Biology subjects

Sirintrapun, S. J.

Publications and source records attributed to Sirintrapun, S. J..

4 recordsLinked to original sources

bioRxiv2026

Weak supervision of H&E slides reveals systems-level biology and functional states that govern therapeutic resistance

Precision oncology lacks scalable methods to identify the mechanisms that mediate therapeutic resistance for individual patients. Resistance often arises from focal cellular niches that are obscured by bulk profiling and costly to resolve with multi-omics. Here, we show that deep learning (DL), applied to routine histology, can localize focal tissue regions enriched for therapeutically relevant biology. Using 3111 breast cancer H&E slides with matched bulk transcriptomics, we trained weakly-supervised DL models to infer activities of immune, metabolic, and tumor-intrinsic phenotypes implicated in therapeutic resistance (AUROC>0.80; PCC>0.64). Accurate inference of these phenotypes should identify tissue regions enriched for the corresponding biological signal. Therefore, we validated phenotype inference and spatial localization with complementary analyses. Tissue-matched multiplexed immunofluorescence showed concordance between inferred immune states and corresponding cell fractions (p=0.006-0.106). Across multi-institutional cohorts, model-derived phenotypes recovered expected relationships with therapeutic outcomes (p<0.045). Finally, in a blinded evaluation, pathologists confirmed that model-derived high-attention regions were enriched for phenotype-specific morphology (p<2.408*10-5). Because evaluated phenotypes represent diverse mechanisms of resistance across therapeutic modalities, these findings provide a foundation for resistance-directed localization using therapeutic outcomes as supervision. By directing deep profiling toward model-prioritized regions, this framework could enable scalable nomination of candidate mediators of resistance for subsequent functional validation across real-world patient populations. One sentence summaryWeakly supervised deep learning localizes focal tissue regions enriched for therapeutically relevant biology in routine histology, thus offering a scalable strategy to study therapeutic resistance across large patient populations.

biophysics↗

bioRxiv2025

ESPWA: a deep learning-enabled tool for precision-based use of endocrine therapy in resource-limited settings

Immunohistochemistry for estrogen receptor (ER) expression is often unavailable in low-and-middle-income countries (LMICs), leading to empiric use of endocrine therapy (ET) and unnecessary toxicity in ER-negative patients. To address this unmet need, we developed ESPWA, a deep-learning model trained on 3448 H&E slides and tissue-matched ER status from breast cancer patients treated at Zanmi Lasante (ZL), Haiti. A model trained on The Cancer Genome Atlas (TCGA) exhibited substantial domain shift when applied to the ZL cohort, with AUROCs dropping from 0.846 on TCGA cross-validation to 0.671 on the ZL cohort. In contrast, ESPWA demonstrated improved performance on ZL cross-validation (AUROC=0.790; p=0.005). In an independent test set of 134 Haitian patients with parallel slides prepared and scanned in Mirebalais Hospital (Haiti) and Brigham and Womens Hospital, ESPWA was robust to variations in slide preparation, quality, and scanners, achieving AUROCs of 0.794 on BWH-prepared WSIs and 0.805 on Mirebalais-prepared WSIs. Prospective studies using ESPWA are underway in sub-Saharan Africa to evaluate its utility in informing precision-based use of ET.

cancer biology↗

bioRxiv2018

Large-Scale Annotation of Histopathology Images from 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 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 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, pre-neoplastic/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 pathobotology.org. We expect our project to cultivate a more connected world of physicians and improve patient care worldwide.

pathology↗

bioRxiv2016

DeepScope: Nonintrusive Whole Slide Saliency Annotation and Prediction from Pathologists at the Microscope

Modern digital pathology departments have grown to produce whole-slide image data at petabyte scale, an unprecedented treasure chest for medical machine learning tasks. Unfortunately, most digital slides are not annotated at the image level, hindering large-scale application of supervised learning. Manual labeling is prohibitive, requiring pathologists with decades of training and outstanding clinical service responsibilities. This problem is further aggravated by the United States Food and Drug Administrations ruling that primary diagnosis must come from a glass slide rather than a digital image. We present the first end-to-end framework to overcome this problem, gathering annotations in a nonintrusive manner during a pathologists routine clinical work: (i) microscope-specific 3D-printed commodity camera mounts are used to video record the glass-slide-based clinical diagnosis process; (ii) after routine scanning of the whole slide, the video frames are registered to the digital slide; (iii) motion and observation time are estimated to generate a spatial and temporal saliency map of the whole slide. Demonstrating the utility of these annotations, we train a convolutional neural network that detects diagnosis-relevant salient regions, then report accuracy of 85.15% in bladder and 91.40% in prostate, with 75.00% accuracy when training on prostate but predicting in bladder, despite different pathologists examining the different tissues. When training on one patient but testing on another, AUROC in bladder is 0.7929 0.1109 and in prostate is 0.9568{+/-}0.0374. Our tool is available at https://bitbucket.org/aschaumberg/deepscope.

pathology↗