Transformer-Based Self-Supervised Learning for Histopathological Classification of Ischemic Stroke Clot Origin
- URL: http://arxiv.org/abs/2405.00908v1
- Date: Wed, 1 May 2024 23:40:12 GMT
- Title: Transformer-Based Self-Supervised Learning for Histopathological Classification of Ischemic Stroke Clot Origin
- Authors: K. Yeh, M. S. Jabal, V. Gupta, D. F. Kallmes, W. Brinjikji, B. S. Erdal,
- Abstract summary: Identifying the thromboembolism source in ischemic stroke is crucial for treatment and secondary prevention.
This study describes a self-supervised deep learning approach in digital pathology of emboli for classifying ischemic stroke clot origin.
- Score: 0.0
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Background and Purpose: Identifying the thromboembolism source in ischemic stroke is crucial for treatment and secondary prevention yet is often undetermined. This study describes a self-supervised deep learning approach in digital pathology of emboli for classifying ischemic stroke clot origin from histopathological images. Methods: The dataset included whole slide images (WSI) from the STRIP AI Kaggle challenge, consisting of retrieved clots from ischemic stroke patients following mechanical thrombectomy. Transformer-based deep learning models were developed using transfer learning and self-supervised pretraining for classifying WSI. Customizations included an attention pooling layer, weighted loss function, and threshold optimization. Various model architectures were tested and compared, and model performances were primarily evaluated using weighted logarithmic loss. Results: The model achieved a logloss score of 0.662 in cross-validation and 0.659 on the test set. Different model backbones were compared, with the swin_large_patch4_window12_384 showed higher performance. Thresholding techniques for clot origin classification were employed to balance false positives and negatives. Conclusion: The study demonstrates the extent of efficacy of transformer-based deep learning models in identifying ischemic stroke clot origins from histopathological images and emphasizes the need for refined modeling techniques specifically adapted to thrombi WSI. Further research is needed to improve model performance, interpretability, validate its effectiveness. Future enhancement could include integrating larger patient cohorts, advanced preprocessing strategies, and exploring ensemble multimodal methods for enhanced diagnostic accuracy.
Related papers
- Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor Classification [9.409646394828293]
Foundation models pretrained on large-scale pathology datasets have shown promising results across various diagnostic tasks.
We analyzed 252 cases comprising five major tumor types: glioblastoma, astrocytoma, oligodendroglioma, primary central nervous system lymphoma, and metastatic tumors.
We found that foundation models demonstrated robust classification performance with as few as 10 patches per case, challenging the traditional assumption that extensive per-case image sampling is necessary.
arXiv Detail & Related papers (2025-01-19T11:18:34Z) - Innovative Silicosis and Pneumonia Classification: Leveraging Graph Transformer Post-hoc Modeling and Ensemble Techniques [2.7612447863077794]
This paper presents a comprehensive study on the classification and detection of Silicosis-related lung inflammation.
We create a newly curated chest X-ray (CXR) image dataset named SVBCX that is tailored to the nuances of lung inflammation caused by distinct agents.
We propose a novel deep-learning architecture that integrates graph transformer networks alongside a traditional deep neural network module.
arXiv Detail & Related papers (2024-12-31T16:03:43Z) - Classification of lung cancer subtypes on CT images with synthetic
pathological priors [41.75054301525535]
Cross-scale associations exist in the image patterns between the same case's CT images and its pathological images.
We propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on CT images.
arXiv Detail & Related papers (2023-08-09T02:04:05Z) - MedFMC: A Real-world Dataset and Benchmark For Foundation Model
Adaptation in Medical Image Classification [41.16626194300303]
Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications.
Recent advances further enable adapting foundation models in downstream tasks efficiently using only a few training samples.
Yet, the application of such learning paradigms in medical image analysis remains scarce due to the shortage of publicly accessible data and benchmarks.
arXiv Detail & Related papers (2023-06-16T01:46:07Z) - Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis [44.45598796591008]
Brain imaging-to-graph generation (BIGG) framework is proposed to map functional magnetic resonance imaging (fMRI) into effective connectivity for mild cognitive impairment analysis.
The hierarchical transformers in the generator are designed to estimate the noise at multiple scales.
Evaluations of the ADNI dataset demonstrate the feasibility and efficacy of the proposed model.
arXiv Detail & Related papers (2023-05-18T06:54:56Z) - DeepTechnome: Mitigating Unknown Bias in Deep Learning Based Assessment
of CT Images [44.62475518267084]
We debias deep learning models during training against unknown bias.
We use control regions as surrogates that carry information regarding the bias.
Applying the proposed method to learn from data exhibiting a strong bias, it near-perfectly recovers the classification performance observed when training with corresponding unbiased data.
arXiv Detail & Related papers (2022-05-26T12:18:48Z) - Ensembling Handcrafted Features with Deep Features: An Analytical Study
for Classification of Routine Colon Cancer Histopathological Nuclei Images [13.858624044986815]
We have used F1-measure, Precision, Recall, AUC, and Cross-Entropy Loss to analyse the performance of our approaches.
We observed from the results that the DL features ensemble bring a marked improvement in the overall performance of the model.
arXiv Detail & Related papers (2022-02-22T06:48:50Z) - A multi-stage machine learning model on diagnosis of esophageal
manometry [50.591267188664666]
The framework includes deep-learning models at the swallow-level stage and feature-based machine learning models at the study-level stage.
This is the first artificial-intelligence-style model to automatically predict CC diagnosis of HRM study from raw multi-swallow data.
arXiv Detail & Related papers (2021-06-25T20:09:23Z) - Patient-independent Epileptic Seizure Prediction using Deep Learning
Models [39.19336481493405]
The purpose of a seizure prediction system is to successfully identify the pre-ictal brain stage, which occurs before a seizure event.
Patient-independent seizure prediction models are designed to offer accurate performance across multiple subjects within a dataset.
We propose two patient-independent deep learning architectures with different learning strategies that can learn a global function utilizing data from multiple subjects.
arXiv Detail & Related papers (2020-11-18T23:13:48Z) - StyPath: Style-Transfer Data Augmentation For Robust Histology Image
Classification [6.690876060631452]
We propose a novel pipeline to build robust deep neural networks for AMR classification based on StyPath.
Each image was generated in 1.84 + 0.03 seconds using a single GTX V TITAN and pytorch.
Our results imply that our style-transfer augmentation technique improves histological classification performance.
arXiv Detail & Related papers (2020-07-09T18:02:49Z)
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.