The integration of deep learning-based tools into diagnostic workflows is increasingly prevalent due to their efficiency and reproducibility in various settings. We investigated the utility of automated nuclear morphometry for assessing nuclear pleomorphism (NP), a criterion of malignancy in the current grading system in canine pulmonary carcinoma (cPC), and its prognostic implications. We developed a deep learning-based algorithm for evaluating NP (variation in size, i.e., anisokaryosis and/or shape) using a segmentation model. Its performance was evaluated on 46 cPC cases with comprehensive follow-up data regarding its accuracy in nuclear segmentation and its prognostic ability. Its assessment of NP was compared to manual morphometry and established prognostic tests (pathologists’ NP estimates (n = 11), mitotic count, histological grading, and TNM-stage). The standard deviation (SD) of the nuclear area, indicative of anisokaryosis, exhibited good discriminatory ability for tumor-specific survival, with an area under the curve (AUC) of 0.80 and a hazard ratio (HR) of 3.38. The algorithm achieved values comparable to manual morphometry. In contrast, the pathologists’ estimates of anisokaryosis resulted in HR values ranging from 0.86 to 34.8, with slight inter-observer reproducibility (k = 0.204). Other conventional tests had no significant prognostic value in our study cohort. Fully automated morphometry promises a time-efficient and reproducible assessment of NP with a high prognostic value. Further refinement of the algorithm, particularly to address undersegmentation, and application to a larger study population are required.

Synovial myxoma, a rare joint tumor in dogs, has traditionally been considered benign, acknowledging that local invasion into regional tissues including bone may be present. Given the diagnostic challenges in distinguishing synovial myxoma from other joint lesions through clinical features and diagnostic imaging, definitive diagnosis relies on characteristic gross and histologic features. Within the inner surface of the joint capsule, synovial myxomas form nodules of stellate-to-spindle cells within abundant myxomatous matrix. We present here 2 cases of synovial myxoma with metastasis to regional lymph nodes and compare these 2 cases to 3 cases without evidence of lymph node metastasis. Aside from lymphovascular invasion in one case with metastasis, there were no overt histologic features of the primary tumor to suggest aggressive biologic behavior. The finding of lymph node metastasis warrants reconsideration of the term “synovial myxoma” for this neoplasm. We suggest the term “synovial myxosarcoma,” considering that histologic features of the primary tumor do not predict biologic behavior. Our case series highlights the importance of lymph node sampling in suspected synovial myxosarcoma cases as well as thorough histologic examination, emphasizing careful evaluation for lymphovascular invasion.