Leukemia cutis (LC), a rare cutaneous manifestation of leukemia, can precede, follow, occur concurrently with, or present in the absence of (aleukemic) systemic leukemia. Leukemia cutis is especially rare as the presenting symptom of leukemia and is associated with a poor prognosis. Although more commonly seen in acute leukemias of myeloid and monocytic lineage, lymphocytic/lymphoblastic leukemias can also involve the skin. Three cases of LC presented with diverse skin lesions ranging from an erythematous rash to violaceous macules and papules to subcutaneous nodules. One case clinically mimicked fixed drug eruption. All the patients had acute myeloid leukemia (AML). Lesions showed two overarching histologic patterns: atypical perivascular infiltrate or nodular dermal histiocytoid infiltrate. Our cases expressed myeloperoxidase (MPO), a helpful marker to distinguish myeloid from non-myeloid cells, and CD68, a monocytic marker frequently expressed in cutaneous AML. CD14, a marker of monocyte maturity, was negative. In the absence of systemic leukemia, common diagnostic tools for hematologic malignancies such as bone marrow biopsy and flow cytometry are non-contributory, making morphologic and immunohistochemical analysis of the skin lesions key to diagnosis.

Pathologists are responsible for rapidly providing a diagnosis on critical health issues. Challenging cases benefit from additional opinions of pathologist colleagues. In addition to on-site colleagues, there is an active worldwide community of pathologists on social media for complementary opinions. Such access to pathologists worldwide has the capacity to improve diagnostic accuracy and generate broader consensus on next steps in patient care. From Twitter we curate 13,626 images from 6,351 tweets from 25 pathologists from 13 countries. We supplement the Twitter data with 113,161 images from 1,074,484 PubMed articles. We develop machine learning and deep learning models to (i) accurately identify histopathology stains, (ii) discriminate between tissues, and (iii) differentiate disease states. Area Under Receiver Operating Characteristic (AUROC) is 0.805-0.996 for these tasks. We repurpose the disease classifier to search for similar disease states given an image and clinical covariates. We report precision@k = 1 = 0.7618 ± 0.0018 (chance 0.397 ± 0.004, mean ±stdev ). The classifiers find that texture and tissue are important clinico-visual features of disease. Deep features trained only on natural images (e.g., cats and dogs) substantially improved search performance, while pathology-specific deep features and cell nuclei features further improved search to a lesser extent. We implement a social media bot (@pathobot on Twitter) to use the trained classifiers to aid pathologists in obtaining real-time feedback on challenging cases. If a social media post containing pathology text and images mentions the bot, the bot generates quantitative predictions of disease state (normal/artifact/infection/injury/nontumor, preneoplastic/benign/low-grade-malignant-potential, or malignant) and lists similar cases across social media and PubMed. Our project has become a globally distributed expert system that facilitates pathological diagnosis and brings expertise to underserved regions or hospitals with less expertise in a particular disease. This is the first pan-tissue pan-disease (i.e., from infection to malignancy) method for prediction and search on social media, and the first pathology study prospectively tested in public on social media. We will share data through http://pathobotology.org . We expect our project to cultivate a more connected world of physicians and improve patient care worldwide.