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

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.

Clinical and pathological features of colorectal cancer in patients at a community hospital in Puerto Rico.

OBJECTIVE: Colorectal cancer (CRC) is among the most common cancers in Puerto Rico. Few studies have correlated clinical and pathological variables with the overall survival of CRC patients in Puerto Rico. We report the clinical and pathological characteristics of patients who underwent surgical resection at a community hospital in Puerto Rico. METHODS: Demographic and pathological variables of patients who underwent CRC surgery at Hospital del Maestro from 2006 through 2011 were reviewed. Descriptive statistics (mean, range, and frequency) and the Cox proportional hazards model were used to determine the influence of demographic and pathological variables on survival, after adjusting for age. RESULTS: Two hundred and five CRC pathology reports were reviewed. Adenocarcinoma represented the most common pathology (202/205; 98.5%). Females represented 52% of the population (106/202) while males represented 48% (96/202). The median age was 71 years (30-96). The right colon was the most common site of presentation (49.7%; 100/201). Stage III was the most common stage at presentation. The presence of mucin, perineural or lymphatic invasion and tumor size were not related to decreased survival. Being male, having a higher stage at diagnosis, and having a moderately or poorly differentiated tumor were characteristics related to decreased survival. CONCLUSION: This study provides information on clinical and pathological variables and their influence on the overall survival of CRC patients at a community hospital in Puerto Rico. Further research must be performed to identify potential disparities and their influence on the prognosis of this patients.