A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography

Abstract

Globally, the incidence rate for breast cancer ranks first. Treatment for early-stage breast cancer is highly cost effective. Five-year survival rate for stage 0–2 breast cancer exceeds 90%. Screening mammography has been acknowledged as the most reliable way to diagnose breast cancer at an early stage. Taiwan government has been urging women without any symptoms, aged between 45 and 69, to have a screening mammogram bi-yearly. This brings about a large workload for radiologists. In light of this, this paper presents a deep neural network (DNN)-based model as an efficient and reliable tool to assist radiologists with mammographic interpretation. For the first time in the literature, mammograms are completely classified into BI-RADS categories 0, 1, 2, 3, 4A, 4B, 4C and 5. The proposed model was trained using block-based images segmented from a mammogram dataset of our own. A block-based image was applied to the model as an input, and a BI-RADS category was predicted as an output. At the end of this paper, the outperformance of this work is demonstrated by an overall accuracy of 94.22%, an average sensitivity of 95.31%, an average specificity of 99.15% and an area under curve (AUC) of 0.9723. When applied to breast cancer screening for Asian women who are more likely to have dense breasts, this model is expected to give a higher accuracy than others in the literature, since it was trained using mammograms taken from Taiwanese women.

Degree of Accuracy With Which Deep Learning for Ultrasound Images Identifies Osteochondritis Dissecans of the Humeral Capitellum

“…There has been extensive research on the DL of US images in the field of breast surgery, wherein the early detection of breast cancer is required. 14,24,33 For this reason, research is under way to improve diagnostic accuracy, and various methods such as data augmentation and segmentation quantization are being used. 24 In the field of orthopaedics, studies on entrapment neuropathies, in which early detection affects the stage of the disease, have been attracting attention in recent years.…”

Neural Network in the Analysis of the MR Signal as an Image Segmentation Tool for the Determination of T1 and T2 Relaxation Times with Application to Cancer Cell Culture

“…The detection of breast asymmetry and classification of calcifications in breast was investigated with neural network [ 22 ]. Other studies [ 23 , 24 , 25 , 26 , 27 ] have found neural network useful in mammography screening. MRI with together with the neural network was used in the analysis of the liver [ 28 ], myocardium [ 29 , 30 , 31 , 32 ], and breast [ 33 ].…”

Targeted demethylation of the CDO1 promoter based on CRISPR system inhibits the malignant potential of breast cancer cells

“…19,21 The 5-year survival rate of BC with early stages (stages I-II) exceeds 90%, whereas it drops below 25% for stage IV. 23 Therefore, early detection of BC is crucial for successful treatment and improving survival rates. However, traditional serum tumour antigen biomarkers for BC, such as CEA, CA153, CA19-9, and CA125, have low sensitivity and specificity, leading to a high rate of missed diagnoses.…”