Deep learning approach for breast cancer diagnosis

Rashed, Essam A.; Seoud, M. Samir Abou El

doi:10.1145/3328833.3328867

Cited by 18 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Increasing the kernel size of O-Net resulted in an improvement in segmentation accuracy. 19 The Three Time Points (3TP) U-Net has been presented by Piantadosi et al, which means that the images used in this model were taken at three different time points: before injection of contrast agent, 2 min after injection of contrast agent, and 6 min after injection of contrast agent. 20 Zhou et al have discussed 3D DenseNet.…”

Section: Deep Learning-based Methods For the Detection Of Mri Breast ...mentioning

confidence: 99%

See 1 more Smart Citation

An improved semantic segmentation for breast lesion from dynamic contrast enhanced MRI images using deep learning

Star,

Milton,

Inbamalar

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

The World Health Organization (WHO) reports that approximately 2.3 million breast cancer cases are diagnosed each year. Early detection is key to tackling this issue, and Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE‐MRI) is a preferred method for detecting tumors. Convolutional Neural Networks (CNNs) can accurately segment images without human assistance. The objective of this study is to develop a computer‐aided diagnosis system that can segment breast lesions from DCE‐MRI images. A 92‐layer deep CNN, called DCNN‐92, and a 94‐layer deep CNN, called DCNN‐94, have been designed to identify lesions. The proposed methods have been validated using images from The Cancer Image Archive (TCIA) database. The proposed DCNN‐92 model segments the tumor pixels effectively, but it exhibits some misclassifications where certain background pixels are incorrectly labeled as tumor and tumor pixels are identified as background. To segment the tumor pixels more accurately, two grouped convolution layers are added to the DCNN‐92 model. The model with 94 layers, that is, DCNN‐94, segments most of the tumor pixels correctly, thereby enhancing the segmentation performance. When compared to DCNN‐92, the DCNN‐94 model exhibits enhanced performance across standard metrics such as sensitivity, dice coefficient, Jaccard coefficient, and area under the curve (AUC). It was found that the training time for DCNN‐94 is shorter. The DCNN‐94 model with dilation factor and group convolution is concluded to be an effective method for lesion segmentation from breast DCE‐MRI images compared to existing methods.

show abstract

Section: Deep Learning-based Methods For the Detection Of Mri Breast ...mentioning

confidence: 99%

“…Rashed and Seoud created the O‐Net, which was the fusion of two UNets to segment tumors from breast mammography. Increasing the kernel size of O‐Net resulted in an improvement in segmentation accuracy 19 …”

Section: Review Of Related Workmentioning

confidence: 99%

An improved semantic segmentation for breast lesion from dynamic contrast enhanced MRI images using deep learning

Star,

Milton,

Inbamalar

2024

Int J Imaging Syst Tech

View full text Add to dashboard Cite

show abstract

“…They applied C-Means algorithm on the centers of a fixed number of groups founded by K-Means, in order to improve the accuracy of classification. Rashed et al (2019) developed a novel network architecture with an inspiration from U-net structure to predict breast cancer in early stages. Omondiagbe (2019) investigated classification performance of Support Vector Machine (using radial basis kernel), Artificial Neural Networks and Naïve Bayes for breast cancer prediction, focusing on integrating machine learning techniques with feature selection and extraction methods.…”

Section: Literature Reviewmentioning

confidence: 99%

An Empirical Comparison of Machine Learning Algorithms for Predicting Breast Cancer

Başçiftçi¹,

Ünal²

2019

Bilge International Journal of Science and Technology Research

View full text Add to dashboard Cite

According to recent statistics, breast cancer is one of the most prevalent cancers among women in the world. It represents the majority of new cancer cases and cancer-related deaths. Early diagnosis is very important, as it becomes fatal unless detected and treated in early stages. With the latest advances in artificial intelligence and machine learning (ML), there is a great potential to diagnose breast cancer by using structured data. In this paper, we conduct an empirical comparison of 10 popular machine learning models for the prediction of breast cancer. We used well known Wisconsin Breast Cancer Dataset (WBCD) to train the models and employed advanced accuracy metrics for comparison. Experimental results show that all models demonstrate superior accuracy, while Support Vector Machines (SVM) had slightly better performance than other methods. Logistic Regression, K-Nearest Neighbors and Neural Networks also proved to be strong classifiers for predicting breast cancer.

show abstract

“…Not only does it allow them to share data and insights about a diagnosis across the globe easily, but with computational pathology, algorithms capabilities may be leveraged to ease pathologists' work on many tasks. Deep learning has shown promising results for various applications such as cancer classification [1,2,3], detection [4,5,6] or segmentation [7,8] of biomarkers required for diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathology

Nerrienet¹,

Peyret²,

Sockeel³

et al. 2023

Preprint

View full text Add to dashboard Cite

Generalization is one of the main challenges of computational pathology. Slide preparation heterogeneity and the diversity of scanners lead to poor model performance when used on data from medical centers not seen during training.In order to achieve stain invariance in breast invasive carcinoma patch classification, we implement a stain translation strategy using cycleGANs for unsupervised image-to-image translation. We compare three cycleGAN-based approaches to a baseline classification model obtained without any stain invariance strategy. Two of the proposed approaches use cycleGAN's translations at inference or training in order to build stain-specific classification models. The last method uses them for stain data augmentation during training. This constrains the classification model to learn stain-invariant features. Baseline metrics are set by training and testing the baseline classification model on a reference stain. We assessed performances using three medical centers with H&E and H&E&S staining. Every approach tested in this study improves baseline metrics without needing labels on target stains. The stain augmentation-based approach produced the best results on every stain. Each method's pros and cons are studied and discussed in this paper.However, training highly performing cycleGANs models in itself represents a challenge. In this work, we introduce a systematical method for optimizing cycleGAN training by setting a novel stopping criterion. This method has the benefit of not requiring any visual inspection of cycleGAN results and proves superiority to methods using a predefined number of training epochs. In addition, we also study the minimal amount of data required for cycleGAN training.

show abstract

Deep learning approach for breast cancer diagnosis

Cited by 18 publications

References 20 publications

An improved semantic segmentation for breast lesion from dynamic contrast enhanced MRI images using deep learning

An improved semantic segmentation for breast lesion from dynamic contrast enhanced MRI images using deep learning

An Empirical Comparison of Machine Learning Algorithms for Predicting Breast Cancer

Standardized CycleGAN training for unsupervised stain adaptation in invasive carcinoma classification for breast histopathology

Contact Info

Product

Resources

About