Invasive Ductal Carcinoma Of Breast Research Articles

Multi-threshold image segmentation using a boosted whale optimization: case study of breast invasive ductal carcinomas

Multi-threshold image segmentation using a boosted whale optimization: case study of breast invasive ductal carcinomas

CNN-based deep learning approach for classification of invasive ductal and metastasis types of breast carcinoma.

Breast cancer is one of the leading cancer causes among women worldwide. It can be classified as invasive ductal carcinoma (IDC) or metastatic cancer. Early detection of breast cancer is challenging due to the lack of early warning signs. Generally, a mammogram is recommended by specialists for screening. Existing approaches are not accurate enough for real-time diagnostic applications and thus require better and smarter cancer diagnostic approaches. This study aims to develop a customized machine-learning framework that will give more accurate predictions for IDC and metastasis cancer classification. This work proposes a convolutional neural network (CNN) model for classifying IDC and metastatic breast cancer. The study utilized a large-scale dataset of microscopic histopathological images to automatically perceive a hierarchical manner of learning and understanding. It is evident that using machine learning techniques significantly (15%-25%) boost the effectiveness of determining cancer vulnerability, malignancy, and demise. The results demonstrate an excellent performance ensuring an average of 95% accuracy in classifying metastatic cells against benign ones and 89% accuracy was obtained in terms of detecting IDC. The results suggest that the proposed model improves classification accuracy. Therefore, it could be applied effectively in classifying IDC and metastatic cancer in comparison to other state-of-the-art models.

71949 - Melatonin MT1 Receptor Expression in Luminal Invasive Ductal Breast Carcinoma in Postmenopausal Women

71949 - Melatonin MT1 Receptor Expression in Luminal Invasive Ductal Breast Carcinoma in Postmenopausal Women

The impact of extensive intraductal component (EIC) on the genomic risk of recurrence in early hormone receptor positive breast cancer

BackgroundEarly invasive ductal carcinoma (IDC) breast cancer often presents with a coexisting ductal carcinoma in situ (DCIS) component, while about 5 % of cases present with an extensive (>25 %) intraductal component (EIC). The impact of EIC on the genomic risk of recurrence is unclear. MethodsPatients with early hormone receptor-positive HER2neu-negative (HR + HER2-) IDC breast cancer and a known OncotypeDX Breast Recurrence Score® (RS) who underwent breast surgery at our institute were included. Using a rule-based text-analysis algorithm, we analyzed pathological reports and categorized patients into three groups: EIC, non-extensive DCIS (DCIS-L), and pure-IDC (NO-DCIS). Genomic risk was determined using OncotypeDX RS. ResultsA total of 33 (4.6 %) EIC cases, 377 (57.2 %) DCIS-L cases and 307 (42.8 %) NO-DCIS cases were identified. Patients in the EIC group were younger and had lower tumor grades than other groups. The distribution of genomic risk varied between the groups, with EIC tumors significantly less likely to have a high RS (>25) compared to DCIS-L and No-DCIS tumors (3 % vs 20 % and 20 %, respectively; p = 0.03). When adjusted to age, tumor size, grade and LNs involvement, both DCIS-L and NO-DCIS groups were significantly correlated with a higher probability of high RS compared to the EIC group (OR 12.3 and OR 13.1, respectively; p < 0.02). Moreover, patients with EIC had a lower likelihood for adjuvant chemotherapy recommendation. ConclusionsIn early HR + HER2- IDC, an EIC correlates with a reduced genomic recurrence risk. The impact on genomic risk seems to be influenced by the extent, not merely the presence, of DCIS.

Radiomics analysis combining gray-scale ultrasound and mammography for differentiating breast adenosis from invasive ductal carcinoma.

To explore the utility of gray-scale ultrasound (GSUS) and mammography (MG) for radiomic analysis in distinguishing between breast adenosis and invasive ductal carcinoma (IDC). Data from 147 female patients with pathologically confirmed breast lesions (breast adenosis: 61 patients; IDC: 86 patients) between January 2018 and December 2022 were retrospectively collected. A training cohort of 113 patients (breast adenosis: 50 patients; IDC: 63 patients) diagnosed from January 2018 to December 2021 and a time-independent test cohort of 34 patients (breast adenosis: 11 patients; IDC: 23 patients) diagnosed from January 2022 to December 2022 were included. Radiomic features of lesions were extracted from MG and GSUS images. The least absolute shrinkage and selection operator (LASSO) regression was applied to select the most discriminant features, followed by logistic regression (LR) to construct clinical and radiomic models, as well as a combined model merging radiomic and clinical features. Model performance was assessed using receiver operating characteristic (ROC) analysis. In the training cohort, the area under the curve (AUC) for radiomic models based on MG features, GSUS features, and their combination were 0.974, 0.936, and 0.991, respectively. In the test cohort, the AUCs were 0.885, 0.876, and 0.949, respectively. The combined model, incorporating clinical and all radiomic features, and the MG plus GSUS radiomics model were found to exhibit significantly higher AUCs than the clinical model in both the training cohort and test cohort (p<0.05). No significant differences were observed between the combined model and the MG plus GSUS radiomics model in the training cohort and test cohort (p>0.05). The effectiveness of radiomic features derived from GSUS and MG in distinguishing between breast adenosis and IDC is demonstrated. Superior discriminatory efficacy is shown by the combined model, integrating both modalities.

Beyond Triple-Negative: High Prevalence of Quadruple-Negative Breast Cancer in African Americans.

Quadruple-negative breast cancer (QNBC) is a triple-negative breast cancer (TNBC) subtype that lacks expression of the androgen (AR) receptor. Few studies have focused on this highly aggressive breast cancer, portending worse survival rates. We aimed to determine the following: (1) QNBC's molecular and clinical characteristics and compare them with other subtypes and (2) QNBC's association with clinicopathological factors and prognostic markers. We performed immunohistochemical evaluations of ARs on tissue tumor microarrays from FFPE tumor blocks of invasive ductal breast carcinomas in 202 African American women. Univariate analysis was performed using the chi-square test, with survival rates calculated using Kaplan-Meier curves. Overall, 75.8% of TNBCs were AR-negative. Compared to the luminal subtypes, TNBC and QNBC tumors were likely to be a higher grade (p < 0.001); HER2+/AR- and QNBCs were also larger than the other subtypes (p < 0.001). They also expressed increasing mean levels of proteins involved in invasion, such as CD44, fascin, and vimentin, as well as decreasing the expression of proteins involved in mammary differentiation, such as GATA3 and mammaglobin. We found no association between QNBC and stage, recurrence-free survival, or overall survival rates. The high prevalence of TNBC AR-negativity in these women could explain observed worse outcomes, supporting the existence of the unique QNBC subtype.

Mean Apparent Propagator MRI: Quantitative Assessment of Tumor-Stroma Ratio in Invasive Ductal Breast Carcinoma.

Purpose To determine whether metrics from mean apparent propagator (MAP) MRI perform better than apparent diffusion coefficient (ADC) value in assessing the tumor-stroma ratio (TSR) status in breast carcinoma. Materials and Methods From August 2021 to October 2022, 271 participants were prospectively enrolled (ClinicalTrials.gov identifier: NCT05159323) and underwent breast diffusion spectral imaging and diffusion-weighted imaging. MAP MRI metrics and ADC were derived from the diffusion MRI data. All participants were divided into high-TSR (stromal component < 50%) and low-TSR (stromal component ≥ 50%) groups based on pathologic examination. Clinicopathologic characteristics were collected, and MRI findings were assessed. Logistic regression was used to determine the independent variables for distinguishing TSR status. The area under the receiver operating characteristic curve (AUC) and sensitivity, specificity, and accuracy were compared between the MAP MRI metrics, either alone or combined with clinicopathologic characteristics, and ADC, using the DeLong and McNemar test. Results A total of 181 female participants (mean age, 49 years ± 10 [SD]) were included. All diffusion MRI metrics differed between the high-TSR and low-TSR groups (P < .001 to P = .01). Radial non-Gaussianity from MAP MRI and lymphovascular invasion were significant independent variables for discriminating the two groups, with a higher AUC (0.81 [95% CI: 0.74, 0.87] vs 0.61 [95% CI: 0.53, 0.68], P < .001) and accuracy (138 of 181 [76%] vs 106 of 181 [59%], P < .001) than that of the ADC. Conclusion MAP MRI may serve as a better approach than conventional diffusion-weighted imaging in evaluating the TSR of breast carcinoma. Keywords: MR Diffusion-weighted Imaging, MR Imaging, Breast, Oncology ClinicalTrials.gov Identifier: NCT05159323 Supplemental material is available for this article. © RSNA, 2024.

Atypical Presentation of Carcinoma Breast as Paraneoplastic Cerebellar Degeneration on [18F]FDG PET/CT

Paraneoplastic neurological syndrome (PNS) represents a rare group of central nervous system disorders that are unrelated to direct tumor invasion or metastasis but may be triggered by an immune system reaction to a neoplasm or malignant tumor. In many patients, PNS is diagnosed before identifying the primary cancer. In such instances, positron emission tomography/computed tomography scan can assess individuals with suspected PNS enabling the detection of hidden malignancies. We share an interesting image of paraneoplastic cerebellar degeneration in a case of invasive ductal carcinoma breast.

Expression of Immune Checkpoint Regulator Cytotoxic T Lymphocyte Antigen 4 (CTLA-4) and Programmed Cell Death Protein Ligand 1 (PD-L1) in Invasive Ductal Carcinoma Breast

Expression of Immune Checkpoint Regulator Cytotoxic T Lymphocyte Antigen 4 (CTLA-4) and Programmed Cell Death Protein Ligand 1 (PD-L1) in Invasive Ductal Carcinoma Breast

The VISTA/VSIG3/PSGL-1 axis: crosstalk between immune effector cells and cancer cells in invasive ductal breast carcinoma

A checkpoint protein called the V-domain Ig suppressor of T cell activation (VISTA) is important for controlling immune responses. Immune cells that interact with VISTA have molecules, or receptors, known as VISTA receptors. Immune system activity can be modified by the interaction between VISTA and its receptors. Since targeting VISTA or its receptors may be beneficial in certain conditions, VISTA has been studied in relation to immunotherapy for cancer and autoimmune illnesses. The purpose of this study was to examine the expression levels and interactions between VISTA and its receptors, VSIG3 and PSGL-1, in breast cancer tissues. IHC analysis revealed higher levels of proteins within the VISTA/VSIG3/PSGL-1 axis in cancer tissues than in the reference samples (mastopathies). VISTA was found in breast cancer cells and intratumoral immune cells, with membranous and cytoplasmic staining patterns. VISTA was also linked with pathological grade and VSIG3 and PSGL-1 levels. Furthermore, we discovered that the knockdown of one axis member boosted the expression of the other partners. This highlights the significance of VISTA/VSIG3/PSGL-1 in tumor stroma and microenvironment remodeling. Our findings indicate the importance of the VISTA/VSIG3/PSGL-1 axis in the molecular biology of cancer cells and the immune microenvironment.

MiRNAs as potential biomarkers in early breast cancer detection: a systematic review.

Breast cancer remains a significant global health challenge, with high incidence and mortality rates. While mammography has contributed to declining mortality, its limitations in sensitivity and specificity for early detection, particularly in distinguishing between pure atypical ductal hyperplasia (ADH), ductal carcinoma in situ (DCIS), and invasive ductal carcinoma (IDC), highlight the need for more precise tools. Even with core needle biopsy (CNB), conclusive diagnoses often require surgical excision. This underscores the urgency for non-invasive biomarkers to improve early detection and differentiation, potentially reducing invasive procedures. Recent research has shifted focus from mRNA to microRNAs (miRNAs) as promising biomarkers for breast cancer screening. These small non-coding RNAs, which exhibit abnormal expression patterns in breast cancer patients' tissue and serum/plasma, play crucial roles in early breast cancer development by modulating proto-oncogenes or tumor suppressor genes at the post-transcriptional level. Notably, miRNAs such as miR-21, miR-155, and miR-200c are key regulators of cell proliferation and apoptosis, with the potential to distinguish between normal tissue and various stages of breast lesions, including ADH, DCIS, and IDC. Additionally, miRNAs in serum and plasma offer a non-invasive method to differentiate breast cancer stages. This review aims to consolidate current knowledge on early breast lesions and explore the potential of miRNAs as biomarkers for early breast cancer detection, which could enhance risk prediction and reduce reliance on invasive diagnostic procedures.

Novel Androgen Receptor Splice Variant 7 in Gynecologic Tumors.

Androgen receptor splicing variant 7 (AR-V7) is a truncated variant of the AR mRNA that may be a predictive biomarker for AR-targeted therapy. AR-V7 has been described in prostate, breast, salivary duct, and hepatocellular carcinomas as well as mammary and extra-mammary Paget disease. We report 2 gynecologic cancers occurring in the lower uterine segment and ovary and both harboring AR-V7 by targeted RNA sequencing. The uterine tumor was an undifferentiated carcinoma consisting of epithelioid cells and focally spindled cells arranged in sheets, nests, and cords associated with brisk mitotic activity and tumor necrosis. The ovarian tumor consisted of glands with cribriform and solid architecture and uniform cytologic atypia. ER and PR were positive in the ovarian tumor and negative in the uterine tumor. Both were positive for AR and negative for HER2, GATA3, and NKX3.1. DNA methylation profiling showed epigenetic similarity of the AR-V7-positive gynecologic cancers to AR-V7-positive breast cancers rather than to prostate cancers. AR-V7 may underpin rare gynecologic carcinomas with undifferentiated histology or cribriform growth reminiscent of prostatic adenocarcinoma and breast invasive ductal carcinoma.

Local intralesional talimogene laherparepvec therapy with complete local response in oral palatine mucosal melanoma: a case report

BackgroundMucosal melanoma, an aggressive type of malignancy different from the cutaneous melanomas commonly seen in the head and neck region, represents < 1% of all malignant melanomas. The pathogenesis of mucosal melanoma is unknown. Targetable mutations commonly seen in cutaneous melanoma, such as in the BRAF and NRAS genes, have a lower incidence in mucosal melanoma. Mucosal melanoma carries a distinct mutational pattern from cutaneous melanoma. Surgery with negative margins is the first-line treatment for mucosal melanoma, and systemic therapy is not well defined. Talimogene laherparepvec, an oncolytic viral immunotherapy, is United States Food and Drug Administration approved for the treatment of advanced malignant cutaneous melanoma, with local therapeutic benefits. Mucosal melanoma was initially excluded from talimogene laherparepvec’s initial phase III clinical trial.Case presentationWe present the case of a white female patient in her 40s with past medical history of systemic lupus erythematous, scleroderma, and estrogen-receptor-positive invasive ductal breast carcinoma. Following a bilateral mastectomy, the patient was found to have BRAF-negative mucosal melanoma of her hard palate with a soft palate skip lesion. Owing to the presence of a skip mucosal lesion as well as the anticipated defect and need for free-flap reconstructive surgery, nonsurgical management was considered. The patient was referred to medical oncology, where—based on the patient’s complicated medical history and the risk of immunotherapy possibly worsening her prior autoimmune diseases—local talimogene laherparepvec injections were chosen as the primary therapy for her mucosal lesions. Though talimogene laherparepvec is approved for the treatment of cutaneous melanoma, there are limited data available on the use of talimogene laherparepvec in mucosal melanomas.ConclusionThe patient had a complete local tumor response at both the primary lesion as well as the skip lesion with the local injections. She had no side effects and maintained a high quality of life during treatment.

Feasibility of perforator flaps in Day surgery. A retrospective study through a two-years’ experience

Day surgery is developing and its popularity is increasing for a variety of reasons: economic constraints, changes in professional practices, a greater adhesion of the patient. In an era of progress in surgical procedures, pedicled-perforator flaps reducing donor site morbidity and avoiding micro-anastomosis could take their place in Day surgery if planned and managed by an experienced team. In the period January 2019 to January 2021, we performed perforator flaps for soft tissue coverage in ambulatory setting. The patients were included retrospectively and data were collected by reviewing the medical records. Major and minor complications were recorded. The retrospective cohort included 32 surgical procedures in 32 patients. In all cases, perforator flaps were realized for resurfacing soft tissue defects consequent to oncodermatology surgery (84.3%), soft tissue sarcoma surgery (12.5%), invasive ductal breast carcinoma (3.1%). Major complications needing a surgical revision overcame 3/32 times (9.4%). In these cases, a failure requiring the drop off the flap overcame once. The average wound healing time was of 33days (15-90) and the mean duration of follow-up was 9.6months (1-22). The low complication rate in our series suggests that this first experience on perforator flaps in outpatient surgery is promising in terms of safety and feasibility. Day surgery could be a practical option for this type of surgical procedures avoiding the conventional department's saturation and allowing the delivery of proper surgical cares.

ANALYSIS OF CARCINOMA BREAST PATIENTS PRESENTING TO SURGICAL UNIT OF A TERTIARY CARE CENTRE IN PESHAWAR

Objective: To determine clinical and pathological features of patients of breast cancer presenting to surgical unit of a tertiary care center in Peshawar. Methodology: This cross-sectional descriptive study was conducted in Khyber Teaching Hospital, Peshawar from 1stJanuary 2022 to 31st December 2022. Cases referred to surgical unit for workup of breast cancer were recruited into the study by non-probability purposive sampling. After taking detailed history and physical examination, true cut biopsy of breast lump was taken and sent for histopathology, receptor studies and Ki67 scoring. Cases who were diagnosed previously in other hospitals were excluded. Data was recorded and analyzed using SPSS version 26. Mean and standard deviation were used for quantitative variables while frequency and percentages were used for qualitative variables. Results: About 230 patients of breast cancer were included in the study. Mean age of study sample was 43±12.94 (range:17-85) years. About 123 (53.5%) cases were premenopausal. Invasive ductal carcinoma was the commonest diagnosis which was seen in 175 (76.1%) cases. Receptor status for estrogen and progesterone was positive in 135 (59.4%) and 107 (47.3.5%) cases respectively. About 123 (53.3%) cases presented in early stage of disease while 34 (14.8%) cases were in metastatic phase. Conclusion: Breast cancer presents in early age in our population. Invasive ductal carcinoma breast is the commonest diagnosis in our setup. The rate of metastatic disease in our setup is high as compared to developed countries. Early referral is warranted for timely diagnosis and treatment of the disease.

Longitudinal assessment of real-world patient adherence: a 12-month electronic patient-reported outcomes follow-up of women with early breast cancer undergoing treatment

BackgroundElectronic patient-reported outcomes (ePROs) assess patients’ health status and quality of life, improving patient care and treatment effects, yet little is known about their use and adherence in routine patient care.AimsWe evaluated the adherence of invasive breast cancer and ductal carcinoma in situ (DCIS) patients to ePROs follow-up and whether specific patient characteristics are related to longitudinal non-adherence.MethodsSince November 2016, the Breast Center at Charité – Universitätsmedizin Berlin has implemented an ongoing prospective PRO routine program, requiring patients to complete ePROs assessments and consent to email-based follow-up in the first 12 months after therapy starts. Frequencies and summary statistics are presented. Multiple logistic regression models were performed to determine an association between patient characteristics and non-adherence.ResultsOut of 578 patients, 239 patients (41.3%, 95%CI: 37.3–45.5%) completed baseline assessment and all five ePROs follow-up during the first 12 months after therapy. On average, above 70% of those patients responded to the ePROs follow-up assessment. Adherence to the ePROs follow-up was higher during the COVID-19 pandemic than in the time periods before (47.4% (111/234) vs. 33.6% (71/211)). Factors associated with longitudinal non-adherence were younger age, a higher number of comorbidities, no chemotherapy, and a low physical functioning score in the EORTC QLQ-C30 at baseline.ConclusionsThe study reveals moderate adherence to 12-month ePROs follow-up assessments in invasive early breast cancer and DCIS patients, with response rates ranging from 60 to 80%. Emphasizing the benefits for young patients and those with high disease burdens might further increase adherence.

Comparison of clinical characteristics and outcomes in primary neuroendocrine breast carcinoma versus invasive ductal carcinoma.

Neuroendocrine breast carcinoma (NECB) is a rare, special histologic type of breast cancer. There are some small sample studies on the clinical outcomes of NECB patients, which are worthy of further discussion. We conducted a retrospective case-control study of clinical characteristics and outcomes among patients with primary NECB versus invasive carcinoma of no special type (NST) between November 2004 and November 2017 in the Peking Union Medical College Hospital, Beijing. NST patients were strictly matched 1:4 during the same period based on the TNM stage. Statistical comparisons were performed to determine the differences in survival between NST and NECB patients and to identify clinical factors that correlate with prognosis. A total of 121 participants affected by primary NECB were included in our analysis from November 2004 to November 2017. Elderly persons (>60 years of age) were more likely to have primary NECB than young persons (p=0.001). In addition, primary NECB patients had significantly higher odds of having tumors 2-5cm (36.5%) and >5cm (6.1%) in size than NST patients. Despite a significant difference in tumor size, the proportion of patients with lymph node metastases showed no difference between the two groups (p=0.021). In addition, the rate of patients with ER-negative tumors in the NECB group (4.2%) was significantly lower than that in the primary NST group (29.8%). Significant differences were noted in the PR-negative (13.3% versus 36.6%, P<0.001) and HER2-negative (90.5% versus 76.4%, P=0.001) expression statuses among these patients. Of 121 primary NECB patients, 11 (9.1%) experienced relapses during the follow-up period. We found that tumor size was an independent risk factor for relapse. For hormone receptors on tumor cells, ER-positive breast cancer patients had significantly lower odds of relapse than receptor-negative patients. Our data demonstrate no significant difference in mortality and relapse between the primary NECB and NST groups. The tumor size in the primary NECB group was significantly larger than that in the NST group. In addition, the absence of ER independently increased the relapse rate for breast carcinoma patients.

Impact of Transfer Learning Using Local Data on Performance of a Deep Learning Model for Screening Mammography.

Purpose To investigate the issues of generalizability and replication of deep learning models by assessing performance of a screening mammography deep learning system developed at New York University (NYU) on a local Australian dataset. Materials and Methods In this retrospective study, all individuals with biopsy or surgical pathology-proven lesions and age-matched controls were identified from a South Australian public mammography screening program (January 2010 to December 2016). The primary outcome was deep learning system performance-measured with area under the receiver operating characteristic curve (AUC)-in classifying invasive breast cancer or ductal carcinoma in situ (n = 425) versus no malignancy (n = 490) or benign lesions (n = 44). The NYU system, including models without (NYU1) and with (NYU2) heatmaps, was tested in its original form, after training from scratch (without transfer learning), and after retraining with transfer learning. Results The local test set comprised 959 individuals (mean age, 62.5 years ± 8.5 [SD]; all female). The original AUCs for the NYU1 and NYU2 models were 0.83 (95% CI: 0.82, 0.84) and 0.89 (95% CI: 0.88, 0.89), respectively. When NYU1 and NYU2 were applied in their original form to the local test set, the AUCs were 0.76 (95% CI: 0.73, 0.79) and 0.84 (95% CI: 0.82, 0.87), respectively. After local training without transfer learning, the AUCs were 0.66 (95% CI: 0.62, 0.69) and 0.86 (95% CI: 0.84, 0.88). After retraining with transfer learning, the AUCs were 0.82 (95% CI: 0.80, 0.85) and 0.86 (95% CI: 0.84, 0.88). Conclusion A deep learning system developed using a U.S. dataset showed reduced performance when applied "out of the box" to an Australian dataset. Local retraining with transfer learning using available model weights improved model performance. Keywords: Screening Mammography, Convolutional Neural Network (CNN), Deep Learning Algorithms, Breast Cancer Supplemental material is available for this article. © RSNA, 2024 See also commentary by Cadrin-Chênevert in this issue.

Abstract PO2-13-08: Cell-free orphan noncoding RNAs and AI enable early detection of invasive breast cancer and ductal carcinoma in-situ

Abstract Background Earlier detection of breast cancer through mammography screening has reduced disease-specific mortality; however, confounding issues such as technical challenges, breast density, and tumor size can result in false negatives and ultimately later stage diagnosis. Next generation liquid biopsy has the potential to complement mammography and enable earlier detection for more women. We have previously demonstrated high sensitivity and specificity for early detection of invasive breast cancer (IBC) by utilizing a novel category of cancer-associated small RNAs, termed orphan noncoding RNAs (oncRNAs), through a liquid biopsy platform. Here, we further improve the ability to detect breast cancer in a larger, multi-source cohort through an AI-driven approach and demonstrate potential for detection of ductal carcinoma in-situ (DCIS). Methods We utilized The Cancer Genome Atlas (TCGA) small RNA-seq database to discover a library of 20,538 oncRNAs, through a female-specific analysis, that were significantly enriched among 1,103 breast tumors compared to 349 normal tissue samples spanning multiple tissue sites. The diagnostic performance of these oncRNAs were assessed in an independent cohort of archived serum samples from 663 female individuals, sourced from Indivumed (Hamburg, Germany), Proteogenex (Inglewood, CA), and MT Group (Los Angeles, CA), including 279 breast cancer patients of various stages (221 IBC and 58 DCIS; mean age: 57.0 ± 13.8 years; ever-smoker: 25.8%) and 304 age-matched controls (mean age: 58.5 ± 13.9 years; ever-smoker: 23.4%) without breast cancer. All samples were collected between 2010–2022 at time of diagnosis for breast cancer patients. We sequenced the small RNA content of these samples at an average depth of 25.28 ± 9.37 million 50-bp single-end reads. We detected 18,025 (87.8%) unique breast cancer-specific oncRNA species within at least one sample from the study cohort. We then trained a generative AI model using 5-fold cross-validation to predict cancer status for all samples. Results Our oncRNA-based model achieved an overall AUC of 0.95 (95% CI, 0.93–0.97) for prediction of IBC versus cancer-free controls with a sensitivity of 0.87 (0.82–0.91) at 90% specificity. We observed high sensitivities, also at 90% specificity, across all tumor stages and tumor sizes (Table 1). Sensitivities for the earliest stage and smallest tumor size were 0.87 (0.78–0.93) and 0.81 (0.61–0.93) for Stage I (n=83) and T1a–b ( &amp;gt;1mm to ≤10mm; n=26), respectively. Additionally, in a small single-source cohort, we also saw high model accuracy and sensitivity for DCIS, which we aim to confirm in additional cohorts. While our overall cancer cohort primarily consisted of individuals with luminal breast cancer, our model had high sensitivities across all breast cancer subtypes at 0.90 (0.84–0.94), 0.73 (0.59–0.85), and 0.86 (0.42–1.0) for luminal (n=181), HER2 positive (n=49), and triple negative (n=7), respectively. Conclusions We further demonstrate the potential utility of oncRNAs as a blood-based biomarker using an AI algorithm for sensitive and accurate early detection of breast cancer in a large cohort. Additionally, we have shown that this oncRNA-based assay performs well in detecting small, early-stage invasive breast tumors, with potential to detect precursors of breast cancer. Table 1: Model sensitivity in breast cancer by tumor stage and size For each tumor stage and size, as defined by the AJCC 7th Edition breast cancer staging system, sensitivity and 95% Pearson-Clopper confidence intervals (CI) are reported at 90% specificity for the number of samples (N). Citation Format: Noura Tbeileh, Taylor Cavazos, Mehran Karimzadeh, Jeffrey Wang, Alice Huang, Dung Ngoc Lam, Seda Kilinc, Jieyang Wang, Xuan Zhao, Andy Pohl, Helen Li, Lisa Fish, Kimberly Chau, Marra Francis, Lee Schwartzberg, Patrick Arensdorf, Hani Goodarzi, Fereydoun Hormozdiari, Babak Alipanahi. Cell-free orphan noncoding RNAs and AI enable early detection of invasive breast cancer and ductal carcinoma in-situ [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-13-08.

KDM7A-DT induces genotoxic stress, tumorigenesis, and progression of p53 missense mutation-associated invasive breast cancer.

Stress-induced promoter-associated and antisense lncRNAs (si-paancRNAs) originate from a reservoir of oxidative stress (OS)-specific promoters via RNAPII pausing-mediated divergent antisense transcription. Several studies have shown that the KDM7A divergent transcript gene (KDM7A-DT), which encodes a si-paancRNA, is overexpressed in some cancer types. However, the mechanisms of this overexpression and its corresponding roles in oncogenesis and cancer progression are poorly understood. We found that KDM7A-DT expression is correlated with highly aggressive cancer types and specific inherently determined subtypes (such as ductal invasive breast carcinoma (BRCA) basal subtype). Its regulation is determined by missense TP53 mutations in a subtype-specific context. KDM7A-DT transcribes several intermediate-sized ncRNAs and a full-length transcript, exhibiting distinct expression and localization patterns. Overexpression of KDM7A-DT upregulates TP53 protein expression and H2AX phosphorylation in nonmalignant fibroblasts, while in semi-transformed fibroblasts, OS superinduces KDM7A-DT expression in a TP53-dependent manner. KDM7A-DT knockdown and gene expression profiling in TP53-missense mutated luminal A BRCA variant, where it is abundantly expressed, indicate its significant role in cancer pathways. Endogenous over-expression of KDM7A-DT inhibits DNA damage response/repair (DDR/R) via the TP53BP1-mediated pathway, reducing apoptosis and promoting G2/M checkpoint arrest. Higher KDM7A-DT expression in BRCA is associated with KDM7A-DT locus gain/amplification, higher histologic grade, aneuploidy, hypoxia, immune modulation scores, and activation of the c-myc pathway. Higher KDM7A-DT expression is associated with relatively poor survival outcomes in patients with luminal A or Basal subtypes. In contrast, it is associated with favorable outcomes in patients with HER2+ER- or luminal B subtypes. KDM7A-DT levels are coregulated with critical transcripts and proteins aberrantly expressed in BRCA, including those involved in DNA repair via non-homologous end joining and epithelial-to-mesenchymal transition pathway. In summary, KDM7A-DT and its si-lncRNA exhibit several intrinsic biological and clinical characteristics that suggest important roles in invasive BRCA and its subtypes. KDM7A-DT-defined mRNA and protein subnetworks offer resources for identifying clinically relevant RNA-based signatures and prospective targets for therapeutic intervention.