Searcharxiv⌕ Search

arXiv subjects

Jonas S. Almeida

Publications and source records attributed to Jonas S. Almeida.

10 recordsLinked to original sources
arXiv2026

Engineering FAIR Privacy-preserving Applications that Learn Histories of Disease

A recent report on "Learning the natural history of human disease with generative transformers" created an opportunity to assess the engineering challenge of delivering user-facing Generative AI applications in privacy-sensitive domains. The application of these models, particularly for personalized healthcare tasks like predicting individual morbidity risk, is typically constrained by data privacy concerns. This project was accordingly designed as an in-browser model deployment exercise (an "App") testing the architectural boundaries of client-side inference generation (no downloads or installations). We relied exclusively on the documentation provided in the reference report to develop the model, specifically testing the "R" component of the FAIR data principles: Findability, Accessibility, Interoperability, and Reusability. The successful model deployment, leveraging ONNX and a custom JavaScript SDK, establishes a secure, high-performance architectural blueprint for the future of private generative AI in medicine.

cs.LG↗
arXiv2025

Leveraging large language models for structured information extraction from pathology reports

Background: Structured information extraction from unstructured histopathology reports facilitates data accessibility for clinical research. Manual extraction by experts is time-consuming and expensive, limiting scalability. Large language models (LLMs) offer efficient automated extraction through zero-shot prompting, requiring only natural language instructions without labeled data or training. We evaluate LLMs' accuracy in extracting structured information from breast cancer histopathology reports, compared to manual extraction by a trained human annotator. Methods: We developed the Medical Report Information Extractor, a web application leveraging LLMs for automated extraction. We developed a gold standard extraction dataset to evaluate the human annotator alongside five LLMs including GPT-4o, a leading proprietary model, and the Llama 3 model family, which allows self-hosting for data privacy. Our assessment involved 111 histopathology reports from the Breast Cancer Now (BCN) Generations Study, extracting 51 pathology features specified in the study's data dictionary. Results: Evaluation against the gold standard dataset showed that both Llama 3.1 405B (94.7% accuracy) and GPT-4o (96.1%) achieved extraction accuracy comparable to the human annotator (95.4%; p = 0.146 and p = 0.106, respectively). While Llama 3.1 70B (91.6%) performed below human accuracy (p <0.001), its reduced computational requirements make it a viable option for self-hosting. Conclusion: We developed an open-source tool for structured information extraction that can be customized by non-programmers using natural language. Its modular design enables reuse for various extraction tasks, producing standardized, structured data from unstructured text reports to facilitate analytics through improved accessibility and interoperability.

cs.CL↗
arXiv2024

TMA-Grid: An open-source, zero-footprint web application for FAIR Tissue MicroArray De-arraying

Background: Tissue Microarrays (TMAs) significantly increase analytical efficiency in histopathology and large-scale epidemiologic studies by allowing multiple tissue cores to be scanned on a single slide. The individual cores can be digitally extracted and then linked to metadata for analysis in a process known as de-arraying. However, TMAs often contain core misalignments and artifacts due to assembly errors, which can adversely affect the reliability of the extracted cores during the de-arraying process. Moreover, conventional approaches for TMA de-arraying rely on desktop solutions.Therefore, a robust yet flexible de-arraying method is crucial to account for these inaccuracies and ensure effective downstream analyses. Results: We developed TMA-Grid, an in-browser, zero-footprint, interactive web application for TMA de-arraying. This web application integrates a convolutional neural network for precise tissue segmentation and a grid estimation algorithm to match each identified core to its expected location. The application emphasizes interactivity, allowing users to easily adjust segmentation and gridding results. Operating entirely in the web-browser, TMA-Grid eliminates the need for downloads or installations and ensures data privacy. Adhering to FAIR principles (Findable, Accessible, Interoperable, and Reusable), the application and its components are designed for seamless integration into TMA research workflows. Conclusions: TMA-Grid provides a robust, user-friendly solution for TMA dearraying on the web. As an open, freely accessible platform, it lays the foundation for collaborative analyses of TMAs and similar histopathology imaging data. Availability: Web application: https://episphere.github.io/tma-grid Code: https://github.com/episphere/tma-grid Tutorial: https://youtu.be/miajqyw4BVk

q-bio.TO↗
arXiv2024

FastImpute: A Baseline for Open-source, Reference-Free Genotype Imputation Methods -- A Case Study in PRS313

Genotype imputation enhances genetic data by predicting missing SNPs using reference haplotype information. Traditional methods leverage linkage disequilibrium (LD) to infer untyped SNP genotypes, relying on the similarity of LD structures between genotyped target sets and fully sequenced reference panels. Recently, reference-free deep learning-based methods have emerged, offering a promising alternative by predicting missing genotypes without external databases, thereby enhancing privacy and accessibility. However, these methods often produce models with tens of millions of parameters, leading to challenges such as the need for substantial computational resources to train and inefficiency for client-sided deployment. Our study addresses these limitations by introducing a baseline for a novel genotype imputation pipeline that supports client-sided imputation models generalizable across any genotyping chip and genomic region. This approach enhances patient privacy by performing imputation directly on edge devices. As a case study, we focus on PRS313, a polygenic risk score comprising 313 SNPs used for breast cancer risk prediction. Utilizing consumer genetic panels such as 23andMe, our model democratizes access to personalized genetic insights by allowing 23andMe users to obtain their PRS313 score. We demonstrate that simple linear regression can significantly improve the accuracy of PRS313 scores when calculated using SNPs imputed from consumer gene panels, such as 23andMe. Our linear regression model achieved an R^2 of 0.86, compared to 0.33 without imputation and 0.28 with simple imputation (substituting missing SNPs with the minor allele frequency). These findings suggest that popular SNP analysis libraries could benefit from integrating linear regression models for genotype imputation, providing a viable and light-weight alternative to reference based imputation.

q-bio.GN↗
arXiv2024

Finding Regions of Interest in Whole Slide Images Using Multiple Instance Learning

Whole Slide Images (WSI), obtained by high-resolution digital scanning of microscope slides at multiple scales, are the cornerstone of modern Digital Pathology. However, they represent a particular challenge to AI-based/AI-mediated analysis because pathology labeling is typically done at slide-level, instead of tile-level. It is not just that medical diagnostics is recorded at the specimen level, the detection of oncogene mutation is also experimentally obtained, and recorded by initiatives like The Cancer Genome Atlas (TCGA), at the slide level. This configures a dual challenge: a) accurately predicting the overall cancer phenotype and b) finding out what cellular morphologies are associated with it at the tile level. To address these challenges, a weakly supervised Multiple Instance Learning (MIL) approach was explored for two prevalent cancer types, Invasive Breast Carcinoma (TCGA-BRCA) and Lung Squamous Cell Carcinoma (TCGA-LUSC). This approach was explored for tumor detection at low magnification levels and TP53 mutations at various levels. Our results show that a novel additive implementation of MIL matched the performance of reference implementation (AUC 0.96), and was only slightly outperformed by Attention MIL (AUC 0.97). More interestingly from the perspective of the molecular pathologist, these different AI architectures identify distinct sensitivities to morphological features (through the detection of Regions of Interest, RoI) at different amplification levels. Tellingly, TP53 mutation was most sensitive to features at the higher applications where cellular morphology is resolved.

cs.CV↗
arXiv2024

ClusterRadar: an Interactive Web-Tool for the Multi-Method Exploration of Spatial Clusters Over Time

Spatial cluster analysis, the detection of localized patterns of similarity in geospatial data, has a wide-range of applications for scientific discovery and practical decision making. One way to detect spatial clusters is by using local indicators of spatial association, such as Local Moran's I or Getis-Ord Gi*. However, different indicators tend to produce substantially different results due to their distinct operational characteristics. Choosing a suitable method or comparing results from multiple methods is a complex task. Furthermore, spatial clusters are dynamic and it is often useful to track their evolution over time, which adds an additional layer of complexity. ClusterRadar is a web-tool designed to address these analytical challenges. The tool allows users to easily perform spatial clustering and analyze the results in an interactive environment, uniquely prioritizing temporal analysis and the comparison of multiple methods. The tool's interactive dashboard presents several visualizations, each offering a distinct perspective of the temporal and methodological aspects of the spatial clustering results. ClusterRadar has several features designed to maximize its utility to a broad user-base, including support for various geospatial formats, and a fully in-browser execution environment to preserve the privacy of sensitive data. Feedback from a varied set of researchers suggests ClusterRadar's potential for enhancing the temporal analysis of spatial clusters.

cs.HC↗
arXiv2023

Wasm-iCARE: a portable and privacy-preserving web module to build, validate, and apply absolute risk models

Objective: Absolute risk models estimate an individual's future disease risk over a specified time interval. Applications utilizing server-side risk tooling, such as the R-based iCARE (R-iCARE), to build, validate, and apply absolute risk models, face serious limitations in portability and privacy due to their need for circulating user data in remote servers for operation. Our objective was to overcome these limitations. Materials and Methods: We refactored R-iCARE into a Python package (Py-iCARE) then compiled it to WebAssembly (Wasm-iCARE): a portable web module, which operates entirely within the privacy of the user's device. Results: We showcase the portability and privacy of Wasm-iCARE through two applications: for researchers to statistically validate risk models, and to deliver them to end-users. Both applications run entirely on the client-side, requiring no downloads or installations, and keeps user data on-device during risk calculation. Conclusions: Wasm-iCARE fosters accessible and privacy-preserving risk tools, accelerating their validation and delivery.

q-bio.QM↗
arXiv2020

Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor Infiltrating Lymphocytes in Invasive Breast Cancer

Quantitative assessment of Tumor-TIL spatial relationships is increasingly important in both basic science and clinical aspects of breast cancer research. We have developed and evaluated convolutional neural network (CNN) analysis pipelines to generate combined maps of cancer regions and tumor infiltrating lymphocytes (TILs) in routine diagnostic breast cancer whole slide tissue images (WSIs). We produce interactive whole slide maps that provide 1) insight about the structural patterns and spatial distribution of lymphocytic infiltrates and 2) facilitate improved quantification of TILs. We evaluated both tumor and TIL analyses using three CNN networks - Resnet-34, VGG16 and Inception v4, and demonstrated that the results compared favorably to those obtained by what believe are the best published methods. We have produced open-source tools and generated a public dataset consisting of tumor/TIL maps for 1,015 TCGA breast cancer images. We also present a customized web-based interface that enables easy visualization and interactive exploration of high-resolution combined Tumor-TIL maps for 1,015TCGA invasive breast cancer cases that can be downloaded for further downstream analyses.

eess.IV↗
arXiv2006

Nearest neighbor embedding with different time delays

A nearest neighbor based selection of time delays for phase space reconstruction is proposed and compared to the standard use of time delayed mutual information. The possibility of using different time delays for consecutive dimensions is considered. A case study of numerically generated solutions of the Lorenz system is used for illustration. The effect of contamination with various levels of additive Gaussian white noise is discussed.

nlin.CD↗