Prognostic Score for De Novo Metastatic Breast Cancer With Liver Metastasis and Its Predictive Value of Locoregional Treatment Benefit

BackgroundThere is a significant survival difference and lack of effective treatment among breast cancer patients with liver metastasis. This present study aimed to construct a novel prognostic score for predicting the prognosis and locoregional treatment benefit of de novo metastatic breast cancer with liver metastasis (BCLM).MethodsIn total, 2,398 eligible patients between 2010 and 2016 were selected from the Surveillance, Epidemiology, and End Results (SEER) database. They were assigned to the training set including 1,662 patients (2010–2014) and validation set comprising 736 patients (2015–2016) depending on the time of diagnosis. The prognostic score was based on regression coefficients in the multivariate Cox regression analysis. And then, patients were stratified into low-, intermediate-, and high-risk groups by the prognostic score. The discrimination and calibration of prognostic score were evaluated using time-dependent receiver operating characteristic (ROC) curves analysis and calibration curves, respectively. Subgroup analysis was performed to evaluate locoregional surgery and chemotherapy benefit in different risk groups.ResultsAge, race, insurance and marital status, T stage, pathological grade, molecular subtypes, and extrahepatic metastasis were identified as independent prognostic variables in the prognostic score. The prognostic score showed high discrimination power with an area under the curve (AUC) of 0.77 and 0.72 and excellent agreement suggested by calibration plots in the training and validation sets, respectively. Intermediate-risk [hazard ratio (HR) 2.39, 95% confidence interval (CI) 2.09–2.73, P<0.001] and high-risk groups (HR 4.88; 95% CI 4.13–5.76; P<0.001) had significantly worse prognosis in comparison with the low-risk group. The median overall survival (OS) in three prognostic groups were 44, 18, and 7 months, with a 3-year survival rate of 56, 23, and 7%, respectively. Apart from the high-risk group (HR 0.79; 95% CI 0.56–1.10; P=0.157), the low-risk (HR 0.64; 95% CI 0.49–0.84; P=0.001) and intermediate-risk groups (HR 0.68; 95% CI 0.55–0.85; P=0.001) could benefit from the surgery of primary site, while chemotherapy improved prognosis in all risk groups.ConclusionsA prognostic score was developed to accurately predict the prognosis of de novo BCLM patients. Moreover, it may be useful for further subdividing them into different risk groups and helping guide clinicians in treatment decisions.

Download Full-text

Patterns of treatment and outcome with 500-mg fulvestrant in postmenopausal women with hormone receptor-positive/HER2-negative metastatic breast cancer: a real-life multicenter Italian experience

Therapeutic Advances in Medical Oncology ◽

10.1177/1758835919833864 ◽

2019 ◽

Vol 11 ◽

pp. 175883591983386 ◽

Cited By ~ 1

Author(s):

Raffaella Palumbo ◽

Federico Sottotetti ◽

Erica Quaquarini ◽

Anna Gambaro ◽

Antonella Ferzi ◽

...

Keyword(s):

Breast Cancer ◽

Metastatic Breast Cancer ◽

Liver Metastasis ◽

Hormone Receptor ◽

De Novo ◽

Large Population ◽

Single Agent ◽

Real Life ◽

Metastatic Breast ◽

Hormone Receptor Positive

Background: Fulvestrant 500 mg (F500) is the most active endocrine single agent in hormone receptor-positive (HR+)/HER2-negative metastatic breast cancer (MBC). Few data are available regarding the effectiveness of the drug in a real-world setting. Patients and methods: This prospective, multicenter cohort study aimed to describe the patterns of treatment and performance of F500 in a large population of unselected women with MBC, focusing on potential prognostic or predictive factors for disease outcome and response. The primary endpoints were progression-free survival (PFS) and clinical benefit rate. Results: From January 2011 to December 2015, 490 consecutive patients treated with F500 were enrolled. Overall, three different cohorts were identified and analyzed: the first received F500 after progression from previous chemotherapy (CT) or endocrine therapy; the second received the drug for de novo metastatic disease; and the third was treated as maintenance following disease stabilization or a response from a previous CT line. Median overall survival (OS) in the whole population was 26.8 months, ranging from 32.4 in first line to 22.0 and 13.7 months in second line and subsequent lines, respectively. Both the presence of liver metastasis and the treatment line were significantly associated with a worse PFS, while only the presence of liver metastasis maintained its predictive role for OS in multivariate analysis. Conclusions: The effectiveness of F500 was detected in patients treated both upon disease progression and as maintenance. The relevant endocrine sensitivity of 80% of patients included in the study could probably explain the good results observed in terms of outcome.

Download Full-text

Reduced Intensity Conditioning with Thiotepa and Fludarabine for Allogeneic Transplantation: Evidence for Low Toxicity and Long-Lasting Disease Control in MDS with Low/Intermediate-1 IPSS Score and in AML from MDS in Complete Remission.

Blood ◽

10.1182/blood.v112.11.3285.3285 ◽

2008 ◽

Vol 112 (11) ◽

pp. 3285-3285

Author(s):

Emilio Paolo Alessandrino ◽

Luca Malcovati ◽

Giorgio La Nasa ◽

Paolo de Fabritiis ◽

Massimo Bernardi ◽

...

Keyword(s):

High Risk ◽

Complete Remission ◽

Cox Regression ◽

Risk Group ◽

Prognostic Score ◽

Conditioning Regimen ◽

Disease Status ◽

Risk Groups ◽

High Risk Group ◽

Valvular Stenosis

Abstract This study investigated Thiotepa (TT) and Fludarabine (Fluda) as a preparative regimen for allogeneic peripheral stem cell transplantation in patients with myelodysplastic syndrome (MDS) or acute leukemia from MDS (MDS-AML) older than 50 or with comorbidities contraindicating standard conditioning. Patients were prepared with TT, given over 3 hours as an i.v. infusion at a dose of 10 mg/kg over two days (day -8 and day -7) and Fluda at the dose of 125 mg/m2 i.v. over five days ( from day -7 to day -3). Fresh or cryopreserved allogeneic peripheral stem cells were infused on day 0 or +1. Graft-versus-Host Disease (GvHD) prophylaxis consisted of cyclosporine A (CyA) at the dose of 1.5 mg/kg day as a continuous iv infusion from day -5 until engraftment. The CyA was then administered orally at the dose of 3 mg/kg twice a day. Doses were adjusted to maintain plasma level concentrations between 150–350 mg/dL. From day +60, in the absence of acute GvHD, the CyA was tapered down by 20% every 2 weeks until withdrawal. In addition, patients received methotrexate 10 mg/m2 on day +1, and 8 mg/m2 on days + 3, +6 and +11 after transplantation. At the time of transplantation, patients were classified in two risk groups (low vs high risk) according to IPSS score (low/intermediate-1 vs. intermediate-2/high) for MDS patients, and disease status (CR vs. not CR) for MDS-AML. Kaplan-Meier survival analysis was carried out to compare Overall Survival (OS), Transplant-Related Mortality (TRM) and probability of relapse. Fifty patients (29 males, 21 females) entered the study; the median age was 54 years (range 38–71). Sixteen MDS patients had a low/intermediate 1 score according to the International Prognostic Score System (IPSS), 16 had an intermediate 2/high IPSS score, 18 had MDS-AML. Thirty patients underwent transplantation as front-line therapy, 20 received one or more cycles of chemotherapy before transplant. Among the latter, nine with MDS-AML were in complete remission at the time of their transplant, while four were in a partial remission. The interval from diagnosis to transplantation ranged from 1 to 52 months (median value 11 months). Contraindications to a standard conditioning regimen were liver disease, hypertrophic cardiomyopathy secondary to hypertension or valvular stenosis, cardiac arrhythmia, diabetes mellitus, hypothyroidism, previous CNS bleeding, and a history of sepsis. All but one patient achieved engraftment, with full donor chimerism by day +30. Patients were followed up for a median time of 21 months (range 0.2–87). TRM at 1 and 2 years after transplantation was 25% and 33%; the 5-year probability of relapse was 27%. Twenty-six patients are alive in complete remission, and the 5-year OS is 50%. The 5-year OS was 73% and 28% in low- and high-risk patients respectively (p=0.002). TRM at 1 and 2 years after transplantation was 13% and 21% in the low-risk group and 39% and 45% in the high-risk group (p=0.046); the 5-year probability of relapse was 10% and 50% in the low- and high-risk group respectively (p=0.015). In a multivariate Cox regression, risk group retained a borderline significance (HR=2.6, p=0.07) when adjusted by age at transplantation (p=0.03) and interval from diagnosis to transplant (n.s.). The combination of Thiotepa and Fludarabine is an effective and well-tolerated conditioning regimen in patients with MDS or MDS-AML who are poor candidates for standard myeloablative transplantation, particularly in MDS patients with low/intermediate-1 IPSS score and MDS-AML patients in CR.

Download Full-text

Locoregional treatment in de novo metastatic breast cancer: a retrospective cohort study

10.21203/rs.3.rs-70080/v1 ◽

2020 ◽

Author(s):

Sun Jianna ◽

Kong Lingjun ◽

Feng Nana ◽

Liu Hong ◽

Ren Chongxi

Keyword(s):

Breast Cancer ◽

Cohort Study ◽

Metastatic Breast Cancer ◽

Survival Benefit ◽

De Novo ◽

Metastatic Breast ◽

Local Therapy ◽

Surgical Margins ◽

Rank Test ◽

Locoregional Treatment

Abstract Background: In an earlier analysis of this cohort study, local therapy based on surgical resection of the primary tumor might confer a survival benefit in women with de novo metastatic breast cancer (dnMBC). Here we report the survival outcomes of locoregional treatment (LRT), focusing on the association of surgical timings and surgical margins with survival in these patients. Methods: The retrospective study included patients with dnMBC in two Chinese tertiary hospitals, between March 1, 2007, and December 31, 2017. Overall survival (OS) was evaluated by means of a stratified log-rank test and summarized with the use of Kaplan–Meier methods. Results: A total of 153 patients were included, of whom 87 underwent LRT and 66 systemic therapy alone (STA). LRT showed a significant OS benefit over STA (HR, 0.47; 95% CI, 0.33 to 0.69; p<.0001). Median OS of LRT group and STA group were 42 months (95% CI, 35.0 to 48.9 months) and 21 months (95% CI, 16.1 to 25.9 months), respectively. The benefit was consistent across most subgroups. The OS of patients undergoing surgery was better than that of patients without surgery (HR, 0.48; 95% CI, 0.33 to 0.70; p=.0001), and there was difference in survival improvement at different surgical timings (surgery before chemotherapy, during chemotherapy and after chemotherapy) (HR, 0.79; 95% CI, 0.65 to 0.95; p=.013). The survival benefit of surgery after chemotherapy was the most, followed by surgery during chemotherapy (Median 56 months, 95% CI, 40.8 to 71.2 months). Moreover, compared with patients with positive margins, the OS of patients with negative margins was significantly improved (HR, 2.35; 95% CI, 1.65 to 3.35; p<.0001), with a median OS of 56 months (95% CI, 45.9 to 66.1 months). Conclusions: Our results suggest that LRT is associated with improved OS in women with dnMBC, and patients who had surgery after or during systemic chemotherapy with negative surgical margins, are expected to benefit more.

Download Full-text

Hypoxia-Related Long Non-Coding RNA Signature Predicts the Prognosis of Breast Cancer

10.21203/rs.3.rs-1084000/v1 ◽

2021 ◽

Author(s):

Jinlong Huo ◽

Shuang Shen ◽

Chen Chen ◽

Rui Qu ◽

Youming Guo ◽

...

Keyword(s):

Breast Cancer ◽

T Cell ◽

High Risk ◽

Risk Group ◽

Risk Groups ◽

High Risk Group ◽

Cytolytic Activity ◽

Low Risk ◽

Gene Set Enrichment Analysis ◽

The Cancer Genome Atlas

Abstract Background: Breast cancer(BC) is the most common tumour in women. Hypoxia stimulates metastasis in cancer and is linked to poor patient prognosis.Methods: We screened prognostic-related lncRNAs(Long Non-Coding RNAs) from the Cancer Genome Atlas (TCGA) data and constructed a prognostic signature based on hypoxia-related lncRNAs in BC.Results: We identified 21 differentially expressed lncRNAs associated with BC prognosis. Kaplan Meier survival analysis indicated a significantly worse prognosis for the high-risk group(P<0.001). Moreover, the ROC-curve (AUC) of the lncRNAs signature was 0.700, a performance superior to other traditional clinicopathological characteristics. Gene set enrichment analysis (GSEA) showed many immune and cancer-related pathways and in the low-risk group patients. Moreover, TCGA revealed that functions including activated protein C (APC)co-inhibition, Cinnamoyl CoA reductase(CCR),check-point pathways, cytolytic activity, human leukocyte antigen (HLA), inflammation-promotion, major histocompatibility complex(MHC) class1, para-inflammation, T cell co-inhibition, T cell co-stimulation, and Type Ⅰ and Ⅱ Interferons (IFN) responses were significantly different in the low-risk and high-risk groups. Immune checkpoint molecules such as ICOS, IDO1, TIGIT, CD200R1, CD28, PDCD1(PD-1), were also expressed differently between the two risk groups. The expression of m6A-related mRNA indicated that YTHDC1, RBM15, METTL3, and FTO were significantly between the high and low-risk groups.Additionally, immunotherapy in patients with BC from the low-risk group yielded a higher frequency of clinical responses to anti-PD-1/PD-L1 therapy or a combination of anti-PD-1/PD-L1and anti-CTLA4 therapies.Except for lapatinib, the results also show that a high-risk score is related to a higher half-maximal inhibitory concentration (IC50) of chemotherapy drugs.Conclusion: A novel hypoxia-related lncRNAs signature may serve as a prognostic model for BC.

Download Full-text

An Autophagy-related Long Non-coding RNA Signature for Breast Cancer

Combinatorial Chemistry & High Throughput Screening ◽

10.2174/1386207324666210603122718 ◽

2021 ◽

Vol 24 ◽

Author(s):

Feng Jiang ◽

Chuyan Wu ◽

Ming Wang ◽

Ke Wei ◽

Jimei Wang

Keyword(s):

Breast Cancer ◽

High Risk ◽

Cox Regression ◽

Risk Group ◽

Expression Profiles ◽

Risk Groups ◽

Low Risk ◽

Optimal Cutoff ◽

Non Coding Rna ◽

Long Non Coding Rna

Background: The most prevalent malignant tumor in women is breast cancer (BC). Autophagic therapies have been identified for their contribution in BC cell death. Therefore, the potential prognostic role of long non-coding RNA (lncRNA) related to autophagy in patients with BC was examined. Methods: The lncRNAs expression profiles were derived from The Cancer Genome Atlas (TCGA) database. Throughout univariate Cox regression and multivariate Cox regression test, lncRNA with BC prognosis have been differentially presented. We then defined the optimal cutoff point between high and low-risk groups. The receiver operating characteristic (ROC) curves were drawn to test this signature. In order to examine possible signaling mechanisms linked to these lncRNAs, the Gene Set Enrichment Analysis (GSEA) has been carried out. Results: Based on the lncRNA expression profiles for BC, a 9 lncRNA signature associated with autophagy was developed. The optimal cutoff value for high-risk and low-risk groups was used. The high-risk group had less survival time than the low-risk group. The result of this lncRNA signature was highly sensitive and precise. GSEA study found that the gene sets have been greatly enriched in many cancer pathways. Conclusions: Our signature of 9 lncRNAs related to autophagy has prognostic value for BC, and these lncRNAs related to autophagy may play an important role in BC biology.

Download Full-text

Identification of an Exosome-Related Signature Associated with Prognosis and Immune Infiltration in Breast Cancer

10.21203/rs.3.rs-1199471/v1 ◽

2022 ◽

Author(s):

Qiaonan Guo ◽

Pengjun Qiu ◽

Kelun Pan ◽

Jianpeng Chen ◽

Jianqing Lin

Keyword(s):

Breast Cancer ◽

T Cells ◽

High Risk ◽

Immune Cell ◽

Risk Group ◽

Risk Groups ◽

Low Risk ◽

Immune Cell Infiltration ◽

Immune Microenvironment ◽

Expression Levels

Abstract Background: Exosomes are nanosized vesicles, play a vital role in breast cancer (BC) occurrence, development, invasion, metastasis, and drug resistance. Nevertheless, studies about exosome-related genes in breast cancer are limited. Besides, the interaction between the exosomes and tumor immune microenvironment (TIME) in BC are still unclear. Hence, we procced to study the potential prognostic value of exosome-related genes and their relationship to immune microenvironment in BC. Methods: 121 exosome-related genes were provided by ExoBCD database and 7 final genes were selected from the intersection of 33 differential expression genes (DEGs) and 19 prognostic genes in BC. Based on the expression levels of the 7 genes, downloaded from The Cancer Genome Atlas (TCGA) database, as well as the regression coefficients, the exosome-related signature was constructed. As a result, the patients in TCGA and GEO database were separated into low- and high- risk groups, respectively. Subsequently, R clusterProfiler package was applied to identify the distinct enrichment pathways between high-risk group and low-risk group. The ESTIMATE method was used to calculate ESTIMATE Score and CIBERSORT was applied to evaluate the immune cell infiltration. Eventually, the different expression levels of immune checkpoint related genes were analyzed between the two risk groups. Results: Results of BC prognosis vary from different risk groups. The low-risk groups were identified with higher survival rate both in TCGA and GEO cohort. The DEGs between high- and low- risk groups were found to enrich in immunity, biological processes, and inflammation pathways. The BC patients with higher ESTIMATE scores were revealed to have better overall survival (OS). Subsequently, CD8+ T cells, naive B cells, CD4+ resting memory T cells, monocytes, and neutrophils were upregulated, while M0 macrophages and M2 macrophages were downregulated in the low-risk group. At last, 4 genes reported as the targets of immune checkpoint inhibitors were further analyzed. The low-risk groups in TCGA and GEO cohorts were indicated with higher expression levels of LAG-3, CD274, TIGIT and CTLA-4. Conclusion: According to this study, exosomes are closely associated with the prognosis and immune cell infiltration of BC patients. These findings may make contributions to improve immunotherapy and bring a new sight for BC treatment strategies.

Download Full-text

Proliferation-, estrogen-, and T-cell-related metagenes to predict outcome after adjuvant/neoadjuvant chemotherapy for operable breast cancer in the ECTO trial.

Journal of Clinical Oncology ◽

10.1200/jco.2013.31.15_suppl.1014 ◽

2013 ◽

Vol 31 (15_suppl) ◽

pp. 1014-1014 ◽

Cited By ~ 1

Author(s):

Giampaolo Bianchini ◽

Vera Cappelletti ◽

Maurizio Callari ◽

Maria Luisa Carcangiu ◽

Wolfgang Eiermann ◽

...

Keyword(s):

Breast Cancer ◽

T Cell ◽

High Risk ◽

Risk Group ◽

Molecular Subtype ◽

Expression Profiles ◽

Risk Groups ◽

Operable Breast Cancer ◽

Low Risk ◽

Phase Iii

1014 Background: Predicting recurrence in operable breast cancer (BC) despite optimal chemotherapy would be relevant to new drug development and tailored treatments. Methods: A large series (n=3,154) of public Affymetrix gene-expression profiles (GEP) was used to define prognostic/predictive metagenes in different BC subtypes. In ER+/HER2- a proliferation and an ER-related metagene were combined to predict low, intermediate and high risk of recurrence. In TN and in HER2+ a T cell metagene was used to predict low, intermediate and high risk (higher expression associated with lower risk). The metagenes were validated in patients enrolled in the phase III ECTO trial (Gianni L. JCO 2009) and treated with the same taxane-anthracycline-CMF regimen as neoadjuvant or adjuvant therapy before endocrine therapy if indicated. The outcome was distant event free survival (DEFS). Results: 283 good quality GEPs were obtained (neoadjuvant n=121; adjuvant n=162) from 464 retrospectively collected samples. Median follow-up was 8.9 years. In ER+/HER2- tumors the 10-yrs DEFS was 92.3, 81.2 and 66.6% in low, intermediate and high risk groups, respectively [high vs low HR 4.38 (1.01-19.1) p=.048] according to proliferation and ER-related metagenes. In HER2+ and TN subgroup the 10-yrs DEFS was 97.2, 75.6 and 78.8% in low, intermediate and high risk groups, respectively [high vs low HR 8.73 (1.09-69.8) p=.041]. In TN tumors, the pCR rate was 20% in the high and 61.5% in the low risk group. By combining the predicted risk group in each molecular subtype the 10-yrs DEFS was 95.3, 79.2 and 71.5% in low (24.2%), intermediate (42.7%) and high (33.1%) risk group, respectively [logrank p=0.003; high vs low HR 6.22 (1.87-20.6) p=.002]. ER, PGR, Ki67 and lymphocyte infiltration (LI) by IHC underperformed compared to genomic predictors. Conclusions: BC patients at higher risk of relapse despite optimal standard treatment can be identified who should be spared ineffective and toxic therapy and considered for investigational new strategies. In TN and HER2+, high T cell metagene and to a lesser extent LI are prognostic/predictive and associated with an extremely low risk of DEFS after chemotherapy.

Download Full-text

Risk Evaluation of Early-stage Hormone Receptor-positive and Human Epidermal Growth Factor Receptor 2-negative Breast Cancer Patients: a Population-based Study From Taiwan

10.21203/rs.3.rs-626553/v1 ◽

2021 ◽

Author(s):

Lei Lei ◽

Han-Ching Chan ◽

Tzu-Pin Lu ◽

Hung-Chun Skye Cheng

Keyword(s):

Breast Cancer ◽

High Risk ◽

Prognostic Value ◽

Risk Group ◽

Early Stage ◽

Growth Factor Receptor ◽

Risk Groups ◽

Low Risk ◽

Hormone Receptor Positive ◽

Epidermal Growth

Abstract PURPOSE: To assess the prognostic value of the Dutch criteria for patients with early-stage hormone receptor-positive and human epidermal growth factor receptor 2-negative breast cancer from the Taiwan Cancer Database. PATIENTS AND METHODS:We included 8,295 patients with early-stage node-negative breast cancer who underwent surgery during January 2008–December 2012. Patients were stratified into low- and high-risk groups based on the Dutch criteria. The Kaplan–Meier method and log-rank test were used to estimate the difference in breast cancer-specific survival (BCSS) and overall survival (OS) between groups. Multivariable analysis was used to evaluate the prognostic value of the Dutch criteria.RESULTS: Overall, the low-risk and high-risk groups comprised 5,375 and 2,920 patients, respectively. In the low- and high-risk groups, the 5-year BCSS rate was 99.6% and 98.2% (P<0.0001) and the 5-year OS rate was 98.3% and 96.8% (P<0.0001), respectively. The hazard ratio for BCSS was 4.18 (95% confidence interval [CI], 2.63–6.63, P<0.0001), and the hazard ratio for OS was 1.94 (95% CI, 1.48–2.55); both were significantly poorer in the high-risk group than in the low-risk group. In the low-risk group, the 5-year BCSS and OS of patients who did and did not receive adjuvant chemotherapy were similar (99.5% versus 99.6% [P=0.927] and 98.8% and 98.1% [P=0.0683], respectively). CONCLUSIONS: The prognosis of low-risk patients as classified using the Dutch criteria is excellent with or without adjuvant chemotherapy. The benefit of multi-gene testing for chemotherapy decision-making might be minimal in these patients.

Download Full-text

Locoregional Treatment in De Novo Metastatic Breast Cancer: A Retrospective Cohort Study

10.21203/rs.3.rs-125308/v1 ◽

2020 ◽

Author(s):

Sun Jianna ◽

Kong Lingjun ◽

Feng Nana ◽

Liu Hong ◽

Ren Chongxi

Keyword(s):

Breast Cancer ◽

Cohort Study ◽

Metastatic Breast Cancer ◽

Survival Benefit ◽

De Novo ◽

Metastatic Breast ◽

Local Therapy ◽

Surgical Margins ◽

Rank Test ◽

Locoregional Treatment

Download Full-text

Integrated Multiparametric Radiomics and Informatics System for Characterizing Breast Tumor Characteristics with the OncotypeDX Gene Assay

Cancers ◽

10.3390/cancers12102772 ◽

2020 ◽

Vol 12 (10) ◽

pp. 2772

Author(s):

Michael A. Jacobs ◽

Christopher B. Umbricht ◽

Vishwa S. Parekh ◽

Riham H. El Khouli ◽

Leslie Cope ◽

...

Keyword(s):

Breast Cancer ◽

High Risk ◽

Risk Group ◽

Area Under The Curve ◽

Risk Groups ◽

High Risk Group ◽

Low Risk ◽

Intermediate Risk ◽

Breast Cancer Patients ◽

Gene Assay

Optimal use of multiparametric magnetic resonance imaging (mpMRI) can identify key MRI parameters and provide unique tissue signatures defining phenotypes of breast cancer. We have developed and implemented a new machine-learning informatic system, termed Informatics Radiomics Integration System (IRIS) that integrates clinical variables, derived from imaging and electronic medical health records (EHR) with multiparametric radiomics (mpRad) for identifying potential risk of local or systemic recurrence in breast cancer patients. We tested the model in patients (n = 80) who had Estrogen Receptor positive disease and underwent OncotypeDX gene testing, radiomic analysis, and breast mpMRI. The IRIS method was trained using the mpMRI, clinical, pathologic, and radiomic descriptors for prediction of the OncotypeDX risk score. The trained mpRad IRIS model had a 95% and specificity was 83% with an Area Under the Curve (AUC) of 0.89 for classifying low risk patients from the intermediate and high-risk groups. The lesion size was larger for the high-risk group (2.9 ± 1.7 mm) and lower for both low risk (1.9 ± 1.3 mm) and intermediate risk (1.7 ± 1.4 mm) groups. The lesion apparent diffusion coefficient (ADC) map values for high- and intermediate-risk groups were significantly (p < 0.05) lower than the low-risk group (1.14 vs. 1.49 × 10−3 mm2/s). These initial studies provide deeper insight into the clinical, pathological, quantitative imaging, and radiomic features, and provide the foundation to relate these features to the assessment of treatment response for improved personalized medicine.

Download Full-text