Breast Mass Detection and Classification Using Deep Convolutional Neural Networks for Radiologist Diagnosis Assistance

Mahmood, Tariq; Li, Jianqiang; Pei, Yan; Akhtar, Faheem Hassan; Jia, Yanhe; Khand, Zahid Hussain

doi:10.1109/compsac51774.2021.00291

Cited by 18 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, breast cancer is also one of the current leading cause of deaths where the mortality rate is still high, even though the mortality trend has been reduced since 1989 [ 3 ]. Hence, researchers focus their work on early detection of breast cancer through deep learning technology [ 103 , 104 ]. This is supported by the overlay visualization in Figure 7 , where the research direction aimed at the efficiency of CNN towards image analysis from 2018 to 2020.…”

Section: Resultsmentioning

confidence: 99%

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Khairi

Bakar

et al. 2021

Healthcare

View full text Add to dashboard Cite

Medical imaging is gaining significant attention in healthcare, including breast cancer. Breast cancer is the most common cancer-related death among women worldwide. Currently, histopathology image analysis is the clinical gold standard in cancer diagnosis. However, the manual process of microscopic examination involves laborious work and can be misleading due to human error. Therefore, this study explored the research status and development trends of deep learning on breast cancer image classification using bibliometric analysis. Relevant works of literature were obtained from the Scopus database between 2014 and 2021. The VOSviewer and Bibliometrix tools were used for analysis through various visualization forms. This study is concerned with the annual publication trends, co-authorship networks among countries, authors, and scientific journals. The co-occurrence network of the authors’ keywords was analyzed for potential future directions of the field. Authors started to contribute to publications in 2016, and the research domain has maintained its growth rate since. The United States and China have strong research collaboration strengths. Only a few studies use bibliometric analysis in this research area. This study provides a recent review on this fast-growing field to highlight status and trends using scientific visualization. It is hoped that the findings will assist researchers in identifying and exploring the potential emerging areas in the related field.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Khairi

Bakar

et al. 2021

Healthcare

View full text Add to dashboard Cite

show abstract

“…A method for distinguishing and ordering microcalcifications in mammogram images to anticipate breast lesions was created by Tariq Mahmood et al by consolidating AI with an interpretable radiomics capability. The method, which was developed using a widely accessible dataset, may help radiologists spot breast cancer in their ordinary clinical work [30]. Breast microcalcifications are the main perceptible side effect of nonpalpable breast malignant growth during screening, and they are an indication of potential carcinoma [46].…”

Section: Breast Microcalcification In the Neoadjuvant Situationmentioning

confidence: 99%

Precancerous microcalcification detection of breast cancer mammogram images using linear time-invariant filtering Wiener method with Tophat transformation

Jamil,

Dong,

Bano

et al. 2023

Preprint

View full text Add to dashboard Cite

Breast microcalcifications, tiny calcium salt deposits, can develop anywhere in the breast tissue. Breast microcalcifications are a frequent mammographic finding. For a proper diagnosis, it is essential to spot microcalcifications in mammograms as soon as possible because they are a typical early indicator of breast cancer. Computer-based detection output can help the radiologist improve diagnosis accuracy because of their tiny size and tendency to be unseen to the radiologist doing the examination. Because of its small size, it is difficult to notice with the naked eye. The identification of microcalcification is essential for cancer prevention. In this paper, I proposed a linear time-invariant filtering Wiener method with Tophat transformation (LFWT) breast microcalcification detection method, applied mammographic image corrections using a Wiener filter to remove noise, and used Contrast Limited Adaptive Histogram Equitation (CLAHE) to improve mammographic image quality. The Wiener and CLAHE filter makes visible the cancer part. After image enhancement, Tophat morphological operators such as opening and closing are applied and the mask is detected. After that, the edges are extracted and selected according to the actual image. The diagnostic performance of the proposed model was evaluated with MIAS data and In comparison to other techniques for spotting microcalcifications in mammograms. These are Local Contrast Method (LCM), Relative Local Contrast Measure Method (RLCMM), and High-Boost-Based Multiscale Local Contrast Measure (HBBMLCM) techniques used to identify cancer microcalcification on mammography imgaes. The LFWT technique was found to be the most effective for the detection of microcalcification of breast cancer compared to the other three methods. The proposed LFWT technique detects all small and tiny spots. The images used in the LFWT method are taken from the MIAS dataset of the microcalcification for breast cancer detection. Before deploying the images, several steps were carried out to remove artifacts such as pectorals and clipping etc. The result is a breast cancer with nice smooth, safe margins and high quality. All MIAS breast cancer images were recorded and in each image, all microcalcifying spots were detected. In every image, where one or more microcalcifications were found in the mammography images, Microcalcifications were detected in the Mammogram images. Microcalcifications were found in either tumor or non-tumour images.

show abstract

“…This research paper extensively explores a range of machine learning (ML) models within data mining, employing widely accepted methodologies [29,30].…”

Section: Importance Of Dataset and Expert-driven Feature Selection Sc...mentioning

confidence: 99%

Analysis of the Factors Influencing the Predictive Learning Performance Using Federated Learning

Naseem

Mahmood

et al. 2023

Preprint

View full text Add to dashboard Cite

Numerous educational institutions utilize data mining techniques to manage student records, particularly those related to academic achievements , which are essential in improving learning experiences and overall 1 Springer Nature 2021 L A T E X template outcomes. Educational Data Mining (EDM) is a thriving research field that employs data mining and machine learning methods to extract valuable insights from educational databases, primarily focused on predicting students’ academic performance. This study proposes a novel Federated Learning (FL) standard that ensures the confidentiality of the dataset and allows predicting student grades, categorized into four levels: Low, Good, Average, and Drop. To enhance model precision, optimized features are incorporated into the training process. This study evaluates the optimized dataset using five machine learning (ML) algorithms , namely Support Vector Machine (SVM), Decision Tree, Nã A¯ve Bayes, K-Nearest Neighbours, and the proposed Federated Learning Model. The models’ performance is assessed regarding accuracy, precision , recall, and F1 score, followed by a comprehensive comparative analysis. The results reveal that FL and SVM outperform the alternative models, demonstrating superior predictive performance for student grade classification. This study showcases the potential of Federated Learning in effectively utilizing educational data from various institutes while maintaining data privacy, contributing to educational data mining and machine learning advancements for student performance prediction.

show abstract

Breast Mass Detection and Classification Using Deep Convolutional Neural Networks for Radiologist Diagnosis Assistance

Cited by 18 publications

References 26 publications

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Deep Learning on Histopathology Images for Breast Cancer Classification: A Bibliometric Analysis

Precancerous microcalcification detection of breast cancer mammogram images using linear time-invariant filtering Wiener method with Tophat transformation

Analysis of the Factors Influencing the Predictive Learning Performance Using Federated Learning

Contact Info

Product

Resources

About