In the context of a global appraisal of the environmental impact of radiology, this survey among members of the European Society of Breast Imaging (EUSOBI) investigated procedural aspects of ultrasound-guided core-needle breast biopsy that may impact its environmental sustainability. A 25-item online questionnaire, developed by a panel of nine breast imaging experts, was distributed from September 25th to December 25th, 2024, within the EUSOBI mailing list and social media platforms. The survey investigated materials routinely used for ultrasound-guided core-needle biopsies, waste disposal practices, the relationship between perceived procedural hygiene levels and self-reported frequency of post-procedural infectious complications, and results' communication methods. Replies were analysed with descriptive and non-parametric statistics. Among the 787/823 respondents (95.6%) who routinely perform ultrasound-guided core-needle biopsy, most (460/787, 58.4%) perceived to attain aseptic conditions, without significant associations (p = 0.334) of hygiene levels with post-procedural infectious complications (never seen by 549/776 respondents, 70.7%). For most disposable materials, the majority of respondents used no more than one unit per procedure, including sterile gloves (551/787, 70.0%), sterile drapes (651/787, 82.7%), and sterile gel packets (729/787, 92.6%), also avoiding to use prepackaged biopsy kits (424/787, 53.9%). However, most respondents did not use recycling bins (404/787, 51.3%) and employed at least oneresource-intensive modality to communicate benign results (in-person or by letter, 584/787, 74.2%). Procedural aspects of ultrasound-guided core-needle biopsy carrying an environmental impact vary widely. In the absence of significant associations between perceived hygiene levels and post-procedural infectious complications, resource-intensive habits could be safely streamlined to improve sustainability. This EUSOBI survey demonstrates that, despite widely varying procedural aspects in ultrasound-guided core-needle breast biopsy, higher perceived sterility levels are not associated with fewer infections, highlighting opportunities to safely reduce resource use and environmental impact. This EUSOBI survey investigated how procedural habits and the use and amount of material in ultrasound-guided core-needle breast biopsy impact its environmental sustainability. Procedural aspects varied widely among the 787/823 respondents who routinely perform ultrasound-guided core-needle breast biopsy. While some economically driven sustainable behaviours are already in place, there are several opportunities to reduce materials use and waste. As no association was found between perceived hygiene levels and post-procedural infections, resource-intensive hygiene-related practices could be streamlined to improve sustainability.

Metastatic lobular carcinoma of the breast in serous effusions is diagnostically challenging because the tumor cells simulate histiocytes and mesothelial cells. The typical metastatic pattern is isolated dispersed tumor cells which are unrelated to surrounding mesothelial cells. Metastatic deposits of lobular carcinoma cells within mesothelial cell clusters have not been previously reported. We report our findings of peritoneal metastatic lobular breast carcinoma cells masquerading in atypical hyperplastic mesothelial cell clusters found in cellblock sections, but were not present in ThinPrep slides. Three patients out of 10 patients diagnosed with breast lobular carcinoma showed infrequent large atypical cell clusters in cellblock sections. They were not identified in ThinPrep slides which showed chronic lymphohistiocytic inflammatory hemorrhagic effusion fluids, that initially were reported as negative for malignant cells and disregarded as mixed inflammatory infiltrates of lymphocytes, plasma cells and histiocytes. However, cellblock sections showed occasional large cell clusters that were confused with atypical mesothelial cell clusters and metastatic adenocarcinoma. Cellblock immunocytochemistry showed peculiar staining patterns. BerEP3 and CEA showed scattered single mononuclear epithelial cells intimately dispersed within WT1 and calretinin-positive mesothelial cell clusters. An extended panel showed intramesothelial epithelial tumor cells expressing GATA3, but were negative for TTF1, Napsin-A, PAX8, CDX2. The tumor cells also expressed ER and mammaglobin. They did not express E-cadherin. The cytologic diagnosis was metastatic lobular carcinoma of the breast. This was confirmed by breast core needle biopsies. Because this phenomenon is not always apparent in ThinPrep slides, cellblock sections supplemented with immunocytochemistry are a valuable diagnostic tool. The remaining seven patients showed the usual dispersed patterns of metastatic lobular carcinoma in ThinPrep slides and cellblock sections in pleural and peritoneal effusions.

To evaluate the risk of symptomatic hematomas in patients receiving epinephrine-containing lidocaine compared with lidocaine alone after core-needle breast biopsies (CNBBs). The efficacy of epinephrine-containing lidocaine in reducing hematoma risk following image-guided CNBB remains unclear. A single-institution, retrospective review of all CNBBs performed during a 6-month period using lidocaine alone (September 1, 2022, to March 15, 2023) due to a national shortage of epinephrine-containing lidocaine and a 6-month period using epinephrine-containing lidocaine (April 1, 2023, to October 1, 2023). A nurse navigator contacted all patients postbiopsy to assess postprocedural complications, including symptomatic hematomas. Postprocedure mammograms were reviewed for detectable hematomas after 9-gauge and 12- to 14-gauge CNBBs. Logistic regression models evaluated the associations between epinephrine-containing lidocaine use and symptomatic and mammographically evident hematomas. A total of 1157 CNBBs were performed in 967 patients; 619 received epinephrine-containing lidocaine and 538 received lidocaine alone. There were 11 (1.0%; 11/1157) symptomatic hematomas, 10 of which occurred following 9-gauge CNBBs (6 with stereotactic/tomosynthesis guidance and 4 with MRI guidance). There was no significant difference in the occurrence of symptomatic hematomas (P = .34) or mammographically evident hematomas (P = .53) after 12- to 14-gauge US-guided CNBBs performed with epinephrine-containing lidocaine vs lidocaine alone. Fewer symptomatic hematomas occurred after 9-gauge CNBBs in the epinephrine-containing lidocaine group (0.6%; 2/310) compared with the lidocaine alone (4.1%; 8/194) (P = .02). After 9-gauge CNBBs, mammographically evident hematomas were less frequent (16.1% vs 41.2%; P <.0001) with epinephrine-containing lidocaine compared with lidocaine alone. Epinephrine-containing lidocaine reduced rates of symptomatic and mammographically detected hematomas after 9-gauge CNBBs. Local infiltration with epinephrine-containing lidocaine could be considered in 9-gauge CNBBs to reduce hematoma risk.

Background Patients diagnosed with ductal carcinoma in situ (DCIS) may also have undetected invasive breast cancer. Radiomic features of calcifications at mammography can predict occult invasive disease among women diagnosed with DCIS at core-needle biopsy, which could affect treatment recommendations. However, the generalizability of these radiomic models must be tested before they are adopted in clinical practice. Purpose To evaluate the generalizability of radiomic models based on mammography features to predict occult invasive cancer among women diagnosed with DCIS at core-needle biopsy from three national datasets. Materials and Methods In this retrospective, cross-national study, digital mammograms from women diagnosed with DCIS at breast core-needle biopsy were collected in the United States, United Kingdom, and the Netherlands between January 1, 2000, and December 31, 2021. Only asymptomatic women who had calcifications but did not have associated masses, architectural distortions, or asymmetries were included. Radiomic models were developed using cross-validated logistic regression on each national dataset, then round-robin tested on the other datasets. Differences across the three datasets in terms of the upstaging rate, age, lesion size, and estrogen and progesterone receptor levels were assessed using Kruskal-Wallis or χ2 test. Results The study included 1498 women (age range, 31-89 years; mean age, 59 years ± 9 [SD]), as follows: 696 women from the United States, 618 women from the United Kingdom, and 184 women from the Netherlands, with upstaging rates of 16.1%, 16.7%, and 14.1%, respectively. Internal cross-validation areas under the receiver operating characteristic curve (AUCs) were 0.675 (95% CI: 0.671, 0.679), 0.603 (95% CI: 0.567, 0.722), and 0.701 (95% CI: 0.697, 0.706) for the U.S., UK, and Netherlands datasets, respectively. The model that was trained on the U.S. dataset yielded cross-national validation AUCs of 0.604 (95% CI: 0.560, 0.648) and 0.682 (95% CI: 0.607, 0.757) for the UK and Netherlands datasets. Conclusion Radiomic machine learning models were shown to have the potential to predict occult invasive cancer in women with DCIS across diverse settings. © RSNA, 2025 Supplemental material is available for this article.

Evaluating the Association Between Allostatic Load and Malignancy on Image-Guided Breast Biopsy.

Abstract Background Small tissue biopsies, particularly core needle biopsy samples, are the preferred method for oncology as they offer a less invasive way of obtaining tissue samples than traditional surgical resections. However, sequencing-based comprehensive genomic profiling (CGP) of these small tissues preserved as formalin-fixed, paraffin-embedded tissue (FFPET) samples remains technically challenging due to the limited tissue volume and often suboptimal quality of DNA extracted from these samples. The AVENIO Tumor Tissue CGP Automated Assay (for Research Use Only, not for use in diagnostic procedures) offers an automated, end-to-end solution for CGP of FFPET specimens. The assay’s tissue extraction method is designed to achieve high DNA yield and quality, which is crucial for analyzing samples with limited tissue volumes. This study assessed the performance of the AVENIO Tumor Tissue CGP Automated assay on these challenging core needle biopsy FFPE tumor tissue specimens. Methods A set of 70 unique FFPET samples originating from breast, lung, and prostate core needle biopsy procedures was processed in duplicates through the AVENIO Tumor Tissue CGP Automated Assay. FFPET blocks were collected from 3 collection sites to represent the various qualities of the samples. Four 10-micron-thick tissue curls were used as input for the assay to increase the input volume. Sequencing QC metrics were compared to evaluate the sample pass rates per collection site. The variants reported were compared within the replicates to assess the reproducibility of the assay. Results FFPET samples from core needle biopsy procedures typically have a smaller tissue volume than those from surgical resection. In this study, tissue volumes for the assay ranged from 0.06mm³ to 1.8mm³, with the smallest volume that met the 40ng DNA input requirement being 0.09mm³. A positive correlation was observed between the tissue volume and DNA yield. Samples from different collection sites showed distinct DNA quality resulting in different sample pass rates, likely due to variations in formalin fixation and specimen processing procedures. In core needle biopsies collected from Site A (breast and lung) and Site B (prostate), 97% (33/34) and 95% (38/40) of samples met the 40ng DNA input requirement, respectively; 100% (34/34) from Site A and 95% (38/40) from Site B passed overall sequencing QC. In contrast, collection Site C showed a substantially lower ratio of samples passed the DNA input at 38% (25/66) and a poor sample pass rate of 24.2% (16/66). Variants reported from the core needle biopsy samples that passed the sequencing QC presented high reproducibility with &amp;gt;90% overall positive call rate within replicates. Conclusion This study demonstrates that the AVENIO Tumor Tissue CGP Automated Assay can effectively process core needle biopsy FFPET specimens, achieving a high sample pass rate and consistent variant detections.

BackgroundConventional histopathological examination for breast core needle biopsy diagnosis is time-consuming and labor-intensive, leading to delayed medical treatments and increased psychological burden for patients. A rapid and reliable diagnostic method is needed to assist routine pathological diagnosis.MethodsWe developed a miniature mass spectrometry platform coupled with paper spray ionization (MiniMaP) for rapid breast cancer diagnosis. This platform enables direct molecular analysis of biopsy samples without sample preparation. A machine learning model was trained to differentiate benign and malignant samples based on molecular profiles. The platform’s performance was further evaluated in a 22-month multicenter validation study.ResultsHere we show that the machine learning model trained on molecular profiles achieves 88% accuracy in distinguishing breast cancer from benign samples. The model identifies 60 molecular features as potential biomarkers. Additionally, MiniMaP is implemented for on-site analysis in a hospital setting, enabling breast cancer diagnosis within 5 min. The platform maintains consistent accuracy (84%) across 540 biopsy samples over the 22-month validation period.ConclusionsOur results demonstrate that the MiniMaP platform enables rapid breast cancer diagnosis and maintains consistent performance in long-term multicenter validation. It holds promise for assisting clinical breast cancer diagnosis by providing instant diagnostic reports to support timely medical decisions and improve medical care.

Abstract Introduction: Cancer cells continue to replicate their DNA and survive mainly due to their unique ability to repair damaged DNA using alternate DNA repair pathways. For example, cancer cells with a deficiency in homologous recombination (HR) proteins (such as BRCA1) can repair their DNA by either relying on other highly expressed HR-related proteins (such as RAD51 or PARP1) or by using backup DNA repair mechanisms such as ALT-NHEJ. Alterations in DNA repair pathways commonly occur during breast cancer (BC) progression. For example, TNBCs have dysfunctional BRCA1/2 but express high levels of RAD51. Further, ER+BC employs ALT- NHEJ, HR, or BER to repair their DNA. The objective of this study was to identify FDA-approved non-cancer drug/s capable of inhibiting DNA repair in BC cells, thereby inhibiting their growth, with potential clinical benefits for BC patients. Methods: BC cells were treated with vehicle and FDA-approved drugs for 72 hours and were subjected to cell-titer Glo assay. The anti-tumor effect of imipramine alone and in combination with Olaparib and tamoxifen was validated using orthotopic xenograft mouse models. The effect of imipramine on DNA repair was determined by immunofluorescence using antibody against 53BP1, and functional DNA repair assays. Based on these results, a window of opportunity clinical trial was conducted to test the efficacy of imipramine in early-stage breast cancer patients. After having a breast core needle biopsy, 15 eligible patients with stage I-III breast cancer were enrolled in the trial and were treated with imipramine at a target dose of 200 mg PO daily for an average of 28 days. Patients were evaluated on day 7, day 14, day 21, and at the end of treatment for toxicity. The primary endpoint for the trial was the absolute change in the Ki67. IHC using an antibody against Ki67 was performed on core biopsy (pre-treatment) and tumor tissue after imipramine treatment. The secondary objectives of this trial were to further define the toxicity profile of imipramine. Results: Imipramine treatment significantly reduced the viability of TNBC and ER+ BC cells. Further, imipramine treatment inhibited the migration and invasion of BC cells. Systemic delivery of imipramine suppressed the growth of BC. Importantly, imipramine blocked the DNA repair capacity of BC cells by inhibiting the expression of DNA repair proteins including FOXM1 and RAD51. Notably, imipramine treatment improved the efficacy of Olapraib in TNBC and sensitized the tamoxifen response in endocrine-resistant ER+ BC cells. The clinical trial on 15 patients treated with imipramine showed a marked reduction in Ki67-positive cells in post-surgical tumor tissues compared to core needle biopsy tissues. Toxicity was mild with only grade 1 and 2 toxicities that included some instances of dizziness and nausea. There was no dose reduction, interruption, or treatment discontinuation. Discussion: Our preclinical and clinical studies showed that imipramine can block DNA repair in both TNBC and HR+ breast cancer. Short-term treatment with imipramine can effectively decrease Ki67 in breast cancer patients. Future clinical trials will involve combining imipramine with other regimens such as Olaparib for TNBC patients and elacestrant/CDK4/6 inhibitor for therapy-resistant ER+ breast cancer patients. Citation Format: Manjeet Rao, Arhan Rao, Santosh Timilsina, Subapriya Rajamanickam, Panneerdoss Subbarayalu, Ismail Jatoi, Yidong Chen, Kate Lathrop, Ratna Vadlamudi, Virginia Kaklamani. Imipramine: A Promising Therapeutic Regimen for Breast Cancer Patients [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2024; 2024 Dec 10-13; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(12 Suppl):Abstract nr P3-08-26.

To evaluate the impact of providing a loving-kindness meditation (LKM) intervention vs. a music intervention during core-needle breast biopsy (CNBB) on adherence to subsequent, clinically recommended breast cancer screening and surveillance. Women (N = 120) were randomly assigned to receive LKM, Music, or Usual Care during CNBB. Patients in the LKM or Music groups listened to audio recordings during CNBB and were provided recordings for home use. Utilization of subsequent recommended breast imaging was assessed via health record review for 18months into the breast cancer surveillance period. The sample was, on average, 53years old (SD = 12.4), partnered (55%), and employed (56%); 28% Black and 68% White. Adherence to recommended breast imaging post-biopsy was: 69% for Usual Care, 71% for Music, and 90% for LKM. Compared to Usual Care, there was no significant difference in adherence for the Music group (OR = 1.11, 95% CI [0.43, 2.89], p = 0.829), but the LKM group was 3.9 times more likely to be adherent (OR = 3.89, 95% CI [1.13, 13.41], p = 0.032). Comparisons between intervention arms showed adherence for the LKM group was 3.5 times higher than the Music group (OR = 3.50, 95% CI [1.02, 12.00], p = 0.046). Patterns of adherence were similar across women with an abnormal biopsy result and those with a benign result. A LKM intervention initiated during CNBB can have significant, positive impacts on women's adherence to subsequent recommended breast imaging. Providing patients with LKM during CNBB is an easily disseminated approach that could improve adherence to breast cancer screening and surveillance after CNBB.

Digital morphometry illustrates a relationship between percentage of ductal carcinoma in-situ in breast needle core biopsy and margin status at lumpectomy

236 Comparative Histological Features of Phyllodes Tumor and Fibroadenoma in Breast Core Needle Biopsies: A Systematic Review and Meta-Analysis

Tissue stiffness, dictated by organisation of interstitial fibrillar collagens, increases breast cancer risk and contributes to cancer progression. Tamoxifen is a standard treatment for receptor-positive breast cancer and is also aproved for primary prevention. We investigated the effect of tamoxifen and its main metabolites on the breast tissue collagen organisation as a proxy for stiffness and explored the relationship between mammographic density (MD) and collagen organisation. This sub-study of the double-blinded dose-determination trial, KARISMA, included 83 healthy women randomised to 6months of 20, 10, 5, 2.5, and 1mg of tamoxifen or placebo. Ultrasound-guided core-needle breast biopsies collected before and after treatment were evaluated for collagen organisation by polarised light microscopy. Tamoxifen reduced the amount of organised collagen and overall organisation, reflected by a shift from heavily crosslinked thick fibres to thinner, less crosslinked fibres. Collagen remodelling correlated with plasma concentrations of tamoxifen metabolites. MD change was not associated with changes in amount of organised collagen but was correlated with less crosslinking in premenopausal women. In this study of healthy women, tamoxifen decreased the overall organisation of fibrillar collagens, and consequently, the breast tissue stiffness. These stromal alterations may play a role in the well-established preventive and therapeutic effects of tamoxifen. Trial registration ClinicalTrials.gov ID: NCT03346200. Registered November 1st, 2017. Retrospectively registered.

In the one-stop breast clinic setting, breast cytology traditionally provides immediate diagnosis of carcinoma. Fluorescence confocal microscopy (FCM) is an emerging optical technique enabling ex vivo analysis of breast biopsies in real-time. This study represents the first proof of concept for integrating FCM imaging into the routine workflow of breast core needle biopsies (CNB) at Gustave Roussy's one-stop breast clinic. Fifty women with breast masses underwent consecutive enrollment. Biopsies were stained with acridine orange and fast green, followed by imaging using the Vivascope 2500M-G4 (FCM). Interpretation was conducted by two pathologists in real time (PT1) or postoperatively (PT2). Concordance with definitive histology, the duration of the FCM protocol, and its impact on conventional histopathology, immunohistochemistry, and FISH analyses were evaluated. In our study of 50 biopsies, a concordant diagnosis of malignancy was performed using FCM on the malignant cases at definitive histology in 93.5% (29/31 cases) and in 90.3% (28/31 cases) according to PT1 and PT2, respectively. When the FCM suspicious cases were added, FCM identified 100% (31/31 cases) and 96.7% (30/31 cases) of the malignant cases according to PT1 and PT2, respectively. A notable false positive case was identified as a complex sclerosing lesion. The median time for sample preparation (including tissue reception) was 5 min, while the median time for imaging acquisition with interpretation was 3 min for PT1, but 1 min required for interpretation alone by PT2. Histopathological alterations were not more prevalent in FCM-imaged biopsies compared to conventionally treated biopsies. The immunophenotyping and molecular assessment of tissue were preserved after FCM protocol. FCM shows promise as a new histological method for the immediate diagnosis of breast carcinoma on core needle biopsies in a one-stop clinic setting, while also preserving tissue specimens for final histology.

Mesenchymal and spindle cell tumors of the breast represent a broad and heterogeneous group of lesions that may be sampled on core needle biopsy or surgical excision. Mesenchymal lesions unique to the breast are those that derive from the specialized breast myofibroblast, such as mammary myofibroblastoma and pseudoangiomatous stromal hyperplasia. However, any mesenchymal lesion arising in extramammary soft tissue may also arise in the breast, including fibroblastic, peripheral nerve sheath, adipocytic, and vascular lesions. The spindle cell lesions pose the greatest diagnostic challenge, due to the significant radiographic, morphologic, and immunophenotypic overlap within the category of mesenchymal lesions and more broadly with other nonmesenchymal breast lesions. The distinction is particularly challenging on the limited material of breast core needle biopsies, and caution should be taken before definitively classifying a breast spindle cell lesion on core needle biopsy to avoid unnecessary treatment if misdiagnosed. Consideration of a wide differential diagnosis, adequate sampling of a resection specimen, use of a targeted immunopanel, and selective use of molecular assays are essential steps for accurate classification of mesenchymal lesions in the breast. This review covers the clinical, histologic, and immunophenotypic features of mesenchymal tumors of the breast, with a special emphasis on the differential diagnoses unique to the breast and challenges encountered on breast core needle biopsy.

The Global Reading Room: Performing a Core Needle Breast Biopsy.

An 80-year-old lady presented with lump Left breast of 8 months duration. Clinically was aT4b lesion, sonomammogram showed BIRADS V lesion and core needle breast biopsy features were suggestive of metaplastic carcinoma breast of adenosquamous type, ER, PR-Positive, Her2Neu-Negative. Patient received preoperative hormonal therapy followed by modified radical mastectomy and postoperative adjuvant chemotherapy and hormonal therapy. Post operative patient showed good clinical recovery and was recurrence free at 6 months follow up although patient had all the poor prognostic factors with large size, LN involvement and high Ki 67. This article is a rare example of metaplastic breast carcinoma presenting in geriatric age group and showing good recovery despite presence of all poor prognostic factors. Hence this report is to enlighten the medical caregivers about the existence of this rare entity and challenges involved in management of this entity.

BackgroundComplications after percutaneous breast biopsy are infrequent but may include hematoma, pseudoaneurysm formation, persistent pain, infection, delayed wound healing, vasovagal reaction, hemothorax, pneumothorax, and neoplastic seeding. The risk factors include tumor factors (size, location, vascularity), procedure-related factors (needle diameter, number of biopsies), and interventionist experience. There has been no previous report of a fatal complication resulting from percutaneous breast biopsy.Case presentationWe report a 54-year-old Asian woman with a 3 cm BI-RADS® 4B left breast mass in the lower-inner quadrant who was biopsied by a 16 G needle under ultrasound guidance at a province hospital. She experienced dizziness and near-syncope afterward. The initial evaluation showed evidence of cardiac tamponade with hemodynamic instability. She underwent urgent subxiphoid pericardial window and was transferred to our facility. We brought her directly to the operating room to perform an explorative median sternotomy and found a 0.2 cm hole in the right ventricle. The injured site was successfully repaired without cardiopulmonary bypass. Postoperative echocardiography demonstrated mild right ventricular dysfunction without evidence of septal or valvular injury. She survived with no significant complications.DiscussionThis case might be the first report of a life-threatening complication related to percutaneous breast core-needle biopsy. The rapid pericardial release is key to the survival of cardiac tamponade. The patient subsequently required cardiac repair and monitoring to avoid long-term complications. In this report, we suggested a safe biopsy method, complications recognition, and appropriate management of penetrating cardiac injury.ConclusionPenetrating cardiac injury resulting from percutaneous breast biopsy is extremely rare but can occur. A biopsy must be done cautiously, and worst-case management should promptly be considered.

De-escalating indications for excision when breast core needle biopsy returns fibroepithelial lesion—not further characterized

e15150 Background: The availability of multiple therapeutic options for breast cancer patients with varying levels of protein expression necessitates precise and standardized HER2 scoring. This study explored the clinical utility of AI-aided HER2 scoring of whole-slide digital images by pathologists in breast core needle biopsies and excisions. Methods: The study included patients (n=764) with multiple subtypes of invasive breast cancer from 3 US reference laboratories and 1 academic medical center. The non-interventional two-arm multi-reader study retrospectively compared manual digital vs. AI-aided HER2 scoring of 8 pathologists. The fully automated HER2 AI solution detects the invasive tumor area and then classifies the tumor cells based on staining pattern based and the 2023 ASCO/CAP guidelines to output slide-level HER2 score. Both study arms were compared to reference ground truth (GT) established by the consensus of two breast subspecialists, ground truthers (GTer), who reviewed the slides digitally. One site recorded the time taken for HER2 scoring of both arms to determine the efficacy of the HER2 AI solution. Results: The initial interobserver agreement among expert GT pathologists for each HER2 score, 0, 1+, 2+, 3+, were 83%, 63.8%, 46%, and 92.6, respectively. At the clinically meaningful cut-offs, the reader pathologists’ performance improved with the AI support. At the 0 vs. 1+/2+/3+ and 0/1+ vs 2+/3+ clinical cutoffs, the readers' accuracy was 86.3% vs 88.6% and 93.7%, 93.8% with and without AI support, respectively. The AI use contributed to approximately 12%-time savings for the readers at the medical center. The AI solution demonstrated high accuracy for HER2 scoring, with 89.2% agreement with GT for 0 vs 1+/2+/3+ scores and 93.1% for 0/1+ vs 2+/3+ cutoff. The results will be updated in the final submission with the additional site data. The reader feedback survey regarding the solution’s usability will also be presented. Conclusions: The pathologists demonstrated improvements in consistency, evidenced by inter-reader agreement and accuracy with the aid of the AI. The AI solution can improve efficiency toward accurate HER2 scoring. [Table: see text]

Abstract A 38-year-old breastfeeding female with no family history of breast or gynecological cancer presented to her PCP with a 4-month history of galactorrhea and enlarged left-sided breast mass. On physical exam, a 4-inch round complex, nonmobile, non-tender mass in the left breast and bloody-to-pink discharge from the nipple was present on the exam. Diagnostic mammogram and US revealed BIRADS 5, microcalcifications consistent with DCIS, 4-cm mass, with a positive lymph node (LN), and needle core biopsy of both breast and LN, showed DCIS and metastatic carcinoma, respectively. Further workup did not show distant or skeletal metastatic disease. Therefore, a diagnosis was made, and the patient was provided a clinical-stage cT3, cN2, cM0, ER+, PR-, and HER2+. The patient completed neoadjuvant therapy with TCHP and underwent a left lumpectomy with sentinel LN biopsy. Additionally, pathology diagnosis showed scant residual DCIS (10mm) and no metastatic disease in the LN. After that, the patient completed adjuvant radiotherapy and was placed on adjuvant therapy with trastuzumab and pertuzumab. In conclusion, any breast abnormality reported by a pregnant or breastfeeding woman should not be neglected and assumed that it is a regular and physiological change until proven otherwise. Future proposals include guidelines for managing abnormal breast findings during pregnancy. Citation Format: Jesus Flores Banda, Kavitha Donthireddy. Delay in Diagnosis of Locally Advanced Breast Cancer during Lactation “Case Report” [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 PO1-20-11.