An automatic and efficient technique for tumor location identification and classification through breast MR images

Jaglan, Poonam; Dass, Rajeshwar; Duhan, Manoj

doi:10.1016/j.eswa.2021.115580

Cited by 7 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Features such as wavelet transform [15], pre trained CNN features [19], and high-level CNN features which have been assessed in this study may provide more accepted classification accuracy. Shape, size, texture, and contrast features could also perform well when using efficient classifiers [21]. Combining GLCM features with other feature extraction methods can drastically increase model performance.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

GLCM and CNN Deep Learning Model for Improved MRI Breast Tumors Detection

Alsalihi

Aljobouri²,

ALTameemi

2022

Int. J. Onl. Eng.

View full text Add to dashboard Cite

Breast cancer is one of the most common types of cancer among Iraqi women. MRI has been used in the detection of breast tumors for its efficient performance in the diagnosis process providing high accuracy. In this paper, breast MRI image data from 89 patients were classified using GLCM and CNN feature extraction methods. Four models were evaluated consisting of GLCM, CNN, combined GLCM and CNN features based models. The statistical ANOVA feature selection method was used to reduce the redundant features. The reduced feature subset was fed to CNN classifier for obtaining either normal or abnormal breast images. The proposed method was assessed in terms of accuracy, precision, recall and F1-score. The model provided 100% classification accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

“…Features of shape, size, texture, and contrast were extracted. There were 27 features eventually classified by SVM [21]. Furthermore, in 2021, Hilal et al proposed a model to classify MRI breast scans.…”

Section: Introductionmentioning

confidence: 99%

GLCM and CNN Deep Learning Model for Improved MRI Breast Tumors Detection

Alsalihi

Aljobouri²,

ALTameemi

2022

Int. J. Onl. Eng.

View full text Add to dashboard Cite

show abstract

“…To surmount the weakness of regular imaging techniques used in machine learning-based approaches, such as limited data size and less information to feed them, Venkata and Lingamgunta 43 introduced a CNN (CNN (LeNet-5)) based diagnosis of breast using Zenker moments which achieved 88.2% sensitivity and 76.92% accurateness, 83.3% sensitivity and 62.5% malignant growth accuracy. Jaglan et al 44 developed a one-ordered algorithm to distinguish breast lesions (normal/abnormal), which consists of an integrated fining technique for de-noising, breast boundary region extraction via selection of nipple and mid-sternum points, and followed by morphological operations and hole filling. For classification, an SVM was implemented in their study.…”

Section: Related Workmentioning

confidence: 99%

Lesion detection in women breast’s dynamic contrast-enhanced magnetic resonance imaging using deep learning

Saikia,

Si,

Deb

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Breast cancer is one of the most common cancers in women and the second foremost cause of cancer death in women after lung cancer. Recent technological advances in breast cancer treatment offer hope to millions of women in the world. Segmentation of the breast’s Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) is one of the necessary tasks in the diagnosis and detection of breast cancer. Currently, a popular deep learning model, U-Net is extensively used in biomedical image segmentation. This article aims to advance the state of the art and conduct a more in-depth analysis with a focus on the use of various U-Net models in lesion detection in women’s breast DCE-MRI. In this article, we perform an empirical study of the effectiveness and efficiency of U-Net and its derived deep learning models including ResUNet, Dense UNet, DUNet, Attention U-Net, UNet++, MultiResUNet, RAUNet, Inception U-Net and U-Net GAN for lesion detection in breast DCE-MRI. All the models are applied to the benchmarked 100 Sagittal T2-Weighted fat-suppressed DCE-MRI slices of 20 patients and their performance is compared. Also, a comparative study has been conducted with V-Net, W-Net, and DeepLabV3+. Non-parametric statistical test Wilcoxon Signed Rank Test is used to analyze the significance of the quantitative results. Furthermore, Multi-Criteria Decision Analysis (MCDA) is used to evaluate overall performance focused on accuracy, precision, sensitivity, F$$_1$$ 1 -score, specificity, Geometric-Mean, DSC, and false-positive rate. The RAUNet segmentation model achieved a high accuracy of 99.76%, sensitivity of 85.04%, precision of 90.21%, and Dice Similarity Coefficient (DSC) of 85.04% whereas ResNet achieved 99.62% accuracy, 62.26% sensitivity, 99.56% precision, and 72.86% DSC. ResUNet is found to be the most effective model based on MCDA. On the other hand, U-Net GAN takes the least computational time to perform the segmentation task. Both quantitative and qualitative results demonstrate that the ResNet model performs better than other models in segmenting the images and lesion detection, though computational time in achieving the objectives varies.

show abstract

Study on Art Pattern Creation and P-filling Algorithm Under Big Data

2022

Cyber Security Intelligence and Analytics

View full text Add to dashboard Cite

An automatic and efficient technique for tumor location identification and classification through breast MR images

Cited by 7 publications

References 43 publications

GLCM and CNN Deep Learning Model for Improved MRI Breast Tumors Detection

GLCM and CNN Deep Learning Model for Improved MRI Breast Tumors Detection

Lesion detection in women breast’s dynamic contrast-enhanced magnetic resonance imaging using deep learning

Study on Art Pattern Creation and P-filling Algorithm Under Big Data

Contact Info

Product

Resources

About