1. Detection of Breast Cancer Lump and BRCA1/2 Genetic Mutation under Deep Learning.
期刊:Computational intelligence and neuroscience
日期:2022-09-19
DOI :10.1155/2022/9591781
To diagnose and cure breast cancer early, thus reducing the mortality of patients with breast cancer, a method was provided to judge threshold of image segmentation by wavelet transform (WT). It was used to obtain information about the general area of breast lumps by making a rough segmentation of the suspected area of the lump on mammogram. The boundary signal of the lump was obtained by region growth calculation or contour model of local activity. Meanwhile, multiplex polymerase chain reaction (mPCR) and mPCR-next-generation sequencing (mPCR-NGS) were used to detect BRCA1/2 genome. Sanger test was used for newly high virulent mutations to verify the correctness of mutagenic sites. The results were compared with the information marked by experts in the database. According to Daubechies wavelet coefficients, the average measurement accuracy was 92.9% and the average false positive rate of each image was 86%. According to mPCR-NGS, there was no pathogenic mutation in the 7 patients with high-risk BRCA1/2 genetic mutations. Single nucleotide polymorphism (SNP) in nonsynonymous coding region was detected, which was consistent with the Sanger test results. This method effectively isolated the lump area of human mammogram, and mPCR-NGS had high specificity and sensitivity in detecting BRCA1/2 genetic mutation sites. Compared with traditional Sanger test and target sequence capture test, it also had such advantages as easy operation, short duration, and low cost of consumables, which was worthy of further promotion and adoption.
添加收藏
创建看单
引用
4区Q3影响因子: 2
英汉
2. DCE-MRI Radiomic analysis in triple negative ductal invasive breast cancer. Comparison between BRCA and not BRCA mutated patients: Preliminary results.
期刊:Magnetic resonance imaging
日期:2024-07-22
DOI :10.1016/j.mri.2024.110214
OBJECTIVE:The research aimed to determine whether and which radiomic features from breast dynamic contrast enhanced (DCE) MRI could predict the presence of BRCA1 mutation in patients with triple-negative breast cancer (TNBC). MATERIAL AND METHODS:This retrospective study included consecutive patients histologically diagnosed with TNBC who underwent breast DCE-MRI in 2010-2021. Baseline DCE-MRIs were retrospectively reviewed; percentage maps of wash-in and wash-out were computed and breast lesions were manually segmented, drawing a 5 mm-Region of Interest (ROI) inside the tumor and another 5 mm-ROI inside the contralateral healthy gland. Features for each map and each ROI were extracted with Pyradiomics-3D Slicer and considered first separately (tumor and contralateral gland) and then together. In each analysis the more important features for BRCA1 status classification were selected with Maximum Relevance Minimum Redundancy algorithm and used to fit four classifiers. RESULTS:The population included 67 patients and 86 lesions (21 in BRCA1-mutated, 65 in non BRCA-carriers). The best classifiers for BRCA mutation were Support Vector Classifier and Logistic Regression in models fitted with both gland and tumor features, reaching an Area Under ROC Curve (AUC) of 0.80 (SD 0.21) and of 0.79 (SD 0.20), respectively. Three features were higher in BRCA1-mutated compared to non BRCA-mutated: Total Energy and Correlation from gray level cooccurrence matrix, both measured in contralateral gland in wash-out maps, and Root Mean Squared, selected from the wash-out map of the tumor. CONCLUSIONS:This study showed the feasibility of a radiomic study with breast DCE-MRI and the potential of radiomics in predicting BRCA1 mutational status.
添加收藏
创建看单
引用
2区Q1影响因子: 4.7
跳转PDF
登录
英汉
3. Improved characterization of sub-centimeter enhancing breast masses on MRI with radiomics and machine learning in BRCA mutation carriers.
作者:Lo Gullo Roberto , Daimiel Isaac , Rossi Saccarelli Carolina , Bitencourt Almir , Gibbs Peter , Fox Michael J , Thakur Sunitha B , Martinez Danny F , Jochelson Maxine S , Morris Elizabeth A , Pinker Katja
期刊:European radiology
日期:2020-06-27
DOI :10.1007/s00330-020-06991-7
OBJECTIVES:To investigate whether radiomics features extracted from MRI of BRCA-positive patients with sub-centimeter breast masses can be coupled with machine learning to differentiate benign from malignant lesions using model-free parameter maps. METHODS:In this retrospective study, BRCA-positive patients who had an MRI from November 2013 to February 2019 that led to a biopsy (BI-RADS 4) or imaging follow-up (BI-RADS 3) for sub-centimeter lesions were included. Two radiologists assessed all lesions independently and in consensus according to BI-RADS. Radiomics features were calculated using open-source CERR software. Univariate analysis and multivariate modeling were performed to identify significant radiomics features and clinical factors to be included in a machine learning model to differentiate malignant from benign lesions. RESULTS:Ninety-six BRCA mutation carriers (mean age at biopsy = 45.5 ± 13.5 years) were included. Consensus BI-RADS classification assessment achieved a diagnostic accuracy of 53.4%, sensitivity of 75% (30/40), specificity of 42.1% (32/76), PPV of 40.5% (30/74), and NPV of 76.2% (32/42). The machine learning model combining five parameters (age, lesion location, GLCM-based correlation from the pre-contrast phase, first-order coefficient of variation from the 1st post-contrast phase, and SZM-based gray level variance from the 1st post-contrast phase) achieved a diagnostic accuracy of 81.5%, sensitivity of 63.2% (24/38), specificity of 91.4% (64/70), PPV of 80.0% (24/30), and NPV of 82.1% (64/78). CONCLUSIONS:Radiomics analysis coupled with machine learning improves the diagnostic accuracy of MRI in characterizing sub-centimeter breast masses as benign or malignant compared with qualitative morphological assessment with BI-RADS classification alone in BRCA mutation carriers. KEY POINTS:• Radiomics and machine learning can help differentiate benign from malignant breast masses even if the masses are small and morphological features are benign. • Radiomics and machine learning analysis showed improved diagnostic accuracy, specificity, PPV, and NPV compared with qualitative morphological assessment alone.
添加收藏
创建看单
引用
1区Q1影响因子: 20.1
跳转PDF
登录
英汉
4. MRI Surveillance and Breast Cancer Mortality in Women With BRCA1 and BRCA2 Sequence Variations.
期刊:JAMA oncology
日期:2024-04-01
DOI :10.1001/jamaoncol.2023.6944
Importance:Magnetic resonance imaging (MRI) surveillance is offered to women with a pathogenic variant in the BRCA1 or BRCA2 gene who face a high lifetime risk of breast cancer. Surveillance with MRI is effective in downstaging breast cancers, but the association of MRI surveillance with mortality risk has not been well defined. Objective:To compare breast cancer mortality rates in women with a BRCA1 or BRCA2 sequence variation who entered an MRI surveillance program with those who did not. Design, Setting, and Participants:Women with a BRCA1 or BRCA2 sequence variation were identified from 59 participating centers in 11 countries. Participants completed a baseline questionnaire between 1995 and 2015 and a follow-up questionnaire every 2 years to document screening histories, incident cancers, and vital status. Women who had breast cancer, a screening MRI examination, or bilateral mastectomy prior to enrollment were excluded. Participants were followed up from age 30 years (or the date of the baseline questionnaire, whichever was later) until age 75 years, the last follow-up, or death from breast cancer. Data were analyzed from January 1 to July 31, 2023. Exposures:Entrance into an MRI surveillance program. Main Outcomes and Measures:Cox proportional hazards modeling was used to estimate the hazard ratios (HRs) and 95% CIs for breast cancer mortality associated with MRI surveillance compared with no MRI surveillance using a time-dependent analysis. Results:A total of 2488 women (mean [range] age at study entry 41.2 [30-69] years), with a sequence variation in the BRCA1 (n = 2004) or BRCA2 (n = 484) genes were included in the analysis. Of these participants, 1756 (70.6%) had at least 1 screening MRI examination and 732 women (29.4%) did not. After a mean follow-up of 9.2 years, 344 women (13.8%) developed breast cancer and 35 women (1.4%) died of breast cancer. The age-adjusted HRs for breast cancer mortality associated with entering an MRI surveillance program were 0.20 (95% CI, 0.10-0.43; P < .001) for women with BRCA1 sequence variations and 0.87 (95% CI, 0.10-17.25; P = .93) for women with BRCA2 sequence variations. Conclusion and Relevance:Results of this cohort study suggest that among women with a BRCA1 sequence variation, MRI surveillance was associated with a significant reduction in breast cancer mortality compared with no MRI surveillance. Further studies of women with BRCA2 sequence variations are needed to ascertain these women obtain the same benefits associated with MRI surveillance.
添加收藏
创建看单
引用
2区Q1影响因子: 11.5
打开PDF
登录
英汉
5. Radiogenomic association of deep MR imaging features with genomic profiles and clinical characteristics in breast cancer.
期刊:Biomarker research
日期:2023-01-24
DOI :10.1186/s40364-023-00455-y
BACKGROUND:It has been believed that traditional handcrafted radiomic features extracted from magnetic resonance imaging (MRI) of tumors are normally shallow and low-ordered. Recent advancement in deep learning technology shows that the high-order deep radiomic features extracted automatically from tumor images can capture tumor heterogeneity in a more efficient way. We hypothesize that MRI-based deep radiomic phenotypes have significant associations with molecular profiles of breast cancer tumors. We aim to identify deep radiomic features (DRFs) from MRI, evaluate their significance in predicting breast cancer (BC) clinical characteristics and explore their associations with multi-level genomic factors. METHODS:A denoising autoencoder was built to retrospectively extract 4,096 DRFs from 110 BC patients' MRI. Visualization and clustering were applied to these DRFs. Linear Mixed Effect models were used to test their associations with multi-level genomic features (GFs) (risk genes, gene signatures, and biological pathway activities) extracted from the same patients' mRNA expression profile. A Least Absolute Shrinkage and Selection Operator model was used to identify the most predictive DRFs for each clinical characteristic (tumor size (T), lymph node metastasis (N), estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2) status). RESULTS:Thirty-six conventional radiomic features (CRFs) for 87 of the 110 BC patients provided by a previous study were used for comparison. More than 1,000 DRFs were associated with the risk genes, gene signatures, and biological pathways activities (adjusted P-value < 0.05). DRFs produced better performance in predicting T, N, ER, PR, and HER2 status (AUC > 0.9) using DRFs. These DRFs showed significant powers of stratifying patients, linking to relevant biological and clinical characteristics. As a contrast, only eight risk genes were associated with CRFs. The RFs performed worse in predicting clinical characteristics than DRFs. CONCLUSIONS:The deep learning-based auto MRI features perform better in predicting BC clinical characteristics, which are more significantly associated with GFs than traditional semi-auto MRI features. Our radiogenomic approach for identifying MRI-based imaging signatures may pave potential pathways for the discovery of genetic mechanisms regulating specific tumor phenotypes and may enable a more rapid innovation of novel imaging modalities, hence accelerating their translation to personalized medicine.
添加收藏
创建看单
引用
4区Q2影响因子: 1.6
跳转PDF
登录
英汉
6. The clinicopathological and MRI features of patients with BRCA1/2 mutations in familial breast cancer.
作者:You Chao , Xiao Qin , Zhu Xinyi , Sun Yiqun , Di Genhong , Liu Guangyu , Hou Yifeng , Chen Canming , Wu Jiong , Shao Zhimin , Gu Yajia , Hu Zhen
期刊:Gland surgery
日期:2021-01-01
DOI :10.21037/gs-20-596
Background:To determine the histopathological and MRI features of BRCA1/2 mutation-associated familial breast cancers compared with those of BRCA1/2 mutation-negative and sporadic breast cancers and to further compare the imaging features of cancers from BRCA1 and BRCA2 mutation carriers according to lesion type on MRI. Methods:A retrospective review of medical records was conducted to determine tumour clinicopathologic features and MRI characteristics between June 2011 and July 2017, and 93 lesions with BRCA mutations, 93 lesions without BRCA mutations from familial breast cancers and 93 lesions from sporadic breast cancers were included. Histopathologic data, including immunohistochemistry findings and MRI data according to the BI-RADS lexicon, were reviewed. The association between MRI or histopathologic findings and BRCA mutations was analysed. Results:BRCA-positive familial breast cancers had a higher number of IDCs with high nuclear grade and lymph node metastasis (all P<0.05), while the BRCA-negative group had a significantly lower Ki-67 index (P<0.001). BPE on MRI was found to be significantly lower for BRCA mutations of familial breast cancer (P=0.024). BRCA1 carriers tended to exhibit the triple-negative phenotype with a more benign shape and margin (P=0.006 and 0.019), whereas BRCA2 mutations were associated with the luminal phenotype and more malignant features. Conclusions:BRCA mutation carriers had a significantly higher number of IDCs with more aggressive cancer, and BRCA-negative cancers had low proliferation levels. Background features on MRI may help to identify BRCA status, while tumour characteristics can differentiate the BRCA1/2 mutation status, consistent with the differences in their clinicopathologic features.
添加收藏
创建看单
引用
2区Q1影响因子: 5.6
跳转PDF
登录
英汉
7. The added value of mammography in different age-groups of women with and without BRCA mutation screened with breast MRI.
作者:Vreemann Suzan , van Zelst Jan C M , Schlooz-Vries Margrethe , Bult Peter , Hoogerbrugge Nicoline , Karssemeijer Nico , Gubern-Mérida Albert , Mann Ritse M
期刊:Breast cancer research : BCR
日期:2018-08-03
DOI :10.1186/s13058-018-1019-6
BACKGROUND:Breast magnetic resonance imaging (MRI) is the most sensitive imaging method for breast cancer detection and is therefore offered as a screening technique to women at increased risk of developing breast cancer. However, mammography is currently added from the age of 30 without proven benefits. The purpose of this study is to investigate the added cancer detection of mammography when breast MRI is available, focusing on the value in women with and without BRCA mutation, and in the age groups above and below 50 years. METHODS:This retrospective single-center study evaluated 6553 screening rounds in 2026 women at increased risk of breast cancer (1 January 2003 to 1 January 2014). Risk category (BRCA mutation versus others at increased risk of breast cancer), age at examination, recall, biopsy, and histopathological diagnosis were recorded. Cancer yield, false positive recall rate (FPR), and false positive biopsy rate (FPB) were calculated using generalized estimating equations for separate age categories (< 40, 40-50, 50-60, ≥ 60 years). Numbers of screens needed to detect an additional breast cancer with mammography (NSN) were calculated for the subgroups. RESULTS:Of a total of 125 screen-detected breast cancers, 112 were detected by MRI and 66 by mammography: 13 cancers were solely detected by mammography, including 8 cases of ductal carcinoma in situ. In BRCA mutation carriers, 3 of 61 cancers were detected only on mammography, while in other women 10 of 64 cases were detected with mammography alone. While 77% of mammography-detected-only cancers were detected in women ≥ 50 years of age, mammography also added more to the FPR in these women. Below 50 years the number of mammographic examinations needed to find an MRI-occult cancer was 1427. CONCLUSIONS:Mammography is of limited added value in terms of cancer detection when breast MRI is available for women of all ages who are at increased risk. While the benefit appears slightly larger in women over 50 years of age without BRCA mutation, there is also a substantial increase in false positive findings in these women.
添加收藏
创建看单
引用
2区Q1影响因子: 6.1
英汉
8. Association of BRCA Mutation Types, Imaging Features, and Pathologic Findings in Patients With Breast Cancer With BRCA1 and BRCA2 Mutations.
作者:Ha Su Min , Chae Eun Young , Cha Joo Hee , Kim Hak Hee , Shin Hee Jung , Choi Woo Jung
期刊:AJR. American journal of roentgenology
日期:2017-08-10
DOI :10.2214/AJR.16.16957
OBJECTIVE:The purpose of this study is to retrospectively evaluate the relationships between the BRCA mutation types, imaging features, and pathologic findings of breast cancers in BRCA1 and BRCA2 mutation carriers. MATERIALS AND METHODS:We identified patients with breast cancer with BRCA gene mutations from January 2000 to December 2014. After excluding patients who underwent lesion excision before MRI, 99 BRCA1 and 103 BRCA2 lesions in 187 women (mean age, 39.7 and 40.4 years, respectively) were enrolled. Mammographic, sonographic, and MRI scans were reviewed according to the BI-RADS lexicon (5th edition). Pathologic data were reviewed, including the immunohistochemistry findings. The relationships between the BRCA mutations and both imaging and pathologic findings were analyzed. RESULTS:The distribution of molecular subtypes of tumors significantly differed by the mutation type. BRCA1 tumors were associated with the triple-negative subtype, whereas BRCA2 tumors were associated with the luminal B subtype (p = 0.002). At MRI, breast cancers with BRCA1 mutations exhibited a circumscribed margin (p = 0.032) and rim enhancement (p = 0.013). No significant differences in mass shape or kinetic features were observed at MRI. Cancers in BRCA1 mutation carriers tended to develop in the posterior location in the breast (p = 0.034). At mammography, no significant difference in the prevalence of calcifications was observed according to the mutation type. At sonography, BRCA1 lesions were found to be associated with posterior acoustic enhancement (p < 0.0001). CONCLUSION:Breast cancers with BRCA1 mutations tend to exhibit benign morphologic features at MRI, mammography, and sonography, compared with BRCA2 mutations. Lesion location may represent another difference on imaging among various genetic phenotypes.
添加收藏
创建看单
引用
2区Q1影响因子: 4.7
跳转PDF
登录
英汉
9. Correction: Quantitative background parenchymal enhancement and fibro-glandular density at breast MRI: Association with BRCA status.