LYSTO: The Lymphocyte Assessment Hackathon and Benchmark Dataset.

We introduce LYSTO, the Lymphocyte Assessment Hackathon, which was held in conjunction with the MICCAI 2019 Conference in Shenzhen (China). The competition required participants to automatically assess the number of lymphocytes, in particular T-cells, in images of colon, breast, and prostate cancer stained with CD3 and CD8 immunohistochemistry. Differently from other challenges setup in medical image analysis, LYSTO participants were solely given a few hours to address this problem. In this paper, we describe the goal and the multi-phase organization of the hackathon; we describe the proposed methods and the on-site results. Additionally, we present post-competition results where we show how the presented methods perform on an independent set of lung cancer slides, which was not part of the initial competition, as well as a comparison on lymphocyte assessment between presented methods and a panel of pathologists. We show that some of the participants were capable to achieve pathologist-level performance at lymphocyte assessment. After the hackathon, LYSTO was left as a lightweight plug-and-play benchmark dataset on grand-challenge website, together with an automatic evaluation platform.

Deep learning-based breast cancer grading and survival analysis on whole-slide histopathology images.

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.

Adversarial attack vulnerability of medical image analysis systems: Unexplored factors.

Adversarial attacks are considered a potentially serious security threat for machine learning systems. Medical image analysis (MedIA) systems have recently been argued to be vulnerable to adversarial attacks due to strong financial incentives and the associated technological infrastructure. In this paper, we study previously unexplored factors affecting adversarial attack vulnerability of deep learning MedIA systems in three medical domains: ophthalmology, radiology, and pathology. We focus on adversarial black-box settings, in which the attacker does not have full access to the target model and usually uses another model, commonly referred to as surrogate model, to craft adversarial examples that are then transferred to the target model. We consider this to be the most realistic scenario for MedIA systems. Firstly, we study the effect of weight initialization (pre-training on ImageNet or random initialization) on the transferability of adversarial attacks from the surrogate model to the target model, i.e., how effective attacks crafted using the surrogate model are on the target model. Secondly, we study the influence of differences in development (training and validation) data between target and surrogate models. We further study the interaction of weight initialization and data differences with differences in model architecture. All experiments were done with a perturbation degree tuned to ensure maximal transferability at minimal visual perceptibility of the attacks. Our experiments show that pre-training may dramatically increase the transferability of adversarial examples, even when the target and surrogate's architectures are different: the larger the performance gain using pre-training, the larger the transferability. Differences in the development data between target and surrogate models considerably decrease the performance of the attack; this decrease is further amplified by difference in the model architecture. We believe these factors should be considered when developing security-critical MedIA systems planned to be deployed in clinical practice. We recommend avoiding using only standard components, such as pre-trained architectures and publicly available datasets, as well as disclosure of design specifications, in addition to using adversarial defense methods. When evaluating the vulnerability of MedIA systems to adversarial attacks, various attack scenarios and target-surrogate differences should be simulated to achieve realistic robustness estimates. The code and all trained models used in our experiments are publicly available.3.

Deep learning-based grading of ductal carcinoma in situ in breast histopathology images.

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.

Automated Quantitative Measures of Terminal Duct Lobular Unit Involution and Breast Cancer Risk.

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 < 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 > 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.

Deep learning assessment of breast terminal duct lobular unit involution: Towards automated prediction of breast cancer risk.

Terminal duct 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 labor-intensive 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. A set of 92 WSIs was annotated for acini, TDLUs 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, median TDLU span 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±0.07, and segmented TDLUs and adipose tissue with Dice scores of 0.84±0.13 and 0.87±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, 0.81 and 0.73, 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 for number of TDLUs per tissue area, 0.57 for median TDLU span, and 0.80 for median acini count per TDLU. TDLU involution measures evaluated by manual and automated assessment were inversely associated with age and menopausal status. We 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.