Deep Learning Approach for Breast Cancer Diagnosis from Microscopy Biopsy Images

Eldin, sara Noor; Hamdy, Jana Khaled; Adnan, Ganna Tamer; Hossam, Maysoon; ElMasry, Noha; Mohammed, Ammar

doi:10.1109/miucc52538.2021.9447653

Cited by 32 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most publications also presented a convolutional neural network-based deep learning classification, which provides a large number of binary classifications, although a small number of papers used multi-class separation [ 13 , 24 ]. Detecting both, the subclasses of the benign and malignant tissues were 10% less accurate in comparison with the binary decisions [ 15 ], which are more important for computer-aided diagnosis to save time and help the pathologist to examine relevant areas for further analysis.…”

Section: Discussionmentioning

confidence: 99%

Breast Tumor Tissue Segmentation with Area-Based Annotation Using Convolutional Neural Network

et al. 2022

View full text Add to dashboard Cite

In this paper, we propose a novel approach to segment tumor and normal regions in human breast tissues. Cancer is the second most common cause of death in our society; every eighth woman will be diagnosed with breast cancer in her life. Histological diagnosis is key in the process where oncotherapy is administered. Due to the time-consuming analysis and the lack of specialists alike, obtaining a timely diagnosis is often a difficult process in healthcare institutions, so there is an urgent need for improvement in diagnostics. To reduce costs and speed up the process, an automated algorithm could aid routine diagnostics. We propose an area-based annotation approach generalized by a new rule template to accurately solve high-resolution biological segmentation tasks in a time-efficient way. These algorithm and implementation rules provide an alternative solution for pathologists to make decisions as accurate as manually. This research is based on an individual database from Semmelweis University, containing 291 high-resolution, bright field microscopy breast tumor tissue images. A total of 70% of the 128 × 128-pixel resolution images (206,174 patches) were used for training a convolutional neural network to learn the features of normal and tumor tissue samples. The evaluation of the small regions results in high-resolution histopathological image segmentation; the optimal parameters were calculated on the validation dataset (29 images, 10%), considering the accuracy and time factor as well. The algorithm was tested on the test dataset (61 images, 20%), reaching a 99.10% f1 score on pixel level evaluation within 3 min on average. Besides the quantitative analyses, the system’s accuracy was measured qualitatively by a histopathologist, who confirmed that the algorithm was also accurate in regions not annotated before.

show abstract

Section: Discussionmentioning

confidence: 99%

Breast Tumor Tissue Segmentation with Area-Based Annotation Using Convolutional Neural Network

et al. 2022

View full text Add to dashboard Cite

show abstract

“…This innovative approach optimizes the residuals between the desired convolution and the input function. Remaining or omitted connections allow the model to recycle the last layer, thereby reducing training time and improving model performance (Eldin, Hamdy, & Adnan, 2021). ResNet101 is designed to use concatenation hops, allowing data to jump blocks of convolutional layers (Mahmud & Abdelgawad, 2023).…”

Section: Resnet101mentioning

confidence: 99%

Image Augmentation for BreaKHis Medical Data using Convolutional Neural Networks

Isthigosah,

Sunyoto,

Hidayat

2023

SinkrOn

View full text Add to dashboard Cite

In applying Convolutional Neural Network (CNN) to computer vision tasks in the medical domain, it is necessary to have sufficient datasets to train models with high accuracy and good general ability in identifying important patterns in medical data. This overfitting is exacerbated by data imbalances, where some classes may have a smaller sample size than others, leading to biased predictive results. The purpose of this augmentation is to create variation in the training data, which in turn can help reduce overfitting and increase the ability of the model to generalize. Therefore, comparing augmentation techniques becomes essential to assess and understand the relative effectiveness of each method in addressing the challenges of overfitting and data imbalance in the medical domain. In the context of the research described, namely a comparative analysis of augmentation performance on CNN models using the ResNet101 architecture, a comparison of augmentation techniques such as Image Generator, SMOTE, and ADASYN provides insight into which technique is most suitable for improving model performance on limited medical data. By comparing these techniques' accuracy, recall, and overall performance results, research can identify the most effective and relevant techniques in addressing the challenges of complex medical datasets. This provides a valuable guide for developing better CNN models in the future and may encourage further research in developing more innovative augmentation methods suitable for the medical domain.

show abstract

“…If cancer is found at later stages with suitable/relevant treatment and palliative therapy then it is possible to control it. S. N. Eldin et al [1] proposed the diagnosis of the breast using the biopsy images using the best three models of deep learning techniques such as Resnet50 & 101, Densenet 169 model, without doing the preprocessing of the images and with preprocessing the input images. Also in this work, they tell about the various preprocessing techniques based on the performance of the models.…”

Section: Related Workmentioning

confidence: 99%

Diagnosis of Carcinoma from Histopathology Images using DA-Deep Convnets Model

Abinaya¹,

Sivakumar²

2022

IJACSA

View full text Add to dashboard Cite

Cancer is a major origin of mortality around the globe, responsible for roughly high morbidity and mortality in 2020, or almost one per six deaths. Cervical, lung, and breast are the most common types of cancers. Cervical is the fourth highest common in women worldwide. Cervical would then kill approximately 4,280 women. Infections that cause, such as human papillomavirus (HPV) and hepatitis, account for approximately 30% of cases in low-and lower-middle-income countries. Many cancers are curable if detected as early as possible. In this proposed work, developed the DA-Deep convnets model (Data augmentation with a deep, Convolutional Neural Network) for the detection of cervical cancer from biopsy images. Deep Convolutional Neural Network presents one of the most applied DL approaches in medical imaging. Today, enhancements in image analysis and processing, particularly medical imaging, have become a major factor in the improvement of various systems in areas such as medical prognosis, treatment, and diagnosis. Based on our proposed model we achieved 99.2% accuracy in detecting the input image has cancer or not.

show abstract

Deep Learning Approach for Breast Cancer Diagnosis from Microscopy Biopsy Images

Cited by 32 publications

References 27 publications

Breast Tumor Tissue Segmentation with Area-Based Annotation Using Convolutional Neural Network

Breast Tumor Tissue Segmentation with Area-Based Annotation Using Convolutional Neural Network

Image Augmentation for BreaKHis Medical Data using Convolutional Neural Networks

Diagnosis of Carcinoma from Histopathology Images using DA-Deep Convnets Model

Contact Info

Product

Resources

About