Multi-Scale Task Multiple Instance Learning for the Classification of Digital Pathology Images with Global Annotations

N. Marini, S. Otalora, F. Ciompi, G. Silvello, S. Marchesin, S. Vatrano, G. Buttafuoco, M. Atzori, H. Muller, N. Burlutskiy, Z. Li, F. Minhas, T. Peng, N. Rajpoot, B. Torbennielsen, J. Der Van Laak, M. Veta, Y. Yuan and I. Zlobec

Cited by ~13

Whole slide images (WSIs) are high-resolution digitized images of tissue samples, stored including different magnification levels. WSIs datasets often include only global annotations, available thanks to pathology reports. Global annotations refer to global findings in the high-resolution image and do not include information about the location of the regions of interest or the magnification levels used to identify a finding. This fact can limit the training of machine learning models, as WSIs are usually very large and each magnification level includes different information about the tissue. This paper presents a Multi-Scale Task Multiple Instance Learning (MuSTMIL) method, allowing to better exploit data paired with global labels and to combine contextual and detailed information identified at several magnification levels. The method is based on a multiple instance learning framework