Image-Based Deep Learning Detection of High-Grade B-Cell Lymphomas Directly from Hematoxylin and Eosin Images

SIMPLE SUMMARY: Double/triple-hit lymphomas (DHLs/THLs) are an aggressive type of high-grade B-cell lymphomas (HGBLs), characterized by translocations in MYC and BCL2/BCL6. DHL patients respond poorly to standard chemoimmunotherapy regimens; thus, timely and accurate diagnosis is of paramount importance for their proper clinical management. The standard technique used for the identification of these translocations is fluorescence in situ hybridization (FISH), which is not routinely performed at every medical center to all potential patients. In the current study, we employed an image-based, artificial intelligence, deep learning algorithmic tool for the identification of DHL/THL cases by analyzing scanned histopathological H&E-stained tissue slide images. Our preliminary results demonstrate high performances, suggesting the potential use of such a solution in the clinical workflow to support the management of HGBL patients. ABSTRACT: Deep learning applications are emerging as promising new tools that can support the diagnosis and classification of different cancer types. While such solutions hold great potential for hematological malignancies, there have been limited studies describing the use of such applications in this field. The rapid diagnosis of double/triple-hit lymphomas (DHLs/THLs) involving MYC, BCL2 and/or BCL6 rearrangements is obligatory for optimal patient care. Here, we present a novel deep learning tool for diagnosing DHLs/THLs directly from scanned images of biopsy slides. A total of 57 biopsies, including 32 in a training set (including five DH lymphoma cases) and 25 in a validation set (including 10 DH/TH cases), were included. The DHL-classifier demonstrated a sensitivity of 100%, a specificity of 87% and an AUC of 0.95, with only two false positive cases, compared to FISH. The DHL-classifier showed a 92% predictive value as a screening tool for performing conventional FISH analysis, over-performing currently used criteria. The work presented here provides the proof of concept for the potential use of an AI tool for the identification of DH/TH events. However, more extensive follow-up studies are required to assess the robustness of this tool and achieve high performances in a diverse population.