Journal article
Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media
Modern pathology, Vol.33(11), pp.2169-2185
11/2020
DOI: 10.1038/s41379-020-0540-1
PMCID: PMC7581495
PMID: 32467650
Abstract
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.
Details
- Title: Subtitle
- Interpretable multimodal deep learning for real-time pan-tissue pan-disease pathology search on social media
- Creators
- Andrew J Schaumberg - Cornell UniversityWendy C Juarez-Nicanor - Manhattan/Hunter Science High School, New York, NY, USASarah J Choudhury - Cornell UniversityLaura G Pastrián - Hospital Universitario La PazBobbi S Pritt - Mayo ClinicMario Prieto Pozuelo - Hospital Universitario HM SanchinarroRicardo Sotillo Sánchez - Departamento de Patología, Virgen de Altagracia Hospital, Manzanares, SpainKhanh Ho - Centre Hospitalier de MouscronNusrat Zahra - Allama Iqbal Medical CollegeBetul Duygu Sener - Department of Pathology, Konya Training and Research Hospital, Konya, Turkey.Stephen Yip - Department of Pathology, BC Cancer, Vancouver, BC, CanadaBin Xu - Health Sciences CentreSrinivas Rao Annavarapu - Royal Victoria InfirmaryAurélien Morini - Université Paris CitéKarra A Jones - University of IowaKathia Rosado-Orozco - HRP Labs, San Juan, PR, USASanjay Mukhopadhyay - Cleveland ClinicCarlos Miguel - Department of Pathology, Centro Médico de Asturias, Oviedo, Spain.Hongyu Yang - Department of Pathology, St Vincent Evansville Hospital, Evansville, IN, USA.Yale Rosen - SUNY Downstate Medical CenterRola H Ali - Kuwait UniversityOlaleke O Folaranmi - University of IlorinJerad M Gardner - University of Arkansas for Medical SciencesCorina Rusu - Department of Pathology, Augusta Hospital, Bochum, Germany.Celina Stayerman - Laboratorio TechniPath, San Pedro Sula, Honduras.John Gross - Mayo ClinicDauda E Suleiman - Abubakar Tafawa Balewa UniversityS Joseph Sirintrapun - Memorial Sloan Kettering Cancer CenterMariam Aly - Columbia UniversityThomas J Fuchs - Cornell University
- Resource Type
- Journal article
- Publication Details
- Modern pathology, Vol.33(11), pp.2169-2185
- DOI
- 10.1038/s41379-020-0540-1
- PMID
- 32467650
- PMCID
- PMC7581495
- ISSN
- 0893-3952
- eISSN
- 1530-0285
- Grant note
- F31 CA214029 / NCI NIH HHS P30 CA008748 / NCI NIH HHS T32 GM083937 / NIGMS NIH HHS
- Language
- English
- Date published
- 11/2020
- Academic Unit
- Pathology
- Record Identifier
- 9984186634702771
Metrics
13 Record Views