Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology

• URL: http://arxiv.org/abs/2404.10242v1
• Date: Tue, 16 Apr 2024 02:42:06 GMT
• Title: Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology
• Authors: Oren Kraus, Kian Kenyon-Dean, Saber Saberian, Maryam Fallah, Peter McLean, Jess Leung, Vasudev Sharma, Ayla Khan, Jia Balakrishnan, Safiye Celik, Dominique Beaini, Maciej Sypetkowski, Chi Vicky Cheng, Kristen Morse, Maureen Makes, Ben Mabey, Berton Earnshaw,
• Abstract summary: This work explores the scaling properties of weakly supervised classifiers and self-supervised masked autoencoders (MAEs) Our results show that ViT-based MAEs outperform weakly supervised classifiers on a variety of tasks, achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from public databases. We develop a new channel-agnostic MAE architecture (CA-MAE) that allows for inputting images of different numbers and orders of channels at inference time.
• Score: 2.7280901660033643
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Featurizing microscopy images for use in biological research remains a significant challenge, especially for large-scale experiments spanning millions of images. This work explores the scaling properties of weakly supervised classifiers and self-supervised masked autoencoders (MAEs) when training with increasingly larger model backbones and microscopy datasets. Our results show that ViT-based MAEs outperform weakly supervised classifiers on a variety of tasks, achieving as much as a 11.5% relative improvement when recalling known biological relationships curated from public databases. Additionally, we develop a new channel-agnostic MAE architecture (CA-MAE) that allows for inputting images of different numbers and orders of channels at inference time. We demonstrate that CA-MAEs effectively generalize by inferring and evaluating on a microscopy image dataset (JUMP-CP) generated under different experimental conditions with a different channel structure than our pretraining data (RPI-93M). Our findings motivate continued research into scaling self-supervised learning on microscopy data in order to create powerful foundation models of cellular biology that have the potential to catalyze advancements in drug discovery and beyond.

Related papers

• ViTally Consistent: Scaling Biological Representation Learning for Cell Microscopy [3.432992120614117]
  We present the largest foundation model for cell microscopy data to date. Compared to a previous published ViT-L/8 MAE, our new model achieves a 60% improvement in linear separability of genetic perturbations.
  arXiv  Detail & Related papers  (2024-11-04T20:09:51Z)
• μ-Bench: A Vision-Language Benchmark for Microscopy Understanding [43.27182445778988]
  Vision-language models (VLMs) offer a promising solution for large-scale biological image analysis. There is a lack of standardized, diverse, and large-scale vision-language benchmarks to evaluate VLMs. mu-Bench is an expert-curated benchmark encompassing 22 biomedical tasks.
  arXiv  Detail & Related papers  (2024-07-01T20:30:26Z)
• Weakly Supervised Set-Consistency Learning Improves Morphological Profiling of Single-Cell Images [0.6491172192043603]
  We propose a set-level consistency learning algorithm, Set-DINO, to improve learned representations of perturbation effects in single-cell images. We conduct experiments on a large-scale Optical Pooled Screening dataset with more than 5000 genetic perturbations.
  arXiv  Detail & Related papers  (2024-06-08T00:53:30Z)
• Masked Autoencoders are Scalable Learners of Cellular Morphology [0.3057210732296065]
  This work explores how self-supervised deep learning approaches scale when training larger models on larger microscopy datasets. Our results show that both CNN- and ViT-based masked autoencoders significantly outperform weakly supervised baselines.
  arXiv  Detail & Related papers  (2023-09-27T23:11:35Z)
• SurgMAE: Masked Autoencoders for Long Surgical Video Analysis [4.866110274299399]
  Masked autoencoders (MAE) got the attention in self-supervised paradigm for Vision Transformers (ViTs) In this paper, we first investigate whether MAE can learn transferrable representations in surgical video domain. We propose SurgMAE, which is a novel architecture with a masking strategy on sampling high-temporal tokens for MAE.
  arXiv  Detail & Related papers  (2023-05-19T06:12:50Z)
• Optimizations of Autoencoders for Analysis and Classification of Microscopic In Situ Hybridization Images [68.8204255655161]
  We propose a deep-learning framework to detect and classify areas of microscopic images with similar levels of gene expression. The data we analyze requires an unsupervised learning model for which we employ a type of Artificial Neural Network - Deep Learning Autoencoders.
  arXiv  Detail & Related papers  (2023-04-19T13:45:28Z)
• AMIGO: Sparse Multi-Modal Graph Transformer with Shared-Context Processing for Representation Learning of Giga-pixel Images [53.29794593104923]
  We present a novel concept of shared-context processing for whole slide histopathology images. AMIGO uses the celluar graph within the tissue to provide a single representation for a patient. We show that our model is strongly robust to missing information to an extent that it can achieve the same performance with as low as 20% of the data.
  arXiv  Detail & Related papers  (2023-03-01T23:37:45Z)
• SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology [48.54269377408277]
  We introduce the Self-Enhancing Multi-Photon Artificial Intelligence (SEMPAI), that integrates hypothesis-driven priors in a data-driven Deep Learning approach. SEMPAI performs joint learning of several tasks to enable prediction for small datasets. SEMPAI outperforms state-of-the-art biomarkers in six of seven predictive tasks, including those with scarce data.
  arXiv  Detail & Related papers  (2022-10-28T17:03:04Z)
• Learning multi-scale functional representations of proteins from single-cell microscopy data [77.34726150561087]
  We show that simple convolutional networks trained on localization classification can learn protein representations that encapsulate diverse functional information. We also propose a robust evaluation strategy to assess quality of protein representations across different scales of biological function.
  arXiv  Detail & Related papers  (2022-05-24T00:00:07Z)
• Deep neural networks approach to microbial colony detection -- a comparative analysis [52.77024349608834]
  This study investigates the performance of three deep learning approaches for object detection on the AGAR dataset. The achieved results may serve as a benchmark for future experiments.
  arXiv  Detail & Related papers  (2021-08-23T12:06:00Z)
• 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.