The accelerating progress of network speed, reliability and security creates an increasing demand to move software and services from being stored and processed locally on users' machines to being managed by third parties that are accessible through the network. This has created the need to develop new software development methods and software architectural styles that meet these new demands. One such example in software architectural design is the recent emergence of the microservices architecture to address the maintenance and scalability demands of online service providers. As microservice architecture is a new research area, the need for a systematic mapping study is crucial in order to summarise the progress so far and identify the gaps and requirements for future studies. In this paper we present a systematic mapping study of microservices architectures and their implementation. Our study focuses on identifying architectural challenges, the architectural diagrams/views and quality attributes related to microsevice systems.

/pdf/a-systematic-mapping-study-in-microservice-architecture-28se10o7ki.pdf

A Systematic Mapping Study in Microservice Architecture

The 2008 LADIS workshop on Large Scale Distributed Systems brought together leaders from the commercial cloud computing community with researchers working on a variety of topics in distributed computing. The dialog yielded some surprises: some hot research topics seem to be of limited near-term importance to the cloud builders, while some of their practical challenges seem to pose new questions to us as systems researchers. This brief note summarizes our impressions.

/pdf/toward-a-cloud-computing-research-agenda-21jy7qmaks.pdf

Toward a cloud computing research agenda

Summary Background Mammography is the current standard for breast cancer screening. This study aimed to develop an artificial intelligence (AI) algorithm for diagnosis of breast cancer in mammography, and explore whether it could benefit radiologists by improving accuracy of diagnosis. Methods In this retrospective study, an AI algorithm was developed and validated with 170 230 mammography examinations collected from five institutions in South Korea, the USA, and the UK, including 36 468 cancer positive confirmed by biopsy, 59 544 benign confirmed by biopsy (8827 mammograms) or follow-up imaging (50 717 mammograms), and 74 218 normal. For the multicentre, observer-blinded, reader study, 320 mammograms (160 cancer positive, 64 benign, 96 normal) were independently obtained from two institutions. 14 radiologists participated as readers and assessed each mammogram in terms of likelihood of malignancy (LOM), location of malignancy, and necessity to recall the patient, first without and then with assistance of the AI algorithm. The performance of AI and radiologists was evaluated in terms of LOM-based area under the receiver operating characteristic curve (AUROC) and recall-based sensitivity and specificity. Findings The AI standalone performance was AUROC 0·959 (95% CI 0·952–0·966) overall, and 0·970 (0·963–0·978) in the South Korea dataset, 0·953 (0·938–0·968) in the USA dataset, and 0·938 (0·918–0·958) in the UK dataset. In the reader study, the performance level of AI was 0·940 (0·915–0·965), significantly higher than that of the radiologists without AI assistance (0·810, 95% CI 0·770–0·850; p Interpretation The AI algorithm developed with large-scale mammography data showed better diagnostic performance in breast cancer detection compared with radiologists. The significant improvement in radiologists' performance when aided by AI supports application of AI to mammograms as a diagnostic support tool. Funding Lunit.

https://ir.ymlib.yonsei.ac.kr/bitstream/22282913/175592/1/T202000784.pdf

Changes in cancer detection and false-positive recall in mammography using artificial intelligence: a retrospective, multireader study

Importance Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. Objective To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. Design, Setting, and Participants In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. Main Outcomes and Measurements Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists’ specificity with radiologists’ sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists’ recall assessment was developed and evaluated. Results Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists’ sensitivity, lower than community-practice radiologists’ specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. Conclusions and Relevance While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation.

https://jamanetwork.com/journals/jamanetworkopen/articlepdf/2761795/schaffter_2020_oi_200024.pdf

Evaluation of Combined Artificial Intelligence and Radiologist Assessment to Interpret Screening Mammograms

This paper proposes a Geo-distributed key-value datastore, named ChainReaction, that offers causal+ consistency, with high performance, fault-tolerance, and scalability. ChainReaction enforces causal+ consistency which is stronger than eventual consistency by leveraging on a new variant of chain replication. We have experimentally evaluated the benefits of our approach by running the Yahoo! Cloud Serving Benchmark. Experimental results show that ChainReaction has better performance in read intensive workloads while offering competitive performance for other workloads. Also we show that our solution requires less metadata when compared with previous work.

ChainReaction: a causal+ consistent datastore based on chain replication

We introduce SpiderCast, a distributed protocol for constructing scalable churn-resistant overlay topologies for supporting decentralized topic-based pub/sub communication. SpiderCast is designed to effectively tread the balance between average overlay degree and communication cost of event dissemination. It employs a novel coverage-optimizing heuristic in which the nodes utilize partial subscription views (provided by a decentralized membership service) to reduce the average node degree while guaranteeing (with high probability) that the events posted on each topic can be routed solely through the nodes interested in this topic (in other words, the overlay is topic-connected). SpiderCast is unique in maintaining an overlay topology that scales well with the average number of topics a node is subscribed to, assuming the subscriptions are correlated insofar as found in most typical workloads. Furthermore, the degree grows logarithmically in the total number of topics, and slowly decreases as the number of nodes increases.We show experimentally that, for many practical work-loads, the SpiderCast overlays are both topic-connected and have a low per-topic diameter while requiring each node to maintain a low average number of connections. These properties are satisfied even in very large settings involving up to 10,000 nodes, 1,000 topics, and 70 subscriptions per-node, and under high churn rates. In addition, our results demonstrate that, in a large setting, the average node degree in SpiderCast is at least 45% smaller than in other overlays typically used to support decentralized pub/sub communication (such as e.g., similarity-based, rings-based, and random overlays).

/pdf/spidercast-a-scalable-interest-aware-overlay-for-topic-based-1vfap1m157.pdf

SpiderCast: a scalable interest-aware overlay for topic-based pub/sub communication

We investigate the problem of designing a scalable overlay network to support decentralized topic-based pub/sub communication. We introduce a new optimization problem, called Minimum Topic-Connected Overlay (Min-TCO), that captures the tradeoff between the scalability of the overlay (in terms of the nodes' fanout) and the message forwarding overhead incurred by the communicating parties. Roughly, the Min-TCO problem is as follows: Given a collection of nodes and their subscriptions, connect the nodes using the minimum possible number of edges so that for each topic t, a message published on t could reach all the nodes interested in t by being forwarded by onlythe nodes interested in t.We show that the decision version of Min-TCO is NP-complete, and present a polynomial algorithm that approximates the optimal solution within a logarithmic factor with respect to the number of edges in theconstructed overlay. We further prove that this approximation ratio is almost tight by showing that no polynomial algorithm can approximate Min-TCO within a constant factor (unless P=NP). We show experimentally that on typical inputs, the fanout of the overlay constructed by our approximation algorithm is significantly lower thanthat of the overlays built by the existing algorithms, and that its running time is just a small fraction of the analytical worst case bound. As Min-TCO can be shown to capture several important aspects of most known overlay-based pub/sub implementations, our study sheds light on the inherent limitations of the existing systems as well asprovides an insight into the best possible feasible solution.Finally, we introduce a flexible framework that generalizes Min-TCO and formalizes most similar overlay design problems that occur in scalable pub/sub systems. We also briefly discuss several examples of such problems, and show some results with respect to their complexity.

http://people.csail.mit.edu/grishac/papers/podc07.pdf

Constructing scalable overlays for pub-sub with many topics

Background Computational models on the basis of deep neural networks are increasingly used to analyze health care data. However, the efficacy of traditional computational models in radiology is a matter of debate. Purpose To evaluate the accuracy and efficiency of a combined machine and deep learning approach for early breast cancer detection applied to a linked set of digital mammography images and electronic health records. Materials and Methods In this retrospective study, 52 936 images were collected in 13 234 women who underwent at least one mammogram between 2013 and 2017, and who had health records for at least 1 year before undergoing mammography. The algorithm was trained on 9611 mammograms and health records of women to make two breast cancer predictions: to predict biopsy malignancy and to differentiate normal from abnormal screening examinations. The study estimated the association of features with outcomes by using t test and Fisher exact test. The model comparisons were performed with a 95% confidence interval (CI) or by using the DeLong test. Results The resulting algorithm was validated in 1055 women and tested in 2548 women (mean age, 55 years ± 10 [standard deviation]). In the test set, the algorithm identified 34 of 71 (48%) false-negative findings on mammograms. For the malignancy prediction objective, the algorithm obtained an area under the receiver operating characteristic curve (AUC) of 0.91 (95% CI: 0.89, 0.93), with specificity of 77.3% (95% CI: 69.2%, 85.4%) at a sensitivity of 87%. When trained on clinical data alone, the model performed significantly better than the Gail model (AUC, 0.78 vs 0.54, respectively; P < .004). Conclusion The algorithm, which combined machine-learning and deep-learning approaches, can be applied to assess breast cancer at a level comparable to radiologists and has the potential to substantially reduce missed diagnoses of breast cancer. © RSNA, 2019 Online supplemental material is available for this article.

https://pubs.rsna.org/doi/pdf/10.1148/radiol.2019182622

Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms.

An effective means for building Internet-scale distributed applications, and in particular those involving group-based information sharing, is to deploy peer-to-peer overlay networks. The key pre-requisite for supporting these types of applications on top of the overlays is efficient distribution of messages to multiple subscribers dispersed across numerous multicast groups.In this paper, we introduce Magnet: a peer-to-peer publish/subscribe system which achieves efficient message distribution by dynamically organizing peers with similar subscriptions into dissemination structures which preserve locality in the subscription space. Magnet is able to significantly reduce the message propagation costs by taking advantage of subscription correlations present in many large-scale group-based applications.We evaluate Magnet by comparing its performance against a strawman pub/sub system which does not cluster similar subscriptions by simulation. We find that Magnet outperforms the strawman by a substantial margin on clustered subscription workloads produced using both generative models and real application traces.

/pdf/magnet-practical-subscription-clustering-for-internet-scale-48xdj4pgow.pdf

Magnet: practical subscription clustering for Internet-scale publish/subscribe

Peer-to-peer (P2P) networks suffer from the problem of "free-loaders", i.e., users who consume resources without contributing anything in return. In this paper, we tackle this problem taking a game theoretic perspective by modeling the system as a non-cooperative game. We introduce Equi-Cast, a wide-area P2P multicast protocol for large groups of selfish nodes. EquiCast is the first P2P multicast protocol that is formally proven to enforce cooperation in selfish environments. Additionally, we prove that EquiCast incurs a low constant load on each user.

/pdf/equicast-scalable-multicast-with-selfish-users-2bgsx5iitg.pdf

Roie Melamed

Papers

SpiderCast: a scalable interest-aware overlay for topic-based pub/sub communication

Constructing scalable overlays for pub-sub with many topics

Predicting Breast Cancer by Applying Deep Learning to Linked Health Records and Mammograms.

Magnet: practical subscription clustering for Internet-scale publish/subscribe

EquiCast: scalable multicast with selfish users