Abstract Background: Pathologists typically diagnose the breast tissue slides under a microscope by examining: (i) lumen and ductal morphology, (ii) nuclei size, shape, and spatial arrangement and their combinations, (iii) intraductal architecture, and (iv) textural properties. These features may be subtle and can overlap between diagnoses which contribute to inter- and intra-observer variability. We aim to mitigate this arbitrary nature of breast diagnoses with an exemplar-driven precision pathology pipeline based on spatial parametric modeling of histological structures. Methods: For our study, we consider a broad spectrum of breast biopsies including: (i) invasive breast cancer, (ii) three high-risk benign lesions: ductal carcinoma in-situ, atypical ductal hyperplasia (ADH), flat epithelial atypia (FEA), and (iii) three low-risk benign lesions: usual ductal hyperplasia, columnar cell change and Normal; where the risk is indicated by the relative chance of developing breast cancer. We build spatial parametric models for a dictionary of histological structures that pathologists frequently use (also documented in the standard reference book from WHO on the classification of tumors) in making complex diagnostic decisions. These models enable our precision pathology pipeline to simultaneously identify distinct exemplar images to account for inter-class heterogeneity, and learn the relative importance of lumen/ductal morphology (LD), intraductal structures including nuclei morphology and spatial arrangements (ID) and textural features (T) from automatically identified exemplar images in assigning diagnostic labels. In doing so, we assert that the assignment of relative importances to LD, ID, and T features is driven by similar looking ducts (‘exemplars’) which were previously encountered during pathology training or clinical practice. Results: We evaluated the inferential power of our exemplar-driven precision pathology pipeline on two separate breast core biopsy image datasets, i) dataset containing 4539 regions of interest (ROIs) images extracted from 387 whole slide images (WSIs, 40x), and ii) dataset containing 1237 ROI images extracted from 93 WSIs (20x). Our precision pathology pipeline shows significant improvement (~20%) in the overall classification performance compared to state-of-the-art black box deep learning methods (e.g., graphical neural networks) on both datasets. In particular, while our performance in detecting invasive lesions is comparable to baseline methods, we show a significant improvement (p< 0.01) in detecting diagnostically important high-risk ADH and FEA ROIs compared to the baseline methods, where inter- and intra-observer variability is a problem. Conclusions: A key highlight of our method is in its ability to provide pathologist friendly diagnostic explanations without largely compromising on the classification performance. The strategy outlined in this work can be generalized to other tissue histologies from other organs as defined in the WHO Classification of Tumors books. Further, our approach can facilitate a communication platform between pathologists and computational scientists to interact and develop AI-driven algorithmic tools that can enhance patient care in a clinical setting. Our framework provides pathologist-friendly explanations paving the way for better, transparent, and trustworthy diagnostic tools. Differential diagnoses of breast biopsies Differential diagnoses of breast biopsies The precision pathology pipeline optimizes the identification of a broad spectrum of breast biopsies (invasive, DCIS, benign), including difficult borderline cases (e.g., ADH, FEA, etc.). It provides pathologist-friendly explanations integrated into a clinical workflow for better, transparent, and trustworthy diagnostic aid. This approach sddresses the limitations of standard black-box AI in building trust with pathologists. Citation Format: Akif Burak Tosun, S. Chakra Chennubhotla. Differential diagnoses of breast biopsies by spatial parametric modeling of histological structures and explainable AI [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P6-04-12.