Recurrent Oropharyngeal Squamous Cell Carcinomas Maintain Anti-tumor Immunity and Multinucleation Levels Following Completion of Radiation

OBJECTIVE

Oropharyngeal squamous cell carcinoma (OPSCC) recurrence is almost universally fatal. Development of effective therapeutic options requires an improved understanding of recurrent OPSCC biology.

METHODS

We analyzed paired primary-recurrent OPSCC from Veterans treated at the Michael E. DeBakey Veterans Affairs Medical Center between 2000 and 2020 who received curative intent radiation-based treatment (with or without chemotherapy). Patient tumors were analyzed using standard immunohistochemistry and automated imaging of infiltrating lymphocytes and multinucleated tumor cells coupled to machine learning algorithms.

RESULTS

Primary and recurrent tumors demonstrated high concordance via p16 and p53 immunohistochemistry, with comparable levels of multinucleation. In contrast, recurrent tumors demonstrated significantly higher levels of CD8+ tumor infiltrating lymphocytes (p<0.05) and higher levels of PD-L1 expression (p<0.05).

CONCLUSION

Exposure to chemo-radiation and recurrence following treatment preserves critical features of intrinsic tumor biology and the tumor immune microenvironment suggesting that novel treatment regimens may be as effective in the salvage setting as in the definitive intent setting.

Visual Assessment of 2-Dimensional Levels Within 3-Dimensional Pathology Data Sets of Prostate Needle Biopsies Reveals Substantial Spatial Heterogeneity

Prostate cancer prognostication largely relies on visual assessment of a few thinly sectioned biopsy specimens under a microscope to assign a Gleason grade group (GG). Unfortunately, the assigned GG is not always associated with a patient's outcome in part because of the limited sampling of spatially heterogeneous tumors achieved by 2-dimensional histopathology. In this study, open-top light-sheet microscopy was used to obtain 3-dimensional pathology data sets that were assessed by 4 human readers. Intrabiopsy variability was assessed by asking readers to perform Gleason grading of 5 different levels per biopsy for a total of 20 core needle biopsies (ie, 100 total images). Intrabiopsy variability (Cohen κ) was calculated as the worst pairwise agreement in GG between individual levels within each biopsy and found to be 0.34, 0.34, 0.38, and 0.43 for the 4 pathologists. These preliminary results reveal that even within a 1-mm-diameter needle core, GG based on 2-dimensional images can vary dramatically depending on the location within a biopsy being analyzed. We believe that morphologic assessment of whole biopsies in 3 dimension has the potential to enable more reliable and consistent tumor grading.

Recurrent oropharyngeal squamous cell carcinomas maintain anti-tumor immunity and multinucleation levels following completion of radiation

Objective

Oropharyngeal squamous cell carcinoma (OPSCC) recurrence is almost universally fatal. Development of effective therapeutic options requires an improved understanding of recurrent OPSCC biology.

Methods

We analyzed paired primary-recurrent OPSCC from Veterans treated at the Michael E. DeBakey Veterans Affairs Medical Center between 2000 and 2020 who received curative intent radiation-based treatment (with or without chemotherapy). Patient tumors were analyzed using standard immunohistochemistry and automated imaging of infiltrating lymphocytes and multinucleated tumor cells coupled to machine learning algorithms.

Results

Primary and recurrent tumors demonstrated high concordance via p16 and p53 immunohistochemistry, with comparable levels of multinucleation. In contrast, recurrent tumors demonstrated significantly higher levels of CD8+ tumor infiltrating lymphocytes (p<0.05) and higher levels of PD-L1 expression (p<0.05).

Conclusion

Exposure to chemo-radiation and recurrence following treatment does not appear deleterious to underlying biological characteristics and anti-tumor immunity of oropharyngeal cancer, suggesting that novel treatment regimens may be as effective in the salvage setting as in the definitive intent setting.

Nondestructive 3D pathology with analysis of nuclear features for prostate cancer risk assessment

Prostate cancer treatment decisions rely heavily on subjective visual interpretation [assigning Gleason patterns or International Society of Urological Pathology (ISUP) grade groups] of limited numbers of two-dimensional (2D) histology sections. Under this paradigm, interobserver variance is high, with ISUP grades not correlating well with outcome for individual patients, and this contributes to the over- and undertreatment of patients. Recent studies have demonstrated improved prognostication of prostate cancer outcomes based on computational analyses of glands and nuclei within 2D whole slide images. Our group has also shown that the computational analysis of three-dimensional (3D) glandular features, extracted from 3D pathology datasets of whole intact biopsies, can allow for improved recurrence prediction compared to corresponding 2D features. Here we seek to expand on these prior studies by exploring the prognostic value of 3D shape-based nuclear features in prostate cancer (e.g. nuclear size, sphericity). 3D pathology datasets were generated using open-top light-sheet (OTLS) microscopy of 102 cancer-containing biopsies extracted ex vivo from the prostatectomy specimens of 46 patients. A deep learning-based workflow was developed for 3D nuclear segmentation within the glandular epithelium versus stromal regions of the biopsies. 3D shape-based nuclear features were extracted, and a nested cross-validation scheme was used to train a supervised machine classifier based on 5-year biochemical recurrence (BCR) outcomes. Nuclear features of the glandular epithelium were found to be more prognostic than stromal cell nuclear features (area under the ROC curve [AUC] = 0.72 versus 0.63). 3D shape-based nuclear features of the glandular epithelium were also more strongly associated with the risk of BCR than analogous 2D features (AUC = 0.72 versus 0.62). The results of this preliminary investigation suggest that 3D shape-based nuclear features are associated with prostate cancer aggressiveness and could be of value for the development of decision-support tools. © 2023 The Pathological Society of Great Britain and Ireland.

Multi-site cross-organ calibrated deep learning (MuSClD): Automated diagnosis of non-melanoma skin cancer

Although deep learning (DL) has demonstrated impressive diagnostic performance for a variety of computational pathology tasks, this performance often markedly deteriorates on whole slide images (WSI) generated at external test sites. This phenomenon is due in part to domain shift, wherein differences in test-site pre-analytical variables (e.g., slide scanner, staining procedure) result in WSI with notably different visual presentations compared to training data. To ameliorate pre-analytic variances, approaches such as CycleGAN can be used to calibrate visual properties of images between sites, with the intent of improving DL classifier generalizability. In this work, we present a new approach termed Multi-Site Cross-Organ Calibration based Deep Learning (MuSClD) that employs WSIs of an off-target organ for calibration created at the same site as the on-target organ, based off the assumption that cross-organ slides are subjected to a common set of pre-analytical sources of variance. We demonstrate that by using an off-target organ from the test site to calibrate training data, the domain shift between training and testing data can be mitigated. Importantly, this strategy uniquely guards against potential data leakage introduced during calibration, wherein information only available in the testing data is imparted on the training data. We evaluate MuSClD in the context of the automated diagnosis of non-melanoma skin cancer (NMSC). Specifically, we evaluated MuSClD for identifying and distinguishing (a) basal cell carcinoma (BCC), (b) in-situ squamous cell carcinomas (SCC-In Situ), and (c) invasive squamous cell carcinomas (SCC-Invasive), using an Australian (training, n = 85) and a Swiss (held-out testing, n = 352) cohort. Our experiments reveal that MuSCID reduces the Wasserstein distances between sites in terms of color, contrast, and brightness metrics, without imparting noticeable artifacts to training data. The NMSC-subtyping performance is statistically improved as a result of MuSCID in terms of one-vs. rest AUC: BCC (0.92 vs 0.87, p = 0.01), SCC-In Situ (0.87 vs 0.73, p = 0.15) and SCC-Invasive (0.92 vs 0.82, p = 1e-5). Compared to baseline NMSC-subtyping with no calibration, the internal validation results of MuSClD (BCC (0.98), SCC-In Situ (0.92), and SCC-Invasive (0.97)) suggest that while domain shift indeed degrades classification performance, our on-target calibration using off-target tissue can safely compensate for pre-analytical variabilities, while improving the robustness of the model.

Spatial interplay patterns of cancer nuclei and tumor-infiltrating lymphocytes (TILs) predict clinical benefit for immune checkpoint inhibitors

Immune checkpoint inhibitors (ICIs) show prominent clinical activity across multiple advanced tumors. However, less than half of patients respond even after molecule-based selection. Thus, improved biomarkers are required. In this study, we use an image analysis to capture morphologic attributes relating to the spatial interaction and architecture of tumor cells and tumor-infiltrating lymphocytes (TILs) from digitized H&E images. We evaluate the association of image features with progression-free (PFS) and overall survival in non-small cell lung cancer (NSCLC) (N = 187) and gynecological cancer (N = 39) patients treated with ICIs. We demonstrated that the classifier trained with NSCLC alone was associated with PFS in independent NSCLC cohorts and also in gynecological cancer. The classifier was also associated with clinical outcome independent of clinical factors. Moreover, the classifier was associated with PFS even with low PD-L1 expression. These findings suggest that image analysis can be used to predict clinical end points in patients receiving ICI.

Prostate Cancer Risk Stratification via Nondestructive 3D Pathology with Deep Learning-Assisted Gland Analysis

Prostate cancer treatment planning is largely dependent upon examination of core-needle biopsies. The microscopic architecture of the prostate glands forms the basis for prognostic grading by pathologists. Interpretation of these convoluted three-dimensional (3D) glandular structures via visual inspection of a limited number of two-dimensional (2D) histology sections is often unreliable, which contributes to the under- and overtreatment of patients. To improve risk assessment and treatment decisions, we have developed a workflow for nondestructive 3D pathology and computational analysis of whole prostate biopsies labeled with a rapid and inexpensive fluorescent analogue of standard hematoxylin and eosin (H&E) staining. This analysis is based on interpretable glandular features and is facilitated by the development of image translation-assisted segmentation in 3D (ITAS3D). ITAS3D is a generalizable deep learning-based strategy that enables tissue microstructures to be volumetrically segmented in an annotation-free and objective (biomarker-based) manner without requiring immunolabeling. As a preliminary demonstration of the translational value of a computational 3D versus a computational 2D pathology approach, we imaged 300 ex vivo biopsies extracted from 50 archived radical prostatectomy specimens, of which, 118 biopsies contained cancer. The 3D glandular features in cancer biopsies were superior to corresponding 2D features for risk stratification of patients with low- to intermediate-risk prostate cancer based on their clinical biochemical recurrence outcomes. The results of this study support the use of computational 3D pathology for guiding the clinical management of prostate cancer. SIGNIFICANCE: An end-to-end pipeline for deep learning-assisted computational 3D histology analysis of whole prostate biopsies shows that nondestructive 3D pathology has the potential to enable superior prognostic stratification of patients with prostate cancer.

An Imaging Biomarker of Tumor-Infiltrating Lymphocytes to Risk-Stratify Patients With HPV-Associated Oropharyngeal Cancer

BACKGROUND

Human papillomavirus (HPV)-associated oropharyngeal squamous cell carcinoma (OPSCC) has excellent control rates compared to nonvirally associated OPSCC. Multiple trials are actively testing whether de-escalation of treatment intensity for these patients can maintain oncologic equipoise while reducing treatment-related toxicity. We have developed OP-TIL, a biomarker that characterizes the spatial interplay between tumor-infiltrating lymphocytes (TILs) and surrounding cells in histology images. Herein, we sought to test whether OP-TIL can segregate stage I HPV-associated OPSCC patients into low-risk and high-risk groups and aid in patient selection for de-escalation clinical trials.

METHODS

Association between OP-TIL and patient outcome was explored on whole slide hematoxylin and eosin images from 439 stage I HPV-associated OPSCC patients across 6 institutional cohorts. One institutional cohort (n = 94) was used to identify the most prognostic features and train a Cox regression model to predict risk of recurrence and death. Survival analysis was used to validate the algorithm as a biomarker of recurrence or death in the remaining 5 cohorts (n = 345). All statistical tests were 2-sided.

RESULTS

OP-TIL separated stage I HPV-associated OPSCC patients with 30 or less pack-year smoking history into low-risk (2-year disease-free survival [DFS] = 94.2%; 5-year DFS = 88.4%) and high-risk (2-year DFS = 82.5%; 5-year DFS = 74.2%) groups (hazard ratio = 2.56, 95% confidence interval = 1.52 to 4.32; P < .001), even after adjusting for age, smoking status, T and N classification, and treatment modality on multivariate analysis for DFS (hazard ratio = 2.27, 95% confidence interval = 1.32 to 3.94; P = .003).

CONCLUSIONS

OP-TIL can identify stage I HPV-associated OPSCC patients likely to be poor candidates for treatment de-escalation. Following validation on previously completed multi-institutional clinical trials, OP-TIL has the potential to be a biomarker, beyond clinical stage and HPV status, that can be used clinically to optimize patient selection for de-escalation.

Abstract PO-017: Annotation-free 3D gland segmentation with generative image-sequence translation for prostate cancer risk assessment

1. Purpose We developed an annotation-free image-translation-based approach for 3D segmentation of prostate glands within 3D-histology datasets of whole biopsies stained with a low-cost and rapid-diffusing fluorescent analog of H&E. 2. Introduction The current diagnostic gold standard of histopathology provides a limited 2D view of complex 3D glandular structures in prostate specimens, which contributes to high interobserver variability and reduced prognostic accuracy. We have recently developed nondestructive 3D pathology methods based on open-top light-sheet (OTLS) microscopy. In order to train prognostic models based on 3D glandular morphology, we have developed an objective (biomarker-based) 3D gland-segmentation method that does not rely upon tedious and subjective manual annotations, and which can operate on images of tissue stained with a cheap and fast-diffusing (small molecule) fluorescent analog of H&E. 3. Methods We first convert H&E-analog images into synthetic 3D immunofluorescence (IF) images of cytokeratin-8 (CK8), a biomarker expressed by the luminal epithelial cells that surround all prostate glands. This conversion was performed by treating the 3D data as sequences of 2D images and adapting a generative adversarial network (GAN)-based video-synthesis model to perform image-sequence translation with high depth-wise continuity between frames. Based on the synthetic CK8 images, glands were then objectively segmented in 3D using a thresholding/morphology-based algorithm. This two-step method obviates the need for labor-intensive and subjective manual 3D annotations, as would be needed to train a single-step segmentation model. A 3D structural similarity (SSIM) index was assessed between synthetic and real CK8 images. In addition, based on ground-truth manual annotations of glands in ten 0.2-mm3 regions, we calculated voxel-based Dice coefficients to compare our segmentation accuracy vs. two baseline methods. 4. Results The synthetic CK8 images exhibited high fidelity (3D SSIM = 0.696) and optimal continuity with depth. Our segmentation accuracy outperformed two baseline methods, with Dice coefficients (averaged for 10 samples) of: 0.882 (our method), 0.725 (3D watershed), 0.643 (2D U-net). We are now applying our method to 3D histology datasets of whole biopsies (n &gt; 1000) acquired ex vivo from prostatectomy specimens (N ~ 200), where we are extracting 3D histomorphometric gland features to predict biochemical recurrence (BCR) post-prostatectomy in men with prostate cancer. 5. Conclusions Our annotation-free segmentation method relies upon generative synthetic 3D IF images from H&E-analog images in order to objectively segment the 3D prostate gland network. These accurate 3D segmentations are being extended to whole-biopsy 3D pathology datasets for prostate cancer risk assessment.

Citation Format: Weisi Xie, Adam Glaser, Nicholas Reder, Nadia Postupna, Chenyi Mao, Can Koyuncu, Patrick Leo, Robert Serafin, Hongyi Huang, Anant Madabhushi, Lawrence True, Jonathan T.C. Liu. Annotation-free 3D gland segmentation with generative image-sequence translation for prostate cancer risk assessment [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-017.

Feature-driven local cell graph (FLocK): New computational pathology-based descriptors for prognosis of lung cancer and HPV status of oropharyngeal cancers

Local spatial arrangement of nuclei in histopathology images of different cancer subtypes has been shown to have prognostic value. In order to capture localized nuclear architectural information, local cell cluster graph-based measurements have been proposed. However, conventional ways of cell graph construction only utilize nuclear spatial proximity, and do not differentiate between different cell types while constructing the graph. In this paper, we present feature-driven local cell cluster graph (FLocK), a new approach to constructing local cell graphs by simultaneously considering spatial proximity and attributes of the individual nuclei (e.g. shape, size, texture). In addition, we have designed a new set of quantitative graph-derived metrics to be extracted from FLocKs, in turn capturing the interplay between different proximally located clusters of nuclei. We have evaluated the efficacy of FLocK features extracted from H&E stained tissue images in two clinical applications: to classify short-term vs. long-term survival among patients of early stage non-small cell lung cancer (ES-NSCLC), and also to predict human papillomavirus (HPV) status of oropharyngeal squamous cell carcinoma (OP-SCCs). In the classification of long-term vs. short-term survival among patients of ES-NSCLC (training cohort, n = 434), the top 10 discriminative FLocK features related to the variation of FLocK size and intersected FLocK distance were identified, via Minimum Redundancy and Maximum Relevance (MRMR) selection, in 100 runs of 10-fold cross-validation, and in conjunction with a linear discriminant classifier yielded a mean AUC of 0.68 for predicting survival in the training cohort. This is better than other state-of-art histomorphometric and deep learning classifiers (cell cluster graphs (AUC = 0.62), global cell graph (AUC = 0.56), nuclear shape (AUC = 0.54), nuclear orientation (AUC = 0.61), AlexNet (AUC = 0.55), ResNet (AUC = 0.56)). The FLocK-based classifier yielded an AUC of 0.70 in an independent testing cohort (n = 150). The patients identified as "high-risk" had significantly poorer overall survival in the testing cohort, with a hazard ratio (95% confidence interval) of 2.24 (1.24-4.05), p = 0.01144). In the classification of HPV status of OP-SCC, the top three FLocK features pertaining to the portion of intersected FLocKs were used to construct a classifier, which yielded an AUC of 0.80 in the training cohort (n = 50), and an accuracy of 0.78 in an independent testing cohort (n = 35). The combination of FLocK measurements with cell cluster graphs, nuclear orientation, and nuclear shape improved the training AUC to 0.87, 0.91 and 0.85, respectively. Deep learning approaches yielded marginally better performance than the FLocK-based classifier in this application, with AUC = 0.78 for AlexNet, AUC = 0.81 for ResNet, and AUC = 0.76 for FLocK-based classifier in the testing cohort. However, the combination of two hand-crafted features: FLocK and nuclear orientation yielded a better performance (AUC = 0.84). FLocK provides a unique and quantitative way to analyze histology images of solid tumors and interrogate tumor morphology from a different aspect than existing histomorphometrics. The source code can be accessed at https://github.com/hacylu/FLocK.

Combination of tumor multinucleation and spatial arrangement of tumor-infiltrating lymphocytes to predict overall survival in oropharyngeal squamous cell carcinoma: A multisite study

6566

Background: Oropharyngeal squamous cell carcinoma patients can have major morbidity from current treatment regimens, necessitating accurate identification of patients with aggressive versus indolent tumors. In this study, we sought to evaluate whether the combination of computer extracted features of tumor cell multinucleation (MN) and spatial interplay of tumor-infiltrating lymphocytes (TILs) is prognostic of overall survival (OS) in OPSCC patients. Methods: OPSCC specimens from 688 patients were retrospectively collected from 3 different sites. 141 patients from site 1 formed the training set (D1) and 322 patients from site 2 and 225 patients from site 3 formed the independent validation cohort (D2, n = 547). A machine learning (ML) model was employed to automatically calculate a Multi-nucleation risk index (MNI), which is the ratio of the number of MN to the number of epithelial cells, to each patient. A separate ML model was also used to capture measurements related to the interplay between TILs and tumor cells (SpaTIL), which were then used to compute a risk score using a Cox regression model. The median value of both the MNIs and the SpaTIL risk scores in D2 were used to identify patients as either low- or high-risk. A definitive label was assigned to each patient by combining the class labels obtained from the MNI and SpaTIL models using a logical AND operation. Results: In D2, the patients with high-risk scores had statistically significantly worse survival in univariate analysis. The univariate analysis yielded an HR = 1.91 (95% CI: 1.25-2.93, p = 0.0027) for D. Multivariate analysis controlling the effect of different clinical variables is shown in the table. Conclusions: We presented a computational pathology approach to prognosticate disease outcome in OPSCC by combining features relating to density of multinucleation and spatial arrangement of TILs and validated the approach on a large multi-site dataset. With additional validation the approach could potentially help identify OPSCC patients who could benefit from de-escalation of therapy. [Table: see text]

Computerized features of spatial interplay of tumor-infiltrating lymphocytes predict disease recurrence in p16+ oropharyngeal squamous cell carcinoma: A multisite validation study

6559

Background: While overall, patients with p16+ oropharyngeal squamous cell carcinoma (OPSCC) have a favorable prognosis, subsets of patients experience disease recurrence (DR) and death despite aggressive multimodality treatment. Aside from routine staging criteria, there are no biomarkers of tumor behavior routinely employed in OPSCC to identify patients at higher risk of DR. In this study we sought to evaluate whether the interplay between tumor-infiltrating lymphocytes (TILs) & cancer cells, in both stromal and epithelial compartments from digitized H&E-stained slides, can predict DR in OPSCC patients. Methods: OPSCC resected specimens from 354 patients (66 with DR) were retrospectively collected from 3 different sites. 107 (16 DR) patients from site 1 formed the training set and 247 (50 DR) patients from sites 2 & 3 formed the independent validation cohort. Computerized algorithms automatically identified 4 types of nuclei (TILs & non-TILs in both stromal & epithelial regions), defined clusters for each nuclei type based on cell proximity, and used network graph concepts to capture measurements relating to the arrangement of these clusters. The top 10 features determined by a statistical selection method (LASSO) were used to train a Cox regression model that assigns a risk of DR to each patient on the training set. The median risk score was used as threshold for stratifying patients on the validation set into low and high-risk of DR. Survival analysis was used to evaluate the stratification given by the trained model. Results: Patients identified by the TIL interplay model as high risk for DR had statistically worse disease specific survival. Univariate analysis yielded an HR=2.49 (95% CI: 1.22-5.07, p=0.04) for site 2 and HR=3.62 (95% CI: 1.39-9.43, p=0.03) for site 3. Multivariate analysis controlling the effect of different clinical variables is shown in the attached table. Conclusions: We introduce a prognostic model based on the automated quantification of the interplay between tumor microenvironment cells that is able to help distinguish OPSCC patients with higher DR risk from those who will experience longer disease-free survival. [Table: see text]