Bel, Thomas de

Abstract Introduction: We used micro-computed tomography (microCT), a high-resolution imaging option, to detect and characterize microcalcifications (MCs) in three dimensions within pathology blocks of benign and malignant breast tissues. Methods: A set of 44 formalin-fixed, paraffin-embedded breast tissue blocks were assessed from n=22 women at two time points: benign breast biopsy and subsequent DCIS or DCIS with invasive disease breast cancer. Blocks were scanned using the Bruker Skyscan 1276 microCT at a resolution of 10 µm. SkyScan analysis CTAn software was utilized to prepare and analyze morphological parameters and multiple MCs contained within each block were averaged. Paired morphological parameters were compared between the benign and subsequent cancer samples within women using Wilcoxon signed-rank tests. Results: Median age of patients was 53 years (range 37-77 years) at initial benign biopsy and developed breast cancer at median of 5.6 years (range: 2.3-12.8 years) later. The initial benign biopsies were for proliferative disease without atypia in the majority (59%), while 23% had non-proliferative lesions and 18% atypical hyperplasia. The average structural model index was consistent with a near rod-like shape (median 2.99, range: 2.71-3.29). Paired comparisons between benign and cancer blocks showed that the average surface area of MCs was significantly higher in the cancer samples (p=0.0467), as was the average volume of MCs (p=0.0298) (Table 1). Conclusions: Preliminarily, we demonstrate that microCT of routinely prepared pathology blocks of breast tissues may be useful in characterizing the 3-D morphometry of MCs with suggestive differences in benign and cancer tissues. Given that MCs are a sentinel radiologic marker of DCIS but are common in benign breast disease, developing improved approaches for classifying MCs may have value in breast cancer screening and management. Table 1. Comparison of MC parameters in biopsy tissues (IQR = Interquartile Range). Benign sample from women who later developed breast cancer Breast cancer after prior benign sample Paired Differences (Cancer - Benign) Wilcoxon signed-rank p value (N=22) (N=22) (N=22) Number of Objects (Median (IQR)) 43.5 (14, 789) 69.5 (33, 289) -6 (-139, 67) 0.6830 Average Surface Area (mm2)(Median (IQR)) 0.0225 (0.0134, 0.0393) 0.0342 (0.0185, 0.0656) 0.0113 (-0.0027, 0.0322) 0.0467 Average Volume (mm3) (Median (IQR)) 0.0003 (0.0001, 0.0007) 0.0007 (0.0003, 0.0022) 0.0003 (0.000002, 0.0020) 0.0298 Average Surface Area/Volume (mm−1)(Median (IQR)) 214.92 (162.25, 328.39) 199.55 (151.89, 230.52) -20.85 (-86.05, 27.04) 0.1433 Average Structural Thickness (mm)(Median (IQR)) 0.0341(0.0196, 0.0446) 0.0395 (0.0336, 0.0505) 0.0074 (-0.0062, 0.0153) 0.1173 Average Structural Model Index (Median (IQR)) 2.9758 (2.8465, 3.1175) 3.0026 (2.9281, 3.0927) 0.0075 (-0.1073, 0.1381) 0.7656 Citation Format: Sarah E. Schrup, Thomas de Bel, Tanya Hoskin, Teresa Allers, Stacey Winham, Derek Radisky, Laura Pacheco-Spann, Lisa Seymour, Amy Degnim, Mark Sherman. High resolution microCT to analyze the 3D morphology of microcalcifications in benign breast disease and breast cancer biopsy tissues. [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 3587.

Abstract Breast cancer risk is increased in parous women in the period following childbirth, peaking at five years. After weaning or in the absence of lactation, the breast undergoes postpartum involution (PPI), a process characterized by epithelial cell death and tissue remodeling that returns the mammary gland to a baseline state, and has previously been associated with increased inflammation and breast cancer development and progression in preclinical models. Features of PPI and determinants of related inflammation have been incompletely characterized among women. In this study, we performed visual and AI analysis of 725 digitized H&E images of normal breast tissues donated to the Komen Tissue Bank (KTB) by parous and nulliparous women ≤45 years, and further investigated the immune microenvironment in specimens from 23 women (also from KTB, 13 parous, 10 nulliparous) using NanoString RNA immuno oncology (IO) 360 panels and immune protein biomarkers by NanoString GeoMx Digital Spatial Profiling (DSP). We found that recently parous women (≤5 years of a last birth) had higher numbers of terminal duct lobular units (TDLUs), immune cells, and plasma cells as compared with nulliparous women, and that beyond 5 years of a last birth, TDLU numbers were still higher in parous women, but the immune and plasma cell content of the breast of parous and nulliparous women were not significantly different. Our gene expression analysis revealed differential expression of genes that clustered according to parity status, with interferon stimulated genes; STAT1 and IFITM1, and interferon alpha receptor 1 (IFNAR1), and MHC class II genes (HLA-DMA, HLA-DPA,HLA-DPB1, and HLA-DRA) elevated in parous women. Our DSP analysis revealed that immune biomarkers with immunosuppressive functions, including ARG1, VISTA, CTLA-4, and CD68 were significantly higher in parous women as compared with nulliparous women. Breast tissues of parous women show lobular expansion and alterations in immune cell components compared with nulliparous tissues. Further research is needed to assess how these alterations may impact risk. Citation Format: Joshua Were Ogony, Thomas De Bel, Derek Radisky, Jeroen VanderLaak, Mark Sherman. Pathology AI features and immune biomarkers of postpartum involution: Implications for postpartum breast cancer [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P2-11-14.

Abstract Background:Breast terminal duct lobular units (TDLUs), the source of most breast cancer (BC) precursors, are shaped by age-related involution, a gradual process, and postpartum involution (PPI), a dramatic inflammatory process that restores baseline microanatomy after weaning. Dysregulated PPI is implicated in the pathogenesis of postpartum BCs. We propose that assessment of TDLUs in the postpartum period may have value in risk estimation, but characteristics of these tissues in relation to epidemiological factors are incompletely described.Methods: Using validated Artificial Intelligence and morphometric methods, we analyzed digitized images of tissue sections of normal breast tissues stained with hematoxylin and eosin from donors <45 years from the Komen Tissue Bank (180 parous and 545 nulliparous). Metrics assessed by AI, included: TDLU count; adipose tissue fraction; mean acini count/TDLU; mean dilated acini; mean average acini area; mean “capillary” area; mean epithelial area; mean ratio of epithelial area versus intralobular stroma; mean mononuclear cell count (surrogate of immune cells); mean fat area proximate to TDLUs and TDLU area. We compared epidemiologic characteristics collected via questionnaire by parity status and race, using a Wilcoxon rank sum test or Fisher’s exact test. Histologic features were compared between nulliparous and parous women (overall and by time between last birth and donation [ recent birth: ≤5 years versus remote birth: >5 years]) using multivariable regression models.Results:Normal breast tissues of parous women contained significantly higher TDLU counts and acini counts, more frequent dilated acini, higher mononuclear cell counts in TDLUs and smaller acini area per TDLU than nulliparas (all multivariable analyses p<0.001). Differences in TDLU counts and average acini size persisted for >5 years postpartum whereas increases in immune cells were most marked <5 years of a birth. Relationships were suggestively modified by several other factors, including demographic and reproductive characteristics, ethanol consumption and breastfeeding duration. Conclusions:Our study identified sustained expansion of TDLU numbers and reduced average acini area among parous versus nulliparous women and notable increases in immune responses within five years following childbirth. Further, we show that quantitative characteristics of normal breast samples vary with demographic features and BC risk factors.

Abstract Background: Biopsy diagnosis of benign breast disease (BBD) based on the most severe lesion in a sample predicts future breast cancer risk and has implications for screening and management. Lobules are the functional unit of the breast and the structures from which BBD arises. We developed and preliminarily validated an automated computational pathology algorithm to discriminate normal from BBD breast lobules as a step toward automated comprehensive characterization of benign biopsies. Methods: 152 BBD biopsies (27 training, 125 validation) from the Mayo Clinic were examined using scanned digital images of H&E stained sections. For each image, a pathologist annotated up to 10 representative lobules as normal or BBD using standard pathology criteria. A deep learning algorithm to quantify lobular features was developed using 129 lobules from 27 subjects. Nine features were identified that discriminate normal vs BBD lobules, expressing lobule size, acini size and number, acinar lumen size, proportion of lobular stroma, and capillaries. Here, we validate their performance to discriminate normal vs BBD lobules in a set of 1250 lobules from 125 subjects using area under the ROC curve (AUC) analysis. Random forest analysis was used for multivariable modeling; model performance was assessed with a tenfold cross-validation approach. Results: Median subject age was 52 years. Among the 125 validation subjects, BBD findings were nonproliferative in 39%, proliferative in 45%, and atypical hyperplasia in 16%. Sections included 552 (44%) normal lobules and 698 BBD (56%) lobules, with representation of both lobule types on each section. In univariate analyses, four individual features showed good discrimination between normal vs. BBD lobules, yielding the following AUCs: lobule size= 0.74, mean acini size= 0.75, epithelial area= 0.75, and number of acini with large lumens= 0.76. Lobule size and epithelial area were highly correlated (Spearman rank correlation r = 0.95), but both of these features showed lower correlation with mean acini size and number of acini with large lumens (each r &lt; 0.5). With random forest modeling, number of acini with large lumens was the strongest discriminating feature, followed by mean acini size, lobule size, and epithelial area. With ten-fold cross validation of the multivariable random forest model, the overall AUC was 0.82 (95% CI: 0.79-0.85). Conclusion: Our validation showed that automated quantitative computational pathology assessment of breast lobules can discriminate normal versus BBD on a per lobule basis. This finding supports the feasibility of developing automated algorithms to classify every lesion in breast biopsies, expanding beyond visual assessment. Further studies using deep learning may reveal novel pathology features for classifying BBD biopsies with the potential to strengthen estimation of breast cancer risk. Citation Format: Amy C. Degnim, Thomas de Bel, Mark E. Sherman, Derek C. Radisky, Stacey J. Winham, Tanya L. Hoskin, Melody L. Stallings Mann, Marlene Frost, Robert A. Vierkant, Brendan T. Broderick, Ethan P. Heinzen, Rushin Brahmbhatt, Muhammad Arshad, Celine M. Vachon, Jodi M. Carter, Lori A. Denison, Daniel W. Visscher, Jeroen van der Laak. Discrimination of benign breast disease from normal lobules using an automated computational pathology algorithm [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 2113.

Significance Statement Histopathologic assessment of kidney tissue currently relies on manual scoring or traditional image-processing techniques to quantify and classify tissue features, time-consuming approaches that have limited reproducibility. The authors present an alternative approach, featuring a convolutional neural network for multiclass segmentation of kidney tissue in sections stained by periodic acid–Schiff. Their findings demonstrate applicability of convolutional neural networks for tissue from multiple centers, for biopsies and nephrectomy samples, and for the analysis of both healthy and pathologic tissues. In addition, they validated the network’s results with components from the Banff classification system. Their convolutional neural network may have utility for quantitative studies involving kidney histopathology across centers and potential for application in routine diagnostics. Background The development of deep neural networks is facilitating more advanced digital analysis of histopathologic images. We trained a convolutional neural network for multiclass segmentation of digitized kidney tissue sections stained with periodic acid–Schiff (PAS). Methods We trained the network using multiclass annotations from 40 whole-slide images of stained kidney transplant biopsies and applied it to four independent data sets. We assessed multiclass segmentation performance by calculating Dice coefficients for ten tissue classes on ten transplant biopsies from the Radboud University Medical Center in Nijmegen, The Netherlands, and on ten transplant biopsies from an external center for validation. We also fully segmented 15 nephrectomy samples and calculated the network’s glomerular detection rates and compared network-based measures with visually scored histologic components (Banff classification) in 82 kidney transplant biopsies. Results The weighted mean Dice coefficients of all classes were 0.80 and 0.84 in ten kidney transplant biopsies from the Radboud center and the external center, respectively. The best segmented class was “glomeruli” in both data sets (Dice coefficients, 0.95 and 0.94, respectively), followed by “tubuli combined” and “interstitium.” The network detected 92.7% of all glomeruli in nephrectomy samples, with 10.4% false positives. In whole transplant biopsies, the mean intraclass correlation coefficient for glomerular counting performed by pathologists versus the network was 0.94. We found significant correlations between visually scored histologic components and network-based measures. Conclusions This study presents the first convolutional neural network for multiclass segmentation of PAS-stained nephrectomy samples and transplant biopsies. Our network may have utility for quantitative studies involving kidney histopathology across centers and provide opportunities for deep learning applications in routine diagnostics.