Privacy-Preserving Detection of Rare Disease-Associated Cell Subsets via Secure Multi-Party Computation

• URL: http://arxiv.org/abs/2608.20118v1
• Date: Thu, 20 Aug 2026 14:49:45 GMT
• Title: Privacy-Preserving Detection of Rare Disease-Associated Cell Subsets via Secure Multi-Party Computation
• Abstract summary: A convolutional neural network (CNN) designed for this task has demonstrated the ability to identify phenotype-associated cell populations at frequencies as low as 0.01%.<n>We propose a secure multi-party computation framework that enables the training and inference of CellCnn entirely on secret-shared data.
• Score: 0.7829352305480284
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The detection of rare disease-associated cell subsets from high-dimensional single-cell measurements is critical for understanding diseases such as leukaemia and viral infections. CellCnn, a convolutional neural network (CNN) designed for this task, has demonstrated the ability to identify phenotype-associated cell populations at frequencies as low as 0.01\%. Training such models reliably requires patient cohorts that are larger and more diverse than any single institution can typically assemble, and the underlying single-cell data is too sensitive to share across institutional boundaries under existing privacy regulations. We propose a secure multi-party computation (MPC) framework that enables the training and inference of CellCnn entirely on secret-shared data. This ensures that neither the participants nor the computing servers ever observe raw patient data or intermediate values. Evaluated on benchmark single-cell datasets for cytomegalovirus infection (CMV) and acute myeloid leukaemia (AML), our implementation preserves accuracy close to its plaintext counterpart while outperforming the prior privacy-preserving baseline. In contrast to earlier privacy-preserving approaches that removed components such as ReLU activations and bias terms, our method retains these key parts of the CellCnn architecture and supports accurate analysis without exposing raw patient data.

Related papers

• CytoBERT: A Foundation Model for Cytometry Data [0.7209218072712748]
  CytoBERT is a publicly available, open-source, open-weight foundation model for single-cell data with variable marker panels.<n>It is pretrained in a self-supervised manner on a large-scale corpus (15 human datasets with heterogeneous marker panels and more than 50 million cells)<n>It curated through marker standardization, enabling it to learn transferable inter-marker relationships within cells.
  arXiv  Detail & Related papers  (2026-08-14T15:57:35Z)
• Differentially Private Modeling of Disease Transmission within Human Contact Networks [5.169635993076461]
  We propose a privacy-preserving pipeline for disease spread simulation studies based on a sensitive network.<n>We evaluate the effectiveness of our approach using a simple Susceptible-Infected-Susceptible disease model.
  arXiv  Detail & Related papers  (2026-04-08T18:34:20Z)
• Key-Embedded Privacy for Decentralized AI in Biomedical Omics [43.072683741556126]
  We present a lightweight federated learning method, INFL, based on Implicit Neural Representations.<n>INFL achieves strong, controllable privacy while maintaining utility, preserving utility for downstream scientific and clinical applications.
  arXiv  Detail & Related papers  (2026-03-30T12:04:50Z)
• An N-of-1 Artificial Intelligence Ecosystem for Precision Medicine [1.2578552444269682]
  We propose a multi-agent ecosystem for N-of-1 decision support.<n>Agents draw on a shared library of models and evidence synthesis tools.<n>This approach seeks to align medical AI with the first principle of medicine: care that is transparent, equitable, and centered on the individual.
  arXiv  Detail & Related papers  (2025-10-28T12:28:02Z)
• Adaptable Cardiovascular Disease Risk Prediction from Heterogeneous Data using Large Language Models [70.64969663547703]
  AdaCVD is an adaptable CVD risk prediction framework built on large language models extensively fine-tuned on over half a million participants from the UK Biobank.<n>It addresses key clinical challenges across three dimensions: it flexibly incorporates comprehensive yet variable patient information; it seamlessly integrates both structured data and unstructured text; and it rapidly adapts to new patient populations using minimal additional data.
  arXiv  Detail & Related papers  (2025-05-30T14:42:02Z)
• Fourier Asymmetric Attention on Domain Generalization for Pan-Cancer Drug Response Prediction [11.649397977546435]
  We propose a novel domain generalization framework, termed FourierDrug, to address this challenge.<n>Our experiments demonstrate that our model effectively learns task-relevant features from diverse source domains, and accurate predictions of drug response for unseen cancer type.<n>These findings underscore the potential of our method for real-world clinical applications.
  arXiv  Detail & Related papers  (2025-02-06T12:53:45Z)
• MMIL: A novel algorithm for disease associated cell type discovery [58.044870442206914]
  Single-cell datasets often lack individual cell labels, making it challenging to identify cells associated with disease. We introduce Mixture Modeling for Multiple Learning Instance (MMIL), an expectation method that enables the training and calibration of cell-level classifiers.
  arXiv  Detail & Related papers  (2024-06-12T15:22:56Z)
• DNA: Differentially private Neural Augmentation for contact tracing [62.740950398187664]
  Contact tracing is an effective way to reduce infection rates by detecting potential virus carriers early. We substantially improve the privacy guarantees of the current state of the art in decentralized contact tracing. This work marks an important first step in integrating deep learning into contact tracing while maintaining essential privacy guarantees.
  arXiv  Detail & Related papers  (2024-04-20T13:43:28Z)
• Single-Cell Deep Clustering Method Assisted by Exogenous Gene Information: A Novel Approach to Identifying Cell Types [50.55583697209676]
  We develop an attention-enhanced graph autoencoder, which is designed to efficiently capture the topological features between cells. During the clustering process, we integrated both sets of information and reconstructed the features of both cells and genes to generate a discriminative representation. This research offers enhanced insights into the characteristics and distribution of cells, thereby laying the groundwork for early diagnosis and treatment of diseases.
  arXiv  Detail & Related papers  (2023-11-28T09:14:55Z)
• Single-cell Multi-view Clustering via Community Detection with Unknown Number of Clusters [64.31109141089598]
  We introduce scUNC, an innovative multi-view clustering approach tailored for single-cell data. scUNC seamlessly integrates information from different views without the need for a predefined number of clusters. We conducted a comprehensive evaluation of scUNC using three distinct single-cell datasets.
  arXiv  Detail & Related papers  (2023-11-28T08:34:58Z)
• Distribution-based Sketching of Single-Cell Samples [6.904244323294012]
  We propose a novel sketching approach based on Kernel Herding that selects a limited subsample of all cells while preserving the underlying frequencies of immune cell-types. We tested our approach on three flow and mass datasets and on one single-cell RNA sequencing dataset.
  arXiv  Detail & Related papers  (2022-06-30T19:43:06Z)
• Towards an Automatic Analysis of CHO-K1 Suspension Growth in Microfluidic Single-cell Cultivation [63.94623495501023]
  We propose a novel Machine Learning architecture, which allows us to infuse a neural deep network with human-powered abstraction on the level of data. Specifically, we train a generative model simultaneously on natural and synthetic data, so that it learns a shared representation, from which a target variable, such as the cell count, can be reliably estimated.
  arXiv  Detail & Related papers  (2020-10-20T08:36:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.