Xiang Li ¹ Casey C. Heirman ² Ashlyn G. Rickard ³ Gina Sotolongo ⁴ Rico Castillo ³ Temitayo Adanlawo ⁵ Jeffrey I. Everitt ⁶ Jeffrey B. Hodgin ⁷ Tammara L. Watts ⁸ Andrew Janowczyk ^10,11,9 Yvonne M. Mowery ^12,3,8 Laura Barisoni ^13,14 Kyle J. Lafata ^1,13,15,3*

• ¹ Department of Electrical and Computer Engineering, Pratt School of Engineering, Duke University, Durham, North Carolina, United States
• ² Duke University, Durham, United States
• ³ Department of Radiation Oncology, School of Medicine, Duke University, Durham, North Carolina, United States
• ⁴ Duke University Health System, Durham, North Carolina, United States
• ⁵ College of Medicine, Howard University, Washington DC, District of Columbia, United States
• ⁶ Department of Pathology, School of Medicine, Duke University, Durham, North Carolina, United States
• ⁷ Department of Pathology, University of Michigan, Ann Arbor, United States
• ⁸ Department of Head and Neck Surgery & Communication Sciences, School of Medicine, Duke University, Durham, North Carolina, United States
• ⁹ Department of Biomedical Engineering, Emory University and Georgia Institute of Technology, Atlanta, United States
• ¹⁰ Department of Oncology, Division of Precision Oncology, Geneva University Hospitals, Geneva, Switzerland
• ¹¹ Department of Diagnostics, Division of Clinical Pathology, Geneva University Hospitals, Geneva, Switzerland
• ¹² Department of Radiation Oncology, UPMC Hillman Cancer Center/University of Pittsburgh, Pittsburgh, United States
• ¹³ Division of AI and Computational Pathology, Department of Pathology, School of Medicine, Duke University, Durham, United States
• ¹⁴ Division of Nephrology, Department of Medicine, School of Medicine, Duke University, Durham, North Carolina, United States
• ¹⁵ Department of Radiology, School of Medicine, Duke University, Durham, North Carolina, United States

Immune dysregulation plays a major role in cancer progression. The quantification of lymphocytic spatial inflammation may enable spatial system biology, improve understanding of therapeutic resistance, and contribute to prognostic imaging biomarkers. In this paper, we propose a knowledgeguided deep learning framework to measure the lymphocytic spatial architecture on human H&E tissue, where the fidelity of training labels is maximized through single-cell resolution image registration of H&E to IHC. We demonstrate that such an approach enables pixel-perfect groundtruth labeling of lymphocytes on H&E as measured by IHC. We then experimentally validate our technique in a genetically engineered, immune-compromised Rag2 mouse model, where Rag2 knockout mice lacking mature lymphocytes are used as a negative experimental control. Such experimental validation moves beyond the classical statistical testing of deep learning models and demonstrates feasibility of more rigorous validation strategies that integrate computational science and basic science. Using our developed approach, we automatically annotated more than 111,000 human nuclei (45,611 CD3/CD20 positive lymphocytes) on H&E images to develop our model, which achieved an AUC of 0.78 and 0.71 on internal hold-out testing data and external testing on an independent dataset, respectively. As a measure of the global spatial architecture of the lymphocytic microenvironment, the average structural similarity between predicted lymphocytic density maps and ground truth lymphocytic density maps was 0.86±0.06 on testing data. On experimental mouse model validation, we measured a lymphocytic density of 96.5%±1.3% in a Rag2 +/-control mouse, compared to an average of 16.2%±5.3% in Rag2 -/-immune knockout mice (p<0.0001, ANOVA-test). These results demonstrate that CD3/CD20 positive lymphocytes can be accurately detected and characterized on H&E by deep learning and generalized across species. Collectively, these data suggest that our understanding of complex biological systems may benefit from computationallyderived spatial analysis, as well as integration of computational science and basic science.