Classification of Breast Cancer Histopathology Images using a Modified Supervised Contrastive Learning Method
- URL: http://arxiv.org/abs/2405.03642v1
- Date: Mon, 6 May 2024 17:06:11 GMT
- Title: Classification of Breast Cancer Histopathology Images using a Modified Supervised Contrastive Learning Method
- Authors: Matina Mahdizadeh Sani, Ali Royat, Mahdieh Soleymani Baghshah,
- Abstract summary: This work improves the supervised contrastive learning method to reduce the impact of false positives.
We evaluate our method on the BreakHis dataset, which consists of breast cancer histopathology images.
This improvement corresponds to 93.63% absolute accuracy, highlighting our approach's effectiveness in leveraging data properties to learn more appropriate representation space.
- Score: 4.303291247305105
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Deep neural networks have reached remarkable achievements in medical image processing tasks, specifically classifying and detecting various diseases. However, when confronted with limited data, these networks face a critical vulnerability, often succumbing to overfitting by excessively memorizing the limited information available. This work addresses the challenge mentioned above by improving the supervised contrastive learning method to reduce the impact of false positives. Unlike most existing methods that rely predominantly on fully supervised learning, our approach leverages the advantages of self-supervised learning in conjunction with employing the available labeled data. We evaluate our method on the BreakHis dataset, which consists of breast cancer histopathology images, and demonstrate an increase in classification accuracy by 1.45% at the image level and 1.42% at the patient level compared to the state-of-the-art method. This improvement corresponds to 93.63% absolute accuracy, highlighting our approach's effectiveness in leveraging data properties to learn more appropriate representation space.
Related papers
- Local Manifold Learning for No-Reference Image Quality Assessment [68.9577503732292]
We propose an innovative framework that integrates local manifold learning with contrastive learning for No-Reference Image Quality Assessment (NR-IQA)
Our approach demonstrates a better performance compared to state-of-the-art methods in 7 standard datasets.
arXiv Detail & Related papers (2024-06-27T15:14:23Z) - Integration of Self-Supervised BYOL in Semi-Supervised Medical Image Recognition [10.317372960942972]
We propose an innovative approach by integrating self-supervised learning into semi-supervised models to enhance medical image recognition.
Our approach optimally leverages unlabeled data, outperforming existing methods in terms of accuracy for medical image recognition.
arXiv Detail & Related papers (2024-04-16T09:12:16Z) - NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level
Multi-Class Classification in Whole-Slide Images [10.8479107614771]
Whole-slide image (WSI) analysis plays a crucial role in cancer diagnosis and treatment.
In this paper, we introduce Nearby Patch Contrastive Learning (NearbyPatchCL), a novel self-supervised learning method.
Our method significantly outperforms the supervised baseline and state-of-the-art SSL methods with top-1 classification accuracy of 87.56%.
arXiv Detail & Related papers (2023-12-12T18:24:44Z) - Cut-Paste Consistency Learning for Semi-Supervised Lesion Segmentation [0.20305676256390934]
Semi-supervised learning has the potential to improve the data-efficiency of training data-hungry deep neural networks.
We present a simple semi-supervised learning method for lesion segmentation tasks based on the ideas of cut-paste augmentation and consistency regularization.
arXiv Detail & Related papers (2022-10-01T04:43:54Z) - PCA: Semi-supervised Segmentation with Patch Confidence Adversarial
Training [52.895952593202054]
We propose a new semi-supervised adversarial method called Patch Confidence Adrial Training (PCA) for medical image segmentation.
PCA learns the pixel structure and context information in each patch to get enough gradient feedback, which aids the discriminator in convergent to an optimal state.
Our method outperforms the state-of-the-art semi-supervised methods, which demonstrates its effectiveness for medical image segmentation.
arXiv Detail & Related papers (2022-07-24T07:45:47Z) - Dissecting Self-Supervised Learning Methods for Surgical Computer Vision [51.370873913181605]
Self-Supervised Learning (SSL) methods have begun to gain traction in the general computer vision community.
The effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored.
We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection.
arXiv Detail & Related papers (2022-07-01T14:17:11Z) - LifeLonger: A Benchmark for Continual Disease Classification [59.13735398630546]
We introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection.
Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch.
Cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge.
arXiv Detail & Related papers (2022-04-12T12:25:05Z) - Unsupervised deep learning techniques for powdery mildew recognition
based on multispectral imaging [63.62764375279861]
This paper presents a deep learning approach to automatically recognize powdery mildew on cucumber leaves.
We focus on unsupervised deep learning techniques applied to multispectral imaging data.
We propose the use of autoencoder architectures to investigate two strategies for disease detection.
arXiv Detail & Related papers (2021-12-20T13:29:13Z) - Positional Contrastive Learning for Volumetric Medical Image
Segmentation [13.086140606803408]
We propose a novel positional contrastive learning framework to generate contrastive data pairs.
The proposed PCL method can substantially improve the segmentation performance compared to existing methods in both semi-supervised setting and transfer learning setting.
arXiv Detail & Related papers (2021-06-16T22:15:28Z) - Multi-label Thoracic Disease Image Classification with Cross-Attention
Networks [65.37531731899837]
We propose a novel scheme of Cross-Attention Networks (CAN) for automated thoracic disease classification from chest x-ray images.
We also design a new loss function that beyond cross-entropy loss to help cross-attention process and is able to overcome the imbalance between classes and easy-dominated samples within each class.
arXiv Detail & Related papers (2020-07-21T14:37:00Z) - Mitosis Detection Under Limited Annotation: A Joint Learning Approach [5.117836409118142]
Deep learning-based mitotic detection is on par with pathologists, but it requires large labeled data for training.
We propose a deep classification framework for enhancing mitosis detection by leveraging class label information, via softmax loss, and spatial distribution information among samples, via distance metric learning.
Our framework significantly improves the detection with small training data and achieves on par or superior performance compared to state-of-the-art methods for using the entire training data.
arXiv Detail & Related papers (2020-06-17T10:46:29Z)
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.