-
Scientific Reports Jul 2022A computer-aided diagnosis (CAD) system requires automated stages of tumor detection, segmentation, and classification that are integrated sequentially into one...
A computer-aided diagnosis (CAD) system requires automated stages of tumor detection, segmentation, and classification that are integrated sequentially into one framework to assist the radiologists with a final diagnosis decision. In this paper, we introduce the final step of breast mass classification and diagnosis using a stacked ensemble of residual neural network (ResNet) models (i.e. ResNet50V2, ResNet101V2, and ResNet152V2). The work presents the task of classifying the detected and segmented breast masses into malignant or benign, and diagnosing the Breast Imaging Reporting and Data System (BI-RADS) assessment category with a score from 2 to 6 and the shape as oval, round, lobulated, or irregular. The proposed methodology was evaluated on two publicly available datasets, the Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) and INbreast, and additionally on a private dataset. Comparative experiments were conducted on the individual models and an average ensemble of models with an XGBoost classifier. Qualitative and quantitative results show that the proposed model achieved better performance for (1) Pathology classification with an accuracy of 95.13%, 99.20%, and 95.88%; (2) BI-RADS category classification with an accuracy of 85.38%, 99%, and 96.08% respectively on CBIS-DDSM, INbreast, and the private dataset; and (3) shape classification with 90.02% on the CBIS-DDSM dataset. Our results demonstrate that our proposed integrated framework could benefit from all automated stages to outperform the latest deep learning methodologies.
Topics: Breast; Breast Neoplasms; Disease Progression; Early Detection of Cancer; Female; Humans; Mammography; Neural Networks, Computer
PubMed: 35851592
DOI: 10.1038/s41598-022-15632-6 -
PloS One 2020Exposure to toxic metals such as mercury has been proposed to be a risk factor for the development of breast cancer since some metals can promote genetic mutations and...
OBJECTIVE
Exposure to toxic metals such as mercury has been proposed to be a risk factor for the development of breast cancer since some metals can promote genetic mutations and epigenetic changes. We sought to find what toxic metals are present in normal breast tissue and in the tumours of women who had mastectomies for invasive ductal breast carcinoma.
MATERIALS AND METHODS
Formalin-fixed paraffin-embedded blocks from mastectomies for breast carcinoma were examined from 50 women aged 34-69 years. Paraffin blocks selected for elemental analysis were from breast tissue not involved by carcinoma and from the carcinoma itself. Seven micrometer-thick sections were stained with autometallography to demonstrate the presence of mercury, and subjected to laser ablation-inductively coupled plasma-mass spectrometry (LA-ICP-MS) to confirm the presence of mercury and to detect other toxic metals.
RESULTS
Autometallography-detected mercury was seen in intraductal secretions and some luminal epithelial cells of normal breast lobules in 26 (55%) of the 47 samples where lobules were present, and in 10 (23%) of carcinomas from the 44 samples where carcinoma was present. In eight samples ductal carcinoma in situ was present and one of these contained mercury. LA-ICP-MS confirmed the presence of mercury in samples that stained with autometallography, and detected lead, iron, nickel, aluminium, chromium and cadmium in some samples.
CONCLUSIONS
Mercury was present in normal breast lobules in more than half of mastectomy samples that contained an invasive carcinoma, and in a smaller proportion of carcinomas and ductal carcinomas in situ. Other toxic metals that may interact synergistically with mercury could be detected in some samples. These findings do not provide direct evidence that toxic metals such as mercury play a role in the pathogenesis of breast cancer, but suggest that future molecular biological investigations on the role of toxic metals in breast cancer are warranted.
Topics: Adult; Aged; Breast; Carcinoma, Ductal, Breast; Environmental Pollutants; Female; Humans; Mercury; Middle Aged; Molecular Imaging
PubMed: 32004334
DOI: 10.1371/journal.pone.0228226 -
Journal of Mammary Gland Biology and... Jun 2020Obesity is a preventable risk factor for breast cancer following menopause. Regardless of menopausal status, obese women who develop breast cancer have a worsened... (Review)
Review
Obesity is a preventable risk factor for breast cancer following menopause. Regardless of menopausal status, obese women who develop breast cancer have a worsened prognosis. Breast tissue is comprised of mammary epithelial cells organized into ducts and lobules and surrounded by adipose-rich connective tissue. Studies utilizing multiple in vivo models of obesity as well as human breast tissue have contributed to our understanding of how obesity alters mammary tissue. Localized changes in mammary epithelial cell populations, elevated secretion of adipokines and angiogenic mediators, inflammation within mammary adipose tissue, and remodeling of the extracellular matrix may result in an environment conducive to breast cancer growth. Despite these significant alterations caused by obesity within breast tissue, studies have suggested that some, but not all, obesity-induced changes may be mitigated with weight loss. Here, we review our current understanding regarding the impact of obesity on the breast microenvironment, how obesity-induced changes may contribute to breast tumor progression, and the impact of weight loss on the breast microenvironment.
Topics: Breast Neoplasms; Female; Humans; Mammary Glands, Human; Obesity; Risk Factors; Tumor Microenvironment
PubMed: 32519090
DOI: 10.1007/s10911-020-09452-5 -
Cancer Apr 2009Lobules in normal breast tissue can be classified based on their degree of development, which may affect their susceptibility to carcinogenesis. However, few...
BACKGROUND
Lobules in normal breast tissue can be classified based on their degree of development, which may affect their susceptibility to carcinogenesis. However, few epidemiologic studies to date have addressed this.
METHODS
The authors examined the association between lobule type and subsequent breast cancer risk in a nested case-control study of benign breast disease (BBD) and breast cancer within the Nurses' Health Studies (200 cases, 915 controls). Benign breast biopsy slides were reviewed by pathologists, and normal terminal duct lobular units were classified as having no type 1 lobules, mixed lobule types, or predominant type 1 and no type 3 lobules. Logistic regression was used to compute odds ratios (ORs) and 95% confidence intervals (CIs) for the association between lobule type and breast cancer risk.
RESULTS
Women with predominant type 1 and no type 3 lobules (54 cases, 321 controls) had a decreased risk of breast cancer compared with those with no type 1 lobules or mixed lobule types (OR=0.63; 95% CI, 0.44-0.91), although this was attenuated after adjustment for histologic category of BBD (OR=0.71; 95% CI, 0.49-1.02). Having predominant type 1 lobules and no type 3 lobules was associated with a similar risk reduction for all categories of BBD (nonproliferative: OR=0.73 [95% CI, 0.36-1.50]; proliferative without atypia: OR=0.80 [95% CI, 0.47-1.35]; and atypical hyperplasia: OR=0.61 [95% CI, 0.28-1.35]).
CONCLUSIONS
These results provided preliminary evidence that lobule type may be an important marker of breast cancer risk in women with BBD.
Topics: Adolescent; Adult; Aged; Biopsy; Breast; Breast Diseases; Breast Neoplasms; Case-Control Studies; Female; Humans; Middle Aged; Precancerous Conditions; Risk
PubMed: 19170235
DOI: 10.1002/cncr.24167 -
Medicina (Kaunas, Lithuania) Dec 2021Phyllodes Tumor (PT) is a rare fibroepithelial breast tumor that can behave differently depending on its biologic features. Traditionally, PTs are classified by their... (Review)
Review
Phyllodes Tumor (PT) is a rare fibroepithelial breast tumor that can behave differently depending on its biologic features. Traditionally, PTs are classified by their histologic features into benign, borderline, and malignant. In most cases that were reported, all PTs may recur, but only the borderline and malignant PT can metastasize. PT usually occurs as a breast lump or accidental finding on ultrasound (US) examination. The clinical features include a well-defined breast mass, regular or lobulated. The diagnosis is based on the integration of morphology features, but remains challenging, particularly in the distinction from fibroadenomas. We report a case of a 36-year-old patient who presented for a voluminous breast mass, rapidly growing in the past 3-4 months. At presentation, the patient was 19 weeks pregnant. The breast tumor had the clinical and US aspect of PT. A core needle biopsy was obtained, confirming a benign PT, and local excision was performed with no postoperative complications. The final pathology report showed a borderline PT with close resection margins of 1 mm. Immunohistochemistry (IHC) established the diagnosis of malignant PT with heterologous sarcomatous differentiation. The case was discussed in the multidisciplinary tumor board (MDT) and mastectomy was recommended. The patient fully consented but refused surgery at 25 weeks' gestation, fearing premature delivery. The right breast was closely monitored by US, and at 9 weeks after the first surgery, signs of local recurrence were detected. At 35 weeks' gestation, right mastectomy was performed, with no perioperative complications. The pregnancy was closely followed up and no complication were found. The final pathology report describes multiples PT recurrences with heterologous sarcomatous differentiation. The pregnancy outcome was uneventful, and the patient delivered a healthy child vaginally at term with no peripartum complication. Postpartum, a computer tomography (CT) examination of the head, thorax, abdomen and pelvis was performed, with no evidence of metastases. Adjuvant chemotherapy and radiotherapy completed the treatment. The follow-up and CT scan showed no metastases or further recurrence 4 years after diagnosis. In conclusion, diagnosis of PT can be difficult, especially because of the easy confusion with fibroadenoma of the breast. There are rare cases when a pathology exam needs further assessment and IHC is recommended for accurate diagnosis. Although malignant PT is rare and accounts for <1% of all breast cancers, the diagnosis and treatment that are recommended are based on the reported cases. Moreover, when complete surgical excision is achieved, the rates of recurrence and distant metastases are low, and adjuvant therapy might not be necessary.
Topics: Adult; Breast Neoplasms; Female; Humans; Margins of Excision; Mastectomy; Phyllodes Tumor; Pregnancy; Prognosis
PubMed: 35056344
DOI: 10.3390/medicina58010036 -
Quantitative Imaging in Medicine and... May 2021It is challenging to differentiate between phyllodes tumors (PTs) and fibroadenomas (FAs). Artificial intelligence (AI) can provide quantitative information regarding...
BACKGROUND
It is challenging to differentiate between phyllodes tumors (PTs) and fibroadenomas (FAs). Artificial intelligence (AI) can provide quantitative information regarding the morphology and textural features of lesions. This study attempted to use AI to evaluate the ultrasonic images of PTs and FAs and to explore the diagnostic performance of AI features in the differential diagnosis of PTs and FAs.
METHODS
A total of 40 PTs and 290 FAs <5 cm in maximum diameter found in female patients were retrospectively analyzed. All tumors were segmented by doctors, and the features of the lesions were collated, including circularity, height-to-width ratio, margin spicules, margin coarseness (MC), margin indistinctness, margin lobulation (ML), internal calcification, angle between the long axis of the lesion and skin, energy, grey entropy, and grey mean. The differences between PTs and FAs were analyzed, and the diagnostic performance of AI features in the differential diagnosis of PTs and FAs was evaluated.
RESULTS
Statistically significant differences (P<0.05) were found in the height-to-width ratio, ML, energy, and grey entropy between the PTs and FAs. Receiver operating characteristic (ROC) curve analysis of single features showed that the area under the curve [(AUC) 0.759] of grey entropy was the largest among the four features with statistically significant differences, and the sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 0.925, 0.459, 0.978, and 0.190, respectively. When considering the combinations of the features, the combination of height-to-width ratio, margin indistinctness, ML, energy, grey entropy, and internal calcification was the most optimal of the combinations of features with an AUC of 0.868, and a sensitivity, specificity, PPV, and NPV of 0.734, 0.900, 0.982, and 0.316, respectively.
CONCLUSIONS
Quantitative analysis of AI can identify subtle differences in the morphology and textural features between small PTs and FAs. Comprehensive consideration of multiple features is important for the differential diagnosis of PTs and FAs.
PubMed: 33936986
DOI: 10.21037/qims-20-919 -
Cancers Jul 2021Invasive lobular breast cancer (ILC) is the most common special histological type of breast cancer (BC). This review recapitulates developments in the histomorphologic... (Review)
Review
Invasive lobular breast cancer (ILC) is the most common special histological type of breast cancer (BC). This review recapitulates developments in the histomorphologic assessment of ILC from its beginnings with the seminal work of Foote and Stewart, which was published in 1941, until today. We discuss different concepts of ILC and their implications. These concepts include (i) BC arising from mammary lobules, (ii) BC growing in dissociated cells and single files, and (iii) BC defined as a morpho-molecular spectrum of tumors with distinct histological and molecular characteristics related to impaired cell adhesion. This review also provides a comprehensive overview of ILC variants, their histomorphology, and differential diagnosis. Furthermore, this review highlights recent advances which have contributed to a better understanding of the histomorphology of ILC, such as the role of the basal lamina component laminin, the molecular specificities of triple-negative ILC, and E-cadherin to P-cadherin expression switching as the molecular determinant of tubular elements in -deficient ILC. Last but not least, we provide a detailed account of the tumor microenvironment in ILC, including tumor infiltrating lymphocyte (TIL) levels, which are comparatively low in ILC compared to other BCs, but correlate with clinical outcome. The distinct histomorphology of ILC clearly reflects a special tumor biology. In the clinic, special treatment strategies have been established for triple-negative, HER2-positive, and ER-positive BC. Treatment specialization for patients diagnosed with ILC is just in its beginnings. Accordingly, ILC deserves greater attention as a special tumor entity in BC diagnostics, patient care, and cancer research.
PubMed: 34359596
DOI: 10.3390/cancers13153695 -
Breast Cancer Research : BCR Jul 2020Breast cancer cells invading the connective tissues outside the mammary lobule or duct immerse in a reservoir of extracellular matrix (ECM) that is structurally and...
BACKGROUND
Breast cancer cells invading the connective tissues outside the mammary lobule or duct immerse in a reservoir of extracellular matrix (ECM) that is structurally and biochemically distinct from that of their site of origin. The ECM is a spatial network of matrix proteins, which not only provide physical support but also serve as bioactive ligands to the cells. It becomes evident that the dimensional, mechanical, structural, and biochemical properties of ECM are all essential mediators of many cellular functions. To better understand breast cancer development and cancer cell biology in native tissue environment, various tissue-mimicking culture models such as hydrogel have been developed. Collagen I (Col I) and Matrigel are the most common hydrogels used in cancer research and have opened opportunities for addressing biological questions beyond the two-dimensional (2D) cell cultures. Yet, it remains unclear whether these broadly used hydrogels can recapitulate the environmental properties of tissue ECM, and whether breast cancer cells grown on CoI I or Matrigel display similar phenotypes as they would on their native ECM.
METHODS
We investigated mammary epithelial cell phenotypes and metabolic profiles on animal breast ECM-derived tissue matrix gel (TMG), Col I, and Matrigel. Atomic force microscopy (AFM), fluorescence microscopy, acini formation assay, differentiation experiments, spatial migration/invasion assays, proliferation assay, and nuclear magnetic resonance (NMR) spectroscopy were used to examine biological phenotypes and metabolic changes. Student's t test was applied for statistical analyses.
RESULTS
Our data showed that under a similar physiological stiffness, the three types of hydrogels exhibited distinct microstructures. Breast cancer cells grown on TMG displayed quite different morphologies, surface receptor expression, differentiation status, migration and invasion, and metabolic profiles compared to those cultured on Col I and Matrigel. Depleting lactate produced by glycolytic metabolism of cancer cells abolished the cell proliferation promoted by the non-tissue-specific hydrogel.
CONCLUSION
The full ECM protein-based hydrogel system may serve as a biologically relevant model system to study tissue- and disease-specific pathological questions. This work provides insights into tissue matrix regulation of cancer cell biomarker expression and identification of novel therapeutic targets for the treatment of human cancers based on tissue-specific disease modeling.
Topics: Animals; Breast Neoplasms; Cell Differentiation; Cell Line, Tumor; Cell Movement; Cell Proliferation; Collagen; Collagen Type I; Drug Combinations; Extracellular Matrix; Extracellular Matrix Proteins; Female; Humans; Hydrogels; Laminin; Microscopy, Atomic Force; Phenotype; Proteoglycans; Swine
PubMed: 32736579
DOI: 10.1186/s13058-020-01321-7 -
FASEB Journal : Official Publication of... Jun 2020Obesity is a risk factor for breast cancer in postmenopausal and high-risk premenopausal women. Changes within the obese breast microenvironment may increase breast...
Obesity is a risk factor for breast cancer in postmenopausal and high-risk premenopausal women. Changes within the obese breast microenvironment may increase breast cancer risk. Transforming growth factor beta-1 (TGFβ1) is a major regulator of mammary epithelial stem/progenitor cells, and its activity is dysregulated under conditions of obesity. Using a high-fat diet model of obesity in mice and breast tissue from women, we observed that TGFβ1 activity is reduced in breast epithelial cells in obesity. Breast ducts and lobules demonstrated increased decorin in the extracellular matrix (ECM) surrounding epithelial cells, and we observed that decorin and latent TGFβ1 complexed together. Under conditions of obesity, macrophages expressed higher levels of decorin and were significantly increased in number surrounding breast epithelial cells. To investigate the relationship between macrophages and decorin expression, we treated obese mice with either IgG control or anti-F4/80 antibodies to deplete macrophages. Mice treated with anti-F4/80 antibodies demonstrated reduced decorin surrounding mammary ducts and enhanced TGFβ1 activity within mammary epithelial cells. Given the role of TGFβ1 as a tumor suppressor, reduced epithelial TGFβ1 activity and enhanced TGFβ1 within the ECM of obese mammary tissue may enhance breast cancer risk.
Topics: Adolescent; Adult; Animals; Breast; Breast Neoplasms; Cells, Cultured; Diet, High-Fat; Epithelial Cells; Extracellular Matrix; Female; Humans; Macrophages; Mammary Glands, Animal; Mammary Glands, Human; Mice; Mice, Inbred C57BL; Mice, Obese; Middle Aged; Obesity; Stem Cells; Transforming Growth Factor beta1; Tumor Microenvironment; Young Adult
PubMed: 32359100
DOI: 10.1096/fj.202000228RR -
BMC Medical Imaging Oct 2021Screening of breast cancer in asymptomatic women is important to evaluate for early diagnosis. In China ultrasound is a more frequently used method than mammography for...
BACKGROUND
Screening of breast cancer in asymptomatic women is important to evaluate for early diagnosis. In China ultrasound is a more frequently used method than mammography for the detection of breast cancer. The objectives of the study were to provide evidence and assessment of parenchymal patterns of ultrasonography for breast cancer detection among Chinese women.
METHODS
Breast ultrasound examinations including the parenchymatous pattern of cytopathological confirmed breast cancer (n = 541) and age-matched cytopathological not confirmed breast cancer (n = 849) women were retrospectively reviewed by seven sonographer physicians. According to compositions of ducts, the thickness of the breast, diameter of ducts, fat lobules, and fibro glandular tissues, the breast parenchymatous pattern was categorized into heterogeneous (high percentage of fatty tissues), ductal (the inner diameters of ducts > 50% of the thick mass of the breast), mixed (the inner diameters of ducts was 50% of the thick mass of the breast), and fibrous categories (a dense classification of the breast).
RESULTS
Heterogeneous (p < 0.0001, OR = 3.972) and fibrous categories (p < 0.0001, OR = 2.702) were higher among women who have cytopathological confirmed breast cancer than those who have not cytopathological confirmed breast cancer. The heterogeneous category was high-risk ultrasonographic examination category followed by the fibrous category. Agreements between sonographer physicians for categories of ultrasonic examinations were fair to good (Cohen's k = 0.591).
CONCLUSIONS
Breast cancer risk in Chinese asymptomatic women differ according to the ultrasonographic breast parenchymal pattern.
LEVEL OF EVIDENCE
III. Technical efficacy stage: 2.
Topics: Adult; Aged; Breast Neoplasms; China; Cross-Sectional Studies; Early Detection of Cancer; Female; Humans; Middle Aged; Retrospective Studies; Ultrasonography, Mammary
PubMed: 34666701
DOI: 10.1186/s12880-021-00687-0