ALL-IDB Patches: Whole slide imaging for Acute Lymphoblastic Leukemia detection using Deep Learning

The detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) is being increasingly performed using Deep Learning models (DL) that analyze each blood sample to detect the presence of lymphoblasts, possible indicators of the disease. However, current databases either contain too large images or images already segmented. In this paper, we introduce ALL-IDB Patches, a novel approach for processing Whole Slide Images (WSI) of ALL to take advantage of all the information available for ALL detection, by generating a larger number of samples, making the images usable by current DL models, and without any pre-performed segmentation. To evaluate the recognition accuracy, we consider the OrthoALLNet, obtained by imposing an additional orthogonality constraint on the filters learned by the CNN, with results confirming the validity of the approach.