Search

Purpose: To develop and validate a convolutional neural network (CNN) to identify regions of interest (ROIs) suspicious for ductal carcinoma in situ (DCIS) and residual malignancy in lumpectomy margins using wide-field optical coherence tomography (WF-OCT). Background: WF-OCT is the optical analog of high-frequency ultrasound and produces high-resolution intraoperative imaging in real time, with a tissue penetration depth up to 2 mm. Multi-reader studies of WF-OCT have demonstrated the ability to differentiate normal breast parenchyma from neoplasms with greater than 85% sensitivity and specificity. Intraoperative evaluation of lumpectomy specimens using WF-OCT may aid in achieving negative margins at the time of primary surgery and avoid re-excisions. CNNs, a form of artificial intelligence (AI), can be trained to spot ROIs in WF-OCT images of margins suspicious for DCIS and, more generally, residual malignancy. Methods: Lumpectomy margins from 126 patients with ductal malignancy were imaged using WF-OCT, compared to permanent histology (PH), and annotated by board-certified breast pathologists to create a training set of 25,000 control ROIs. A CNN algorithm was developed with 3 convolutional layers, a 3x3 kernel, and 3 fully connected layers to perform binary classification of images as either “suspicious” or “non-suspicious” for malignancy. A weighted loss function was implemented to balance the training data available for non-suspicious vs. suspicious images and to tune sensitivity and specificity. Once trained and properly weighted, the CNN was tested in a prospective study using WF-OCT images of margins from 29 lumpectomy specimens from 29 patients with biopsy-proven DCIS, invasive ductal carcinoma (IDC), or both. The CNN results were compared to PH. Results: Patients were 61.5 ± 7.3 years old, 100% female, with Stage 0-1 disease. Disease types included DCIS (n=27), atypical ductal hyperplasia (n=24), IDC (n=20), invasive lobular carcinoma (n=2), mixed (n=74), and benign findings including usual ductal hyperplasia (n=35), atypical lobular hyperplasia (n=19), duct ectasia (n=17), lymphatic invasion (n=13), and lobular carcinoma in situ (n=12). Following primary surgery, fresh margins were scanned using WF-OCT and approximately 1.9M ROIs were analyzed by the CNN, yielding 15,136 as suspicious for malignancy. Overall, four hundred and ten (410) ROIs were correctly identified, yielding a 74% true positive and 0.8% false positive detection rate; sensitivity and specificity were 74.4% and 99.2%, respectively. Specific to DCIS, the CNN demonstrated a 73% true and 0.5% false positive rate; sensitivity and specificity were 73.0% and 99.5%, respectively. Conclusions: Automated analysis of WF-OCT images of lumpectomy specimens, using a trained CNN to identify ROIs suspicious for malignancy is feasible, demonstrating high concordance with PH. Specific to DCIS, the CNN demonstrated equivalent utility with a lower false positive rate. A prospective trial is needed to evaluate specimens in real time to determine improvement in re-excision rates. Citation Format: David Rempel, Andrew Berkeley, Alastair Thompson, Savitri Krishnamurthy, Beryl Augustine, Kelly Hunt, Ismail Jatoi, Alia Nazarullah, Chandandeep Nagi, Yanir Levy. Development and validation of a convolutional neural network to identify ductal carcinoma in situ in lumpectomy margins using wide field optical coherence tomography [abstract]. In: Proceedings of the AACR Special Conference on Rethinking DCIS: An Opportunity for Prevention?; 2022 Sep 8-11; Philadelphia, PA. Philadelphia (PA): AACR; Can Prev Res 2022;15(12 Suppl_1): Abstract nr A004.

Introduction: Treatment options for women diagnosed with DCIS require careful consideration of the potential risks and benefits. An interactive decision support tool (DST) was developed to provide information about these options, including their potential long-term risk. The DST was implemented through the website www.dcisoptions.org in collaboration with the AFT-25 Comparing an Operation to Monitoring, with or without Endocrine Therapy (COMET), for low-risk DCIS study. Methods: The DST provides personalized prediction of the potential clinical impact of six different treatment options over a 10-year period. Women were asked to select one or more option, and to complete two surveys - one prior to interacting with the DST and one following interaction. Chi-square tests were used to compare the distribution of age group and DCIS grade among women who completed both surveys and those who completed the pre-tool survey only. Mean age was compared using the t-test and median age was compared using the Wilcoxon-Mann-Whitney test. The signed-rank test was used to compare the median age. The cohort that answered both surveys was analyzed for potential differences in response (pre- versus post-tool). The McNemar test was used to compare percentage distributions and the paired t-test was used to compare mean responses for questions using the Likert scale. A signed rank test was used to compare median changes from pre- to post-tool. Statistical significance was defined as P Citation Format: Thomas Lynch, Ann Partridge, E. Shelley Hwang, Alastair Thompson, Elizabeth Frank, Donna Pinto, Deborah Collyar, Desiree Basila, Terry Hyslop, Marc Ryser, Anna Weiss, Anna Rapperport, Rinaa Punglia, Elissa Ozanne. Effectiveness of an online decision support tool in communicating information about treatment options and related risks for ductal carcinoma in situ (DCIS) [abstract]. In: Proceedings of the AACR Special Conference on Rethinking DCIS: An Opportunity for Prevention?; 2022 Sep 8-11; Philadelphia, PA. Philadelphia (PA): AACR; Can Prev Res 2022;15(12 Suppl_1): Abstract nr A011.

Introduction: Ductal carcinoma in situ (DCIS) is considered a non-obligate precursor of invasive ductal carcinoma. With the aim of preventing a subsequent invasive cancer, all DCIS lesions are currently treated with surgical excision often supplemented with radiotherapy (RT). To prevent DCIS over- or undertreatment, a reliable marker of DCIS invasiveness risk is urgently needed. Methods: We studied two large DCIS cohorts: the Sloane cohort, a prospective breast screening cohort from the UK (median follow-up of 11 years), and a Dutch population-based cohort (NKI, median follow-up of 13 years). FFPE tissue specimens from patients with pure primary DCIS after breast-conserving surgery (BCS) +/- RT that did develop a subsequent ipsilateral event (DCIS or invasive) were considered as cases, whereas patients that did not develop any form of recurrence up to the last follow-up or death were considered as controls. We performed copy number analysis (CNA) and RNAseq analysis on 229 cases (80 DCIS only recurrences) and 344 controls. Results: DCIS was classified into the PAM50 subtypes using RNAseq data which revealed an enrichment of luminal A phenotype in DCIS that did not recur (P = 0.01, Fisher Exact test). No single copy number aberration was more common in cases compared to controls. RNAseq data did not reveal any genes significantly over/under-expressed in cases versus controls after FDR correction. However, by limiting the analysis to samples that had not had RT and excluding pure DCIS recurrences, we could develop a penalized Cox model from RNAseq data. The model was trained on weighted samples (to correct for the biased sampling of the case-control dataset) from the NKI series with double loop cross-validation. The genes were selected using the Elastic net framework of penalization. Using this predicted hazard ratio, the samples were split into high, medium, and low-risk quantiles, with a recurrence risk of 23%, 7% and 2%, respectively at 5 years (p = 10-10, Wald test). The NKI-trained predictor was independently validated in the Sloane No RT no DCIS recurrence cohort (p = 0.02, Wald test). GSEA analysis revealed proliferation hallmarks enriched in the recurrence predictor (FDR = 0.058). The RNAseq predictor was more predictive of recurrence than PAM50, clinical features (Grade, Her2 and ER) and the 12-gene Oncotype DCIS score (p < 0.001, permutation test using the Wald statistic) in both the NKI and Sloane series. Conclusion: Genomic profiling of two independent series of DCIS with outcome data did not reveal any clear associations with recurrence until analysis was limited to a set of samples who had not had radiotherapy and DCIS recurrences were excluded. We then identified an RNAseq-based classifier that could differentiate primary DCIS in low-, medium-, and high-risk groups, and validated it in an independent cohort. This classifier, if validated in other datasets, will allow us to identify women who do not need intensive treatment for their DCIS. Citation Format: Maria Roman Escorza, Michael Sheinman, Tycho Bismeijer, Ahmed A. Ahmed, Vandna Shah, Jeffrey R. Marks, Lorraine M. King, Anargyros Megalios, Lindy L. Visser, Marlous Hoogstrat, Helen R. Davies, Tapsi Kumar, Deborah Collyar, Hilary Stobart, Sarah Pinder, Nicholas N. Navin, Andrew Futreal, Serena Nik-Zainal, E. Shelley Hwang, Esther H. Lips, Alastair Thompson, Lodewyk F.A. Wessels, Jelle Wesseling, Elinor J. Sawyer. Genomic predictor can discriminate between high- and low-risk DCIS [abstract]. In: Proceedings of the AACR Special Conference on Rethinking DCIS: An Opportunity for Prevention?; 2022 Sep 8-11; Philadelphia, PA. Philadelphia (PA): AACR; Can Prev Res 2022;15(12 Suppl_1): Abstract nr PR002.

Ductal carcinoma in situ (DCIS) is early-stage non-malignant breast cancer that tumor cells are confined to the lumens of ducts. Over 50,000 DCIS patients are diagnosed each year in the United States, however, less than half of DCIS will develop into invasive breast cancer (IBC), suggesting a risk of overtreatment for some DCIS patients. A comprehensive investigation of the molecular mechanisms of DCIS initiation and progression is urgently needed that can facilitate us stratifying the risk of DCIS invasion and design better intervention approaches. In this study, we conducted single-cell RNA-seq and spatial transcriptomics (ST) on DCIS and IBC samples (most estrogen receptor positive). We first inferred copy number aberrations (CNA) in these samples and found that DCIS and IBC shared the most copy number events while only marginal differences were identified. Tumor CNA subclones colocalized in different ductal regions from the ST data. Further, we applied a sample-wise non-negative matrix factorization (NMF) to identify robust gene expression metaprograms across tumor samples. On the ST data, we found these metaprograms also displayed distinct spatial patterns. For non-tumor cells in the TME, we sub-clustering them into cell states and identified that some cell states showed a gradual change along breast cancer initiation and progression. To recapitulate the tumor ecosystems, we also conducted an ecotype analysis in DCIS samples and identified that some ecotypes showed an increasing/decreasing trend in IBC patients. Further, tumor and TME ecotypes also showed spatially colocalizations based on our ST data. In summary, these results demonstrated that genomic signatures could hardly predict the DCIS progression while tumor metaprograms and TME ecotypes might serve as a potential risk stratification approach for DCIS patients. Citation Format: Runmin Wei, Siyuan He, Shanshan Bai, Emi Sei, Min Hu, Chandandeep Nagi, Brian Menegaz, Huma Javaid, Jelle Wesseling, Andrew Futreal, Alastair Thompson, Savitri Krishnamurthy, Nicholas Navin. A single-cell and spatial investigation of tumor and TME for DCIS [abstract]. In: Proceedings of the AACR Special Conference on Rethinking DCIS: An Opportunity for Prevention?; 2022 Sep 8-11; Philadelphia, PA. Philadelphia (PA): AACR; Can Prev Res 2022;15(12 Suppl_1): Abstract nr IA013.