scholarly journals Histo-CADx: duo cascaded fusion stages for breast cancer diagnosis from histopathological images

2021 ◽  
Vol 7 ◽  
pp. e493
Author(s):  
Omneya Attallah ◽  
Fatma Anwar ◽  
Nagia M. Ghanem ◽  
Mohamed A. Ismail
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Early Stage ◽  
Breast Cancer Diagnosis ◽  
Extraction Methods ◽  
Automatic Diagnosis ◽  
Multiple Classifier ◽  
Histopathological Images ◽  
Public Datasets ◽  
The Impact

Breast cancer (BC) is one of the most common types of cancer that affects females worldwide. It may lead to irreversible complications and even death due to late diagnosis and treatment. The pathological analysis is considered the gold standard for BC detection, but it is a challenging task. Automatic diagnosis of BC could reduce death rates, by creating a computer aided diagnosis (CADx) system capable of accurately identifying BC at an early stage and decreasing the time consumed by pathologists during examinations. This paper proposes a novel CADx system named Histo-CADx for the automatic diagnosis of BC. Most related studies were based on individual deep learning methods. Also, studies did not examine the influence of fusing features from multiple CNNs and handcrafted features. In addition, related studies did not investigate the best combination of fused features that influence the performance of the CADx. Therefore, Histo-CADx is based on two stages of fusion. The first fusion stage involves the investigation of the impact of fusing several deep learning (DL) techniques with handcrafted feature extraction methods using the auto-encoder DL method. This stage also examines and searches for a suitable set of fused features that could improve the performance of Histo-CADx. The second fusion stage constructs a multiple classifier system (MCS) for fusing outputs from three classifiers, to further improve the accuracy of the proposed Histo-CADx. The performance of Histo-CADx is evaluated using two public datasets; specifically, the BreakHis and the ICIAR 2018 datasets. The results from the analysis of both datasets verified that the two fusion stages of Histo-CADx successfully improved the accuracy of the CADx compared to CADx constructed with individual features. Furthermore, using the auto-encoder for the fusion process has reduced the computation cost of the system. Moreover, the results after the two fusion stages confirmed that Histo-CADx is reliable and has the capacity of classifying BC more accurately compared to other latest studies. Consequently, it can be used by pathologists to help them in the accurate diagnosis of BC. In addition, it can decrease the time and effort needed by medical experts during the examination.

scholarly journals Serial Assessment of Urinary Incontinence in Breast Cancer Survivors Undergoing (Neo)Adjuvant Therapy

2020 ◽  
Vol 18 (6) ◽  
pp. 712-716
Author(s):  
Christopher P. Chung ◽  
Carolyn Behrendt ◽  
Louise Wong ◽  
Sarah Flores ◽  
Joanne E. Mortimer
Keyword(s):  
Breast Cancer ◽  
Urinary Incontinence ◽  
Adjuvant Therapy ◽  
Cancer Survivors ◽  
Breast Cancer Survivors ◽  
Early Stage ◽  
Treatment Strategies ◽  
Breast Cancer Diagnosis ◽  
Urinary Symptoms ◽  
The Impact

Background: Among breast cancer survivors, urinary incontinence (UI) is often attributed to cancer therapy. We prospectively assessed urinary symptoms before and after (neo)adjuvant treatment of early-stage breast cancer. Methods: With consent, women with stage I–III breast cancer completed the Urogenital Distress Inventory and the Incontinence Impact Questionnaire before and 3 months after initiating (neo)adjuvant therapy. Patients with UI were at least slightly bothered by urinary symptoms. If UI was present pretreatment, it was considered prevalent; if UI was new or worse at 3 months posttreatment, it was considered incident; if prevalent UI was no worse at 3 months posttreatment, it was considered stable. Ordinal logistic regression models identified characteristics associated with the level of prevalent UI and with the degree of UI impact on quality of life (QoL). Results: On pretreatment surveys, participants (N=203; age 54.5 ± 11.4 years) reported 79.8% prevalence of UI, including overactive bladder (29.1%), stress incontinence (10.8%), or both (39.9%). The level of prevalent UI increased with body mass index (BMI; P<.05). Of 163 participants assessed at both time points, incident UI developed in 12 of 32 patients without prevalent UI and 27 of 131 patients with prevalent UI. Regardless of whether UI was prevalent (n=162), incident (n=39), or stable (n=94) at QoL assessment, the impact of UI increased (P<.01) with the number and severity of UI symptoms, subjective urinary retention, and BMI. Adjusted for those characteristics, incident UI had less impact on QoL (P<.05) than did prevalent or stable UI. Conclusions: We found that UI is highly prevalent at breast cancer diagnosis and that new or worsened UI is common after (neo)adjuvant therapy. Because UI often impairs QoL, appropriate treatment strategies are needed.

scholarly journals Overview in Breast Cancer Screening in Lebanon

2021 ◽  
Vol 28 ◽  
pp. 107327482110394
Author(s):  
Eman Sbaity ◽  
Rachelle Bejjany ◽  
Malek Kreidieh ◽  
Sally Temraz ◽  
Ali Shamseddine
Keyword(s):  
Breast Cancer ◽  
Early Stage ◽  
Breast Cancer Diagnosis ◽  
Mammographic Screening ◽  
Early Stage Disease ◽  
Western Countries ◽  
Attitudes And Practices ◽  
Awareness Campaigns ◽  
Screening Mammograms ◽  
The Impact

Breast cancer (BC) is the most common cancer in women and men combined, and it is the second cause of cancer deaths in women after lung cancer. In Lebanon, the same epidemiological profile applies where BC is the leading cancer among Lebanese females, representing 38.2% of all cancer cases. As per the Center for Disease Control, there was a decline in BC mortality rate from 2003 to 2012 reflecting the adoption of national mammographic screening as the gold standard for BC detection by Western countries. The aim of this review study is to summarize current recommendations for BC screening and the available modalities for detecting BC in different countries, particularly in Lebanon. It also aims at exploring the impact of screening campaigns on BC early stage diagnosis in Lebanon. Despite the considerable debates whether screening mammograms provides more harm than benefits, screening awareness should be stressed since its benefits far outweigh its risks. In fact, the majority of BC mortality cases in Western countries are non-preventable by the use of screening mammograms alone. As such, Lebanon adopted a public focus on education and awareness campaigns encouraging early BC screening. Several studies showed the impact of early detection that is reflected by an increase in early stage disease and a decrease in more aggressive stages. Further studies should shed the light on the effect of awareness campaigns on early breast cancer diagnosis and clinical down staging at a national scope; therefore, having readily available data on pre- and post-adoption of screening campaigns is crucial for analyzing trends in mortality of breast cancer origin and reduction in advanced stages diseases. There is still room for future studies evaluating post-campaigns knowledge, attitudes, and practices of women having participated, emphasizing on the barriers refraining Lebanese women to contribute in BC screening campaigns.

The clinical impact of ASCO “choosing wisely” recommendations on staging imaging for early stage breast cancers: An interrupted time-series analysis utilizing SEER-Medicare data.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. 2078-2078
Author(s):  
Alan Baltz ◽  
Issam Makhoul ◽  
Eric R Siegel
Keyword(s):  
Breast Cancer ◽  
Cancer Diagnosis ◽  
Negative Binomial ◽  
Early Stage ◽  
Breast Cancer Diagnosis ◽  
Choosing Wisely ◽  
Breast Cancers ◽  
Interrupted Time Series Analysis ◽  
Medicare Data ◽  
The Impact

2078 Background: The “Choosing Wisely” (CW) list, released by the American Society for Clinical Oncology (ASCO), highlights low-value procedures. In 2012, the CW recommendations advised against the use of staging imaging, including Positron Emission Tomography (PET), Computerized Tomography (CT) and radionuclide bone scans, for the staging of early breast cancer at low risk for metastasis. The objective of this study was therefore to assess the impact of the ASCO CW recommendations on staging imaging among early stage breast cancers. Methods: Women above the age of 66 with an early stage incident breast cancer diagnoses between 2010 and 2015 were identified within the linked SEER-Medicare data. The primary outcome of interest was the proportion of patients with a claim for staging imaging in the six months following the breast cancer diagnosis. Negative binomial regression, adjusting for pre-recommendation trends, was performed to estimate the changes in the rate of imaging staging within each year following the release of the recommendation. Results: A total of 50,004 women were identified during the study period. Prior to the release of the recommendations in 2012, the staging imaging rates among women newly diagnosed with early stage breast cancers were 5% greater in 2010 (p<.01) and 4% greater in 2011 (p<.01). Following the release of the recommendations, staging imaging rates did not decrease significantly in 2013 (2%;p=0.18). Imaging rates did, however, significantly decrease by 13% in 2014 (p<0.01) and by 16% in 2015 (p<0.01). Conclusions: The CW recommendation was associated with a significant decrease in unadvised staging imaging among incident early stage breast cancer diagnosis in the second and third year following its release. These findings demonstrate an improvement in the proportion of potentially inappropriate staging imaging in early stage breast cancers. The creation and dissemination of resources, such as the CW recommendations, serves as a powerful tool to improve clinical practice, quality of care, and patient safety from secondary malignancies, anxiety, and overdiagnosis.

scholarly journals Conventional Machine Learning versus Deep Learning for Magnification Dependent Histopathological Breast Cancer Image Classification: A Comparative Study with Visual Explanation

Diagnostics ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 528
Author(s):  
Said Boumaraf ◽  
Xiabi Liu ◽  
Yuchai Wan ◽  
Zhongshu Zheng ◽  
Chokri Ferkous ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Deep Learning ◽  
Large Scale ◽  
Binary Classification ◽  
Breast Cancer Diagnosis ◽  
Visual Interpretation ◽  
Support Tool ◽  
Histopathological Images ◽  
Conventional Machine

Breast cancer is a serious threat to women. Many machine learning-based computer-aided diagnosis (CAD) methods have been proposed for the early diagnosis of breast cancer based on histopathological images. Even though many such classification methods achieved high accuracy, many of them lack the explanation of the classification process. In this paper, we compare the performance of conventional machine learning (CML) against deep learning (DL)-based methods. We also provide a visual interpretation for the task of classifying breast cancer in histopathological images. For CML-based methods, we extract a set of handcrafted features using three feature extractors and fuse them to get image representation that would act as an input to train five classical classifiers. For DL-based methods, we adopt the transfer learning approach to the well-known VGG-19 deep learning architecture, where its pre-trained version on the large scale ImageNet, is block-wise fine-tuned on histopathological images. The evaluation of the proposed methods is carried out on the publicly available BreaKHis dataset for the magnification dependent classification of benign and malignant breast cancer and their eight sub-classes, and a further validation on KIMIA Path960, a magnification-free histopathological dataset with 20 image classes, is also performed. After providing the classification results of CML and DL methods, and to better explain the difference in the classification performance, we visualize the learned features. For the DL-based method, we intuitively visualize the areas of interest of the best fine-tuned deep neural networks using attention maps to explain the decision-making process and improve the clinical interpretability of the proposed models. The visual explanation can inherently improve the pathologist’s trust in automated DL methods as a credible and trustworthy support tool for breast cancer diagnosis. The achieved results show that DL methods outperform CML approaches where we reached an accuracy between 94.05% and 98.13% for the binary classification and between 76.77% and 88.95% for the eight-class classification, while for DL approaches, the accuracies range from 85.65% to 89.32% for the binary classification and from 63.55% to 69.69% for the eight-class classification.

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

Cancers ◽  
2021 ◽  
Vol 13 (23) ◽  
pp. 6116
Author(s):  
Muhammad Firoz Mridha ◽  
Md. Abdul Hamid ◽  
Muhammad Mostafa Monowar ◽  
Ashfia Jannat Keya ◽  
Abu Quwsar Ohi ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Cancer Diagnosis ◽  
Performance Metrics ◽  
Early Stage ◽  
Breast Cancer Diagnosis ◽  
Imaging Modalities ◽  
Research Directions ◽  
Comprehensive Survey ◽  
Processing Techniques

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.

Diagnosing breast cancer tumors using stacked ensemble model

2021 ◽  
pp. 1-9
Author(s):  
Ahmet Haşim Yurttakal ◽  
Hasan Erbay ◽  
Türkan İkizceli ◽  
Seyhan Karaçavuş ◽  
Cenker Biçer
Keyword(s):  
Breast Cancer ◽  
Deep Learning ◽  
Medical Imaging ◽  
Early Stage ◽  
False Negative ◽  
Gradient Boosting ◽  
Physical Sign ◽  
Ensemble Model ◽  
Learning Methods ◽  
Dce Mri

Breast cancer is the most common cancer that progresses from cells in the breast tissue among women. Early-stage detection could reduce death rates significantly, and the detection-stage determines the treatment process. Mammography is utilized to discover breast cancer at an early stage prior to any physical sign. However, mammography might return false-negative, in which case, if it is suspected that lesions might have cancer of chance greater than two percent, a biopsy is recommended. About 30 percent of biopsies result in malignancy that means the rate of unnecessary biopsies is high. So to reduce unnecessary biopsies, recently, due to its excellent capability in soft tissue imaging, Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) has been utilized to detect breast cancer. Nowadays, DCE-MRI is a highly recommended method not only to identify breast cancer but also to monitor its development, and to interpret tumorous regions. However, in addition to being a time-consuming process, the accuracy depends on radiologists’ experience. Radiomic data, on the other hand, are used in medical imaging and have the potential to extract disease characteristics that can not be seen by the naked eye. Radiomics are hard-coded features and provide crucial information about the disease where it is imaged. Conversely, deep learning methods like convolutional neural networks(CNNs) learn features automatically from the dataset. Especially in medical imaging, CNNs’ performance is better than compared to hard-coded features-based methods. However, combining the power of these two types of features increases accuracy significantly, which is especially critical in medicine. Herein, a stacked ensemble of gradient boosting and deep learning models were developed to classify breast tumors using DCE-MRI images. The model makes use of radiomics acquired from pixel information in breast DCE-MRI images. Prior to train the model, radiomics had been applied to the factor analysis to refine the feature set and eliminate unuseful features. The performance metrics, as well as the comparisons to some well-known machine learning methods, state the ensemble model outperforms its counterparts. The ensembled model’s accuracy is 94.87% and its AUC value is 0.9728. The recall and precision are 1.0 and 0.9130, respectively, whereas F1-score is 0.9545.

Simple and fast isolation of circulating exosomes with chitosan modified shuttle flow microchip towards breast cancer diagnosis

Lab on a Chip ◽  
2021 ◽  
Author(s):  
Wenwen Chen ◽  
Rongkai Cao ◽  
Wentao Su ◽  
xu zhang ◽  
Yuhai Xu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Medical Treatment ◽  
Cancer Diagnosis ◽  
Biological Samples ◽  
Early Stage ◽  
Breast Cancer Diagnosis ◽  
Early Stage Cancer ◽  
Tumor Prognosis ◽  
Huge Challenge

Tumor-derived exosomes have been recognized as promising biomarkers for early-stage cancer diagnosis, tumor prognosis monitoring and individual medical treatment. However, separating exosomes from trace biological samples is a huge challenge...

scholarly journals A Review of Computer-Aided Expert Systems for Breast Cancer Diagnosis

Cancers ◽  
2021 ◽  
Vol 13 (11) ◽  
pp. 2764
Author(s):  
Xin Yu Liew ◽  
Nazia Hameed ◽  
Jeremie Clos
Keyword(s):  
Breast Cancer ◽  
Machine Learning ◽  
Deep Learning ◽  
Main Process ◽  
Learning Approaches ◽  
Learning Methods ◽  
Advantages And Disadvantages ◽  
Computer Aided ◽  
Conventional Methods ◽  
The Impact

A computer-aided diagnosis (CAD) expert system is a powerful tool to efficiently assist a pathologist in achieving an early diagnosis of breast cancer. This process identifies the presence of cancer in breast tissue samples and the distinct type of cancer stages. In a standard CAD system, the main process involves image pre-processing, segmentation, feature extraction, feature selection, classification, and performance evaluation. In this review paper, we reviewed the existing state-of-the-art machine learning approaches applied at each stage involving conventional methods and deep learning methods, the comparisons within methods, and we provide technical details with advantages and disadvantages. The aims are to investigate the impact of CAD systems using histopathology images, investigate deep learning methods that outperform conventional methods, and provide a summary for future researchers to analyse and improve the existing techniques used. Lastly, we will discuss the research gaps of existing machine learning approaches for implementation and propose future direction guidelines for upcoming researchers.

Sign in / Sign up

Export Citation Format

Share Document