WeakSTIL: Weak whole-slide image level stromal tumor infiltrating
lymphocyte scores are all you need
- URL: http://arxiv.org/abs/2109.05892v1
- Date: Mon, 13 Sep 2021 11:55:28 GMT
- Title: WeakSTIL: Weak whole-slide image level stromal tumor infiltrating
lymphocyte scores are all you need
- Authors: Yoni Schirris, Mendel Engelaer, Andreas Panteli, Hugo Mark Horlings,
Efstratios Gavves, Jonas Teuwen
- Abstract summary: We present WeakSTIL, an interpretable two-stage weak label deep learning pipeline for scoring the percentage of stromal tumor infiltrating lymphocytes (sTIL%) in H&E-stained whole-slide images (WSIs) of breast cancer tissue.
- Score: 18.810431173767636
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present WeakSTIL, an interpretable two-stage weak label deep learning
pipeline for scoring the percentage of stromal tumor infiltrating lymphocytes
(sTIL%) in H&E-stained whole-slide images (WSIs) of breast cancer tissue. The
sTIL% score is a prognostic and predictive biomarker for many solid tumor
types. However, due to the high labeling efforts and high intra- and
interobserver variability within and between expert annotators, this biomarker
is currently not used in routine clinical decision making. WeakSTIL compresses
tiles of a WSI using a feature extractor pre-trained with self-supervised
learning on unlabeled histopathology data and learns to predict precise sTIL%
scores for each tile in the tumor bed by using a multiple instance learning
regressor that only requires a weak WSI-level label. By requiring only a weak
label, we overcome the large annotation efforts required to train currently
existing TIL detection methods. We show that WeakSTIL is at least as good as
other TIL detection methods when predicting the WSI-level sTIL% score, reaching
a coefficient of determination of $0.45\pm0.15$ when compared to scores
generated by an expert pathologist, and an AUC of $0.89\pm0.05$ when treating
it as the clinically interesting sTIL-high vs sTIL-low classification task.
Additionally, we show that the intermediate tile-level predictions of WeakSTIL
are highly interpretable, which suggests that WeakSTIL pays attention to latent
features related to the number of TILs and the tissue type. In the future,
WeakSTIL may be used to provide consistent and interpretable sTIL% predictions
to stratify breast cancer patients into targeted therapy arms.
Related papers
- Boosting Medical Image-based Cancer Detection via Text-guided Supervision from Reports [68.39938936308023]
We propose a novel text-guided learning method to achieve highly accurate cancer detection results.
Our approach can leverage clinical knowledge by large-scale pre-trained VLM to enhance generalization ability.
arXiv Detail & Related papers (2024-05-23T07:03:38Z) - Fast TILs estimation in lung cancer WSIs based on semi-stochastic patch sampling [0.0]
The pipeline efficiently excludes approximately 70% of areas not relevant for prognosis and requires only 5% of the remaining patches to maintain prognostic accuracy.
The pipeline demonstrates potential for enhancing NSCLC prognostication and personalization of treatment.
Future research should focus on verifying its broader clinical utility and investigating additional biomarkers to improve NSCLC prognosis.
arXiv Detail & Related papers (2024-05-05T12:41:55Z) - A Weakly Supervised Segmentation Network Embedding Cross-scale Attention
Guidance and Noise-sensitive Constraint for Detecting Tertiary Lymphoid
Structures of Pancreatic Tumors [19.775101438245272]
The presence of tertiary lymphoid structures (TLSs) on pancreatic pathological images is an important prognostic indicator of pancreatic tumors.
We propose a weakly supervised segmentation network to detect the TLSs in a manner of few-shot learning.
Experimental results on two collected datasets demonstrate that our proposed method significantly outperforms the state-of-the-art segmentation-based algorithms in terms of TLSs detection accuracy.
arXiv Detail & Related papers (2023-07-27T03:25:09Z) - LESS: Label-efficient Multi-scale Learning for Cytological Whole Slide
Image Screening [19.803614403803962]
We propose a weakly-supervised Label-Efficient WSI Screening method, dubbed LESS, for cytological WSI analysis with only slide-level labels.
We provide appropriate supervision by using slide-level labels to improve the learning of patch-level features.
It outperforms state-of-the-art MIL methods on pathology WSIs and realizes automatic cytological WSI cancer screening.
arXiv Detail & Related papers (2023-06-06T05:09:20Z) - Active Learning Enhances Classification of Histopathology Whole Slide
Images with Attention-based Multiple Instance Learning [48.02011627390706]
We train an attention-based MIL and calculate a confidence metric for every image in the dataset to select the most uncertain WSIs for expert annotation.
With a novel attention guiding loss, this leads to an accuracy boost of the trained models with few regions annotated for each class.
It may in the future serve as an important contribution to train MIL models in the clinically relevant context of cancer classification in histopathology.
arXiv Detail & Related papers (2023-03-02T15:18:58Z) - Learning to diagnose cirrhosis from radiological and histological labels
with joint self and weakly-supervised pretraining strategies [62.840338941861134]
We propose to leverage transfer learning from large datasets annotated by radiologists, to predict the histological score available on a small annex dataset.
We compare different pretraining methods, namely weakly-supervised and self-supervised ones, to improve the prediction of the cirrhosis.
This method outperforms the baseline classification of the METAVIR score, reaching an AUC of 0.84 and a balanced accuracy of 0.75.
arXiv Detail & Related papers (2023-02-16T17:06:23Z) - Less is More: Adaptive Curriculum Learning for Thyroid Nodule Diagnosis [50.231954872304314]
We propose an Adaptive Curriculum Learning framework, which adaptively discovers and discards the samples with inconsistent labels.
We also contribute TNCD: a Thyroid Nodule Classification dataset.
arXiv Detail & Related papers (2022-07-02T11:50:02Z) - A graph-transformer for whole slide image classification [11.968797693846476]
We present a Graph-Transformer (GT) that fuses a graph-based representation of an whole slide image (WSI) and a vision transformer for processing pathology images, called GTP, to predict disease grade.
Our findings demonstrate GTP as an interpretable and effective deep learning framework for WSI-level classification.
arXiv Detail & Related papers (2022-05-19T16:32:10Z) - 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) - Multi-Scale Input Strategies for Medulloblastoma Tumor Classification
using Deep Transfer Learning [59.30734371401316]
Medulloblastoma is the most common malignant brain cancer among children.
CNN has shown promising results for MB subtype classification.
We study the impact of tile size and input strategy.
arXiv Detail & Related papers (2021-09-14T09:42:37Z) - DeepSMILE: Contrastive self-supervised pre-training benefits MSI and HRD
classification directly from H&E whole-slide images in colorectal and breast
cancer [22.46523830554047]
We propose a Deep learning-based weak label learning method for analyzing whole slide images (WSIs) of Hematoxylin and Eosin stained tumor tissue.
We apply DeepSMILE to the task of Homologous recombination deficiency (HRD) and microsatellite instability (MSI) prediction.
arXiv Detail & Related papers (2021-07-20T11:00:16Z)
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.