AI platform in mammography to screening breast cancer: A sole-center experience.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e18052-e18052
Author(s):  
Jie Li ◽  
Zhicheng Zhang ◽  
Jia Chang ◽  
Bo Lin ◽  
Weiming Lv
Keyword(s):  
Breast Cancer ◽  
High Performance ◽  
Area Under The Curve ◽  
Recall Rate ◽  
Breast Cancer Patients ◽  
Mass Detection ◽  
Training Set ◽  
Internal Validation ◽  
Malignant Case ◽  
Case Atlas

e18052 {\rtf1\ansi\ansicpg936\cocoartf1347\cocoasubrtf570 {\fonttbl\f0\froman\fcharset0 Times-Roman;\f1\fnil\fcharset0 Calibri;\f2\fswiss\fcharset0 Helvetica; \f3\fnil\fcharset134 STHeitiSC-Light;\f4\froman\fcharset0 TimesNewRomanPSMT;} {\colortbl;\red255\green255\blue255;\red0\green0\blue0;} \paperw11900\paperh16840\margl1440\margr1440\vieww25400\viewh13600\viewkind0 \deftab720 \pard\pardeftab720 \f0\fs24 \cf2 \expnd0\expndtw0\kerning0 \outl0\strokewidth0 \strokec2 AI platform in mammagraphy to screening breast cancer: a sole center experence. \f1\fs21 \cf0 \kerning1\expnd0\expndtw0 \outl0\strokewidth0 \ \pard\pardeftab720\ri714\qj \cf0 Background: The aim of this study was to use deep convolutional neural network (DCNN) to relieve radiologists ' burden and to minimize misses and interpretation errors of suspicious lesions at digital mammography. Methods: We developed and trained the DCNN model on the training set, then validated it in an internal validation set. The labeled data were used for training the DCNN model, and the mass detection, calcification detection and benign and malignant diagnosis were interpreted respectively. After verifying the feasibility of the DCNN model in the diagnosis of breast cancer, we gradually increased the number of cases in the training set and established the verification set to test the training results. The latest training sets include 21100 atlas of our hospital between April 2010 and October 2017, among which the malignant case atlas is 1774. Each atlas contains 2 ipsilateral mammography images. The verification set includes 1307 atlas, among which the malignant case atlas is 248. Results: The DCNN model achieved high performance in identifying breast cancer patients in the validation sets tested, with sensitivity of 98.02%, specificity of 91.86% \f3 \'a3\'ac \f2 and area under the curve values of 0.9813. As for mass detection, we reached a recall rate of 89.6% on the premise of lowing the false positive to 0.168%. For the latest clinical data between October 2018 and November 2018 including 1043 atlas from 576 patients, the sensitivity was 78.6% (95%CI 62.8-89.1) versus 90.5% (95%CI 76.5 \f4 - \f2 96.9; p=0.021) and specificity was 93.4% (95%CI 91.6 \f4 - \f2 94.8) versus 82.7% (95%CI 80.2 \f4 - \f2 85 \f4 . \f2 0; p<0.0001). Conclusions: The DCNN model showed improved specificity in diagnosis breast cancer compared with a group of skilled radiologists. As the number of cases in the training set increases, the capacity of DCNN model will be further improved.

scholarly journals Prevalence of RECQL germline variants in Pakistani early-onset and familial breast cancer patients

2020 ◽  
Vol 18 (1) ◽  
Author(s):  
Muhammad Usman Rashid ◽  
Noor Muhammad ◽  
Faiz Ali Khan ◽  
Umara Shehzad ◽  
Humaira Naeemi ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Early Onset ◽  
Familial Breast Cancer ◽  
High Performance ◽  
Breast Cancer Patients ◽  
Germline Variants ◽  
Variants Of Unknown Significance ◽  
Breast Cancer Predisposition ◽  
Novel Variants

Abstract Background The RecQ Like Helicase (RECQL) gene has previously been shown to predispose to breast cancer mainly in European populations, in particular to estrogen receptor (ER) and/or progesterone receptor (PR) positive tumor. Here, we investigated the contribution of pathogenic RECQL germline variants to hereditary breast cancer in early-onset and familial breast cancer patients from Pakistan. Methods Comprehensive RECQL variant analysis was performed in 302 BRCA1 and BRCA2 negative patients with ER and/or PR positive breast tumors using denaturing high-performance liquid chromatography followed by DNA sequencing. Novel variants were classified using Sherloc guidelines. Results One novel pathogenic protein-truncating variant (p.W75*) was identified in a 37-year-old familial breast cancer patient. The pathogenic variant frequencies were 0.3% (1/302) in early-onset and familial breast cancer patients and 0.8% (1/133) in familial patients. Further, three novel variants of unknown significance, p.I141F, p.S182S, and p.C475C, were identified in familial breast cancer patients at the age of 47, 68, and 47 respectively. All variants were absent in 250 controls. Conclusions Our data suggest that the RECQL gene plays a negligible role in breast cancer predisposition in Pakistan.

scholarly journals Electrocardiographic Characteristics of Breast Cancer Patients Treated with Chemotherapy

2020 ◽  
Vol 2020 ◽  
pp. 1-7
Author(s):  
Xufei Liang ◽  
Yueying Wang ◽  
Xi Yin ◽  
Xiaohong Gong ◽  
Shuo Pan ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Cardiac Dysfunction ◽  
Area Under The Curve ◽  
Qt Dispersion ◽  
Drug Regimen ◽  
P Wave ◽  
Breast Cancer Patients ◽  
P Wave Dispersion ◽  
Cutoff Value

Introduction. Patients receiving chemotherapy for breast cancer may be at risk of developing cardiac dysfunction and electrophysiological abnormalities. The aim of this study is to evaluate alterations in electrocardiographic (ECG) parameters in breast cancer patients receiving chemotherapy. Materials and Methods. This was a prospective single-center cohort study conducted in the Fourth Hospital of Hebei Medical University, China. Participants with breast cancer referred for chemotherapy from May 1, 2019, to October 1, 2019, were invited to participate in the study. Standard 12-lead ECG and echocardiography were performed at baseline or before chemotherapy (prechemotherapy) (T0), after 1 cycle (T1), after 3 cycles (T2), and at the end of chemotherapy (T3). Results. A total of 64 patients with diagnosed breast cancer undergoing chemotherapy were included. Echocardiographic parameters showed no significant variation during the entire procedure (all P > 0.05 ). The incidence of abnormal ECG increased from 43.75% at baseline to 65.63% at the end of chemotherapy, of which only the prevalence of fragmented QRS (fQRS) was significantly increased after the drug regimen (26.56% to 53.13%). At the end of the treatment, heart rate, P-wave dispersion, corrected QT interval, T-peak to T-end, RR, SV1, RV5, Sokolow–Lyon index (SLI), and index of cardioelectrophysiological balance deteriorated markedly (all P < 0.05 ). The area under the curve for SLI and QT dispersion (QTd) derived by ECG was 0.710 and 0.606, respectively. The cutoff value with 2.12 of SLI by ECG had a sensitivity of 67.2% and specificity of 71.9% for differentiating patients after therapy from baselines. The cutoff value with 0.55 of QTd had a sensitivity of 60.9% and specificity of 60.9%. Conclusions. The current study demonstrated that ECGs can be used to detect electrophysiological abnormalities in breast cancer patients receiving chemotherapy. ECG changes can reflect subclinical cardiac dysfunction before the echocardiographic abnormalities.

scholarly journals Use of serum biomarkers in staging of canine hepatic fibrosis

2019 ◽  
Vol 31 (5) ◽  
pp. 665-673 ◽  
Author(s):  
Maud Menard ◽  
Alexis Lecoindre ◽  
Jean-Luc Cadoré ◽  
Michèle Chevallier ◽  
Aurélie Pagnon ◽  
...  
Keyword(s):  
Liver Biopsy ◽  
Hepatic Fibrosis ◽  
External Validation ◽  
Model Performance ◽  
Area Under The Curve ◽  
Gamma Glutamyl Transferase ◽  
Training Set ◽  
Internal Validation ◽  
Validation Set ◽  
Glutamyl Transferase

Accurate staging of hepatic fibrosis (HF) is important for treatment and prognosis of canine chronic hepatitis. HF scores are used in human medicine to indirectly stage and monitor HF, decreasing the need for liver biopsy. We developed a canine HF score to screen for moderate or greater HF. We included 96 dogs in our study, including 5 healthy dogs. A liver biopsy for histologic examination and a biochemistry profile were performed on all dogs. The dogs were randomly split into a training set of 58 dogs and a validation set of 38 dogs. A HF score that included alanine aminotransferase, alkaline phosphatase, total bilirubin, potassium, and gamma-glutamyl transferase was developed in the training set. Model performance was confirmed using the internal validation set, and was similar to the performance in the training set. The overall sensitivity and specificity for the study group were 80% and 70% respectively, with an area under the curve of 0.80 (0.71–0.90). This HF score could be used for indirect diagnosis of canine HF when biochemistry panels are performed on the Konelab 30i (Thermo Scientific), using reagents as in our study. External validation is required to determine if the score is sufficiently robust to utilize biochemical results measured in other laboratories with different instruments and methodologies.

scholarly journals Identification of miRNAs Enriched in Extracellular Vesicles Derived from Serum Samples of Breast Cancer Patients

Biomolecules ◽  
2020 ◽  
Vol 10 (1) ◽  
pp. 150 ◽  
Author(s):  
Patricia M. M. Ozawa ◽  
Evelyn Vieira ◽  
Débora S. Lemos ◽  
Ingrid L. Melo Souza ◽  
Silvio M. Zanata ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Extracellular Vesicles ◽  
Area Under The Curve ◽  
Precipitation Method ◽  
Sequencing Analysis ◽  
Breast Cancer Patients ◽  
Serum Samples ◽  
Luminal A ◽  
Liquid Biopsies ◽  
Advanced Tumor

MicroRNAs derived from extracellular vesicles (EV-miRNAs) are circulating miRNAs considered as potential new diagnostic markers for cancer that can be easily detected in liquid biopsies. In this study, we performed RNA sequencing analysis as a screening strategy to identify EV-miRNAs derived from serum of clinically well-annotated breast cancer (BC) patients from the south of Brazil. EVs from three groups of samples (healthy controls (CT), luminal A (LA), and triple-negative (TNBC)) were isolated from serum using a precipitation method and analyzed by RNA-seq (screening phase). Subsequently, four EV-miRNAs (miR-142-5p, miR-150-5p, miR-320a, and miR-4433b-5p) were selected to be quantified by quantitative real-time PCR (RT-qPCR) in individual samples (test phase). A panel composed of miR-142-5p, miR-320a, and miR-4433b-5p distinguished BC patients from CT with an area under the curve (AUC) of 0.8387 (93.33% sensitivity, 68.75% specificity). The combination of miR-142-5p and miR-320a distinguished LA patients from CT with an AUC of 0.9410 (100% sensitivity, 93.80% specificity). Interestingly, decreased expression of miR-142-5p and miR-150-5p were significantly associated with more advanced tumor grades (grade III), while the decreased expression of miR-142-5p and miR-320a was associated with a larger tumor size. These results provide insights into the potential application of EVs-miRNAs from serum as novel specific markers for early diagnosis of BC.

scholarly journals Plasma microRNAs Predict Chemoresistance in Patients With Metastatic Breast Cancer

2019 ◽  
Vol 18 ◽  
pp. 153303381982870 ◽  
Author(s):  
Bin Shao ◽  
Xiaoxia Wang ◽  
Lei Zhang ◽  
Deyu Li ◽  
Xiaoran Liu ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Metastatic Breast Cancer ◽  
Cancer Patients ◽  
Quantitative Polymerase Chain Reaction ◽  
Area Under The Curve ◽  
Metastatic Breast ◽  
Chemotherapy Response ◽  
Breast Cancer Patients ◽  
Resistant Group ◽  
Sensitive Group

Background: MicroRNAs contribute to chemotherapy response in different types of cancer. We hypothesized that plasma miRNAs are potentially associated with chemotherapy response in patients with metastatic breast cancer. Patients and Methods: Fourteen candidate microRNAs were chosen from the literature, and their plasma levels were measured by quantitative polymerase chain reaction (PCR). Forty metastatic breast cancer patients were chosen as the training groups. The potential significant microRNAs were validated in another 103 plasma samples. Results: In the training set, we identified 3 microRNAs (miR-200a, miR-210, and miR-451) as significantly dysregulated miRNAs between sensitive group (partial response (and stable disease) and resistant group (progressive disease). Then, in the validation set, miR-200a (area under the curve = 0.881, sensitivity = 94.1%, specificity = 76.7%) and miR-210 (area under the curve = 0.851, sensitivity = 88.2%, specificity = 72.1%) showed high diagnostic accuracy for distinguishing sensitive group from resistant group. Furthermore, the plasma level of miR-200a was significantly associated with the stage in surgery ( P = .035), and the high level of miR-210 expression was associated with internal organ metastasis (liver, lung, and brain; P = .024). Conclusions: Plasma miR-200a and miR-210 could be effective biomarkers for the prediction of chemotherapy resistance in metastatic breast cancer patients.

scholarly journals Direct Serum Assay for MicroRNA-21 Concentrations in Early and Advanced Breast Cancer

2011 ◽  
Vol 57 (1) ◽  
pp. 84-91 ◽  
Author(s):  
Sota Asaga ◽  
Christine Kuo ◽  
Tung Nguyen ◽  
Marilou Terpenning ◽  
Armando E Giuliano ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Direct Detection ◽  
Area Under The Curve ◽  
Serum Concentrations ◽  
Breast Cancer Patients ◽  
Visceral Metastasis ◽  
Small Noncoding Rnas ◽  
Serum Assay ◽  
Healthy Donors ◽  
Healthy Female

BACKGROUND MicroRNAs (miRs) are a class of small noncoding RNAs whose expression changes have been associated with cancer development and progression. Current techniques to isolate miRs for expression analysis from blood are inefficient. We developed a reverse-transcription quantitative real-time PCR (RT-qPCR) assay for direct detection of circulating miRs in serum. We hypothesized that serum concentrations of miR-21, a biomarker increased in breast tumors, would correlate with the presence and extent of breast cancer. METHODS The RT-qPCR applied directly in serum (RT-qPCR-DS) assay for circulating miR-21 was tested in sera from 102 patients with different stages of breast cancer and 20 healthy female donors. RESULTS The assay was sensitive for detection of miR-21 in 0.625 μL of serum from breast cancer patients. For differentiation of samples from patients with locoregional breast cancer from those from healthy donors, the odds ratio was 1.796 and the area under the curve was 0.721. In a multivariate analysis that included standard clinicopathologic prognostic factors, high circulating miR-21 concentrations correlated significantly (P &lt; 0.001) with visceral metastasis. CONCLUSIONS A novel RT-qPCR-DS can improve the efficiency of miR assessment. Use of this assay to detect circulating miR-21 has diagnostic and prognostic potential in breast cancer.

scholarly journals A Scoring System to Predict Arm Lymphedema Risk for Individual Chinese Breast Cancer Patients

Breast Care ◽  
2016 ◽  
Vol 11 (1) ◽  
pp. 52-56 ◽  
Author(s):  
Ling Wang ◽  
Hui-Ping Li ◽  
An-Nuo Liu ◽  
De-Bin Wang ◽  
Ya-Juan Yang ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
Cancer Patients ◽  
Scoring System ◽  
Prognostic Score ◽  
Risk Scores ◽  
Axillary Lymph ◽  
Breast Cancer Patients ◽  
Total Risk ◽  
Internal Validation

Background: Lymphedema (LE) is recognized as a common complication after axillary lymph node dissection (ALND). Numerous studies have attempted to identify risk factors for LE. However, it is difficult to predict the probability of LE for an individual patient. The purpose of this study was to construct a scoring system for predicting the probability of LE after ALND for Chinese breast cancer patients. Patients and Methods: 358 breast cancer patients were surveyed and followed for 12 months. LE was defined by circumferential measurement. Univariate and multivariate logistic regression analyses were used to screen risk factors of LE. Based on this, ß-coefficient of each risk factor was translated into a prognostic score and the scoring system was constructed. The area under the receiver operating characteristic curve (AUC) and calibration were calculated as an index for the predictive value of the scoring system. The model was internally validated using bootstrapping techniques. Results: The incidence rate of LE was 31.84%. Variables associated with LE and their corresponding score in the scoring system were: the level of ALND (level I = 0, level II = 1, level III = 2), history of hypertension (yes = 1, no = 0), surgery on dominant arm (yes = 1, no = 0), radiotherapy (yes = 2, no = 0), and surgical infection/seroma/early edema (yes = 2, no = 0). The probability of LE was predicted according to the total risk scores. The system had good discrimination, with an AUC at 0.877. If a cut-off value of 3 was used, the sensitivity was 81.20% and the specificity was 80.90%. An individual whose total risk score was higher than 3 was recognized as being at risk for LE. On internal validation, the bootstrap-corrected predictive accuracy was 0.798. The model demonstrated excellent calibration in the development set and internal validation. Conclusions: Our scoring system could be a simple and easy tool for physicians to estimate the risk of LE.

Development of a high-performance, blood-based screening diagnostic to detect early-stage breast cancer.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. e22083-e22083
Author(s):  
Joseph Wagner ◽  
Karen Chapman ◽  
Maria Prendes-Garcia ◽  
Markus Lacher ◽  
Jennifer Kidd ◽  
...  
Keyword(s):  
Breast Cancer ◽  
High Performance ◽  
Early Stage ◽  
Low Cost ◽  
High Sensitivity ◽  
Screening Mammography ◽  
Early Stage Breast Cancer ◽  
Breast Cancer Patients ◽  
Elevated Expression ◽  
Sera Samples

e22083 Background: Limitations of current screening mammography, particularly in younger women, demonstrate the need for an alternative breast cancer screening strategy. A non-invasive, easily interpreted and low cost test should address this need. Methods: Gene expression microarray analysis was carried out on 128 individual tumor samples representing over 20 tumor types, 86 samples representing 31 diverse normal tissue types, 68 tumor cell lines and 97 diverse normal primary cell cultures. Genes were ranked for elevated expression in either: i) a large number and variety of tumors relative to normal tissues, or ii) in breast tumors. Elevated expression was verified for a subset of genes using qPCR in a set of independent RNA samples. Proteins coded by genes elevated in breast cancer samples were analyzed in a retrospective training set of breast cancer patient sera samples with cancer-free patient and benign pathology controls using ELISA or bead-based detection assay. Results: Based on availability of suitable reagents, 25 candidate biomarkers were assessed in patient sera samples (31-227 patient samples per biomarker) using ELISA or bead-based assays. Individually, the performance of individual markers varied (ROC AUC, 0.51 - 0.88); however, when expression levels of the best performing markers were combined, the multiplex test demonstrated high-sensitivity (>80%) and specificity (>90%) in identifying early-stage breast cancer patients. Conclusions: A multiplex, proteomic-based approach may provide for a high-performance, blood-based screening diagnostic for breast cancer.

A nomogram based on genetic and clinicopathologic features to predict the nonsentinel lymph node metastases in Chinese women breast cancer patients.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e12577-e12577
Author(s):  
Liling Zhu ◽  
Ke Liu ◽  
Fengyun Li ◽  
Wentao Liang ◽  
Wenzhao Shi ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Lymph Node ◽  
Sentinel Lymph Node ◽  
Cancer Patients ◽  
Chinese Women ◽  
Lasso Regression ◽  
Breast Cancer Patients ◽  
Internal Validation ◽  
Genetic Features ◽  
Clinicopathologic Factors

e12577 Background: Sentinel lymph node biopsy (SLNB) is the standard treatment for breast cancer patients with clinically negative axilla. However, axillary lymph node dissection (ALND) is still the standard care for sentinel lymph node (SLN) positive patients. Clinical data reveals 20–60 % of patients without non-sentinel lymph node metastasis (NSLNM) after ALND. Unnecessary ALND increases the risk of lymphedema and detracts from quality of life. In this study, we expect to develop a nomogram based on genetic and clinicopathologic features to predict the risk of NSLN metastasis in SLN-positive Chinese women breast cancer patients. Methods: This retrospective study collected data from 310 women breast cancer patients who underwent SLNB followed by ALND and without any neo-adjuvant therapy in Chinese PLA General Hospital, China, between 2016 and 2017. Genetic features contain 96 single nucleotide polymorphisms (SNPs) associated with breast cancer susceptibility and prognosis based on the GWAS studies and clinical information. SNP genotyping was identified by the quantitative PCR detection platform. The genetic features were divided into two clusters by the gene functions and signaling pathways. The polygenic risk score (PRS) was used to evaluate the combined effect of each SNP cluster. Least absolute shrinkage and selection operator (LASSO) regression model was adopted for feature selection and nomogram construction. Internal validation was performed and the area under ROC curve (AUC) was assessed. Results: 81 patients of 310 patients (26%) had a positive axillary NSLNM. The LASSO regression analysis identified the clinicopathologic characteristics including molecular subtype, cN-stage, number of positive SLNs and number of negative SLNs as significant predictors of NSLNM. Furthermore, two SNP clusters were also showed statistically significant in the prediction of NSLNM. In internal validation, the average AUC of the nomogram was 0.795 and the model was well calibrated. Conclusions: We present a new nomogram by combining genetic and clinicopathologic factors to achieve higher sensitivity and specificity comparing with traditional clinicopathologic factors to predict NSLNM in Chinese women breast cancer. It is recommended that more validations are required in prospective studies among different patient populations.

scholarly journals Relative Potencies of Anastrozole and Letrozole to Suppress Estradiol in Breast Cancer Patients Undergoing Ovarian Stimulation before in Vitro Fertilization

2007 ◽  
Vol 92 (6) ◽  
pp. 2197-2200 ◽  
Author(s):  
Amr A. Azim ◽  
Maria Costantini-Ferrando ◽  
K. Lostritto ◽  
Kutluk Oktay
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Ovarian Stimulation ◽  
Area Under The Curve ◽  
Oocyte Retrieval ◽  
Embryo Cryopreservation ◽  
Breast Cancer Patients ◽  
Vitro Fertilization ◽  
The Mean

Abstract Context: Breast cancer patients undergoing controlled ovarian hyperstimulation (COH) for embryo or oocyte cryopreservation should be induced by the method that leads to the least increase in estradiol (E2) levels. Objective: The aim of the study was to determine the potency of anastrozole to suppress serum E2 levels in breast cancer patients undergoing COH. Design and Setting: A prospective sequential cohort study was conducted in an academic center for reproductive medicine between May 2003 and November 2005 for letrozole and between December 2005 and April 2006 for anastrozole. Patients: Breast cancer patients presenting for fertility preservation participated in the study. Intervention: COH using FSH and letrozole (n = 47) or anastrozole (n = 7) was followed by oocyte retrieval and embryo cryopreservation. Main Outcome Measures: Serum E2 levels, area under the curve for E2, and outcomes of COH cycles were measured. Results: There were no significant differences between the two groups regarding length of stimulation, total gonadotropin dose, number of follicles larger than 17 mm, and the lead follicle size on human chorionic gonadotropin (hCG) day and number of embryos cryopreserved. The mean E2 levels on the day of hCG and post-hCG days were higher in the anastrozole group compared to the letrozole group (1325.89 ± 833.17 and 2515.07 ± 1368.52 vs. 427.78 ± 278.24 and 714.38 ± 440.83 pg·d/ml; P ≤ 0.01), respectively, even when anastrozole dose was increased up to 10 mg/d. The mean area under the curve was significantly higher in the anastrozole group compared to the letrozole group (4402.93 ± 1526.7 vs. 1287.48 ± 732.17 pg·d/ml; P &lt;0.004). Conclusions: Breast cancer patients who underwent ovarian stimulation with anastrozole had a significantly higher exposure to E2 than those who were stimulated with letrozole.

Sign in / Sign up

Export Citation Format

Share Document