Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology

• URL: http://arxiv.org/abs/2402.17228v4
• Date: Thu, 25 Jul 2024 01:20:23 GMT
• Title: Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
• Authors: Wenhao Tang, Fengtao Zhou, Sheng Huang, Xiang Zhu, Yi Zhang, Bo Liu,
• Abstract summary: Multiple instance learning (MIL) is the most widely used framework in computational pathology. The existing MIL paradigm typically requires an offline instance feature extractor, such as a pre-trained ResNet or a foundation model. We propose a Re-embedded Regional Transformer (R$2$T) for re-embedding the instance features online, which captures fine-grained local features and establishes connections across different regions.
• Score: 11.840041304518516
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Multiple instance learning (MIL) is the most widely used framework in computational pathology, encompassing sub-typing, diagnosis, prognosis, and more. However, the existing MIL paradigm typically requires an offline instance feature extractor, such as a pre-trained ResNet or a foundation model. This approach lacks the capability for feature fine-tuning within the specific downstream tasks, limiting its adaptability and performance. To address this issue, we propose a Re-embedded Regional Transformer (R$^2$T) for re-embedding the instance features online, which captures fine-grained local features and establishes connections across different regions. Unlike existing works that focus on pre-training powerful feature extractor or designing sophisticated instance aggregator, R$^2$T is tailored to re-embed instance features online. It serves as a portable module that can seamlessly integrate into mainstream MIL models. Extensive experimental results on common computational pathology tasks validate that: 1) feature re-embedding improves the performance of MIL models based on ResNet-50 features to the level of foundation model features, and further enhances the performance of foundation model features; 2) the R$^2$T can introduce more significant performance improvements to various MIL models; 3) R$^2$T-MIL, as an R$^2$T-enhanced AB-MIL, outperforms other latest methods by a large margin.The code is available at: https://github.com/DearCaat/RRT-MIL.

Related papers

• Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology [47.45485718033888]
  We show that supervised end-to-end (E2E) learning faces challenges such as high computational demands and suboptimal results.<n>We propose a novel MIL called ABMILX to mitigate this problem.<n>An E2E trained ResNet with ABMILX surpasses SOTA foundation models under the two-stage paradigm.
  arXiv  Detail & Related papers  (2025-06-03T03:46:50Z)
• SimMIL: A Universal Weakly Supervised Pre-Training Framework for Multi-Instance Learning in Whole Slide Pathology Images [12.827931905880163]
  This paper proposes to pre-train feature extractor for MIL via a weakly-supervised scheme.<n>To learn effective features for MIL, we delve into several key components, including strong data augmentation, a non-linear prediction head and the robust loss function.<n>We conduct experiments on common large-scale WSI datasets and find it achieves better performance than other pre-training schemes.
  arXiv  Detail & Related papers  (2025-05-10T17:23:36Z)
• A Spatially-Aware Multiple Instance Learning Framework for Digital Pathology [4.012490059423154]
  Multiple instance learning (MIL) is a promising approach for weakly supervised classification in pathology using whole slide images. Recent advancements, such as Transformer based MIL (TransMIL), have incorporated spatial context and inter-patch relationships. In this work, we enhance the ABMIL framework by integrating interaction-aware representations to address this question.
  arXiv  Detail & Related papers  (2025-04-24T08:53:46Z)
• How Effective Can Dropout Be in Multiple Instance Learning ? [2.0792866989795864]
  Multiple Instance Learning (MIL) is a popular weakly-supervised method for various applications. We propose a novel MIL-specific dropout method, termed MIL-Dropout, which systematically determines which instances to drop. Experiments on five MIL benchmark datasets and two WSI datasets demonstrate that MIL-Dropout boosts the performance of current MIL methods with a negligible computational cost.
  arXiv  Detail & Related papers  (2025-04-21T00:46:31Z)
• Reinforced Model Merging [53.84354455400038]
  We present an innovative framework termed Reinforced Model Merging (RMM), which encompasses an environment and agent tailored for merging tasks. By utilizing data subsets during the evaluation process, we addressed the bottleneck in the reward feedback phase, thereby accelerating RMM by up to 100 times.
  arXiv  Detail & Related papers  (2025-03-27T08:52:41Z)
• Mamba2MIL: State Space Duality Based Multiple Instance Learning for Computational Pathology [17.329498427735565]
  We propose a novel Multiple Instance Learning framework called Mamba2MIL. Mamba2MIL exploits order-related and order-independent features, resulting in suboptimal utilization of sequence information. We conduct extensive experiments across multiple datasets, achieving improvements in nearly all performance metrics.
  arXiv  Detail & Related papers  (2024-08-27T13:01:19Z)
• The Power of Resets in Online Reinforcement Learning [73.64852266145387]
  We explore the power of simulators through online reinforcement learning with local simulator access (or, local planning) We show that MDPs with low coverability can be learned in a sample-efficient fashion with only $Qstar$-realizability. We show that the notorious Exogenous Block MDP problem is tractable under local simulator access.
  arXiv  Detail & Related papers  (2024-04-23T18:09:53Z)
• MamMIL: Multiple Instance Learning for Whole Slide Images with State Space Models [56.37780601189795]
  We propose a framework named MamMIL for WSI analysis. We represent each WSI as an undirected graph. To address the problem that Mamba can only process 1D sequences, we propose a topology-aware scanning mechanism.
  arXiv  Detail & Related papers  (2024-03-08T09:02:13Z)
• MatFormer: Nested Transformer for Elastic Inference [91.45687988953435]
  MatFormer is a novel Transformer architecture designed to provide elastic inference across diverse deployment constraints. MatFormer achieves this by incorporating a nested Feed Forward Network (FFN) block structure within a standard Transformer model. We show that a 850M decoder-only MatFormer language model (MatLM) allows us to extract multiple smaller models spanning from 582M to 850M parameters.
  arXiv  Detail & Related papers  (2023-10-11T17:57:14Z)
• PDL: Regularizing Multiple Instance Learning with Progressive Dropout Layers [2.069061136213899]
  Multiple instance learning (MIL) was a weakly supervised learning approach that sought to assign binary class labels to collections of instances known as bags. We present a novel approach in the form of a Progressive Dropout Layer (PDL) to address overfitting and empower the MIL model in uncovering intricate and impactful feature representations.
  arXiv  Detail & Related papers  (2023-08-19T21:20:30Z)
• TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classification [13.195971707693365]
  We develop a Trainable Prototype enhanced deep MIL framework for weakly supervised WSI classification. Our method is able to reveal the correlations between different tumor subtypes through distances between corresponding trained prototypes. We test our method on two WSI datasets and it achieves a new SOTA.
  arXiv  Detail & Related papers  (2023-05-01T07:39:19Z)
• Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning [70.52689048213398]
  This paper studies the performance of overfitted meta-learning under a linear regression model with Gaussian features. We find new and interesting properties that do not exist in single-task linear regression. Our analysis suggests that benign overfitting is more significant and easier to observe when the noise and the diversity/fluctuation of the ground truth of each training task are large.
  arXiv  Detail & Related papers  (2023-04-09T20:36:13Z)
• Feature Re-calibration based MIL for Whole Slide Image Classification [7.92885032436243]
  Whole slide image (WSI) classification is a fundamental task for the diagnosis and treatment of diseases. We propose to re-calibrate the distribution of a WSI bag (instances) by using the statistics of the max-instance (critical) feature. We employ a position encoding module (PEM) to model spatial/morphological information, and perform pooling by multi-head self-attention (PSMA) with a Transformer encoder.
  arXiv  Detail & Related papers  (2022-06-22T07:00:39Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)
• CIL: Contrastive Instance Learning Framework for Distantly Supervised Relation Extraction [52.94486705393062]
  We go beyond typical multi-instance learning (MIL) framework and propose a novel contrastive instance learning (CIL) framework. Specifically, we regard the initial MIL as the relational triple encoder and constraint positive pairs against negative pairs for each instance. Experiments demonstrate the effectiveness of our proposed framework, with significant improvements over the previous methods on NYT10, GDS and KBP.
  arXiv  Detail & Related papers  (2021-06-21T04:51:59Z)
• Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting [60.98700344526674]
  Low-complexity models such as linear function representation play a pivotal role in enabling sample-efficient reinforcement learning. In this paper, we investigate a new sampling protocol, which draws samples in an online/exploratory fashion but allows one to backtrack and revisit previous states in a controlled and infrequent manner. We develop an algorithm tailored to this setting, achieving a sample complexity that scales practicallyly with the feature dimension, the horizon, and the inverse sub-optimality gap, but not the size of the state/action space.
  arXiv  Detail & Related papers  (2021-05-17T17:22:07Z)
• Dual-stream Maximum Self-attention Multi-instance Learning [11.685285490589981]
  Multi-instance learning (MIL) is a form of weakly supervised learning where a single class label is assigned to a bag of instances while the instance-level labels are not available. We propose a dual-stream maximum self-attention MIL model (DSMIL) parameterized by neural networks. Our method achieves superior performance compared to the best MIL methods and demonstrates state-of-the-art performance on benchmark MIL datasets.
  arXiv  Detail & Related papers  (2020-06-09T22:44:58Z)

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.