Detection of abnormalities in mammograms using deep features

Tavakoli, Nasrin; Karimi, Maryam; Norouzi, Alireza; Karimi, Nader; Samavi, Shadrokh; Soroushmehr, S. M. Reza

doi:10.1007/s12652-019-01639-x

Cited by 22 publications

(10 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… The proposed method is compared with spatial clustering[ 24 ] (SC), adaptive thresholding[ 25 ] (AT), multilevel thresholding[ 26 ] (MT), Havrda and Charvat entropy and Otsu N thresholding[ 73 ] (HC), cellular neural network[ 27 ] (CelNN), wavelet processing and adaptive thresholding[ 28 ] (WPAT), dual-stage adaptive thresholding[ 29 ] (DuSAT), deep convolutional neural network with support vector machine[ 40 ] (DCNN_SVM), convolutional neural networks and a decision scheme[ 45 ] (convolutional neural networks + DS), multiscale all convolutional neural Network[ 50 ] (M All convolutional neural network) and our proposed method …”

Section: Resultsmentioning

confidence: 99%

“…We assess the performance of our method on Mini-MIAS with respect to some state-of-the-art methods, which are mainly based on spatial clustering,[ 24 ] adaptive thresholding (AT),[ 25 ] multilevel thresholding,[ 26 ] Havrda and Charvat entropy and Otsu N thresholding,[ 72 ], CelNN,[ 27 ] wavelet processing and adaptive thresholding[ 28 ], DuSAT,[ 29 ] DCNN with SVM,[ 40 ] CNNs + DS,[ 45 ] and multiscale All CNN[ 50 ] (M All CNN). Because only sensitivity and false-positive number per image are available from other methods, we compare our method by looking at sensitivity values as shown in plot in Figure 12 .…”

Section: Resultsmentioning

confidence: 99%

“…A limitation of Ribli et al 's method is the small size of the publicly available dataset. Tavakoli et al [ 45 ] came up with a new method based on CNNs and a decision scheme (CNNs + DS). In greater detail, the authors first used a preprocessing block around each pixel that, then, is fed into a trained CNN to determine whether the pixel belongs to normal or abnormal tissues on images from the Mini-MIAS dataset.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A novel solution based on scale invariant feature transform descriptors and deep learning for the detection of suspicious regions in mammogram images

et al. 2020

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel solution based on scale invariant feature transform descriptors and deep learning for the detection of suspicious regions in mammogram images

et al. 2020

View full text Add to dashboard Cite

“…DL approaches are currently being used by researchers all around the world to yield promising outcomes in a variety of medical image analysis and interpretation applications [ 5 ]. When it comes to breast cancer diagnosis, Zhang and colleagues [ 6 ] proposed a nine-layer convolutional neural network that had a 94 percent accuracy rate [ 7 ]. Attempts of a similar kind have been made to identify tuberculosis disease, with higher performance accuracy being seen.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning and Transfer Learning for Malaria Detection

Jameela

Athotha

Singh

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Infectious disease malaria is a devastating infectious disease that claims the lives of more than 500,000 people worldwide every year. Most of these deaths occur as a result of a delayed or incorrect diagnosis. At the moment, the manual microscope is considered to be the most effective equipment for diagnosing malaria. It is, on the other hand, time-consuming and prone to human error. Because it is such a serious global health issue, it is important that the evaluation process be automated. The objective of this article is to advocate for the automation of the diagnosis process in order to eliminate the need for human intervention in the process. Convolutional neural networks (CNNs) and other deep-learning technologies, such as image processing, are being utilized to evaluate parasitemia in microscopic blood slides in order to enhance diagnostic accuracy. The approach is based on the intensity characteristics of Plasmodium parasites and erythrocytes, which are both known to be variable. Images of infected and noninfected erythrocytes are gathered and fed into the CNN models ResNet50, ResNet34, VGG-16, and VGG-19, which are all trained on the same dataset. The techniques of transfer learning and fine-tuning are employed, and the outcomes are contrasted. The VGG-19 model obtained the best overall performance given the parameters and dataset that were evaluated.

show abstract

“…Various image pre-processing methods were applied to the images of these datasets before feeding them into the CNNs. Tavakoli, N. et al [65] discussed the importance of performing image pre-processing to create training data. They mentioned that removing unwanted areas from the images will produce more accurate results.…”

Section: E Significance Of Image Pre-processing For D-cnnmentioning

confidence: 99%

Preprocessing of Breast Cancer Images to Create Datasets for Deep-CNN

et al. 2021

View full text Add to dashboard Cite

Breast cancer is the most diagnosed cancer in Australia with crude incidence rates increasing drastically from 62.8 at ages 35-39 to 271.4 at ages 50-54 (cases per 100,000 women). Various researchers have proposed methods and tools based on Machine Learning and Convolutional Neural Networks for assessing mammographic images, but these methods have produced detection and interpretation errors resulting in false-positive and false-negative cases when used in the real world. We believe that this problem can potentially be resolved by implementing effective image pre-processing techniques to create training data for Deep-CNN. Therefore, the main aim of this research is to propose effective image preprocessing methods to create datasets that can save computational time for the neural network and improve accuracy and classification rates. To do so, this research proposes methods for background removal, pectoral muscle removal, adding noise to the images, and image enhancements. Adding noise without affecting the quality of details in the images makes the input images for the neural network more representative, which may improve the performance of the neural network model when used in the real world. The proposed method for background removal is the "Rolling Ball Algorithm" and "Huang's Fuzzy Thresholding", which succeed in removing background from 100% of the images. For pectoral muscle removal "Canny Edge Detection" and "Hough's Line Transform" are used, which removed muscle from 99.06% of the images. "Invert", "CTI_RAS" and "ISOCONTOUR" lookup tables (LUTs) were used for image enhancements to outline the ROIs and regions within the ROIs.

show abstract

Detection of abnormalities in mammograms using deep features

Cited by 22 publications

References 36 publications

A novel solution based on scale invariant feature transform descriptors and deep learning for the detection of suspicious regions in mammogram images

A novel solution based on scale invariant feature transform descriptors and deep learning for the detection of suspicious regions in mammogram images

Deep Learning and Transfer Learning for Malaria Detection

Preprocessing of Breast Cancer Images to Create Datasets for Deep-CNN

Contact Info

Product

Resources

About