Survey on Machine Learning and Deep Learning Applications in Breast Cancer Diagnosis

Multi-Scale Vision Transformer with Optimized Feature Fusion for Mammographic Breast Cancer Classification

Background: Breast cancer remains one of the leading causes of mortality among women worldwide, highlighting the critical need for accurate and efficient diagnostic methods. Methods: Traditional deep learning models often struggle with feature redundancy, suboptimal feature fusion, and inefficient selection of discriminative features, leading to limitations in classification performance. To address these challenges, we propose a new deep learning framework that leverages MAX-ViT for multi-scale feature extraction, ensuring robust and hierarchical representation learning. A gated attention fusion module (GAFM) is introduced to dynamically integrate the extracted features, enhancing the discriminative power of the fused representation. Additionally, we employ Harris Hawks optimization (HHO) for feature selection, reducing redundancy and improving classification efficiency. Finally, XGBoost is utilized for classification, taking advantage of its strong generalization capabilities. Results: We evaluate our model on the King Abdulaziz University Mammogram Dataset, categorized based on BI-RADS classifications. Experimental results demonstrate the effectiveness of our approach, achieving 98.2% for accuracy, 98.0% for precision, 98.1% for recall, 98.0% for F1-score, 98.9% for the area under the curve (AUC), and 95% for the Matthews correlation coefficient (MCC), outperforming existing state-of-the-art models. Conclusions: These results validate the robustness of our fusion-based framework in improving breast cancer diagnosis and classification.

Machine Learning-Powered Optimization of a CHO Cell Cultivation Process

Chinese Hamster Ovary (CHO) cells are the most widely used cell lines to produce recombinant therapeutic proteins such as monoclonal antibodies (mAbs). However, the optimization of the CHO cell culture process is very complex and influenced by various factors. This study investigates the use of machine learning (ML) algorithms to optimize an established industrial CHO cell cultivation process. A ML algorithm in the form of an artificial neural network (ANN) was used and trained on datasets from historical and newly generated CHO cell cultivation runs. The algorithm was then used to find better cultivation conditions and improve cell productivity. The selected artificial intelligence (AI) tool was able to suggest optimized cultivation settings and new condition combinations, which promised both increased cell growth and increased mAb titers. After performing the validation experiments, it was shown that the ML algorithm was able to successfully optimize the cultivation process and significantly improve the antibody production. The best results showed an increase in final mAb titer up to 48%, demonstrating that the use of ML algorithms is a promising approach to optimize the productivity of bioprocesses like CHO cell cultivation processes clearly.

Advanced machine learning framework for enhancing breast cancer diagnostics through transcriptomic profiling

PURPOSE

This study proposes an advanced machine learning (ML) framework for breast cancer diagnostics by integrating transcriptomic profiling with optimized feature selection and classification techniques.

MATERIALS AND METHODS

A dataset of 1759 samples (987 breast cancer patients, 772 healthy controls) was analyzed using Recursive Feature Elimination, Boruta, and ElasticNet for feature selection. Dimensionality reduction techniques, including Non-Negative Matrix Factorization (NMF), Autoencoders, and transformer-based embeddings (BioBERT, DNABERT), were applied to enhance model interpretability. Classifiers such as XGBoost, LightGBM, ensemble voting, Multi-Layer Perceptron, and Stacking were trained using grid search and cross-validation. Model evaluation was conducted using accuracy, AUC, MCC, Kappa Score, ROC, and PR curves, with external validation performed on an independent dataset of 175 samples.

RESULTS

XGBoost and LightGBM achieved the highest test accuracies (0.91 and 0.90) and AUC values (up to 0.92), particularly with NMF and BioBERT. The ensemble Voting method exhibited the best external accuracy (0.92), confirming its robustness. Transformer-based embeddings and advanced feature selection techniques significantly improved model performance compared to conventional approaches like PCA and Decision Trees.

CONCLUSION

The proposed ML framework enhances diagnostic accuracy and interpretability, demonstrating strong generalizability on an external dataset. These findings highlight its potential for precision oncology and personalized breast cancer diagnostics.

Advancing lung cancer diagnosis: Combining 3D auto-encoders and attention mechanisms for CT scan analysis

ObjectiveThe goal of this study is to assess the effectiveness of a hybrid deep learning model that combines 3D Auto-encoders with attention mechanisms to detect lung cancer early from CT scan images. The study aims to improve diagnostic accuracy, sensitivity, and specificity by focusing on key features in the scans.Materials and methodsA hybrid model was developed that combines feature extraction using 3D Auto-encoder networks with attention mechanisms. First, the 3D Auto-encoder model was tested without attention, using feature selection techniques such as RFE, LASSO, and ANOVA. This was followed by evaluation using several classifiers: SVM, RF, GBM, MLP, LightGBM, XGBoost, Stacking, and Voting. The model's performance was evaluated based on accuracy, sensitivity, F1-Score, and AUC-ROC. After that, attention mechanisms were added to help the model focus on important areas in the CT scans, and the performance was re-assessed.ResultsThe 3D Auto-encoder model without attention achieved an accuracy of 93% and sensitivity of 89%. When attention mechanisms were added, the performance improved across all metrics. For example, the accuracy of SVM increased to 94%, sensitivity to 91%, and AUC-ROC to 0.96. Random Forest (RF) also showed improvements, with accuracy rising to 94% and AUC-ROC to 0.93. The final model with attention improved the overall accuracy to 93.4%, sensitivity to 90.2%, and AUC-ROC to 94.1%. These results highlight the important role of attention in identifying the most relevant features for accurate classification.ConclusionsThe proposed hybrid deep learning model, especially with the addition of attention mechanisms, significantly improves the early detection of lung cancer. By focusing on key features in the CT scans, the attention mechanism helps reduce false negatives and boosts overall diagnostic accuracy. This approach has great potential for use in clinical applications, particularly in the early-stage detection of lung cancer.

Improved early detection accuracy for breast cancer using a deep learning framework in medical imaging

PROBLEM

The most prevalent cancer in women is breast cancer (BC), and effective treatment depends on being detected early. Many people seek medical imaging techniques to help in the early detection of problems, but results often need to be corrected for increased accuracy.

AIM

A new deep learning approach for medical images is applied in the detection of BC in this paper. Early detection is carried out through the proposed method using a combination of Convolutional Neural Network (CNNs) with feature selection and fusion methods.

METHODS

The proposed method may decrease the mortality rate due to the early-stage detection of BC with high precision. In this work, the proposed Deep Learning Framework (DLF) uses many levels of artificial neural networks to sort images of BC into categories correctly.

RESULTS

This proposed method further increases the scalability of convolutional recurrent networks. It also achieved 94.93 % accuracy, 93.66 % precision, 89.21 % recall and 98.86 % F1-score. Through this approach, cancer tumors in a specific location can be detected more accurately.

CONCLUSION

The existing methods are dependent mainly on manually selecting and extracting features. The proposed framework automatically learns and finds relevant features from images that result in outperforming existing methods.

Application of an improved LightGBM hybrid integration model combining gradient harmonization and Jacobian regularization for breast cancer diagnosis

Cancer, as a shocking disease, is one of the most common malignant tumors among women, posing a huge threat to the physical health and safety of women worldwide. With the continuous development of science and technology, more and more high and new technologies are involved in the diagnosis and prediction of breast cancer. In recent years, intelligent medical assistants supported by data mining and machine learning algorithms have provided necessary support for doctors' diagnosis. This study proposes an improved LightGBM hybrid integration model. Introducing gradient harmonic loss and cross entropy loss to enhance the model's attention to minority classes in the dataset and alleviate the impact of data imbalance on diagnostic results. Designing whale optimization algorithm to improve LightGBM to achieve iterative optimization of hyperparameters, and enhance the overall performance of the model. Proposing Jacobian regularization method to denoise LightGBM to solve the problem of model sensitivity to noise. Developing the LightGBM hybrid integration model to ensure the accuracy and stability of model diagnosis on diverse and imbalanced datasets. The effectiveness of the proposed method has been comprehensively compared and verified through the dataset in the UCI machine learning repository, and the results show that the proposed method has achieved good diagnostic performance in all indicators. The hybrid integration model proposed in this paper can provide effective auxiliary support for doctors to diagnose breast cancer.

Golden eagle optimized CONV-LSTM and non-negativity-constrained autoencoder to support spatial and temporal features in cancer drug response prediction

Advanced machine learning (ML) and deep learning (DL) methods have recently been utilized in Drug Response Prediction (DRP), and these models use the details from genomic profiles, such as extensive drug screening data and cell line data, to predict the response of drugs. Comparatively, the DL-based prediction approaches provided better learning of such features. However, prior knowledge, like pathway data, is sometimes discarded as irrelevant since the drug response datasets are multidimensional and noisy. Optimized feature learning and extraction processes are suggested to handle this problem. First, the noise and class imbalance problems must be tackled to avoid low identification accuracy, long prediction times, and poor applicability. This article aims to apply the Non-Negativity-Constrained Auto Encoder (NNCAE) network to tackle these issues, enhance the adaptive search for the optimal size of sliding windows, and ensure that deep network architectures are adept at learning the vital hidden features. NNCAE methodology is used after performing the standard pre-processing procedures to handle the noise and class imbalance problem. This class balanced and noise-removed input data features are learned to train the proposed hybrid classifier. The classification model, Golden Eagle Optimization-based Convolutional Long Short-Term Memory neural networks (GEO-Conv-LSTM), is assembled by integrating Convolutional Neural Network CNN and LSTM models, with parameter tuning performed by the GEO algorithm. Evaluations are conducted on two large datasets from the Genomics of Drug Sensitivity in Cancer (GDSC) repository, and the proposed NNCAE-GEO-Conv-LSTM-based approach has achieved 96.99% and 97.79% accuracies, respectively, with reduced processing time and error rate for the DRP problem.

An optimal deep learning approach for breast cancer detection and classification with pre-trained CNN-based feature learning mechanism

Breast cancer (BC) is the most dominant kind of cancer, which grows continuously and serves as the second highest cause of death for women worldwide. Early BC prediction helps decrease the BC mortality rate and improve treatment plans. Ultrasound is a popular and widely used imaging technique to detect BC at an earlier stage. Segmenting and classifying the tumors from ultrasound images is difficult. This paper proposes an optimal deep learning (DL)-based BC detection system with effective pre-trained transfer learning models-based segmentation and feature learning mechanisms. The proposed system comprises five phases: preprocessing, segmentation, feature learning, selection, and classification. Initially, the ultrasound images are collected from the breast ultrasound images (BUSI) dataset, and the preprocessing operations, such as noise removal using the Wiener filter and contrast enhancement using histogram equalization, are performed on the collected data to improve the dataset quality. Then, the segmentation of cancer-affected regions from the preprocessed data is done using a dilated convolution-based U-shaped network (DCUNet). The features are extracted or learned from the segmented images using spatial and channel attention including densely connected convolutional network-121 (SCADN-121). Afterwards, the system applies an enhanced cuckoo search optimization (ECSO) algorithm to select the features from the extracted feature set optimally. Finally, the ECSO-tuned long short-term memory (ECSO-LSTM) was utilized to classify BC into '3' classes, such as normal, benign, and malignant. The experimental outcomes proved that the proposed system attains 99.86% accuracy for BC classification, which is superior to the existing state-of-the-art methods.

Enhancing cancer stage prediction through hybrid deep neural networks: a comparative study

Efficiently detecting and treating cancer at an early stage is crucial to improve the overall treatment process and mitigate the risk of disease progression. In the realm of research, the utilization of artificial intelligence technologies holds significant promise for enhancing advanced cancer diagnosis. Nonetheless, a notable hurdle arises when striving for precise cancer-stage diagnoses through the analysis of gene sets. Issues such as limited sample volumes, data dispersion, overfitting, and the use of linear classifiers with simple parameters hinder prediction performance. This study introduces an innovative approach for predicting early and late-stage cancers by integrating hybrid deep neural networks. A deep neural network classifier, developed using the open-source TensorFlow library and Keras network, incorporates a novel method that combines genetic algorithms, Extreme Learning Machines (ELM), and Deep Belief Networks (DBN). Specifically, two evolutionary techniques, DBN-ELM-BP and DBN-ELM-ELM, are proposed and evaluated using data from The Cancer Genome Atlas (TCGA), encompassing mRNA expression, miRNA levels, DNA methylation, and clinical information. The models demonstrate outstanding prediction accuracy (89.35%-98.75%) in distinguishing between early- and late-stage cancers. Comparative analysis against existing methods in the literature using the same cancer dataset reveals the superiority of the proposed hybrid method, highlighting its enhanced accuracy in cancer stage prediction.

A New Method to Detect Buffalo Mastitis Using Udder Ultrasonography Based on Deep Learning Network

Mastitis is one of the most predominant diseases with a negative impact on ranch products worldwide. It reduces milk production, damages milk quality, increases treatment costs, and even leads to the premature elimination of animals. In addition, failure to take effective measures in time will lead to widespread disease. The key to reducing the losses caused by mastitis lies in the early detection of the disease. The application of deep learning with powerful feature extraction capability in the medical field is receiving increasing attention. The main purpose of this study was to establish a deep learning network for buffalo quarter-level mastitis detection based on 3054 ultrasound images of udders from 271 buffaloes. Two data sets were generated with thresholds of somatic cell count (SCC) set as 2 × 105 cells/mL and 4 × 105 cells/mL, respectively. The udders with SCCs less than the threshold value were defined as healthy udders, and otherwise as mastitis-stricken udders. A total of 3054 udder ultrasound images were randomly divided into a training set (70%), a validation set (15%), and a test set (15%). We used the EfficientNet_b3 model with powerful learning capabilities in combination with the convolutional block attention module (CBAM) to train the mastitis detection model. To solve the problem of sample category imbalance, the PolyLoss module was used as the loss function. The training set and validation set were used to develop the mastitis detection model, and the test set was used to evaluate the network's performance. The results showed that, when the SCC threshold was 2 × 105 cells/mL, our established network exhibited an accuracy of 70.02%, a specificity of 77.93%, a sensitivity of 63.11%, and an area under the receiver operating characteristics curve (AUC) of 0.77 on the test set. The classification effect of the model was better when the SCC threshold was 4 × 105 cells/mL than when the SCC threshold was 2 × 105 cells/mL. Therefore, when SCC ≥ 4 × 105 cells/mL was defined as mastitis, our established deep neural network was determined as the most suitable model for farm on-site mastitis detection, and this network model exhibited an accuracy of 75.93%, a specificity of 80.23%, a sensitivity of 70.35%, and AUC 0.83 on the test set. This study established a 1/4 level mastitis detection model which provides a theoretical basis for mastitis detection in buffaloes mostly raised by small farmers lacking mastitis diagnostic conditions in developing countries.

2S-BUSGAN: A Novel Generative Adversarial Network for Realistic Breast Ultrasound Image with Corresponding Tumor Contour Based on Small Datasets

Deep learning (DL) models in breast ultrasound (BUS) image analysis face challenges with data imbalance and limited atypical tumor samples. Generative Adversarial Networks (GAN) address these challenges by providing efficient data augmentation for small datasets. However, current GAN approaches fail to capture the structural features of BUS and generated images lack structural legitimacy and are unrealistic. Furthermore, generated images require manual annotation for different downstream tasks before they can be used. Therefore, we propose a two-stage GAN framework, 2s-BUSGAN, for generating annotated BUS images. It consists of the Mask Generation Stage (MGS) and the Image Generation Stage (IGS), generating benign and malignant BUS images using corresponding tumor contours. Moreover, we employ a Feature-Matching Loss (FML) to enhance the quality of generated images and utilize a Differential Augmentation Module (DAM) to improve GAN performance on small datasets. We conduct experiments on two datasets, BUSI and Collected. Moreover, results indicate that the quality of generated images is improved compared with traditional GAN methods. Additionally, our generated images underwent evaluation by ultrasound experts, demonstrating the possibility of deceiving doctors. A comparative evaluation showed that our method also outperforms traditional GAN methods when applied to training segmentation and classification models. Our method achieved a classification accuracy of 69% and 85.7% on two datasets, respectively, which is about 3% and 2% higher than that of the traditional augmentation model. The segmentation model trained using the 2s-BUSGAN augmented datasets achieved DICE scores of 75% and 73% on the two datasets, respectively, which were higher than the traditional augmentation methods. Our research tackles imbalanced and limited BUS image data challenges. Our 2s-BUSGAN augmentation method holds potential for enhancing deep learning model performance in the field.

A hybrid machine learning model for timely prediction of breast cancer

Breast cancer is one of the leading causes of untimely deaths among women in various countries across the world. This can be attributed to many factors including late detection which often increase its severity. Thus, detecting the disease early would help mitigate its mortality rate and other risks associated with it. This study developed a hybrid machine learning model for timely prediction of breast cancer to help combat the disease. The dataset from Kaggle was adopted to predict the breast tumor growth and sizes using random tree classification, logistic regression, XBoost tree and multilayer perceptron on the dataset. The implementation of these machine learning algorithms and visualization of the results was done using Python. The results achieved a high accuracy (99.65%) on training and testing datasets which is far better than traditional means. The predictive model has good potential to enhance early detection and diagnosis of breast cancer and improvement of treatment outcome. It could also assist patients to timely deal with their condition or life patterns to support their recovery or survival.

An Ensembled Framework for Human Breast Cancer Survivability Prediction Using Deep Learning

Breast cancer is categorized as an aggressive disease, and it is one of the leading causes of death. Accurate survival predictions for both long-term and short-term survivors, when delivered on time, can help physicians make effective treatment decisions for their patients. Therefore, there is a dire need to design an efficient and rapid computational model for breast cancer prognosis. In this study, we propose an ensemble model for breast cancer survivability prediction (EBCSP) that utilizes multi-modal data and stacks the output of multiple neural networks. Specifically, we design a convolutional neural network (CNN) for clinical modalities, a deep neural network (DNN) for copy number variations (CNV), and a long short-term memory (LSTM) architecture for gene expression modalities to effectively handle multi-dimensional data. The independent models' results are then used for binary classification (long term > 5 years and short term < 5 years) based on survivability using the random forest method. The EBCSP model's successful application outperforms models that utilize a single data modality for prediction and existing benchmarks.

Accuracy Assessment of Machine Learning Algorithms Used to Predict Breast Cancer

Machine learning (ML) was used to develop classification models to predict individual tumor patients’ outcomes. Binary classification defined whether the tumor was malignant or benign. This paper presents a comparative analysis of machine learning algorithms used for breast cancer prediction. This study used a dataset obtained from the National Cancer Institute (NIH), USA, which contains 1.7 million data records. Classical and deep learning methods were included in the accuracy assessment. Classical decision tree (DT), linear discriminant (LD), logistic regression (LR), support vector machine (SVM), and ensemble techniques (ET) algorithms were used. Probabilistic neural network (PNN), deep neural network (DNN), and recurrent neural network (RNN) methods were used for comparison. Feature selection and its effect on accuracy were also investigated. The results showed that decision trees and ensemble techniques outperformed the other techniques, as they both achieved a 98.7% accuracy.

Multiview Deep Forest for Overall Survival Prediction in Cancer

Overall survival (OS) in cancer is crucial for cancer treatment. Many machine learning methods have been applied to predict OS, but there are still the challenges of dealing with multiview data and overfitting. To overcome these problems, we propose a multiview deep forest (MVDF) in this paper. MVDF can learn the features of each view and fuse them with integrated learning and multiple kernel learning. Then, a gradient boost forest based on the information bottleneck theory is proposed to reduce redundant information and avoid overfitting. In addition, a pruning strategy for a cascaded forest is used to limit the impact of outlier data. Comprehensive experiments have been carried out on a data set from West China Hospital of Sichuan University and two public data sets. Results have demonstrated that our method outperforms the compared methods in predicting overall survival.

Imbalanced data preprocessing techniques for machine learning: a systematic mapping study

Machine Learning (ML) algorithms have been increasingly replacing people in several application domains-in which the majority suffer from data imbalance. In order to solve this problem, published studies implement data preprocessing techniques, cost-sensitive and ensemble learning. These solutions reduce the naturally occurring bias towards the majority sample through ML. This study uses a systematic mapping methodology to assess 9927 papers related to sampling techniques for ML in imbalanced data applications from 7 digital libraries. A filtering process selected 35 representative papers from various domains, such as health, finance, and engineering. As a result of a thorough quantitative analysis of these papers, this study proposes two taxonomies-illustrating sampling techniques and ML models. The results indicate that oversampling and classical ML are the most common preprocessing techniques and models, respectively. However, solutions with neural networks and ensemble ML models have the best performance-with potentially better results through hybrid sampling techniques. Finally, none of the 35 works apply simulation-based synthetic oversampling, indicating a path for future preprocessing solutions.

Machine Learning Methods for Survival Analysis with Clinical and Transcriptomics Data of Breast Cancer

Breast cancer is one of the most common cancers in women worldwide, which causes an enormous number of deaths annually. However, early diagnosis of breast cancer can improve survival outcomes enabling simpler and more cost-effective treatments. The recent increase in data availability provides unprecedented opportunities to apply data-driven and machine learning methods to identify early-detection prognostic factors capable of predicting the expected survival and potential sensitivity to treatment of patients, with the final aim of enhancing clinical outcomes. This tutorial presents a protocol for applying machine learning models in survival analysis for both clinical and transcriptomic data. We show that integrating clinical and mRNA expression data is essential to explain the multiple biological processes driving cancer progression. Our results reveal that machine-learning-based models such as random survival forests, gradient boosted survival model, and survival support vector machine can outperform the traditional statistical methods, i.e., Cox proportional hazard model. The highest C-index among the machine learning models was recorded when using survival support vector machine, with a value 0.688, whereas the C-index recorded using the Cox model was 0.677. Shapley Additive Explanation (SHAP) values were also applied to identify the feature importance of the models and their impact on the prediction outcomes.

BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images

Breast cancer is the most commonly diagnosed cancer and registers the highest number of deaths for women. Advances in diagnostic activities combined with large-scale screening policies have significantly lowered the mortality rates for breast cancer patients. However, the manual inspection of tissue slides by pathologists is cumbersome, time-consuming and is subject to significant inter- and intra-observer variability. Recently, the advent of whole-slide scanning systems has empowered the rapid digitization of pathology slides and enabled the development of Artificial Intelligence (AI)-assisted digital workflows. However, AI techniques, especially Deep Learning, require a large amount of high-quality annotated data to learn from. Constructing such task-specific datasets poses several challenges, such as data-acquisition level constraints, time-consuming and expensive annotations and anonymization of patient information. In this paper, we introduce the BReAst Carcinoma Subtyping (BRACS) dataset, a large cohort of annotated Hematoxylin and Eosin (H&E)-stained images to advance AI development in the automatic characterization of breast lesions. BRACS contains 547 Whole-Slide Images (WSIs) and 4539 Regions Of Interest (ROIs) extracted from the WSIs. Each WSI and respective ROIs are annotated by the consensus of three board-certified pathologists into different lesion categories. Specifically, BRACS includes three lesion types, i.e., benign, malignant and atypical, which are further subtyped into seven categories. It is, to the best of our knowledge, the largest annotated dataset for breast cancer subtyping both at WSI and ROI levels. Furthermore, by including the understudied atypical lesions, BRACS offers a unique opportunity for leveraging AI to better understand their characteristics. We encourage AI practitioners to develop and evaluate novel algorithms on the BRACS dataset to further breast cancer diagnosis and patient care.

Database URL: https://www.bracs.icar.cnr.it/

Computer-aided diagnosis for breast cancer classification using deep neural networks and transfer learning

BACKGROUND AND OBJECTIVE

 Many developed and non-developed countries worldwide suffer from cancer-related fatal diseases. In particular, the rate of breast cancer in females increases daily, partially due to unawareness and undiagnosed at the early stages. A proper first breast cancer treatment can only be provided by adequately detecting and classifying cancer during the very early stages of its development. The use of medical image analysis techniques and computer-aided diagnosis may help the acceleration and the automation of both cancer detection and classification by also training and aiding less experienced physicians. For large datasets of medical images, convolutional neural networks play a significant role in detecting and classifying cancer effectively.

METHODS

 This article presents a novel computer-aided diagnosis method for breast cancer classification (both binary and multi-class), using a combination of deep neural networks (ResNet 18, ShuffleNet, and Inception-V3Net) and transfer learning on the BreakHis publicly available dataset.

RESULTS AND CONCLUSIONS

 Our proposed method provides the best average accuracy for binary classification of benign or malignant cancer cases of 99.7%, 97.66%, and 96.94% for ResNet, InceptionV3Net, and ShuffleNet, respectively. Average accuracies for multi-class classification were 97.81%, 96.07%, and 95.79% for ResNet, Inception-V3Net, and ShuffleNet, respectively.

Federated Learning-Based Detection of Invasive Carcinoma of No Special Type with Histopathological Images

Invasive carcinoma of no special type (IC-NST) is known to be one of the most prevalent kinds of breast cancer, hence the growing research interest in studying automated systems that can detect the presence of breast tumors and appropriately classify them into subtypes. Machine learning (ML) and, more specifically, deep learning (DL) techniques have been used to approach this problem. However, such techniques usually require massive amounts of data to obtain competitive results. This requirement makes their application in specific areas such as health problematic as privacy concerns regarding the release of patients’ data publicly result in a limited number of publicly available datasets for the research community. This paper proposes an approach that leverages federated learning (FL) to securely train mathematical models over multiple clients with local IC-NST images partitioned from the breast histopathology image (BHI) dataset to obtain a global model. First, we used residual neural networks for automatic feature extraction. Then, we proposed a second network consisting of Gabor kernels to extract another set of features from the IC-NST dataset. After that, we performed a late fusion of the two sets of features and passed the output through a custom classifier. Experiments were conducted for the federated learning (FL) and centralized learning (CL) scenarios, and the results were compared. Competitive results were obtained, indicating the positive prospects of adopting FL for IC-NST detection. Additionally, fusing the Gabor features with the residual neural network features resulted in the best performance in terms of accuracy, F1 score, and area under the receiver operation curve (AUC-ROC). The models show good generalization by performing well on another domain dataset, the breast cancer histopathological (BreakHis) image dataset. Our method also outperformed other methods from the literature.

Shape-Based Breast Lesion Classification Using Digital Tomosynthesis Images: The Role of Explainable Artificial Intelligence

Computer-aided diagnosis (CAD) systems can help radiologists in numerous medical tasks including classification and staging of the various diseases. The 3D tomosynthesis imaging technique adds value to the CAD systems in diagnosis and classification of the breast lesions. Several convolutional neural network (CNN) architectures have been proposed to classify the lesion shapes to the respective classes using a similar imaging method. However, not only is the black box nature of these CNN models questionable in the healthcare domain, but so is the morphological-based cancer classification, concerning the clinicians. As a result, this study proposes both a mathematically and visually explainable deep-learning-driven multiclass shape-based classification framework for the tomosynthesis breast lesion images. In this study, authors exploit eight pretrained CNN architectures for the classification task on the previously extracted regions of interests images containing the lesions. Additionally, the study also unleashes the black box nature of the deep learning models using two well-known perceptive explainable artificial intelligence (XAI) algorithms including Grad-CAM and LIME. Moreover, two mathematical-structure-based interpretability techniques, i.e., t-SNE and UMAP, are employed to investigate the pretrained models’ behavior towards multiclass feature clustering. The experimental results of the classification task validate the applicability of the proposed framework by yielding the mean area under the curve of 98.2%. The explanability study validates the applicability of all employed methods, mainly emphasizing the pros and cons of both Grad-CAM and LIME methods that can provide useful insights towards explainable CAD systems.

An improved deep convolutional neural network architecture for chromosome abnormality detection using hybrid optimization model

Chromosomes are thread-like structures located in the cell nucleus that contains the human body blueprint. Chromosome analysis is also known as karyotyping is the test taken to detect the abnormalities identified in the human chromosome. The two types of widely known chromosome abnormalities are structural and numerical abnormalities. Manual karyotyping is complex, time-consuming, and error-prone. To overcome these complexities, automated chromosome karyotype architecture is proposed using the deep convolutional neural network (DCNN) architecture. Training the DCNN architecture from scratch needs a huge dataset and to overcome this problem a generative adversarial networks is used to create adversarial samples that resemble the images in the actual dataset. The time-consuming hyperparameter tuning in the DCNN architecture is overcome using the hybrid moth-flame optimization integrated with the hill-climbing strategy (HMFOHC). The HMFOHC algorithm is mainly utilized in this article to minimize the huge number of parameters associated with the DCNN architecture. The efficiency of the proposed methodology is evaluated using two datasets namely the BioImLab chromosome dataset and hospital dataset. The proposed HMFOHC optimized DCNN architecture is mainly utilized for multiclass classification where it differentiates five numerical chromosome abnormalities, namely Trisomy 13, Trisomy 18, Trisomy 21, Trisomy XXY syndrome, and Monosomy X. The proposed model offers an accuracy, F1-score, and kappa coefficient value of 98.65%, 98.86%, and 0.9894, respectively. The results obtained show that the proposed model achieves higher classification accuracy when compared with the different state-of-art techniques such as deep learning, random forest, and CNN. The inference time of the proposed methodology is 12.5 s which is relatively lower than the state-of-art techniques. The proposed approach can help cytogenetics forensic experts make better decisions and save time by automating manual karyotyping.

Feature Importance Score-Based Functional Link Artificial Neural Networks for Breast Cancer Classification

Growth of malignant tumors in the breast results in breast cancer. It is a cause of death of many women across the world. As a part of treatment, a woman might have to go through painful surgery and chemotherapy that may further lead to severe side effects. However, it is possible to cure it if it is diagnosed in the initial stage. Recently, many researchers have leveraged machine learning (ML) techniques to classify breast cancer. However, these methods are computationally expensive and prone to the overfitting problem. A simple single-layer neural network, i.e., functional link artificial neural network (FLANN), is proposed to overcome this problem. Further, the F-score is used to reduce the issue of overfitting by selecting features having a higher significance level. In this paper, FLANN is proposed to classify breast cancer using Wisconsin Breast Cancer Dataset (WBCD) (with 699 samples) and Wisconsin Diagnostic Breast Cancer (WDBC) (with 569 samples) datasets. Experimental results reveal that the proposed models can diagnose breast cancer with higher performance. The proposed model can be used in the early breast cancer diagnosis with 99.41% accuracy.

An Augmented Artificial Intelligence Approach for Chronic Diseases Prediction

Chronic diseases are increasing in prevalence and mortality worldwide. Early diagnosis has therefore become an important research area to enhance patient survival rates. Several research studies have reported classification approaches for specific disease prediction. In this paper, we propose a novel augmented artificial intelligence approach using an artificial neural network (ANN) with particle swarm optimization (PSO) to predict five prevalent chronic diseases including breast cancer, diabetes, heart attack, hepatitis, and kidney disease. Seven classification algorithms are compared to evaluate the proposed model's prediction performance. The ANN prediction model constructed with a PSO based feature extraction approach outperforms other state-of-the-art classification approaches when evaluated with accuracy. Our proposed approach gave the highest accuracy of 99.67%, with the PSO. However, the classification model's performance is found to depend on the attributes of data used for classification. Our results are compared with various chronic disease datasets and shown to outperform other benchmark approaches. In addition, our optimized ANN processing is shown to require less time compared to random forest (RF), deep learning and support vector machine (SVM) based methods. Our study could play a role for early diagnosis of chronic diseases in hospitals, including through development of online diagnosis systems.

A Comprehensive Survey on Deep-Learning-Based Breast Cancer Diagnosis

Breast cancer is now the most frequently diagnosed cancer in women, and its percentage is gradually increasing. Optimistically, there is a good chance of recovery from breast cancer if identified and treated at an early stage. Therefore, several researchers have established deep-learning-based automated methods for their efficiency and accuracy in predicting the growth of cancer cells utilizing medical imaging modalities. As of yet, few review studies on breast cancer diagnosis are available that summarize some existing studies. However, these studies were unable to address emerging architectures and modalities in breast cancer diagnosis. This review focuses on the evolving architectures of deep learning for breast cancer detection. In what follows, this survey presents existing deep-learning-based architectures, analyzes the strengths and limitations of the existing studies, examines the used datasets, and reviews image pre-processing techniques. Furthermore, a concrete review of diverse imaging modalities, performance metrics and results, challenges, and research directions for future researchers is presented.

Breast histopathological image analysis using image processing techniques for diagnostic puposes: A methodological review

Breast cancer in women is the second most common cancer worldwide. Early detection of breast cancer can reduce the risk of human life. Non-invasive techniques such as mammograms and ultrasound imaging are popularly used to detect the tumour. However, histopathological analysis is necessary to determine the malignancy of the tumour as it analyses the image at the cellular level. Manual analysis of these slides is time consuming, tedious, subjective and are susceptible to human errors. Also, at times the interpretation of these images are inconsistent between laboratories. Hence, a Computer-Aided Diagnostic system that can act as a decision support system is need of the hour. Moreover, recent developments in computational power and memory capacity led to the application of computer tools and medical image processing techniques to process and analyze breast cancer histopathological images. This review paper summarizes various traditional and deep learning based methods developed to analyze breast cancer histopathological images. Initially, the characteristics of breast cancer histopathological images are discussed. A detailed discussion on the various potential regions of interest is presented which is crucial for the development of Computer-Aided Diagnostic systems. We summarize the recent trends and choices made during the selection of medical image processing techniques. Finally, a detailed discussion on the various challenges involved in the analysis of BCHI is presented along with the future scope.

King Abdulaziz University Breast Cancer Mammogram Dataset (KAU-BCMD)

The current era is characterized by the rapidly increasing use of computer-aided diagnosis (CAD) systems in the medical field. These systems need a variety of datasets to help develop, evaluate, and compare their performances fairly. Physicians indicated that breast anatomy, especially dense ones, and the probability of breast cancer and tumor development, vary highly depending on race. Researchers reported that breast cancer risk factors are related to culture and society. Thus, there is a massive need for a local dataset representing breast cancer in our region to help develop and evaluate automatic breast cancer CAD systems. This paper presents a public mammogram dataset called King Abdulaziz University Breast Cancer Mammogram Dataset (KAU-BCMD) version 1. To our knowledge, KAU-BCMD is the first dataset in Saudi Arabia that deals with a large number of mammogram scans. The dataset was collected from the Sheikh Mohammed Hussein Al-Amoudi Center of Excellence in Breast Cancer at King Abdulaziz University. It contains 1416 cases. Each case has two views for both the right and left breasts, resulting in 5662 images based on the breast imaging reporting and data system. It also contains 205 ultrasound cases corresponding to a part of the mammogram cases, with 405 images as a total. The dataset was annotated and reviewed by three different radiologists. Our dataset is a promising dataset that contains different imaging modalities for breast cancer with different cancer grades for Saudi women.