Breast Cancer Histopathology Images Research Articles

Multi-Branch Spectral Channel Attention Network for Breast Cancer Histopathology Image Classification

Deep-learning-based breast cancer image diagnosis is currently a prominent and growingly popular area of research. Existing convolutional-neural-network-related methods mainly capture breast cancer image features based on spatial domain characteristics for classification. However, according to digital signal processing theory, texture images usually contain repeated patterns and structures, which appear as intense energy at specific frequencies in the frequency domain. Motivated by this, we make an attempt to explore a breast cancer histopathology classification application in the frequency domain and further propose a novel multi-branch spectral channel attention network, i.e., the MbsCANet. It expands the interaction of frequency domain attention mechanisms from a multi-branch perspective via combining the lowest frequency features with selected high frequency information from two-dimensional discrete cosine transform, thus preventing the loss of phase information and gaining richer context information for classification. We thoroughly evaluate and analyze the MbsCANet on the publicly accessible BreakHis breast cancer histopathology dataset. It respectively achieves the optimal image-level and patient-level classification results of 99.01% and 98.87%, averagely outperforming the spatial-domain-dominated models by a large margin, and visualization results also demonstrate the effectiveness of the MbsCANet for this medical image application.

Ensemble of Deep Features for Breast Cancer Histopathological Image Classification

Abstract Analysis of histopathological images (HIs) is crucial for detecting breast cancer (BR). However, because they vary, it is still very difficult to extract well-designed elements. Deep learning (DL) is a recent development that is used to extract high-level features. However, DL techniques continue to confront several difficult problems, such as the need for sufficient training data for DL models, which reduces the classification findings. In this study, an ensemble deep transfer convolutional neural network is presented to address this problem. The pre-trained models (ResNet50 and MobileNet) are employed to extract high-level features by freezing the front layer parameters while fine-tuning the last layers. In the proposed ensemble framework, KNN, SVM, logistic regression and neural networks are used as base classifiers. The majority vote and product approaches are used to integrate the predictions of each separate classifier. In the benchmark BreaKHis dataset, the suggested ensemble model is compared to some current approaches. It demonstrates that while the ensemble model obtains a considerable accuracy of 97.72% for the multiclass classification test, it achieves an accuracy of 99.2% for the binary task. The suggested ensemble model’s effectiveness in extracting useful features for BR images is demonstrated by comparison with existing cutting-edge models.

WHRIME: A weight-based recursive hierarchical RIME optimizer for breast cancer histopathology image segmentation

In medical image processing, multi-threshold image segmentation has been challenging, as selecting appropriate thresholds is crucial for distinguishing different structures within an image, especially when dealing with breast cancer images. Breast cancer images are complex with multiple tissue types, which pose challenges to precise diagnosis. A weight-based recursive hierarchical bootstrapping rime algorithm (WHRIME) is proposed to tackle this case effectively. The proposed WHRIME segregates the population into elite and non-elite individuals. The hierarchical bootstrapping strategy ensures comprehensive exploration of the solution space, with elite individuals guiding the position updates of non-elite individuals. A weighted method is introduced based on solution quality differences to maintain population diversity and enhance convergence accuracy. We apply WHRIME in multi-threshold image segmentation on breast cancer histopathology images. Experimental results on both the IEEE CEC 2017 benchmark suit and breast cancer histopathology images from the Databiox dataset validate the superiority of WHRIME over competing algorithms, affirming WHRIME’s capability in addressing complex breast cancer histopathology image segmentation problems.

Collaborative Transfer Network for Multi-Classification of Breast Cancer Histopathological Images.

The incidence of breast cancer is increasing rapidly around the world. Accurate classification of the breast cancer subtype from hematoxylin and eosin images is the key to improve the precision of treatment. However, the high consistency of disease subtypes and uneven distribution of cancer cells seriously affect the performance of multi-classification methods. Furthermore, it is difficult to apply existing classification methods to multiple datasets. In this article, we propose a collaborative transfer network (CTransNet) for multi-classification of breast cancer histopathological images. CTransNet consists of a transfer learning backbone branch, a residual collaborative branch, and a feature fusion module. The transfer learning branch adopts the pre-trained DenseNet structure to extract image features from ImageNet. The residual branch extracts target features from pathological images in a collaborative manner. The feature fusion strategy of optimizing these two branches is used to train and fine-tune CTransNet. Experiments show that CTransNet achieves 98.29% classification accuracy on the public BreaKHis breast cancer dataset, exceeding the performance of state-of-the-art methods. Visual analysis is carried out under the guidance of oncologists. Based on the training parameters of the BreaKHis dataset, CTransNet achieves superior performance on other two public breast cancer datasets (breast-cancer-grade-ICT and ICIAR2018_BACH_Challenge), indicating that CTransNet has good generalization performance.

LMHistNet: Levenberg–Marquardt Based Deep Neural Network for Classification of Breast Cancer Histopathological Images

LMHistNet: Levenberg–Marquardt Based Deep Neural Network for Classification of Breast Cancer Histopathological Images

Data Augmentation for Medical Image Classification based on Gaussian Laplacian Pyramid Blending with a Similarity Measure.

Breast cancer is a devastating disease that affects women worldwide, and computer-aided algorithms have shown potential in automating cancer diagnosis. Recently Generative Artificial Intelligence (GenAI) opens new possibilities for addressing the challenges of labeled data scarcity and accurate prediction in critical applications. However, a lack of diversity, as well as unrealistic and unreliable data, have a detrimental impact on performance. Therefore, this study proposes an augmentation scheme to address the scarcity of labeled data and data imbalance in medical datasets. This approach integrates the concepts of the Gaussian-Laplacian pyramid and pyramid blending with similarity measures. In order to maintain the structural properties of images and capture inter-variability of patient images of the same category similarity-metric-based intermixing has been introduced. It helps to maintain the overall quality and integrity of the dataset. Subsequently, deep learning approach with significant modification, that leverages transfer learning through the usage of concatenated pre-trained models is applied to classify breast cancer histopathological images. The effectiveness of the proposal, including the impact of data augmentation, is demonstrated through a detailed analysis of three different medical datasets, showing significant performance improvement over baseline models. The proposal has the potential to contribute to the development of more accurate and reliable approach for breast cancer diagnosis.

Combining a forward supervised filter learning with a sparse NMF for breast cancer histopathological image classification

Histopathological images play a important role in clinical diagnosis, particularly in identifying and assessing the severity of abnormal conditions like benign lesions and malignant tumors. Traditional machine learning techniques for processing histopathology images involve the extraction of manual features from these images, which is typically done with the assistance of industry experts. Recent advancements in Deep Learning (DL), especially with Convolutional Neural Networks (CNN), have enabled the automatic extraction of multi-level abstract features directly from raw data. This capability significantly enhances the performance of complex computer vision tasks. Classic CNN models like AlexNet and VggNet employ back-propagation algorithms to learn filters in the training phase. However, these algorithms demand large labeled datasets, resulting in extensive computational processing. Additionally, they often face the vanishing gradient problem, which can negatively impact the quality of the learning process. Besides, in many domains, acquiring enough labeled images for conducting properly the training phase is a real challenge. To address these challenges, a feed-forward propagation approach was proposed using Non-Negative Matrix Factorization(NMF). The NMF technique factorizes the input data into two latent factors (non-negative matrices). It has been shown that by enforcing constraints such as sparsity on the latent factors, dominant features that are mostly correlated with tumors types can be extracted. In this work, a novel model combining sparse NMF and Support Vector Machine (SVM) was developed for classifying histopathological images. We have derived a mathematical model of a novel feed-forward filter learning approach that combines sparse NMF (SNMF) and Support Vector Machine technique (SVM). The model was used to design and implement a feed-forward CNN classifier to classify histopathology images. This model has been evaluated on the histopathology images from Sultan Qaboos University Hospital (SQUH dataset) and the public BreaKHis dataset. The experiments we have conducted demonstrate the efficiency of the proposed model, especially on small-sized SQUH datasets achieving an AUC of 0.90, 0.89, 0.85, and 0.86 on 4x,10x, 20x, and 40x magnifications, respectively, and achieving an AUC of 0.95 BreaKHis dataset.

FINE-TUNING MobileNetV3 WITH DIFFERENT WEIGHT OPTIMIZATION ALGORITHMS FOR CLASSIFICATION OF DENOISED BLOOD CELL IMAGES USING CONVOLUTIONAL NEURAL NETWORK

Breast cancer remains a formidable global health concern, underscoring the urgency for advanced diagnostic methodologies. This research presents a multifaceted framework aimed at significantly enhancing breast cancer diagnosis through innovative approaches in image processing and machine learning. The proposed framework encompasses several key contributions. Firstly, a robust denoising strategy is implemented using Convolutional Neural Network encoder-decoder architecture, augmented with data augmentation techniques. This addresses the challenge of vanishing gradients through enhanced Rectified Linear Units based Convolutional Neural Network, enhancing the model's generalization capability. Subsequent to denoising, feature extraction is performed utilizing a fine-tuned MobileNetV3 model. The model's performance is optimized through Modified Rectified Linear Units and NRMSProp approaches, effectively eliminating undesired features and improving overall efficiency. Crucially, a novel feature selection process is introduced, leveraging the Artificial Hummingbird Algorithm based on Manta Ray Foraging Optimization Algorithm. This algorithm selectively identifies essential features from breast cancer images, significantly elevating classification accuracy. To validate the proposed framework, a comprehensive evaluation is conducted, comparing its performance with a hybrid of five different metaheuristic algorithms, including Marine Predators Algorithm, Tunicate Swarm Algorithm, Manta Ray Foraging Optimization algorithm, Arithmetic Optimization Algorithm, and Jelly Fish optimization algorithm. Artificial Hummingbird Algorithm based on Manta Ray Foraging Optimization Algorithm emerges as the most effective among these algorithms, showcasing superior performance. The evaluation utilized the Breast Cancer Histopathological Image Classification dataset, resulting in an impressive classification accuracy of 99.51% for the proposed model.

Breast Cancer Histopathology Images Classification Through Multi-View Augmented Contrastive Learning and Pre-Learning Knowledge Distillation

Breast Cancer Histopathology Images Classification Through Multi-View Augmented Contrastive Learning and Pre-Learning Knowledge Distillation

Hybrid Deep Learning EfficientNetV2 and Vision Transformer (EffNetV2-ViT) Model for Breast Cancer Histopathological Image Classification

Hybrid Deep Learning EfficientNetV2 and Vision Transformer (EffNetV2-ViT) Model for Breast Cancer Histopathological Image Classification

Classification of Breast Cancer Histopathological Images Using Transfer Learning with DenseNet121

Breast cancer (BC) continues to be a prominent issue in global public health, emphasizing the need for precise and timely detection. This paper employs a deep learning (DL) approach to introduce an extensive methodology for categorizing histopathology images associated with breast cancer into automated binary classifications. The proposed framework architecture is validated on the standard database which is accessible to the public, called Breast Cancer Histopathological Database (BreakHis). Data augmentation techniques are employed for the pre-processing stage. This paper uses the DenseNet 121 pre-trained model for feature extraction and fully connected layers (FCL) to fine-tune the model further. In this experiment, the highest accuracy of 96.09% is observed with the 100X. The experimental results showed an improvement in accuracy for all the magnification factors compared to the existing works.

Enhancing breast cancer classification via histopathological image analysis: Leveraging self-supervised contrastive learning and transfer learning

Breast cancer, a significant threat to women's health, demands early detection. Automating histopathological image analysis offers a promising solution to enhance efficiency and accuracy in diagnosis. This study addresses the challenge of breast cancer histopathological image classification by leveraging the ResNet architecture, known for its depth and skip connections. In this work, two distinct approaches were pursued, each driven by unique motivations. The first approach aimed to improve the learning process through self-supervised contrastive learning. It utilizes a small subset of the training data for initial model training and progressively expands the training set by incorporating confidently labeled data from the unlabeled pool, ultimately achieving a reliable model with limited training data. The second approach focused on optimizing the architecture by combining ResNet50 and Inception module to get a lightweight and efficient classifier. The dataset utilized in this work comprises histopathological images categorized into benign and malignant classes at varying magnification levels (40X, 100X, 200X, 400X), all originating from the same source image. The results demonstrate state-of-the-art performance, achieving 98% accuracy for images magnified at 40X and 200X, and 94% for 100X and 400X. Notably, the proposed architecture boasts a substantially reduced parameter count of approximately 3.6 million, contrasting with existing leading architectures, which possess parameter sizes at least twice as large.

An enhanced multi-scale deep convolutional orchard capsule neural network for multi-modal breast cancer detection

Breast cancer is the second-leading cause of cancer death in women. Breast cells develop into malignant, cancerous lumps, the first signs of breast cancer. Breast cancer can be discovered by the automated diagnostic system when it is still too little to be found by conventional medical methods. Early breast cancers identified with automated screening and diagnosis technologies are generally treatable. This study proposes an enhanced multi-scale deep Convolutional Capsule Neural Network (CapsNet) optimized with Orchard Optimization Algorithm for breast cancer detection. The proposed system consists of preprocessing, feature extraction, segmentation, and classification process. Two input images are taken initially: the Breast Cancer Histopathology Images dataset and the Infrared Thermal Images dataset. The quality of the collected data is improved, and unwanted noises are removed. The features are extracted to segment the image to derive a Region of Interest for effectively segmenting the affected region. Finally, the images are classified as benign/malignant for histopathology images and healthy/cancer for thermal images. The proposed CapsNet is implemented in Python, run for 200 epochs, and compared with existing methods in terms of evaluation metrics. The result shows that the proposed CapsNet attained 99.74 % accuracy, 0.0482 binary entropy loss on the Breast Cancer Histopathology Image dataset and 97 % accuracy, 0.2081 binary entropy loss on the Infrared Thermal Images dataset while incrementing the epochs at each level.

The Techniques Used in Mitosis Detection in Breast Cancer Histopathology Images: A Survey

Breast cancer consider as the second cause of death around the world after heart disease, and it is the primary cause of death for women. Timely detection of breast cancer plays a crucial role in lowering mortality rates, as it enhances the patient's prospects of survival through prompt diagnosis and appropriate treatment. The discovery of the mitotic number is one of the necessary procedures that must be performed for a person suffering from breast cancer because it is an important marker for determining the aggressiveness of the tumor. According to the Nottingham scale, it gives 3 degrees to determine the degree of the tumor, whether it is of the first degree, the second degree, or the third degree of seriousness. Deep learning algorithms have many contributions in the medical fields, including in the field of mitotic number discovery, as the mitotic number process is a difficult and tiring task that requires time and effort from pathologists (diagnostic doctors), because the work environment is under microscopes with high magnification degrees, for this reason deep learning techniques were used to reduce the burden on diagnostic doctors and save time for the patient to know the result of his examination, as the biopsy results in developed countries take from 10 days to two weeks for the results to appear. In this survey, we will evaluate the deep learning techniqus employed for mitotic number detection.

A hybrid lightweight breast cancer classification framework using the histopathological images

A crucial element in the diagnosis of breast cancer is the utilization of a classification method that is efficient, lightweight, and precise. Convolutional neural networks (CNNs) have garnered attention as a viable approach for classifying histopathological images. However, deeper and wider models tend to rely on first-order statistics, demanding substantial computational resources and struggling with fixed kernel dimensions that limit encompassing diverse resolution data, thereby degrading the model’s performance during testing. This study introduces BCHI-CovNet, a novel lightweight artificial intelligence (AI) model for histopathological breast image classification. Firstly, a novel multiscale depth-wise separable convolution is proposed. It is introduced to split input tensors into distinct tensor fragments, each subject to unique kernel sizes integrating various kernel sizes within one depth-wise convolution to capture both low- and high-resolution patterns. Secondly, an additional pooling module is introduced to capture extensive second-order statistical information across the channels and spatial dimensions. This module works in tandem with an innovative multi-head self-attention mechanism to capture the long-range pixels contributing significantly to the learning process, yielding distinctive and discriminative features that further enrich representation and introduce pixel diversity during training. These novel designs substantially reduce computational complexities regarding model parameters and FLOPs, which is crucial for resource-constrained medical devices. The outcomes achieved by employing the suggested model on two openly accessible datasets for breast cancer histopathological images reveal noteworthy performance. Specifically, the proposed approach attains high levels of accuracy: 99.15 % at 40× magnification, 99.08 % at 100× magnification, 99.22 % at 200× magnification, and 98.87 % at 400× magnification on the BreaKHis dataset. Additionally, it achieves an accuracy of 99.38 % on the BACH dataset. These results highlight the exceptional effectiveness and practical promise of BCHI-CovNet for the classification of breast cancer histopathological images.

Feed-forward networks using logistic regression and support vector machine for whole-slide breast cancer histopathology image classification

The performance of an image classification depends on the efficiency of the feature learning process. This process is a challenging task that traditionally requires prior knowledge from domain experts. Recently, representation learning was introduced to extract features directly from the raw images without any prior knowledge. Deep learning using a Convolutional Neural Network (CNN) has gained massive attention for performing image classification, as it achieves remarkable accuracy that sometimes exceeds human performance. But this type of network learns features by using a back-propagation approach. This approach requires a huge amount of training data and suffers from the vanishing gradient problem that deteriorates the feature learning. The forward-propagation approach uses predefined filters or filters learned outside the model and applied in a feed-forward manner. This approach is proven to achieve good results with small size labeled datasets. In this work, we investigate the suitability of using two feed-forward methods such as Convolutional Logistic Regression Network (CLR), and Convolutional Support Vector Machine Network for Histopathology Images (CSVM-H). The experiments we have conducted on two small breast cancer datasets (Sultan Qaboos University Hospital (SQUH) and BreaKHis dataset) demonstrate the advantage of using feed-forward approaches over the traditional back-propagation ones. On those datasets, the proposed models CLR and CSVM-H were faster to train and achieved better classification performance than the traditional back-propagation methods (VggNet-16 and ResNet-50) on the SQUH dataset. Importantly, our proposed approach CLR and CSVM-H efficiently learn representations from small amounts of breast cancer whole-slide images and achieve an AUC of 0.83 and 0.84, respectively, on the SQUH dataset. Moreover, the proposed models reduce memory footprint in the classification of Whole-Slide histopathology images since their training time is significantly reduced compared to the traditional CNN on the SQUH and BreaKHis datasets.

Breast cancer diagnosis through knowledge distillation of Swin transformer-based teacher–student models

Breast cancer is a significant global health concern, emphasizing the crucial need for a timely and accurate diagnosis to enhance survival rates. Traditional diagnostic methods rely on pathologists analyzing whole-slide images (WSIs) to identify and diagnose malignancies. However, this task is complex, demanding specialized expertise and imposing a substantial workload on pathologists. Additionally, existing deep learning models, commonly employed for classifying histopathology images, often need enhancements to ensure their suitability for real-time deployment on WSI, especially when trained for small regions of interest (ROIs). This article introduces two Swin transformer-based architectures: the teacher model, characterized by its moderate size, and the lightweight student model. Both models are trained using a publicly available dataset of breast cancer histopathology images, focusing on ROIs with varying magnification factors. Transfer learning is applied to train the teacher model, and knowledge distillation (KD) transfers its capabilities to the student model. To enhance validation accuracy and minimize the total loss in KD, we employ the state–action–reward–state–action (SARSA) reinforcement learning algorithm. The algorithm dynamically computes temperature and a weighting factor throughout the KD process to achieve high accuracy within a considerably shorter training timeframe. Additionally, the student model is deployed to analyze malignancies in WSI. Despite the student model being only one-third the size and flops of the teacher model, it achieves an impressive accuracy of 98.71%, slightly below the teacher’s accuracy of 98.91%. Experimental results demonstrate that the student model can process WSIs at a throughput of 1.67 samples s−1 with an accuracy of 82%. The proposed student model, trained using KD and the SARSA algorithm, exhibits promising breast cancer classification and WSI analysis performance. These findings indicate its potential for assisting pathologists in diagnosing breast cancer accurately and effectively.

Histopathological breast cancer classification using CNN

In the year 2021, there were 2.26 million new diagnoses of breast cancer cases among women globally. Over the years, various imaging methods such as mammography, Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), X-ray, and Computer Tomography (CT) have been used as helpful diagnostic tools for cancer prognosis. However, these methods expose the patient to rays that have the potential to be cancerous. Added to the cancerous risk, due to the fatigue experienced by histopathologists, many errors can be introduced in such diagnosis. Recently, Computer Aided Diagnosis (CAD) via Convolutional Neural Network (CNN) has been employed to overcome the fatigue and decrease in concentration experienced by histopathologists and clinicians during a cancer diagnosis. Though CNN has shown better results than conventional cancer diagnosis methods, using a single dataset for CNN training has been an accuracy challenge in diagnosing breast cancer. This study proposed a classification of histopathological images of breast cancer using CNN. A hybrid dataset was curated by preprocessing the histopathological dataset from two popular datasets, namely, BreakHis and Histo to the best of our knowledge this combination of is new. The cancer tissue images were classified as either Malignant or Benign. Instead of using a model with random weights from scratch, this study uses transfer learning to build four pre-trained models, namely DenseNet201, ResNet50, ResNet101 and MobileNet-v2. Five protocol setups for the dataset were set up and divided into 70% and 30% for training and testing, respectively. Of the four pre-trained models, DensNet201 achieved an accuracy of 91.37% and a sensitivity level of 100% at a 200x magnification factor. Our best-performed model outperforms state-of-the-art models by achieving an accuracy of 91.37%.

Chasing a Better Decision Margin for Discriminative Histopathological Breast Cancer Image Classification

When considering a large dataset of histopathologic breast images captured at various magnification levels, the process of distinguishing between benign and malignant cancer from these images can be time-intensive. The automation of histopathological breast cancer image classification holds significant promise for expediting pathology diagnoses and reducing the analysis time. Convolutional neural networks (CNNs) have recently gained traction for their ability to more accurately classify histopathological breast cancer images. CNNs excel at extracting distinctive features that emphasize semantic information. However, traditional CNNs employing the softmax loss function often struggle to achieve the necessary discriminatory power for this task. To address this challenge, a set of angular margin-based softmax loss functions have emerged, including angular softmax (A-Softmax), large margin cosine loss (CosFace), and additive angular margin (ArcFace), each sharing a common objective: maximizing inter-class variation while minimizing intra-class variation. This study delves into these three loss functions and their potential to extract distinguishing features while expanding the decision boundary between classes. Rigorous experimentation on a well-established histopathological breast cancer image dataset, BreakHis, has been conducted. As per the results, it is evident that CosFace focuses on augmenting the differences between classes, while A-Softmax and ArcFace tend to emphasize augmenting within-class variations. These observations underscore the efficacy of margin penalties on angular softmax losses in enhancing feature discrimination within the embedding space. These loss functions consistently outperform softmax-based techniques, either by widening the gaps among classes or enhancing the compactness of individual classes.

An integrated approach for magnification independent breast cancer classification

Breast cancer (BC) is the second most common cancer worldwide, and its diagnosis and treatment rely heavily on histopathology image analysis. Moreover, continuous evaluation of deep learning techniques in medical imaging modalities is essential for improving early diagnosis. The Break-His dataset is the de facto standard for such analysis. Researchers have actively explored various approaches to classifying these images into binary, four, and eight based on the magnification-independent (MI) and magnification-dependent (MD). However, existing processes necessitate separate models for each classification based on the magnification factor and entail training multiple models. It leads to increased training time and model complexity. Moreover, model performance in eight-class is relatively low compared to other classifications. This paper introduces a modified Swin-Transformer V2 architecture for multi-labeled and eight-class classification on BC histopathology images. Further, the eight-class output was reconfigured to operate in an integrated approach, allowing the model to predict binary, four, and eight classes simultaneously for both MI and MD. On the Break-His dataset, the proposed model achieved an accuracy of 98.27%, 97.95%, 98.97%, and 99.16% for eight-class, malignant, benign, and binary classification tasks, respectively. Additionally, the multi-labeled approach demonstrated a performance improvement in the eight-class category compared to current leading models, achieving an enhancement of up to 5%, and the model was trained in just 2 h. Overall, the proposed model can improve the prognosis of breast cancer patients by leading to more accurate diagnosis and treatment. The implemented code can be accessed at https://github.com/kbnarayanavit/integrated-approach.