Image-based cell phenotyping is an important and open problem in computational pathology. The two principal challenges are: 1) making the cell cluster properties insensitive to experimental settings (like seed point and feature selection) and 2) ensuring that the phenotypes emerging are biologically relevant and support clinical reporting. To gauge robustness, we first compare the consistency of the phenotypes using self-supervised and supervised features. Through case classification, we analyse the relevance of the self-supervised and supervised feature sets with respect to the clinical diagnosis. In addition, we demonstrate how we can add model explainability through Shapley values to identify more disease relevant cellular phenotypes and measure their importance in context of the disease. Here, myeloproliferative neoplasms, a haematopoietic stem cell disorder, where one particular cell type is of diagnostic relevance is used as an exemplar. The experiments conducted on a set of bone marrow trephines demonstrate an improvement of 7.4 % in accuracy for case classification using cellular phenotypes derived from the supervised scenario.