Cookies on this website
We use cookies to ensure that we give you the best experience on our website. If you click 'Continue' we'll assume that you are happy to receive all cookies and you won't see this message again. Click 'Find out more' for information on how to change your cookie settings.

Improving the accuracy of myeloproliferative neoplasm typing at diagnosis will enable better selection of treatments for improved patient outcomes.

Myeloproliferative Neoplasms (MPNs) are a group of closely related disorders of the bone marrow that are categorised into three main types: myelofibrosis (the most severe); essential thrombocythaemia (ET); and polycythaemia vera (PV). In PV and ET, red blood cells or platelets, respectively, are over-produced which increases the risk of blood clots, heart attacks and strokes. In myelofibrosis, destructive scarring (‘fibrosis’) of the bone marrow develops, leading to failure of the marrow to produce blood cells and severe symptoms. Patients with all MPNs are at higher risk of developing leukaemia, especially patients with myelofibrosis when this develops in >10% patients.

Unfortunately, there are currently no cures for these conditions, however proper monitoring and treatments for ET and PV allow most patients to enjoy a normal quality of life and lifespan. For myelofibrosis, targeted therapies can effectively control symptoms, but this does not alter the natural history of the disease and survival remains less than 5-10 years following diagnosis.

Because the treatment strategy varies depending on the MPN type, accurate assessment of MPN type at diagnosis is crucial for optimal treatment selection. In addition to mutational and blood count analysis, morphological analysis of a bone marrow biopsy is a key component for classification. Unfortunately, this is highly subjective, reliant on qualitative observations and there is great variability even when it is done by expert haematopathologists.

A more accurate method for bone marrow-based MPN typing at diagnosis is very much needed. Megakaryocyte cells – the large bone marrow cells that produce blood platelets – are abnormal in all MPN types and are thought to play a key role in the disease pathology. Interestingly, although megakaryocytes are over-produced all three MPNs, subtle differences in the appearance and location of these cells within the bone marrow occur in the different MPN subtypes.

To try to improve MPN classification, a team led by Professor Jens Rittscher (Institute of Biomedical Engineering & Ludwig Institute for Cancer Research) and Dr Daniel Royston (Radcliffe Department of Medicine and Cellular Pathology, Oxford University Hospitals) developed an AI approach to screen and classify MPNs based on features of the megakaryocytes such as their cell size, clustering and internal complexity. Their machine learning approach, published in published in Blood Advances, revealed that there are clear differences between MPN subtypes and their platform was able to more accurately classify patients by assessing subtle morphological differences in the biopsies that could not have been identified by the naked eye.

 

It has long been recognised that a multitude of subtle differences in megakaryocyte morphology can distinguish between the MPN subtypes. However, this means that assessment of bone marrow biopsies is poorly reproducible, sometimes leading to diagnostic uncertainty and inappropriate treatment plans for patients. The approach developed here is really exciting for the field, as it is now possible to perform deep phenotyping of megakaryocytes and more accurate disease classification using simple H&E slides which are routinely prepared in all diagnostic facilities. This will be incredibly useful both for research aimed at better understanding the role of megakaryocytes in blood cancers as well as improving diagnosis and treatment pathways for our patients. - Dr Beth Psaila, a clinician scientist at the MRC Weatherall Institute of Molecular Medicine and a haematology consultant specialising in MPNs

The team hopes that in the future, this work can be combined with other histological assessments to optimise the clinical application of AI approaches, and create a more comprehensive quantitative description of the bone marrow microenvironment and its cancers.