Dual Stage Normalization Approach Towards Classification of Breast Cancer
TL;DR: The objective of the study was to establish a histopathological basis for the prognosis of breast cancer in women with a history of atypical mastectomy and establish a standard of care for such cancer.
Abstract: Breast cancer is a major concern among women that causes high risk of death. Early diagnosis of such cancer becomes challenging due to alterations in the color of the histopathological breast image...
Citations
More filters
TL;DR: In this article , the authors examined a modern Computer-Aided Diagnosis (CAD) framework that uses DL to extract features and classify them for aiding radiologists in breast cancer diagnosis.
Abstract: Breast cancer is one of the deadly cancer types that causes high mortality among women globally. Meanwhile, Deep Learning (DL) emerges as the most frequently utilized and rapidly developing branch of classical machine learning. The study examines a modern Computer-Aided Diagnosis (CAD) framework that uses DL to extract features and classify them for aiding radiologists in breast cancer diagnosis. This is accomplished through four distinct experimentations aimed at identifying the most optimal method of effective classification. Here, the first uses Deep CNNs that are pre-trained, such as AlexNet, GoogleNet, ResNet50, and Dense-Net121. The second is based on experiments using Deep CNNs to extract features and applying them onto a Support Vector Machine algorithm using three different kernels. The next one involves the fusion of different deep features for demonstrating the classification improvement by fusion of these deep features. The final experiment involves Principal Component Analysis (PCA) for reducing the computational cost and for decreasing the larger feature vectors created during fusion. The abovesaid experimentations are carried out in two different mammogram datasets namely MIAS and INbreast. The classification accuracy attained for both datasets through the fuzing of deep features (97.93% for MIAS and 96.646% for INbreast) is the highest compared with the state-of-the-art frameworks. In contrast, the classification performance did not enhance while applying the PCA on combined deep features; but the decrease in execution time provides a reduced computational cost.Abbreviations: CAD: Computer Aided Diagnosis; CNN: Convolution Neural Network; CSI: Classification Success Index; DCNN: Deep Convolution Neural Network; DICOM: Digital Imaging and Communications in Medicine; DL: Deep Learning; FC layer: Fully Connected layer; FFDM: Full-Field Digital Mammograms; FN: False Negative; FP: False Positive; ICSI: Individual Classification Success Index; MIAS: Mammographic Image Analysis Society; ML: Machine Learning; MLO: Medio-Lateral Oblique; PCA: Principal Component Analysis; PGM: Portable Gray Map; PPV: Positive Predictive Value; RBF: Radial Basis Function; SGDM: Stochastic Gradient Descent with Momentum; SVM: Support Vector Machine; TN: True Negative; TP: True Positive; TPR: True Positive Rate; UK: United Kingdom
15 citations
TL;DR: In this paper , the color appearance matrices and density maps of the stain were estimated to improve the color estimation of histological images, and a method for normalizing hematoxylin and eosin-stained histology images was proposed.
References
More filters
TL;DR: This tutorial provides a high-level overview of how to build a deep neural network for medical image classification, and provides code that can help those new to the field begin their informatics projects.
Abstract: There is recent popularity in applying machine learning to medical imaging, notably deep learning, which has achieved state-of-the-art performance in image analysis and processing. The rapid adoption of deep learning may be attributed to the availability of machine learning frameworks and libraries to simplify their use. In this tutorial, we provide a high-level overview of how to build a deep neural network for medical image classification, and provide code that can help those new to the field begin their informatics projects.
83 citations
TL;DR: This paper presents a method for automatic color and intensity normalization of digitized histology slides stained with two different agents using prior information on the stain vectors in the plane estimation process, resulting in improved stability of the estimates.
72 citations
TL;DR: Gleason grading is now the sole prostatic carcinoma grading system recommended by the World Health Organization and it is imperative that there be good interobserver reproducibility within this system worldwide.
Abstract: Context.—Gleason grading is now the sole prostatic carcinoma grading system recommended by the World Health Organization. It is imperative that there be good interobserver reproducibility ...
71 citations
TL;DR: This method offers an opportunity to augment histopathological diagnosis and tumor classification with quantitative measures of biochemicals in the same tissue sample and should prove valuable as an adjunct to differentiate cancer aggressiveness.
Abstract: Background
Metabolomics, the non-targeted interrogation of small molecules in a biological sample, is an ideal technology for identifying diagnostic biomarkers. Current tissue extraction protocols involve sample destruction, precluding additional uses of the tissue. This is particularly problematic for high value samples with limited availability, such as clinical tumor biopsies that require structural preservation to histologically diagnose and gauge cancer aggressiveness. To overcome this limitation and increase the amount of information obtained from patient biopsies, we developed and characterized a workflow to perform metabolomic analysis and histological evaluation on the same biopsy sample.
66 citations
TL;DR: DBT, as an adjunct to FFDM, has a higher cancer detection rate, increasing the effectiveness of breast cancer screening, and additional benefits of DBT may also include reduced recalls and, consequently, reduced costs and distress caused to women who would have been recalled.
60 citations