Abstract A004: Development and validation of a convolutional neural network to identify ductal carcinoma in situ in lumpectomy margins using wide field optical coherence tomography

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.

Abstract 458: Development and validation of convolutional neural network to identify regions of interest in lumpectomy margins using optical coherence tomography

Background/Objective: Optical coherence tomography (OCT) is the optical analog of high-frequency ultrasound and produces real-time, high-resolution images up to 2 mm deep. Multi-reader studies of OCT have shown differentiation of normal parenchyma from neoplasms, including DCIS and cancers, with >85% sensitivity and specificity. Intraoperative evaluation of breast lumpectomy margins (LMs) with OCT may help achieve negative margins at primary surgery and avoid re-excision. Artificial Intelligence can be trained to spot regions of interest (ROI) in OCT LM images suspicious for malignancy. The purpose of this study was to develop and validate an automated convolutional neural network (CNN) to screen OCT LM images for ROIs.

Methods: Following IRB approval, LMs from 126 patients with ductal malignancy were OCT imaged. Images were compared to corresponding permanent histology and annotated by 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 “suspicious” or “non-suspicious” for malignancy. A weighted loss function was used to balance the training data for non-suspicious vs. suspicious images and to tune sensitivity and specificity. Once trained and weighted, the CNN was tested in a prospective study using OCT images of 29 LMs from 29 patients with biopsy-proven ductal carcinoma in situ (DCIS), invasive ductal carcinoma (IDC), or both. CNN results were compared to permanent histology.

Results: The patient population was 61.5 ± 7.3 years old, 100% female, with Stage 0-1 disease. Disease included IDC (n=20), invasive lobular (n=2), DCIS (n=27), mixed (n=74), atypical ductal hyperplasia (n=24), as well as benign findings including atypical lobular hyperplasia (n=19), lymphatic invasion (n=13), lobular carcinoma in situ (n=12), usual ductal hyperplasia (n=35), and duct ectasia (n=17). Following primary surgery, LMs were scanned using OCT and images were CNN analyzed. Approximately 1.9 M OCT ROIs were assessed, identifying 101,099 suspicious ROIs. Three hundred and eighty-four (384) ROIs were correctly identified, yielding a 70% true positive and 5.2% false positive rate with 70% sensitivity and 96% specificity. The receiver operating curve is shown below.

Conclusions: Automated analysis of OCT images using a trained CNN to identify ROIs suspicious for DCIS or IDC in LMs is feasible, demonstrating high concordance with permanent pathology. These findings indicate the utility of AI for screening OCT images with potential utilization for intraoperative evaluation of LMs. A pivotal prospective clinical trial will be necessary to evaluate breast specimens in real time to determine if this application may improve re-excision rates in lumpectomy.

Citation Format: David Rempel, Andrew Berkeley, Chandandeep Nagi, Vladimir Pekar, Margaret Burns, Beryl Augustine, Alia Nazarullah, Ismail Jatoi, Kelly K. Hunt, Alastair Thompson, Savitri Krishnamurthy. Development and validation of convolutional neural network to identify regions of interest in lumpectomy margins using optical coherence tomography [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 458.

Role of Kip2 during early mitosis - impact on spindle pole body separation and chromosome capture

Mitotic spindle dynamics are regulated during the cell cycle by microtubule motor proteins. In Saccharomyces cerevisiae, one such protein is Kip2p, a plus-end motor that regulates the polymerization and stability of cytoplasmic microtubules (cMTs). Kip2p levels are regulated during the cell cycle, and its overexpression leads to the formation of hyper-elongated cMTs. To investigate the significance of varying Kip2p levels during the cell cycle and the hyper-elongated cMTs, we overexpressed KIP2 in the G1 phase and examined the effects on the separation of spindle pole bodies (SPBs) and chromosome segregation. Our results show that failure to regulate the cMT lengths during G1-S phase prevents the separation of SPBs. This, in turn, affects chromosome capture and leads to the activation of spindle assembly checkpoint (SAC) and causes mitotic arrest. These defects could be rescued by either the inactivation of checkpoint components or by co-overexpression of CIN8, which encodes a motor protein that elongates inter-polar microtubules (ipMTs). Hence, we propose that the maintenance of Kip2p level and cMT lengths during early cell division is important to ensure coordination between SPB separation and chromosome capture by kinetochore microtubules (kMTs).

Timely Endocytosis of Cytokinetic Enzymes Prevents Premature Spindle Breakage during Mitotic Exit

Cytokinesis requires the spatio-temporal coordination of membrane deposition and primary septum (PS) formation at the division site to drive acto-myosin ring (AMR) constriction. It has been demonstrated that AMR constriction invariably occurs only after the mitotic spindle disassembly. It has also been established that Chitin Synthase II (Chs2p) neck localization precedes mitotic spindle disassembly during mitotic exit. As AMR constriction depends upon PS formation, the question arises as to how chitin deposition is regulated so as to prevent premature AMR constriction and mitotic spindle breakage. In this study, we propose that cells regulate the coordination between spindle disassembly and AMR constriction via timely endocytosis of cytokinetic enzymes, Chs2p, Chs3p, and Fks1p. Inhibition of endocytosis leads to over accumulation of cytokinetic enzymes during mitotic exit, which accelerates the constriction of the AMR, and causes spindle breakage that eventually could contribute to monopolar spindle formation in the subsequent round of cell division. Intriguingly, the mitotic spindle breakage observed in endocytosis mutants can be rescued either by deleting or inhibiting the activities of, CHS2, CHS3 and FKS1, which are involved in septum formation. The findings from our study highlight the importance of timely endocytosis of cytokinetic enzymes at the division site in safeguarding mitotic spindle integrity during mitotic exit.

The cytokinesis machinery that is required for physical separation of mother-daughter cells during mitosis is highly conserved from yeast to humans. In budding yeast, cytokinesis is achieved via timely delivery of cytokinetic enzymes to the division site that eventually triggers the constriction of AMR. It has been previously demonstrated that cytokinesis invariably occurs after the disassembly of the mitotic spindle. Intriguingly, Chs2p that is responsible for laying down the primary septum has been shown to localize to the division site before mitotic spindle disassembly. In this study, we show that mitotic spindle integrity upon sister chromatid separation is dependent on the continuous endocytosis of cytokinetic enzymes. Failure in the internalization of cytokinetic proteins during mitotic exit causes premature AMR constriction that eventually contributes to the shearing of mitotic spindle. Consequently, cells fail to re-establish a bipolar spindle in the subsequent round of cell division cycle. Our findings provide insights into how the levels of secreted proteins at the division site impacts cytokinesis. We believe this regulation mechanism might be conserved in higher eukaryotic cells as a secreted protein, hemicentin, has been shown recently to be involved in regulating cytokinesis in both Caenorhabditis elegans and mouse embryos.