Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media

Andrew J. Schaumberg, Wendy C. Juarez-Nicanor, Sarah J. Choudhury, Laura G. Pastrián, Bobbi S. Pritt, Mario Prieto Pozuelo, Ricardo Sotillo Sánchez, Khanh Ho, Nusrat Zahra, Betul Duygu Sener, Stephen Yip, Bin Xu, Srinivas Rao Annavarapu, Aurélien Morini, Karra A. Jones, Kathia Rosado-Orozco, Sanjay Mukhopadhyay, Carlos Miguel, Hongyu Yang, Yale RosenRola H. Ali, Olaleke O. Folaranmi, Jerad M. Gardner, Corina Rusu, Celina Stayerman, John Gross, Dauda E. Suleiman, S. Joseph Sirintrapun, Mariam Aly, Thomas J. Fuchs

Research output: Contribution to journalArticlepeer-review

5 Scopus citations


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 We expect our project to cultivate a more connected world of physicians and improve patient care worldwide.

Original languageEnglish (US)
Pages (from-to)2169-2185
Number of pages17
JournalModern Pathology
Issue number11
StatePublished - Nov 1 2020

ASJC Scopus subject areas

  • General Medicine


Dive into the research topics of 'Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media'. Together they form a unique fingerprint.

Cite this