosis based on objective morphometric parameters extracted from tens of thousands of nuclei among 103 patients with MCL to derive a significant and human-interpretable result. We developed a deep learning algorithm to delineate the nuclear contours of MCL tumor cells automatically. Morphometric parameters were extracted and calculated, and their prognostic significance was evaluated.

Unlike blastoid/pleomorphic morphology, which is identified by human eyes, the current morphometric parameters can be objectively measured. 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.

Figure 1. Overview of the study design. MCL, mantle cell lymphoma; ROI, region of interest.


bottom of page