Establishing Truly Causal Relationship Between Whole Slide Image Predictions and Diagnostic Evidence Subregions in Deep Learning
- URL: http://arxiv.org/abs/2407.17157v1
- Date: Wed, 24 Jul 2024 11:00:08 GMT
- Title: Establishing Truly Causal Relationship Between Whole Slide Image Predictions and Diagnostic Evidence Subregions in Deep Learning
- Authors: Tianhang Nan, Yong Ding, Hao Quan, Deliang Li, Mingchen Zou, Xiaoyu Cui,
- Abstract summary: Multiple Instance Learning (MIL) has gained significant attention due to its ability to be trained using only slide-level diagnostic labels.
Previous MIL researches have primarily focused on enhancing feature aggregators for globally analyzing WSIs, but overlook a causal relationship in diagnosis.
We propose Causal Inference Multiple Instance Learning (CI-MIL) to establish the truly causal relationship between model predictions and diagnostic evidence regions.
- Score: 3.783430751544095
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: In the field of deep learning-driven Whole Slide Image (WSI) classification, Multiple Instance Learning (MIL) has gained significant attention due to its ability to be trained using only slide-level diagnostic labels. Previous MIL researches have primarily focused on enhancing feature aggregators for globally analyzing WSIs, but overlook a causal relationship in diagnosis: model's prediction should ideally stem solely from regions of the image that contain diagnostic evidence (such as tumor cells), which usually occupy relatively small areas. To address this limitation and establish the truly causal relationship between model predictions and diagnostic evidence regions, we propose Causal Inference Multiple Instance Learning (CI-MIL). CI-MIL integrates feature distillation with a novel patch decorrelation mechanism, employing a two-stage causal inference approach to distill and process patches with high diagnostic value. Initially, CI-MIL leverages feature distillation to identify patches likely containing tumor cells and extracts their corresponding feature representations. These features are then mapped to random Fourier feature space, where a learnable weighting scheme is employed to minimize inter-feature correlations, effectively reducing redundancy from homogenous patches and mitigating data bias. These processes strengthen the causal relationship between model predictions and diagnostically relevant regions, making the prediction more direct and reliable. Experimental results demonstrate that CI-MIL outperforms state-of-the-art methods. Additionally, CI-MIL exhibits superior interpretability, as its selected regions demonstrate high consistency with ground truth annotations, promising more reliable diagnostic assistance for pathologists.
Related papers
- Augmentation-based Unsupervised Cross-Domain Functional MRI Adaptation for Major Depressive Disorder Identification [23.639488571585044]
Major depressive disorder (MDD) is a common mental disorder that typically affects a person's mood, cognition, behavior, and physical health.
In this work, we propose a new augmentation-based unsupervised cross-domain fMRI adaptation framework for automatic diagnosis of MDD.
arXiv Detail & Related papers (2024-05-31T13:55:33Z) - Semantics-Aware Attention Guidance for Diagnosing Whole Slide Images [5.856390270089738]
We introduce a novel framework named Semantics-Aware Attention Guidance (SAG)
SAG includes 1) a technique for converting diagnostically relevant entities into attention signals, and 2) a flexible attention loss that efficiently integrates semantically significant information.
Our experiments on two distinct cancer datasets demonstrate consistent improvements in accuracy, precision, and recall.
arXiv Detail & Related papers (2024-04-16T20:37:14Z) - Diagnosis Of Takotsubo Syndrome By Robust Feature Selection From The
Complex Latent Space Of DL-based Segmentation Network [4.583480375083946]
Using classification or segmentation models on medical to learn latent features opt out robust feature selection and may lead to overfitting.
We propose a novel feature selection technique using the latent space of a segmentation model that can aid diagnosis.
Our approach shows promising results in differential diagnosis of a rare cardiac disease with 82% diagnosis accuracy beating the previous state-of-the-art (SOTA) approach.
arXiv Detail & Related papers (2023-12-19T22:53:32Z) - Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites:
A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area.
We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions.
We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
arXiv Detail & Related papers (2023-08-31T00:36:10Z) - CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and
Subtyping in Whole Slide Images [0.0]
We propose the Context-Aware Multiple Instance Learning (CAMIL) architecture for cancer diagnosis.
CAMIL incorporates neighbor-constrained attention to consider dependencies among tiles within a Whole Slide Images (WSI) and integrates contextual constraints as prior knowledge into the MIL model.
We evaluate CAMIL on subtyping non-small cell lung cancer (TCGA-NSCLC) and detecting lymph node metastasis, achieving test AUCs of 0.959% and 0.975%, respectively.
arXiv Detail & Related papers (2023-05-09T10:06:37Z) - Ambiguous Medical Image Segmentation using Diffusion Models [60.378180265885945]
We introduce a single diffusion model-based approach that produces multiple plausible outputs by learning a distribution over group insights.
Our proposed model generates a distribution of segmentation masks by leveraging the inherent sampling process of diffusion.
Comprehensive results show that our proposed approach outperforms existing state-of-the-art ambiguous segmentation networks.
arXiv Detail & Related papers (2023-04-10T17:58:22Z) - Deep Stable Representation Learning on Electronic Health Records [8.256340233221112]
Causal Healthcare Embedding (CHE) aims at eliminating the spurious statistical relationship by removing the dependencies between diagnoses and procedures.
Our proposed CHE method can be used as a flexible plug-and-play module that can enhance existing deep learning models on EHR.
arXiv Detail & Related papers (2022-09-03T04:10:45Z) - Label Cleaning Multiple Instance Learning: Refining Coarse Annotations
on Single Whole-Slide Images [83.7047542725469]
Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms development.
We present a method, named Label Cleaning Multiple Instance Learning (LC-MIL), to refine coarse annotations on a single WSI without the need of external training data.
Our experiments on a heterogeneous WSI set with breast cancer lymph node metastasis, liver cancer, and colorectal cancer samples show that LC-MIL significantly refines the coarse annotations, outperforming the state-of-the-art alternatives, even while learning from a single slide.
arXiv Detail & Related papers (2021-09-22T15:06:06Z) - Counterfactual Maximum Likelihood Estimation for Training Deep Networks [83.44219640437657]
Deep learning models are prone to learning spurious correlations that should not be learned as predictive clues.
We propose a causality-based training framework to reduce the spurious correlations caused by observable confounders.
We conduct experiments on two real-world tasks: Natural Language Inference (NLI) and Image Captioning.
arXiv Detail & Related papers (2021-06-07T17:47:16Z) - Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for
Thoracic Disease Identification [83.6017225363714]
deep learning has become the most powerful computer-aided diagnosis technology for improving disease identification performance.
For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming.
In this paper, we propose many-to-one distribution learning (MODL) and K-nearest neighbor smoothing (KNNS) methods to improve a single model's disease identification performance.
arXiv Detail & Related papers (2021-02-26T02:29:30Z) - Statistical control for spatio-temporal MEG/EEG source imaging with
desparsified multi-task Lasso [102.84915019938413]
Non-invasive techniques like magnetoencephalography (MEG) or electroencephalography (EEG) offer promise of non-invasive techniques.
The problem of source localization, or source imaging, poses however a high-dimensional statistical inference challenge.
We propose an ensemble of desparsified multi-task Lasso (ecd-MTLasso) to deal with this problem.
arXiv Detail & Related papers (2020-09-29T21:17:16Z)
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.