BACKGROUND:Ongoing active monitoring (AM) trials for women with ductal carcinoma in situ (DCIS) are investigating the safety and efficacy of monitoring DCIS lesions vs the current standard of care (surgical treatment). The frequency of upgrade in women undergoing AM for DCIS remains unknown. OBJECTIVE:To evaluate the frequency of upgrade of DCIS at core-needle biopsy to invasive carcinoma at surgical excision among women who meet eligibility criteria for AM trials. METHODS:A retrospective review between 2010 and 2023 was performed of women at an National Cancer Institute-designated comprehensive cancer center with a diagnosis of DCIS at core-needle biopsy who underwent subsequent surgical excision. Medical records were reviewed for clinical presentation, imaging findings, core biopsy, and final surgical pathology. Each patient was evaluated for AM trial eligibility based on published criteria for the LORD, LORIS, and COMET trials. Fisher's exact test compared proportions, with a P-value <.05 considered statistically significant. RESULTS:Of 264 women, 10/264 (3.8%) were eligible for the LORD trial, 24/264 (9.1%) for the LORIS trial, and 64/264 (24.2%) for the COMET trial. Invasive carcinoma was found at surgical excision in 1/10 (10%) patients eligible for the LORD trial, 2/24 (8.3%) for the LORIS trial, and 9/64 (14.1%) for the COMET trial. All occult invasive carcinomas detected at surgical excision in trial-eligible patients were node-negative, with a median size of invasive cancer measuring 3.5 mm (interquartile range, 1-7 mm). CONCLUSION:A subset of women who meet eligibility criteria for DCIS AM trials are at risk for occult invasive carcinoma, with frequency of upgrade ranging from 8% to 14%. CLINICAL IMPACT:More precise criteria and predictive biomarkers are needed to better stratify DCIS lesions and exclude women harboring invasive carcinomas from AM regimens.

OBJECTIVE:To determine if quantitative volumetric habitat concentration analysis of triple negative breast cancer (TNBC) on pre-treatment MRI correlates with neoadjuvant treatment response in patients treated with combination Talimogene Laherparepvec (TVEC) neoadjuvant immunotherapy and chemotherapy (NAIC). METHODS:Patients with TNBC in a single institution phase I/II trial from 5/2017-9/2020 underwent pre-treatment breast MRI followed by ultrasound-guided intratumoral TVEC injections and NAC prior to surgery. Pre-treatment MRIs were evaluated quantitatively using functional tumor volume (FTV) assessment and temporal voxel intensity categorization (high vs low plus phase of peak) to establish percentage habitat concentrations (%HC) for each quantitative method. These were correlated with pathologic response at surgery. Statistical analyses were performed using Mann Whitney U and comparison of proportions tests, with p < 0.05 considered statistically significant. RESULTS:Twenty-five female patients, aged 32-66 (avg 49), were included. Average %FTV and %High-Enhancement Volume (HEV) was 75.7 % and 87.1 %, respectively. Twelve patients (48 %) achieved pCR. On average, patients achieving pCR had higher %FTV (84.8 % vs 67.4 %, p = 0.022) and %HEV (93.3 % vs 81.3 %, p = 0.010). Patients with %HC above average for FTV and HEV also had lower average percent tumor cellularity (TC, 1 and 1.1 % vs 14.3 and 17.1 %, p = 0.023 and 0.003, respectively). Indeed, tumors with above average %FTV and %HEV achieved pCR in 71 % (10/14) and 69 % (11/16), respectively. In contrast, those below average achieved pCR in only 18 % (2/11) and 11 % (1/9), with p = 0.008 and 0.006, respectively. CONCLUSION:Above-average concentration of functional tumor/high enhancement voxels within tumors before NAIC correlates with higher pCR rates and lower %TC at surgery.

Background and purpose Information in multiparametric Magnetic Resonance (mpMR) images is relatable to voxel-level tumor response to Radiation Treatment (RT). We have investigated a deep learning framework to predict (i) post-treatment mpMR images from pre-treatment mpMR images and the dose map (“forward models”), and, (ii) the RT dose map that will produce prescribed changes within the Gross Tumor Volume (GTV) on post-treatment mpMR images (“inverse model”), in Breast Cancer Metastases to the Brain (BCMB) treated with Stereotactic Radiosurgery (SRS). Materials and methods Local outcomes, planning computed tomography (CT) images, dose maps, and pre-treatment and post-treatment Apparent Diffusion Coefficient of water (ADC) maps, T1-weighted unenhanced (T1w) and contrast-enhanced (T1wCE), T2-weighted (T2w) and Fluid-Attenuated Inversion Recovery (FLAIR) mpMR images were curated from 39 BCMB patients. mpMR images were co-registered to the planning CT and intensity-calibrated. A 2D pix2pix architecture was used to train 5 forward models (ADC, T2w, FLAIR, T1w, T1wCE) and 1 inverse model on 1940 slices from 18 BCMB patients, and tested on 437 slices from another 9 BCMB patients. Results Root Mean Square Percent Error (RMSPE) within the GTV between predicted and ground-truth post-RT images for the 5 forward models, in 136 test slices containing GTV, were (mean ± SD) 0.12 ± 0.044 (ADC), 0.14 ± 0.066 (T2w), 0.08 ± 0.038 (T1w), 0.13 ± 0.058 (T1wCE), and 0.09 ± 0.056 (FLAIR). RMSPE within the GTV on the same 136 test slices, between the predicted and ground-truth dose maps, was 0.37 ± 0.20 for the inverse model. Conclusions A deep learning-based approach for radiologic outcome-optimized dose planning in SRS of BCMB has been demonstrated.

Purpose: To determine whether time-dependent deep learning models can outperform single time point models in predicting preoperative upgrade of ductal carcinoma in situ (DCIS) to invasive malignancy at dynamic contrast-enhanced (DCE) breast MRI without a lesion segmentation prerequisite. Materials and Methods: In this exploratory study, 154 cases of biopsy-proven DCIS (25 upgraded at surgery and 129 not upgraded) were selected consecutively from a retrospective cohort of preoperative DCE MRI in women with a mean age of 59 years at time of diagnosis from 2012 to 2022. Binary classification was implemented with convolutional neural network (CNN)-long short-term memory (LSTM) architectures benchmarked against traditional CNNs without manual segmentation of the lesions. Combinatorial performance analysis of ResNet50 versus VGG16-based models was performed with each contrast phase. Binary classification area under the receiver operating characteristic curve (AUC) was reported. Results: VGG16-based models consistently provided better holdout test AUCs than did ResNet50 in CNN and CNN-LSTM studies (multiphase test AUC, 0.67 vs 0.59, respectively, for CNN models [P P = .04] and 0.73 vs 0.62 for CNN-LSTM models [P P = .008]). The time-dependent model (CNN-LSTM) provided a better multiphase test AUC over single time point (CNN) models (0.73 vs 0.67; P = .04). Conclusion: Compared with single time point architectures, sequential deep learning algorithms using preoperative DCE MRI improved prediction of DCIS lesions upgraded to invasive malignancy without the need for lesion segmentation.

A large body of evidence supports the use of adjuvant partial breast irradiation (PBI) in the management of early-stage hormone receptor–positive (HR+) breast cancer (BrCa).1 Multiple randomized controlled trials demonstrated equivalent efficacy, similar rates of toxicity, and improved patient convenience compared with conventional whole-breast radiation therapy (WBRT).2-4

Preclinical genetically engineered mouse models (GEMMs) of lung adenocarcinoma are invaluable for investigating molecular drivers of tumor formation, progression, and therapeutic resistance. However, histological analysis of these GEMMs requires significant time and training to ensure accuracy and consistency. To achieve a more objective and standardized analysis, we used machine learning to create GLASS-AI, a histological image analysis tool that the broader cancer research community can utilize to grade, segment, and analyze tumors in preclinical models of lung adenocarcinoma. GLASS-AI demonstrates strong agreement with expert human raters while uncovering a significant degree of unreported intratumor heterogeneity. Integrating immunohistochemical staining with high-resolution grade analysis by GLASS-AI identified dysregulation of Mapk/Erk signaling in high-grade lung adenocarcinomas and locally advanced tumor regions. Our work demonstrates the benefit of employing GLASS-AI in preclinical lung adenocarcinoma models and the power of integrating machine learning and molecular biology techniques for studying the molecular pathways that underlie cancer progression.

We report domain knowledge-based rules for assigning voxels in brain multiparametric MRI (mpMRI) to distinct tissuetypes based on their appearance on Apparent Diffusion Coefficient of water (ADC) maps, T1-weighted unenhanced and contrast-enhanced, T2-weighted, and Fluid-Attenuated Inversion Recovery images. The development dataset comprised mpMRI of 18 participants with preoperative high-grade glioma (HGG), recurrent HGG (rHGG), and brain metastases. External validation was performed on mpMRI of 235 HGG participants in the BraTS 2020 training dataset. The treatment dataset comprised serial mpMRI of 32 participants (total 231 scan dates) in a clinical trial of immunoradiotherapy in rHGG (NCT02313272). Pixel intensity-based rules for segmenting contrast-enhancing tumor (CE), hemorrhage, Fluid, non-enhancing tumor (Edema1), and leukoaraiosis (Edema2) were identified on calibrated, co-registered mpMRI images in the development dataset. On validation, rule-based CE and High FLAIR (Edema1 + Edema2) volumes were significantly correlated with ground truth volumes of enhancing tumor (R = 0.85;p < 0.001) and peritumoral edema (R = 0.87;p < 0.001), respectively. In the treatment dataset, a model combining time-on-treatment and rule-based volumes of CE and intratumoral Fluid was 82.5% accurate for predicting progression within 30 days of the scan date. An explainable decision tree applied to brain mpMRI yields validated, consistent, intratumoral tissuetype volumes suitable for quantitative response assessment in clinical trials of rHGG.

Supplements with additional descriptions of datasets, feature selection, and results.

Stereotactic Radiosurgery (SRS) of asymptomatic brain metastases provides lasting tumor control with only minor side effects to healthy brain. An active research area is the development of models to predict tumor response to a given dose of Radiation Treatment (RT) from analysis of pre-RT and post-RT MR images (i.e., the forward problem). Here we propose an approach to train a deep neural net on pre-RT MR images of patients with Breast Cancer Metastases to the Brain (BCMB), for predicting RT dose maps that will yield desired/target tumor voxel intensities on post-RT MR images (i.e., the inverse problem).

Novel biomarkers that can be utilized for clinical decision support to improve patient outcomes are critically needed for ovarian cancer. At present, there are no standard of care biomarkers to inform the first-line treatment regimen (neoadjuvant chemotherapy vs. upfront surgical debulking) best suited for each patient or which patients are at the highest risk of recurrence. To address this unmet need, we identified pre-treatment computed tomography (CT) image-based radiomic features predictive of outcomes and primary treatment response among 298 women diagnosed with serous ovarian cancer from 2008 to 2019. A decision tree analysis identified a single volumetric feature, region of interest (ROI) volume center of mass (CoM) in the X direction, as the most informative radiomic feature that stratified patients with upfront surgery into high- and low-risk groups for overall survival. The high-risk group consists of patients with higher values of the radiomic feature. In the training (N=91) and test (N=91) cohorts of women treated with upfront surgery, high-risk patients had worse survival compared to low-risk patients (HR=2.01, 95% CI=1.07, 3.77 and HR=2.23, 95% CI=1.19, 4.17, respectively). This radiomic feature was not associated with survival among women treated with neoadjuvant chemotherapy (N=116; HR=1.23, 95% CI=0.73, 2.07). To reveal potential underlying biology of this radiomic feature, we performed RNAseq gene expression profiling on 47 formalin-fixed paraffin-embedded tumor specimens and correlated gene expression with the radiomic feature using DESeq2 from RSEM estimates. Dichotomized analysis (high- vs. low-risk) yielded 7 significant genes and continuous analysis yielded 15 significant genes (adjusted p<0.05), with both approaches identifying AKT2 and PSMC4. Gene set enrichment analysis (GSEA) was used to identify enriched gene sets from continuous associations using the MSigDB Hallmarks pathways (adjusted p<0.05). GSEA identified the oxidative phosphorylation (OXPHOS) pathway as one of the gene sets most negatively associated with the predictive radiomic feature (Hallmark Normalized Enrichment Score=-2.28, adjusted p<0.001). We derived a PCA-based gene signature from significantly associated OXPHOS genes (p<0.01) resulting in a negative correlation with the radiomic feature (R=-0.65, p<0.001). Prior studies have shown that high OXPHOS ovarian tumors are associated with an increased response to conventional chemotherapy, suggesting that OXPHOS may be a key pathway for chemoresistance in ovarian cancer. In summary, we identified an OXPHOS-associated radiomic feature predictive of survival among women with serous ovarian cancer treated with upfront surgery. Further research is needed to elucidate the biologic and mechanistic underpinnings of the identified radiomic feature and to validate these findings in a larger cohort of women with ovarian cancer. Citation Format: Christelle Colin-Leitzinger, Jaileene Perez-Morales, Steven Eschrich, Jamie K. Teer, Sweta Sinha, Melissa J. McGettigan, Daniel K. Jeong, Olya Stringfield, Mahmoud A. Abdalah, Natarajan Raghunand, Robert J. Gillies, Jing-Yi Chern, Matthew Schabath, Lauren Cole Peres. Oxidative phosphorylation-associated radiomic feature and survival of women with serous ovarian cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 6485.

This archive contains the paired image and label patches used to train our machine learning pipeline, Grading of Lung Adenocarcinoma with Simultaneous Segmentation by Artificial Intelligence (GLASS-AI). Image patches were generated from whole slide images of H&E-stained sections using an Aperio ScanScope AT2 Slide Scanner (Leica) at 20x magnification with a 0.5022 microns/pixel resolution. The individual tumors and airways were annotated by an expert human before being divided into 224x224 pixel patches of the H&E image and paired annotation layer. For more details regarding how these data were used to train GLASS-AI, please see our forthcoming manuscript.

Objective:To quantitatively evaluate intratumoral habitats on dynamic contrast-enhanced (DCE) breast MRI to predict pathologic breast cancer response to stereotactic ablative body radiotherapy (SABR).Methods:Participants underwent SABR treatment (28.5 Gy x3), baseline and post-SABR MRI, and breast-conserving surgery for ER/PR+ HER2- breast cancer. MRI analysis was performed on DCE T1-weighted images. MRI voxels were assigned eight habitats based on high (H) or low (L) maximum enhancement and the sequentially numbered dynamic sequence of maximum enhancement (H1-4, L1-4). MRI response was analyzed by percent tumor volume remaining (%VR = volume post-SABR/volume pre-SABR), and percent habitat makeup (%HM of habitat X = habitat X voxels/total voxels in the segmented volume). These were correlated with percent tumor bed cellularity (%TC) for pathologic response.Results:Sixteen patients completed the trial. The %TC ranged 20%-80%. MRI %VR demonstrated strong correlations with %TC (Pearson R = 0.7-0.89). Pre-SABR tumor %HMs differed significantly from whole breasts (P = 0.005 to <0.00001). Post-SABR %HM of tumor habitat H4 demonstrated the largest change, increasing 13% (P = 0.039). Conversely, combined %HM for H1-3 decreased 17% (P = 0.006). This change correlated with %TC (P < 0.00001) and distinguished pathologic partial responders (≤70 %TC) from nonresponders with 94% accuracy, 93% sensitivity, 100% specificity, 100% positive predictive value, and 67% negative predictive value.Conclusion:In patients undergoing preoperative SABR treatment for ER/PR+ HER2- breast cancer, quantitative MRI habitat analysis of %VR and %HM change correlates with pathologic response.

While HDAC inhibitors have shown promise in hematologic cancers, their efficacy remains limited in solid cancers. In the present study, we evaluated the immunomodulatory properties of the HDAC6 inhibitor, Citarinostat (ACY241) on lung tumor immune compartment and its therapeutic potential in combination with Oxaliplatin. As a single agent, ACY241 treatment promoted increased infiltration, activation, proliferation, and effector function of T cells in the tumors of lung adenocarcinoma-bearing mice. Furthermore, tumor-associated macrophages exhibited downregulated expression of inhibitory ligands in favor of increased MHC and co-stimulatory molecules in addition to higher expression of CCL4 that favored increased T cell numbers in the tumors. RNA-sequencing of tumor-associated T cells and macrophages after ACY241 treatment revealed significant genomic changes that is consistent with improved T cell viability, reduced inhibitory molecular signature, and enhancement of macrophage capacity for improved T cell priming. Finally, coupling these ACY241-mediated effects with the chemotherapy drug Oxaliplatin led to significantly enhanced tumor-associated T cell effector functionality in lung cancer-bearing mice and in patient-derived tumors. Collectively, our studies highlight the molecular underpinnings of the expansive immunomodulatory activity of ACY241 and supports its suitability as a partner agent in combination with rationally selected chemotherapy agents for therapeutic intervention in NSCLC.

Background: There are two first-line treatment recommendations for advanced ovarian cancer: i) upfront cytoreductive debulking followed by chemotherapy and ii) neoadjuvant chemotherapy prior to surgical debulking. The choice between these two treatment strategies is controversial as there are no standardized guidelines for clinical decision support. As such, there remains a critical unmet need to identity biomarkers to personalize the most effective treatment strategies. The primary objective of this study is to identify and validate radiomic biomarkers that predict treatment response among patients with high-grade serous ovarian cancer treated with upfront surgical debulking. Methods: Intratumoral radiomic features (n=308) were extracted from pre-treatment contrast-enhanced CT images; analyses were conducted to remove correlated, non-stable, and non-reproducible features. Patients treated with upfront surgery (N=182) were split into training (N=91) and test (N=91) cohorts and a cohort of patients treated with upfront neoadjuvant (N=116) was used to determine if the radiomic features were prognostic or predictive. Overall (OS) and progression-free survival (PFS) were the main endpoints. Classification and Regression Tree analysis was used to identity the most informative radiomic features in the training cohort, which were then analyzed in the test cohort and the upfront neoadjuvant cohort. Results: Decision tree analysis identified a volumetric feature, ROI volume center of mass (CoM) in X direction, as the most informative radiomic feature which stratified upfront surgery patients into high- and low-risk. In the training cohort, high-risk patients were associated with significantly worse OS versus low-risk patients (HR=2.01; 95% CI 1.07-3.77 vs. 1.00 and 5-year OS=39.9% vs. 56.1%, respectively; log-rank p-value=0.03). In the test cohort, the high- vs. low-risk patients were also associated with poor OS (HR=2.23; 95% CI 1.19-4.17 vs. 1.00 and 5-year OS=23.3% vs. 51.3%, respectively; log-rank p-value=0.01). This radiomic feature was not associated with OS among patients with upfront neoadjuvant (HR=1.23; 95% CI 0.73-2.07 vs. 1.00 and 5-year OS=23.9% vs. 36.6%, respectively; log-rank p-value=0.44). Similar findings were observed for PFS. Conclusion: Utilizing standard-of-care imaging, we identified and validated a predictive radiomic feature associated with outcomes among patients with high-grade serous ovarian cancer treated with upfront surgical debulking but not among patients treated with neoadjuvant chemotherapy. This radiomic biomarker, which describes the location of center of mass inside the tumor in pixels in the x-direction, could be potentially utilized as clinical decision support to guide first-line treatment options. This study was generously funded by a Miles for Moffitt pilot grant. Citation Format: Jaileene Perez-Morales, Christelle M. Colin Leitzinger, Sweta K. Sinha, Melissa J. McGettigan, Daniel K. Jeong, Olya Stringfield, Mahmoud Abdala, Natarajan Raghunand, Robert J. Gillies, Jing-Yi Chern, Lauren C. Peres, Matthew B. Schabath. Radiomic biomarkers to optimize treatment decision and predict patient outcomes in serous ovarian carcinoma [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 3218.

The association of body mass index (BMI) with survival of women with ovarian cancer remains unclear due to mixed epidemiological evidence. This may be due, in part, to the fact that BMI is an imperfect measure of body fat as BMI does not distinguish weight from lean muscle versus adipose tissue. Here, we investigated the association of adiposity measured by computed tomography (CT) with survival among the most common histotype of ovarian cancer, high-grade serous ovarian cancer (HGSOC). The present study included 383 women diagnosed with HGSOC from 2008 to 2019 who were evaluated at H. Lee Moffitt Cancer Center and Research Institute and had pre-treatment computed tomography scans available for analysis. The sliceOmatic v5.0 rev13 (Tomovision, Magog, Canada) medical image analysis software and accompanying ABACS module for segmentation was used to quantify subcutaneous (SAT), visceral (VAT), and intermuscular adipose tissue (IMAT) from the third lumbar (L3) axial slice including the transverse processes. We used Cox proportional hazard regression to estimate hazard ratios (HR) and 95% confidence intervals (CIs) for the association of each measure of adiposity with overall survival (OS) and recurrence-free survival (RFS) while adjusting for age at diagnosis, stage, race and ethnicity, and first-line treatment. The degree of ascites was included in the VAT models as ascites fluid density can mask VAT. We also assessed these associations within first-line treatment groups (upfront chemotherapy [n=147], upfront surgery [n=236]). In the overall study population, we observed a positive but not statistically significant association with OS and RFS for the highest vs. lowest tertile of IMAT (HR= 1.18, 95% CI=0.83, 1.67 and HR=1.16, 95% CI=0.85, 1.58, respectively). Among women who received upfront surgery, the highest tertile of IMAT was associated with a 57% increased risk of recurrence compared to the lowest tertile (HR=1.57, 95% CI=1.04, 2.37), while the association between IMAT and OS was similar to the findings in the overall population (HR=1.14, 95% CI=0.73, 1.78). No association was observed between IMAT and OS or RFS among women who received upfront chemotherapy. No associations with OS or RFS were observed for SAT or VAT overall or within first-line treatment groups. In summary, we observed inferior RFS among HGSOC patients with higher IMAT. These findings suggest that IMAT measured from standard-of-care imaging may represent a biomarker of recurrence among HGSOC patients, and incorporating lifestyle and behavioral changes (e.g., diet, exercise) to decrease IMAT may be warranted for this patient population. Citation Format: Christelle Colin-Leitzinger, Daniel Jeong, Mahmoud Abdalah, Rikki Cannioto, Jing-Yi Chern, Evan Davis, Robert Gillies, Melissa McGettigan, Jaileene Perez-Morales, Natarajan Raghunand, Sweta Sinha, Olya Stringfield, Rajwantee Tirbene, Matthew Schabath, Lauren C. Peres. Pre-treatment adiposity measured by computed tomography and survival of women with high-grade serous ovarian cancer [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 5886.

ObjectiveThis study evaluates breast MRI response of ER/PR+ HER2- breast tumors to pre-operative SABR with pathologic response correlation.MethodsWomen enrolled in a phase 2 single institution trial of SABR for ER/PR+ HER2- breast cancer were retrospectively evaluated for radiologic-pathologic correlation of tumor response. These patients underwent baseline breast MRI, SABR (28.5 Gy in 3 fractions), follow-up MRI 5 to 6 weeks post-SABR, and lumpectomy. Tumor size and BI-RADS descriptors on pre and post-SABR breast MRIs were compared to determine correlation with surgical specimen % tumor cellularity (%TC). Reported MRI tumor dimensions were used to calculate percent cubic volume remaining (%VR). Partial MRI response was defined as a BI-RADs descriptor change or %VR ≤ 70%, while partial pathologic response (pPR) was defined as %TC ≤ 70%.ResultsNineteen patients completed the trial, and %TC ranged 10% to 80%. For BI-RADS descriptor analysis, 12 of 19 (63%) showed change in lesion or kinetic enhancement descriptors post-SABR. This was associated with lower %TC (29% vs. 47%, P = .042). BI-RADS descriptor change analysis also demonstrated high PPV (100%) and specificity (100%) for predicting pPR to treatment (sensitivity 71%, accuracy 74%), but low NPV (29%). MRI %VR demonstrated strong linear correlation with %TC (R = 0.70, P < .001, Pearson's Correlation) and high accuracy (89%) for predicting pPR (sensitivity 88%, specificity 100%, PPV 100%, and NPV 50%).ConclusionEvaluating breast cancer response on MRI using %VR after pre-operative SABR treatment can help identify patients benefiting the most from neoadjuvant radiation treatment of their ER/PR+ HER2- tumors, a group in which pCR to neoadjuvant therapy is rare.

Abstract BACKGROUND Stereotactic radiosurgery (SRS) is a cornerstone in the management of Breast Cancer Metastases to the Brain (BCMB). While control rates are high following SRS, radiation necrosis is a rare but potentially devastating long-term toxicity. There is a clinical need for automated/semi-automated methods to assess tumor response and optimize the RT plans for local control with minimal long-term toxicity. Multiparametric MRI (mpMRI), particularly Apparent Diffusion Coefficient of water (ADC) maps, contain information that is mechanistically relatable to voxel-level tumor response to RT. We report a deep learning-based approach to predict post-SRS ADC maps, FLAIR, T2-weighted (T2W), T1-weighted unenhanced (T1W) and contrast-enhanced (T1WCE) images, from pre-SRS T1W, T1WCE, T2W and FLAIR images, ADC maps, and the delivered RT dose map. These “forward models” will enable the radiation oncologist to simulate radiologic outcomes and iteratively optimize RT plans for local control with minimal toxicity. METHODS We trained a variant of the pix2pix Generative Adversarial Network (GAN) on MRI and RT dose map data from 18 BCMB patients treated with stereotactic radiation with confirmed controlled and locally recurrent metastases. Patients were treated with stereotactic radiation dose of 1-40 Gy between 2013-2019. RESULTS On test data from 6 BCMB patients, the trained forward model predicted post-SRS ADC values within the Gross Tumor Volume (GTV) that were broadly in agreement with ground truth post-SRS ADC maps. In agreement with expectations, the forward model also predicts increasing post-RT ADC within the GTV with increasing simulated RT doses in the range of 1-71 Gy. We have also explored an inverse model to predict the RT dose map required to produce “prescribed” post-SRS ADC values within the GTV. CONCLUSIONS We envision that the forward models will assist the radiation oncologist in initial RT dose plan optimization, while the inverse model may be useful for daily RT plan optimization.

Abstract Preclinical mouse models of lung adenocarcinoma are invaluable for the discovery of molecular drivers of tumor formation, progression, and therapeutic resistance. Histological analyses of these preclinical models require significant investments of time and training to ensure accuracy and consistency. Analysis by a clinical pathologist is the gold standard in this approach, but may be difficult to obtain due to the cost and availability of their services. As an alternative we have developed a digital pathology tool to identify, segment, grade, and analyze tumors in mouse models of lung adenocarcinoma. This convolutional neural network (CNN) model, based on ResNet18, was trained to classify normal lung tissue, normal airways, and the different grades (1 – 4) of lung adenocarcinoma from 100,000 224 × 224 pixel image patches (~16,000 patches per class). Our training dataset was constructed from whole slide images of hematoxylin and eosin stained lung sections from 4 different mouse models of lung adenocarcinoma with oncogenic Kras (KrasG12D/+), in combination with oncogenic p53 mutations (KrasG12D/+; p53R172H/+ and KrasG12D/+;p53R270H/+), or with the loss of the tumor suppressive TAp73 (KrasG12D/+;TAp7fltd/fltd). Our CNN demonstrated a strong correspondence with human pathologists on our holdout dataset, achieving a micro-F1 score of 0.81 on a pixel-by-pixel basis. As a test of our CNN, we analyzed two mouse models to better understand the role of TAp73 in lung adenocarcinoma: KrasG12D/+ (“K”) and KrasG12D/+;TAp73fltd/fltd (“TK”). Both human raters and our CNN reported a significant increase in the tumor burden of the compound mutant “TK” mice compared to the single mutant “K” mice. According to our CNN, this increased tumor burden was driven primarily by an increase in tumor size and not an increased number of tumors in “TK” mice. Because our CNN can assign different grades to regions within the same image patch and tumor, we also uncovered a high degree of intratumor heterogeneity that was not reported by the human pathologists, who are trained to assign one grade to a single tumor with a bias for the highest grade present in a given tumor. The finer grading resolution allowed our CNN to uncover the increased tumor size observed in the “TK” mice was due to expansion of Grade 2 regions (characterized by enlarged nuclei without irregular shape) within tumors that would be considered a higher grade by pathologists. Our CNN also provides a detailed map of tumor grades overlaid on the H&E images used for analysis, allowing for precise targeting of regions within tumors with other assays. We are currently utilizing these outputs in conjunction with other assays, such as spatial transcriptomic analysis and immunohistochemistry, to investigate the molecular mechanisms that underlie the expansion of Grade 2 tumor regions in “TK” mice. Future work will expand this tool into a multidimensional digital pathology pipeline that can accelerate current investigations and reveal new therapeutic targets and prognostic markers. Citation Format: John H. Lockhart, Hayley D. Ackerman, Kyubum Lee, Mahmoud Abdalah, Andrew Davis, Nicole Montey, Theresa Boyle, James Saller, Ayensur Keske, Kay Hänggi, Brian Ruffell, Olya Stringfield, Aik Choon Tan, Elsa R. Flores. Automated tumor segmentation, grading, and analysis of tumor heterogeneity in preclinical models of lung adenocarcinoma [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-082.

Sarcomatoid differentiation in RCC (sRCC) is associated with a poor prognosis, necessitating more aggressive management than RCC without sarcomatoid components (nsRCC). Since suspected renal cell carcinoma (RCC) tumors are not routinely biopsied for histologic evaluation, there is a clinical need for a non-invasive method to detect sarcomatoid differentiation pre-operatively. We utilized unsupervised self-organizing map (SOM) and supervised Learning Vector Quantizer (LVQ) machine learning to classify RCC tumors on T2-weighted, non-contrast T1-weighted fat-saturated, contrast-enhanced arterial-phase T1-weighted fat-saturated, and contrast-enhanced venous-phase T1-weighted fat-saturated MRI images. The SOM was trained on 8 nsRCC and 8 sRCC tumors, and used to compute Activation Maps for each training, validation (3 nsRCC and 3 sRCC), and test (5 nsRCC and 5 sRCC) tumor. The LVQ classifier was trained and optimized on Activation Maps from the 22 training and validation cohort tumors, and tested on Activation Maps of the 10 unseen test tumors. In this preliminary study, the SOM-LVQ model achieved a hold-out testing accuracy of 70% in the task of identifying sarcomatoid differentiation in RCC on standard multiparameter MRI (mpMRI) images. We have demonstrated a combined SOM-LVQ machine learning approach that is suitable for analysis of limited mpMRI datasets for the task of differential diagnosis.

The National Lung Screening Trial (NLST) demonstrated that screening with low-dose computed tomography (LDCT) is associated with a 20% reduction in lung cancer mortality. One potential limitation of LDCT screening is overdiagnosis of slow growing and indolent cancers. In this study, peritumoral and intratumoral radiomics was used to identify a vulnerable subset of lung patients associated with poor survival outcomes. Incident lung cancer patients from the NLST were split into training and test cohorts and an external cohort of non-screen detected adenocarcinomas was used for further validation. After removing redundant and non-reproducible radiomics features, backward elimination analyses identified a single model which was subjected to Classification and Regression Tree to stratify patients into three risk-groups based on two radiomics features (NGTDM Busyness and Statistical Root Mean Square [RMS]). The final model was validated in the test cohort and the cohort of non-screen detected adenocarcinomas. Using a radio-genomics dataset, Statistical RMS was significantly associated with FOXF2 gene by both correlation and two-group analyses. Our rigorous approach generated a novel radiomics model that identified a vulnerable high-risk group of early stage patients associated with poor outcomes. These patients may require aggressive follow-up and/or adjuvant therapy to mitigate their poor outcomes.