Correlation between imaging and prognostic factors: molecular classification of breast cancers

Mammographic and ultrasonographic features of triple-negative breast cancer compared with non-triple-negative breast cancer

OBJECTIVE

To evaluate and compare the mammographic and ultrasonographic features of TNBC with non-TNBC.

METHODS

A retrospective review of 193 invasive breast cancer patients (TNBC = 32 and non-TNBC = 161) was collected from January 2014 to June 2019. The imaging features were reviewed according to the 5th edition of the American College of Radiology Breast Imaging Reporting and Data System lexicon. We used the student t-test, Mann-Whitney U test, and Fisher's exact test for statistical analyses.

RESULTS

Mass without calcifications was the most mammographic feature of TNBC (22 of 32, 68.8%) and more commonly found in TNBC than in non-TNBC (p = 0.007). The irregular shape (19 of 28, 67.9%) and indistinct margin (10 of 28, 35.7%) were the most common findings in the TNBC group. However, TNBC lesions appeared as round or oval shape and microlobulated margin more frequently than non-TNBC lesions (p < 0.001). Additionally, the tumor size and histological grade of TNBC were significantly higher than non-TNBC (p < 0.001).

CONCLUSION

TNBC has distinct imaging features compared to non-TNBC. The imaging features on mammography combined with ultrasonography can be used to detect and differentiate this subtype from other breast cancers.

Evaluating the Accuracy of Breast Cancer and Molecular Subtype Diagnosis by Ultrasound Image Deep Learning Model

Background: Breast ultrasound is the first choice for breast tumor diagnosis in China, but the Breast Imaging Reporting and Data System (BI-RADS) categorization routinely used in the clinic often leads to unnecessary biopsy. Radiologists have no ability to predict molecular subtypes with important pathological information that can guide clinical treatment.

Materials and Methods: This retrospective study collected breast ultrasound images from two hospitals and formed training, test and external test sets after strict selection, which included 2,822, 707, and 210 ultrasound images, respectively. An optimized deep learning model (DLM) was constructed with the training set, and the performance was verified in both the test set and the external test set. Diagnostic results were compared with the BI-RADS categorization determined by radiologists. We divided breast cancer into different molecular subtypes according to hormone receptor (HR) and human epidermal growth factor receptor 2 (HER2) expression. The ability to predict molecular subtypes using the DLM was confirmed in the test set.

Results: In the test set, with pathological results as the gold standard, the accuracy, sensitivity and specificity were 85.6, 98.7, and 63.1%, respectively, according to the BI-RADS categorization. The same set achieved an accuracy, sensitivity, and specificity of 89.7, 91.3, and 86.9%, respectively, when using the DLM. For the test set, the area under the curve (AUC) was 0.96. For the external test set, the AUC was 0.90. The diagnostic accuracy was 92.86% with the DLM in BI-RADS 4a patients. Approximately 70.76% of the cases were judged as benign tumors. Unnecessary biopsy was theoretically reduced by 67.86%. However, the false negative rate was 10.4%. A good prediction effect was shown for the molecular subtypes of breast cancer with the DLM. The AUC were 0.864, 0.811, and 0.837 for the triple-negative subtype, HER2 (+) subtype and HR (+) subtype predictions, respectively.

Conclusion: This study showed that the DLM was highly accurate in recognizing breast tumors from ultrasound images. Thus, the DLM can greatly reduce the incidence of unnecessary biopsy, especially for patients with BI-RADS 4a. In addition, the predictive ability of this model for molecular subtypes was satisfactory,which has specific clinical application value.

Integrating biology and access to care in addressing breast cancer disparities: 25 years' research experience in the Carolina Breast Cancer Study

Purpose of Review

To review research on breast cancer mortality disparities, emphasizing research conducted in the Carolina Breast Cancer Study, with a focus on challenges and opportunities for integration of tumor biology and access characteristics across the cancer care continuum.

Recent Findings

Black women experience higher mortality following breast cancer diagnosis, despite lower incidence compared to white women. Biological factors, such as stage at diagnosis and breast cancer subtypes, play a role in these disparities. Simultaneously, social, behavioral, environmental, and access to care factors are important. However, integrated studies of biology and access are challenging and it is uncommon to have both data types available in the same study population. The central emphasis of Phase 3 of the Carolina Breast Cancer Study, initiated in 2008, was to collect rich data on biology (including germline and tumor genomics and pathology) and health care access in a diverse study population, with the long term goal of defining intervention opportunities to reduce disparities across the cancer care continuum.

Summary

Early and ongoing research from CBCS has identified important interactions between biology and access, leading to opportunities to build greater equity. However, sample size, population-specific relationships among variables, and complexities of treatment paths along the care continuum pose important research challenges. Interdisciplinary teams, including experts in novel data integration and causal inference, are needed to address gaps in our understanding of breast cancer disparities.

Molecular profile of breast cancers in Guinean oncological settings

Breast cancer is a complex disease characterized by the accumulation of multiple molecular alterations giving each tumor phenotype and an own evolutionary potential. This study aimed to describe the distribution of the profile and molecular subtypes of breast cancers followed at Surgical Oncology Unit of Donka National Hospital. This was retrospective and descriptive study on cases of breast cancer in which the hormone receptor status and expression of the Her2 oncogene have been performed from 2007 to 2016. We recorded 58 cases including 56 (96.6%) women and 2 (3.4%) men. The average age was 48.2 ± 10.9. Invasive ductal carcinoma accounted for 50 (86.2%) cases. The SBR grade was II in 31(53.4%) cases, III in 21 (36.2%) cases and I in 6 (10.3%) cases. The tumor was classified as T4 in 36 (62.1%) cases; it was metastatic in 11(19.0%) cases. Estrogen receptors were positive in 29 (50.0%) cases, progesterone receptors positive in 25 (43.1%) cases, the Her2 oncogene was positive in 22 (39.3%) cases. The distribution of molecular sub-types was: 20 (34.5%) luminal A, 15 (25.9%) triple negative, 13 (22.4%) Her2 overexpressed, 8 (13.8%) luminal B and 2 (3.2%) undetermined. This preliminary study showed the poor accessibility of immunohistochemistry for the molecular diagnosis of breast cancer in our country. Luminal A subtypes and triple negatives were more common. The determination of molecular subtypes is a rational basis for hormone therapy and targeted therapy, thus personalizing the treatment of breast cancer.

In-cell determination of Lactate Dehydrogenase Activity in a Luminal Breast Cancer Model ⁻ ex vivo Investigation of Excised Xenograft Tumor Slices Using dDNP Hyperpolarized [1-13C]pyruvate

[1-¹³C]pyruvate, the most widely used compound in dissolution-dynamic nuclear polarization (dDNP) magnetic resonance (MR), enables the visualization of lactate dehydrogenase (LDH) activity. This activity had been demonstrated in a wide variety of cancer models, ranging from cultured cells, to xenograft models, to human tumors in situ. Here we quantified the LDH activity in precision cut tumor slices (PCTS) of breast cancer xenografts. The Michigan Cancer Foundation-7 (MCF7) cell-line was chosen as a model for the luminal breast cancer type which is hormone responsive and is highly prevalent. The LDH activity, which was manifested as [1-¹³C]lactate production in the tumor slices, ranged between 3.8 and 6.1 nmole/nmole adenosine tri-phosphate (ATP) in 1 min (average 4.6 ± 1.0) on three different experimental set-ups consisting of arrested vs. continuous perfusion and non-selective and selective RF pulsation schemes and combinations thereof. This rate was converted to an expected LDH activity in a mass ranging between 3.3 and 5.2 µmole/g in 1 min, using the ATP level of these tumors. This indicated the likely utility of this approach in clinical dDNP of the human breast and may be useful as guidance for treatment response assessment in a large number of tumor types and therapies ex vivo.

Energy Dispersive X-ray (EDX) microanalysis: A powerful tool in biomedical research and diagnosis

The Energy Dispersive X-ray (EDX) microanalysis is a technique of elemental analysis associated to electron microscopy based on the generation of characteristic Xrays that reveals the presence of elements present in the specimens. The EDX microanalysis is used in different biomedical fields by many researchers and clinicians. Nevertheless, most of the scientific community is not fully aware of its possible applications. The spectrum of EDX microanalysis contains both semi-qualitative and semi-quantitative information. EDX technique is made useful in the study of drugs, such as in the study of drugs delivery in which the EDX is an important tool to detect nanoparticles (generally, used to improve the therapeutic performance of some chemotherapeutic agents). EDX is also used in the study of environmental pollution and in the characterization of mineral bioaccumulated in the tissues. In conclusion, the EDX can be considered as a useful tool in all works that require element determination, endogenous or exogenous, in the tissue, cell or any other sample.

Computer-Aided Breast Cancer Diagnosis with Optimal Feature Sets: Reduction Rules and Optimization Techniques

This chapter introduces a new method for knowledge extraction from databases for the purpose of finding a discriminative set of features that is also a robust set for within-class classification. Our method is generic and we introduce it here in the field of breast cancer diagnosis from digital mammography data. The mathematical formalism is based on a generalization of the k-Feature Set problem called (α, β)-k-Feature Set problem, introduced by Cotta and Moscato (J Comput Syst Sci 67(4):686-690, 2003). This method proceeds in two steps: first, an optimal (α, β)-k-feature set of minimum cardinality is identified and then, a set of classification rules using these features is obtained. We obtain the (α, β)-k-feature set in two phases; first a series of extremely powerful reduction techniques, which do not lose the optimal solution, are employed; and second, a metaheuristic search to identify the remaining features to be considered or disregarded. Two algorithms were tested with a public domain digital mammography dataset composed of 71 malignant and 75 benign cases. Based on the results provided by the algorithms, we obtain classification rules that employ only a subset of these features.

Correlating mammographic and pathologic findings in clinical decision support using natural language processing and data mining methods

BACKGROUND

A key challenge to mining electronic health records for mammography research is the preponderance of unstructured narrative text, which strikingly limits usable output. The imaging characteristics of breast cancer subtypes have been described previously, but without standardization of parameters for data mining.

METHODS

The authors searched the enterprise-wide data warehouse at the Houston Methodist Hospital, the Methodist Environment for Translational Enhancement and Outcomes Research (METEOR), for patients with Breast Imaging Reporting and Data System (BI-RADS) category 5 mammogram readings performed between January 2006 and May 2015 and an available pathology report. The authors developed natural language processing (NLP) software algorithms to automatically extract mammographic and pathologic findings from free text mammogram and pathology reports. The correlation between mammographic imaging features and breast cancer subtype was analyzed using one-way analysis of variance and the Fisher exact test.

RESULTS

The NLP algorithm was able to obtain key characteristics for 543 patients who met the inclusion criteria. Patients with estrogen receptor-positive tumors were more likely to have spiculated margins (P = .0008), and those with tumors that overexpressed human epidermal growth factor receptor 2 (HER2) were more likely to have heterogeneous and pleomorphic calcifications (P = .0078 and P = .0002, respectively).

CONCLUSIONS

Mammographic imaging characteristics, obtained from an automated text search and the extraction of mammogram reports using NLP techniques, correlated with pathologic breast cancer subtype. The results of the current study validate previously reported trends assessed by manual data collection. Furthermore, NLP provides an automated means with which to scale up data extraction and analysis for clinical decision support. Cancer 2017;114-121. © 2016 American Cancer Society.