Deep-Learning Based Morphological Segmentation of Canine Diffuse Large B-cell Lymphoma

Kenneth Ancheta^1*Androniki Psifidi²Andrew D Yale²Sophie Le Calvez³Jonathan Williams¹

• ¹The Royal Veterinary College Department of Pathobiology and Population Sciences, Hatfield, United Kingdom
• ²The Royal Veterinary College Department of Clinical Science and Services, Hatfield, United Kingdom
• ³IDEXX Laboratories Ltd, Wetherby, United Kingdom

Diffuse large B-cell lymphoma is the most common type of non-Hodgkin lymphoma (NHL) in humans, accounting for about 30-40% of NHL cases worldwide. Canine diffuse large B-cell lymphoma (cDLBCL) is the most common lymphoma subtype in dogs and demonstrates an aggressive biologic behaviour. For tissue biopsies, current confirmatory diagnostic approaches for enlarged lymph nodes rely on expert histopathological assessment, which is time-consuming and requires specialist expertise. Therefore, there is an urgent need to develop tools to support and improve veterinary diagnostic workflows. Advances in molecular and computational approaches have opened new avenues for morphological analysis. This study explores the use of convolutional neural networks (CNNs) to differentiate cDLBCL from non-neoplastic lymph nodes, specifically reactive lymphoid hyperplasia (RLH). Whole slide images (WSIs) of haematoxylin-eosin stained lymph node slides were digitised at 20× magnification and pre-processed using a modified Aachen protocol. Extracted images were split at the patient level into training (60%), validation (30%), and testing (10%) datasets. Here, we introduce HawksheadNet, a novel lightweight CNN architecture for cancer image classification and highlight the critical role of stain normalisation in CNN training. Once fine-tuned, HawksheadNet demonstrated strong generalisation performance in differentiating cDLBCL from RLH, achieving an area under the receiver operating characteristic (AUROC) of up to 0.9691 using fine-tuned parameters on StainNet-normalised images, outperforming pre-trained CNNs such as EfficientNet (up to 0.9492), Inception (up to 0.9311), and MobileNet (up to 0.9498). Additionally, WSI segmentation was achieved by overlaying the tile-wise predictions onto the original slide, providing a visual representation of the diagnosis that closely aligned with pathologist interpretation. Overall, this study highlights the potential of CNNs in cancer image analysis, offering promising advancements for clinical pathology workflows, patient care, and prognostication.