No abstract

Breast cancer tumor grade is strongly associated with patient survival. In current clinical practice, pathologists assign tumor grade after visual analysis of tissue specimens. However, different studies show significant inter-observer variation in breast cancer grading. Computer-based breast cancer grading methods have been proposed but only work on specifically selected tissue areas and/or require labor-intensive annotations to be applied to new datasets. In this study, we trained and evaluated a deep learning-based breast cancer grading model that works on whole-slide histopathology images. The model was developed using whole-slide images from 706 young (< 40 years) invasive breast cancer patients with corresponding tumor grade (low/intermediate vs. high), and its constituents nuclear grade, tubule formation and mitotic rate. The performance of the model was evaluated using Cohen’s kappa on an independent test set of 686 patients using annotations by expert pathologists as ground truth. The predicted low/intermediate (n = 327) and high (n = 359) grade groups were used to perform survival analysis. The deep learning system distinguished low/intermediate versus high tumor grade with a Cohen’s Kappa of 0.59 (80% accuracy) compared to expert pathologists. In subsequent survival analysis the two groups predicted by the system were found to have a significantly different overall survival (OS) and disease/recurrence-free survival (DRFS/RFS) (p < 0.05). Univariate Cox hazard regression analysis showed statistically significant hazard ratios (p < 0.05). After adjusting for clinicopathologic features and stratifying for molecular subtype the hazard ratios showed a trend but lost statistical significance for all endpoints. In conclusion, we developed a deep learning-based model for automated grading of breast cancer on whole-slide images. The model distinguishes between low/intermediate and high grade tumors and finds a trend in the survival of the two predicted groups.

No abstract

Ductal carcinoma in situ (DCIS) is a non-invasive breast cancer that can progress into invasive ductal carcinoma (IDC). Studies suggest DCIS is often overtreated since a considerable part of DCIS lesions may never progress into IDC. Lower grade lesions have a lower progression speed and risk, possibly allowing treatment de-escalation. However, studies show significant inter-observer variation in DCIS grading. Automated image analysis may provide an objective solution to address high subjectivity of DCIS grading by pathologists. In this study, we developed and evaluated a deep learning-based DCIS grading system. The system was developed using the consensus DCIS grade of three expert observers on a dataset of 1186 DCIS lesions from 59 patients. The inter-observer agreement, measured by quadratic weighted Cohen’s kappa, was used to evaluate the system and compare its performance to that of expert observers. We present an analysis of the lesion-level and patient-level inter-observer agreement on an independent test set of 1001 lesions from 50 patients. The deep learning system (dl) achieved on average slightly higher inter-observer agreement to the three observers (o1, o2 and o3) (κo1,dl = 0.81, κo2,dl = 0.53 and κo3,dl = 0.40) than the observers amongst each other (κo1,o2 = 0.58, κo1,o3 = 0.50 and κo2,o3 = 0.42) at the lesion-level. At the patient-level, the deep learning system achieved similar agreement to the observers (κo1,dl = 0.77, κo2,dl = 0.75 and κo3,dl = 0.70) as the observers amongst each other (κo1,o2 = 0.77, κo1,o3 = 0.75 and κo2,o3 = 0.72). The deep learning system better reflected the grading spectrum of DCIS than two of the observers. In conclusion, we developed a deep learning-based DCIS grading system that achieved a performance similar to expert observers. To the best of our knowledge, this is the first automated system for the grading of DCIS that could assist pathologists by providing robust and reproducible second opinions on DCIS grade.

Background: Manual qualitative and quantitative measures of terminal duct lobular unit (TDLU) involution were previously reported to be inversely associated with breast cancer risk. We developed and applied a deep learning method to yield quantitative measures of TDLU involution in normal breast tissue. We assessed the associations of these automated measures with breast cancer risk factors and risk. Methods: We obtained eight quantitative measures from whole slide images from a benign breast disease (BBD) nested case–control study within the Nurses' Health Studies (287 breast cancer cases and 1,083 controls). Qualitative assessments of TDLU involution were available for 177 cases and 857 controls. The associations between risk factors and quantitative measures among controls were assessed using analysis of covariance adjusting for age. The relationship between each measure and risk was evaluated using unconditional logistic regression, adjusting for the matching factors, BBD subtypes, parity, and menopausal status. Qualitative measures and breast cancer risk were evaluated accounting for matching factors and BBD subtypes. Results: Menopausal status and parity were significantly associated with all eight measures; select TDLU measures were associated with BBD histologic subtype, body mass index, and birth index (P &lt; 0.05). No measure was correlated with body size at ages 5–10 years, age at menarche, age at first birth, or breastfeeding history (P &gt; 0.05). Neither quantitative nor qualitative measures were associated with breast cancer risk. Conclusions: Among Nurses' Health Studies women diagnosed with BBD, TDLU involution is not a biomarker of subsequent breast cancer. Impact: TDLU involution may not impact breast cancer risk as previously thought.

Terminal ductal lobular unit (TDLU) involution is the regression of milk-producing structures in the breast. Women with less TDLU involution are more likely to develop breast cancer. A major bottleneck in studying TDLU involution in large cohort studies is the need for laborintensive manual assessment of TDLUs. We developed a computational pathology solution to automatically capture TDLU involution measures.Whole slide images (WSIs) of benign breast biopsies were obtained from the Nurses' Health Study (NHS). A first set of 92 WSIs was annotated for TDLUs, acini and adipose tissue to train deep convolutional neural network (CNN) models for detection of acini, and segmentation of TDLUs and adipose tissue. These networks were integrated into a single computational method to capture TDLU involution measures including number of TDLUs per tissue area (mm 2 ), median TDLU span (µm) and median number of acini per TDLU. We validated our method on 40 additional WSIs by comparing with manually acquired measures.Our CNN models detected acini with an F1 score of 0.73±0.09, and segmented TDLUs and adipose tissue with Dice scores of 0.86±0.11 and 0.86±0.04, respectively. The inter-observer ICC scores for manual assessments on 40 WSIs of number of TDLUs per tissue area, median TDLU span, and median acini count per TDLU were 0.71, 95% CI [0.51, 0.83], 0.81, 95% CI [0.67, 0.90], and 0.73, 95% CI [0.54, 0.85], respectively. Intra-observer reliability was evaluated on 10/40 WSIs with ICC scores of >0.8. Inter-observer ICC scores between automated results and the mean of the two observers were: 0.80, 95% CI [0.63, 0.90] for number of TDLUs per tissue area, 0.57, 95% CI [0.19, 0.77] for median TDLU span, and 0.80, 95% CI [0.62, 0.89] for median acini count per TDLU. TDLU involution measures evaluated by manual and automated assessment were inversely associated with age and menopausal status.We have developed a computational pathology method to measure TDLU involution. This technology eliminates the labor-intensiveness and subjectivity of manual TDLU assessment, and can be applied to future breast cancer risk studies. Wetstein et al. 3

and case study poster sessions will be conducted during the 2019 College of American Pathologists Annual Meeting (CAP19), which is scheduled for September 21 to 25, 2019. The meeting will take place at the Gaylord Palms Resort & Convention Center, Kissimmee, Florida. The poster sessions will occur in the CAP19 Exhibit Hall. Specific dates and times for each poster session are listed below; “poster focus” times are dedicated poster-viewing periods. Also shown before each poster session are the subject areas that will be presented.

Background Terminal duct lobular units (TDLUs) involute with age. Prior studies using qualitative or semi-quantitative measures of TDLU involution found inverse associations with breast cancer (BC) risk. We applied our validated deep learning computational method to yield quantitative measures of TDLU involution in normal breast tissue and then assessed their association with established BC risk factors and BC risk. Materials and Methods This study used a nested case-control design within the Nurses' Health Study cohorts. Cases and controls were diagnosed with benign breast disease (BBD) and cases subsequently developed BC (median 7.75 years later). Cases and controls were matched on year of BBD diagnosis, age at BC diagnosis (or index date for controls), and years between BBD and BC diagnosis (or index date). We applied our computational method to 3951 whole slide images of normal breast tissue from BBD biopsies (287 cases and 1083 controls; median 3 images per woman). Quantitative estimates of TDLU involution were derived for 3 standardized measures (median TDLU span, TDLU count per non-adipose tissue area, median acini count) and 5 novel measures (median TDLU area, TDLU area as a percentage of total tissue area, TDLU area as a percentage of total non-adipose tissue area, acini count per non-adipose tissue area, median acini density). TDLU involution was also manually categorized in 177 cases and 857 controls. Associations between TDLU involution measures and risk factors were evaluated among controls using Spearman's rho or Chi-squared tests. The relationship between each measure and BC risk was evaluated using logistic regression models controlling for the matching factors and BBD histological subtypes. Results All 8 TDLU measures were significantly inversely correlated with age at BBD biopsy (range: rho -0.07 to -0.42; p&lt;0.05) and menopausal status (p&lt;0.05). Parity was positively associated with 6 metrics (p&lt;0.05); birth index was inversely associated with another 6 metrics (p&lt;0.05). Select TDLU measures were also significantly associated with BBD histological subtype, BMI, age at first birth, and/or length of total breastfeeding (p&lt;0.05). No metric was significantly correlated with body size at ages 5-10 years or age of menarche. No quantitative TDLU involution measure was associated with subsequent BC risk; results remained null within strata of parity and menopausal status. Qualitative categorizations of TDLU involution were also not associated with BC risk (predominant lobule type 1 no type 3 versus no type 1, adjusted OR=0.95, 95%CI 0.54-1.71). Conclusion Quantitative measures of TDLU involution were associated with age and reproductive BC risk factors. However, automated and manual assessments of TDLU involution in normal tissue were not associated with BC risk. Further work will include applying our method to assess TDLU involution and BC risk in other cohorts. Citation Format: Kevin H. Kensler, Emily Z. Liu, Suzanne C. Wetstein, Allison M. Onken, Christina I. Luffman, Gabrielle M. Baker, Laura C. Collins, Stuart J. Schnitt, Vanessa C. Bret-Mounet, Mitko Veta, Josien P. Pluim, Ying Liu, Graham A. Colditz, Rulla M. Tamimi, Yu Jing Jan Heng. Automated quantitative measures of terminal duct lobular unit involution and breast cancer risk [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 4632.