Challenge Contest Research Articles

The utility of a deep learning-based approach in Her-2/neu assessment in breast cancer

IntroductionHER-2/neu is a protein present on the surface of specific cancer cells and has been linked to the development and progression of certain cancer types. It is present in 15 to 20% of breast cancers and is clinically significant due to the availability of multiple anti-Her2 treatment options. Immunohistochemistry (IHC) is the most commonly used method to evaluate and quantify the expression of Her-2/neu. Although IHC is well-standardized in clinical practice, it is still subjected to inter-observer variability. Automating Her-2/neu scoring can improve accuracy, efficiency, consistency, and cost-effectiveness while reducing pathologists' workload. Materials and MethodsA deep learning-based automatic framework was utilized for the automatic detection of Her-2/neu score from whole slide images (WSI). The framework consists of three phases: identification of tumor patches, scoring of tumor patches, and Her-2/neu score prediction for whole slide images (WSI) based on the distribution of each score. This work used the dataset from the University of Warwick HER2 challenge contest. Two expert pathologists evaluated all 86 WSIs and assigned Her-2/neu scores to them. In addition, patches were generated from 50 WSIs and annotated individually by the pathologists. A total of 6641 extracted patches were generated out of which, 947 were labeled as 0, 327 as 1+, 1401 as 2+, 2950 as 3+, and 1016 were marked for discarding. Four pre-trained image classification models, namely DenseNet201, GoogleNet, MobileNet_v2, and a Vision Transformer based model, were fine-tuned, and tested on the generated patches. In order to predict the Her-2/neu score of the entire WSI, a random forest classifier was trained to predict the Her-2/neu score from the percentages of patches of each score present in the whole slide image. ResultsIn patch classification performances, the vision transformer-based model outperformed the other models by achieving an accuracy of 92.6% on tumor patch classification and 91.15% on patch score classification. The random forest classifier achieved an accuracy of 88% on four score classification (0, 1+, 2 + and 3 + ) and 96% on three score classification (0/1+, 2 + and 3 + ). ConclusionThe proposed deep learning-based framework for the automatic detection and evaluation of Her-2/neu expression in breast cancer obtained encouraging results. This framework has the potential to be used as a prognostic tool, providing a cost-effective and time-efficient alternative for generating clinically relevant results. However, additional research is required to assess the applicability of this pipeline in different contexts.

PD31-10 PRODUCTION OF VASCULARIZED FUNCTIONAL ORGAN CONSTRUCTS WITH LONG-TERM SURVIVAL

You have accessJournal of UrologyCME1 Apr 2023PD31-10 PRODUCTION OF VASCULARIZED FUNCTIONAL ORGAN CONSTRUCTS WITH LONG-TERM SURVIVAL Kelsey Willson, Sang Jin Lee, Young-Wook Moon, John Jackson, Colin Bishop, James Yoo, and Anthony Atala Kelsey WillsonKelsey Willson More articles by this author , Sang Jin LeeSang Jin Lee More articles by this author , Young-Wook MoonYoung-Wook Moon More articles by this author , John JacksonJohn Jackson More articles by this author , Colin BishopColin Bishop More articles by this author , James YooJames Yoo More articles by this author , and Anthony AtalaAnthony Atala More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003324.10AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Developing large vascularized tissue constructs that can maintain long-term is an ongoing challenge. A strategy that has been gaining much attention is to bioengineer prevascularize tissue constructs that allow for immediate perfusion. We present the development of a large vascularized functional human liver construct that can be maintained for 30 days with high viability METHODS: Vascularized human liver tissue constructs of 1.5 cm in diameter and 6 cm in length were fabricated using an extrusion-based 3D printing system, seeded with hepatocytes (HepG2) in bulk hydrogel (alginate) and human umbilical vein endothelial cells (HUVECs) within the vascular channels. The alginate/HepG2 mixture was placed into a mold. A sacrificial gel (calcium chloride/HUVECs) was used to create vessels. Post printing, the samples were cured using calcium chloride and incubated at 37°C to liquefy the sacrificial gel. The liver tissue constructs were maintained in a media bath for 4 days, followed by media perfusion for 30 days using a peristaltic pump. The tissue samples were removed every 10 days and analyzed for cellular viability and biochemical functionality (albumin/bilirubin production). Immunohistochemistry was used to confirm the location of hepatocytes and endothelial cells. RESULTS: Alginate and calcium chloride was successfully used to fabricate constructs patterned with internal vascular channels running the entire length of the construct. The final constructs were cylindrical and maintained their structural integrity. The liver tissue samples showed high viability following fabrication and maintained a greater than 94 percent viability throughout the 30-day time point. The liver tissue constructs produced albumin and bilirubin at levels comparable to human liver tissue (assayed at 10, 20, and 30 days). In the retrieved constructs endothelial cells were identified on the vascular channel walls surrounded by hepatocytes in the hydrogel. CONCLUSIONS: We have successfully created large vascularized liver tissue constructs patterned with hollow channels using 3D bioprinting. The combination of perfusion and internal channels maintained high viability for 30 days. The liver tissue constructs produced albumin and bilirubin levels comparable to human liver tissue. This is a major step towards creating large vascularized functional liver tissue constructs that could be used for translational applications. Source of Funding: This work is a winner of NASA’s Vascular Tissue Challenge contest. The authors thank NASA for supporting this work in a zero-gravity environment on the International Space Station © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e904 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Kelsey Willson More articles by this author Sang Jin Lee More articles by this author Young-Wook Moon More articles by this author John Jackson More articles by this author Colin Bishop More articles by this author James Yoo More articles by this author Anthony Atala More articles by this author Expand All Advertisement PDF downloadLoading ...

Engaging Youth and Young Adults in the COVID-19 Pandemic Response via the "It's Our Turn" Crowdsourcing Contest.

As the coronavirus disease (COVID-19) pandemic continued to progress into 2021, appeals were made to take a stronger focus on the perceptions and practices of youth and young adults (YYAs) regarding COVID-19 mitigation, as well as the impact of mitigation strategies on the overall wellbeing of YYAs. In this paper, we describe our efforts to increase YYA engagement in Arizona's COVID-19 response by pairing embedded values from youth participatory action research (YPAR) with a crowdsourcing challenge contest design. The research protocol and implementation are described, followed by a thematic analysis of YYA-led messaging portrayed in 23 contest submissions and reflections formed by 223 community voters after viewing contest submissions. The authors conclude that a YYA-led crowdsourcing contest presented an opportunity to (a.) investigate the perceptions and behaviors of YYAs and their networks regarding the COVID-19 pandemic and mitigation efforts and (b.) amplify the voices of YYAs in the pandemic response. Perhaps even more importantly, this approach also offered insight into the exacerbated impact of the pandemic on YYA mental health and wellbeing, and the utility of YPAR in raising awareness of these effects among the contexts and social networks of YYAs.

Multiparallel MMT: Faster ISD Algorithm Solving High-Dimensional Syndrome Decoding Problem

The hardness of the syndrome decoding problem (SDP) is the primary evidence for the security of code-based cryptosystems, which are one of the finalists in a project to standardize post-quantum cryptography conducted by the U.S. National Institute of Standards and Technology (NIST-PQC). Information set decoding (ISD) is a general term for algorithms that solve SDP efficiently. In this paper, we conducted a concrete analysis of the time complexity of the latest ISD algorithms under the limitation of memory using the syndrome decoding estimator proposed by Esser et al. As a result, we present that theoretically nonoptimal ISDs, such as May-Meurer-Thomae (MMT) and May-Ozerov, have lower time complexity than other ISDs in some actual SDP instances. Based on these facts, we further studied the possibility of multiple parallelization for these ISDs and proposed the first GPU algorithm for MMT, the multiparallel MMT algorithm. In the experiments, we show that the multiparallel MMT algorithm is faster than existing ISD algorithms. In addition, we report the first successful attempts to solve the 510-, 530-, 540- and 550-dimensional SDP instances in the Decoding Challenge contest using the multiparallel MMT.

Unpacking the challenges of conducting embedded, learning health system research: The winning entries of a Challenge Contest sponsored by AcademyHealth.

Unpacking the challenges of conducting embedded, learning health system research: The winning entries of a Challenge Contest sponsored by AcademyHealth.

Approaching healthcare delivery through a new lens: a crowdsourcing challenge to identify health-related social innovations to increase universal health coverage in Nigeria

BackgroundNigeria, the most populous country in Africa, is faced with several health challenges including neglected tropical diseases, non-communicable diseases and emerging infectious diseases. Unfortunately, the country has a weak health...

ECG-based expert-knowledge attention network to tachyarrhythmia recognition

An expert-knowledge attention network (EKANet) was designed to improve the accuracy of arrhythmia diagnosis and reduce the recheck time. This network classifies four tachyarrhythmia on electrocardiogram (ECG) signals, encompassing most arrhythmia diseases. In the EKANet, two attention modules based on the knowledge of cardiology can rapidly capture the ECG rhythm and P waves in multiple leads without any training. This mechanism is performed to reduce the computational time of re-building a model. The EKANet integrates a six-layer convolutional neural network (CNN) and a gated recurrent unit (GRU) as the classifier to realise the tachyarrhythmia classification. The EKANet outperformed 1D CNN and ArrhythmiaNet on the MIT-BIH datasets by 3.1% on average accuracy. Furthermore, the EKANet achieved approximately 8.5% and 3.9% average F1-score increases on the dataset of China ECG challenge contest compared with time-incremental CNN (TI-CNN) and attention-based TI-CNN, respectively. Meanwhile, the EKANet has a much lower complexity than that of the other typical models with a competitive accuracy.

What can Analysis of the Organizations’ Web Sites tell us about AI? Comparative Study of the Online Resources operated at Google, Yandex, and Baidu

The current social and cultural debates on AI and how it is being embedded into the reality of social life have reignited scientific debates on how to study AI, what counts as data, and the conditions under which information and data pertaining AI turn into knowledge. In this paper the authors’ focus was exploring new sources of data on AI and methods of AI phenomena examination. The paper presents the results of a comparative analysis of Google, Yandex, and Baidu’s websites. Contrary to these companies commonly being perceived as online search engines, Google, Baidu, and Yandex have multiple offerings across mobile products and services, knowledge products, translation services, open platforms for startups, PC client software and AI technologies. In the first part of the paper the authors compare information presented on these companies’ websites about their goals, their technologies, how they define AI, the proclaimed social problems associated with using AI, and the forms of interaction between these companies and their audiences. The second part of the paper analyzes 20 projects that won the Google AI Impact Challenge contest. Analyzing these projects allowed for identifying areas of application of AI technologies inside and outside organizations, for characterizing AI’s potential roles as a mediator in relations between people, and finally for highlighting utopian and dystopian scenarios associated with implementing AI in social relations. In the conclusion the authors formulate a set of broader questions for social analytics concerning artificial intelligence grounded in the results of their analysis.

Joint international consensus statement on crowdsourcing challenge contests in health and medicine: results of a modified Delphi process

ObjectivesTo develop a consensus statement to provide advice on designing, implementing and evaluating crowdsourcing challenge contests in public health and medical contexts.DesignModified Delphi using three rounds of survey questionnaires and...

\u2018When she rises, we all rise\u2019: a crowdsourcing challenge to increase women\u2019s participation in an infectious diseases research fellowship

BackgroundWomen are under-represented in many mid-career infectious diseases research fellowships, including a TDR fellowship for low- and middle-income country (LMIC) researchers. TDR solicited creative ideas as part of a challenge contest to increase the number of women fellowship applicants. The purpose of this study is to examine themes from submitted ideas and the impact of implementing the top three ideas on the number of women applicants.MethodsWe solicited ideas for modifying the TDR fellowship using a crowdsourcing challenge. Then we used a mixed methods approach to evaluate texts submitted in response to the challenge. The qualitative analysis identified themes from eligible submissions. The quantitative analysis examined the mean score (1–10 scale) assigned to submitted ideas and also the number of eligible women applicants before (2014–7) and after (2018) implementing the top three ideas.ResultsWe received 311 ideas on improving women’s participation in this fellowship from 63 countries. Among all ideas, 282 (91%) were from women and 286 (92%) were from low- and middle-income countries (LMICs). Thirty-three (17%) ideas received an overall mean score of 7.0 or greater. The top three ideas included enhanced social media communication targeting women, improving career mentorship, and creating a nomination system to nudge women applicants. These ideas were implemented as part of the 2018 fellowship application cycle. The number of eligible women applicants increased from 11 in 2016 to 48 in 2018. The number of eligible men applicants increased from 55 in 2016 to 114 in 2018. Women represent 44% (8/18) of the 2018 cohort.ConclusionThis suggests that the challenge contest resulted in strong participation from women in LMICs. The three top ideas likely contributed to a greater number of women applicants to this mid-career fellowship. Further ways of enhancing women’s participation in global health training are needed.

How Active Service Participation by Engineering Undergraduates is Paving Way to Enhance Eco-friendly Projects?

Abstract Today’s youth is tomorrow’s promise and tomorrow’s promise is our students. It is said that youth period is like soft clay in the hands of a potter. We need to channelize the potentials and technical skills of the students to facilitate the growth of the society and nation. The engineering education should train the students with adequate technological skills and unfold them as best human beings along with a sense of socio-economic and civic responsibility. Today, requirements for engineering programs reflect a movement with a paradigm shift in the existing practices to resolve the current engineering education problems.Many engineering educators see service learning as a way to enhance their programs by exposing students to engineering context, moreovergiving them a chance to develop professional and interpersonal skills. During the process, qualitative and quantitative surveys were done to collect longitudinal data from electrical and electronics engineering undergraduates (n=65) who have been the winners for consecutive two years of National solar vehicle challenge (NSVC) contest. NSVC is an annual contest organized by dynamic motors with a vision to stir young technocrats to make way for India to become the largest renewable energy hub in the world. The pre-test and post-test survey consist of demographics and qualitative questions. The outcome variables analyzed are civic responsibility, eagerness in service participation, knowledge on eco-friendly projects and sustainable thinking level of the engineering undergraduates.Service participation showed significant positive effects on all the outcome measures among 25% of the actively participated engineering undergraduates. In addition, they were technically enhanced to design single /multi sitter, light weighed and efficient solar vehicles.

Diagnostics and antimicrobial resistance: A clinical case challenge contest

Diagnostics and antimicrobial resistance: A clinical case challenge contest

Learning Where to See: A Novel Attention Model for Automated Immunohistochemical Scoring.

Estimating over-amplification of human epidermal growth factor receptor 2 (HER2) on invasive breast cancer is regarded as a significant predictive and prognostic marker. We propose a novel deep reinforcement learning (DRL)-based model that treats immunohistochemical (IHC) scoring of HER2 as a sequential learning task. For a given image tile sampled from multi-resolution giga-pixel whole slide image (WSI), the model learns to sequentially identify some of the diagnostically relevant regions of interest (ROIs) by following a parameterized policy. The selected ROIs are processed by recurrent and residual convolution networks to learn the discriminative features for different HER2 scores and predict the next location, without requiring to process all the sub-image patches of a given tile for predicting the HER2 score, mimicking the histopathologist who would not usually analyze every part of the slide at the highest magnification. The proposed model incorporates a task-specific regularization term and inhibition of return mechanism to prevent the model from revisiting the previously attended locations. We evaluated our model on two IHC datasets: a publicly available dataset from the HER2 scoring challenge contest and another dataset consisting of WSIs of gastroenteropancreatic neuroendocrine tumor sections stained with Glo1 marker. We demonstrate that the proposed model outperforms other methods based on state-of-the-art deep convolutional networks. To the best of our knowledge, this is the first study using DRL for IHC scoring and could potentially lead to wider use of DRL in the domain of computational pathology reducing the computational burden of the analysis of large multi-gigapixel histology images.

Segmentation of glandular epithelium in colorectal tumours to automatically compartmentalise IHC biomarker quantification: A deep learning approach.

In this paper, we propose a method for automatically annotating slide images from colorectal tissue samples. Our objective is to segment glandular epithelium in histological images from tissue slides submitted to different staining techniques, including usual haematoxylin-eosin (H&E) as well as immunohistochemistry (IHC). The proposed method makes use of Deep Learning and is based on a new convolutional network architecture. Our method achieves better performances than the state of the art on the H&E images of the GlaS challenge contest, whereas it uses only the haematoxylin colour channel extracted by colour deconvolution from the RGB images in order to extend its applicability to IHC. The network only needs to be fine-tuned on a small number of additional examples to be accurate on a new IHC dataset. Our approach also includes a new method of data augmentation to achieve good generalisation when working with different experimental conditions and different IHC markers. We show that our methodology enables to automate the compartmentalisation of the IHC biomarker analysis, results concurring highly with manual annotations.

FASCINATING READ MOVIE LIKE: PENERAPAN MEDIA SOSIAL INSTAGRAM SEBAGAI PROMOSI RUANG BACA VOKASI UNIVERSITAS BRAWIJAYA

The rise of the use of social networking media instagram among modern society, especially among teenagers make the social networking media is very popular today. One of the utilization of information technology in the library is by using social media for various library interests. Included in the college library. One of the topics of promotional issues is through a film adapted from the novel. Therefore the vocational reading room using social media instagram as a communication service with users who no other is a vocational student. The targets in this campaign are the increasing number of Instagram Spreadsheet Readers, likes, comments, and hashtag # 4FAMEruangbacavokasi. In this research, researchers use qualitative research methods. Data collection is done using observation and interview techniques. Qualitative research is used because data collection is done when the research is more to throw an object such as photo challenge contest with the theme Fascinating Read Movie Like. After the photo challenge is completed the researchers also held an interview about how the opinion of the participants in the race held in the vocational reading room. The result of this research is the implementation cycle conducted by researchers as much as four cycles. The first cycle applied 12 times post, second cycle applied 8 times post, third cycle applied 10 post and fourth cycle only 1 post. Within a period of three weeks photo challenge was held, there are eleven followers who follow this photo challenge contest. Of the total participants are drawn four winners with the most like, the most interesting photos and comments.

The Mayhem Cyber Reasoning System

Mayhem is one of the first generation of autonomous computer security bots that finds and fixes vulnerabilities without any human intervention. Mayhem won the DARPA Cyber Grand Challenge (CGC) contest and $2,000,000 in August 2016 against six other finalists. The contest was the result of a two-year DARPA program, but the R&D necessary to compete stands on the shoulders of decades of basic academic and industry scientific research in program analysis, verification, and self-healing systems. The Mayhem system alone was developed over a decade of research in academia, which was spun out to a company called ForAllSecure. Mayhem is now being commercialized by ForAllSecure to autonomously check and protect the world’s software from exploitable bugs. In this article, we look back and give our story in creating Mayhem, and also look forward to a vision where autonomous security bots like Mayhem will radically improve the security of computer systems.

Ciphertext-only cryptanalysis of short Hagelin M-209 ciphertexts

ABSTRACTThe Hagelin M-209 was a mechanical encryption device used by the U.S. Army during World War 2 (WWII) and the Korean War, as well as by other armies and diplomatic services. The Hagelin M-209 has been the focus of extensive research by codebreaking agencies. Several ciphertext-only attacks have been published, but, those attacks are applicable only to the case of long cryptograms. In this article, the authors present a nested hill-climbing and simulated annealing algorithm for recovering the full key settings from ciphertext only, with ciphertexts as short as 500 letters, compared to a minimum of 750 to 1,250 letters with prior methods. With this method, the authors have solved the last problem of a public Hagelin M-209 challenge contest.

HER2 challenge contest: a detailed assessment of automated HER2 scoring algorithms in whole slide images of breast cancer tissues.

Evaluating expression of the human epidermal growth factor receptor 2 (HER2) by visual examination of immunohistochemistry (IHC) on invasive breast cancer (BCa) is a key part of the diagnostic assessment of BCa due to its recognized importance as a predictive and prognostic marker in clinical practice. However, visual scoring of HER2 is subjective, and consequently prone to interobserver variability. Given the prognostic and therapeutic implications of HER2 scoring, a more objective method is required. In this paper, we report on a recent automated HER2 scoring contest, held in conjunction with the annual PathSoc meeting held in Nottingham in June 2016, aimed at systematically comparing and advancing the state-of-the-art artificial intelligence (AI)-based automated methods for HER2 scoring. The contest data set comprised digitized whole slide images (WSI) of sections from 86 cases of invasive breast carcinoma stained with both haematoxylin and eosin (H&E) and IHC for HER2. The contesting algorithms predicted scores of the IHC slides automatically for an unseen subset of the data set and the predicted scores were compared with the 'ground truth' (a consensus score from at least two experts). We also report on a simple 'Man versus Machine' contest for the scoring of HER2 and show that the automated methods could beat the pathology experts on this contest data set. This paper presents a benchmark for comparing the performance of automated algorithms for scoring of HER2. It also demonstrates the enormous potential of automated algorithms in assisting the pathologist with objective IHC scoring.

Robust detection and segmentation of cell nuclei in biomedical images based on a computational topology framework.

The segmentation of cell nuclei is an important step towards the automated analysis of histological images. The presence of a large number of nuclei in whole-slide images necessitates methods that are computationally tractable in addition to being effective. In this work, a method is developed for the robust segmentation of cell nuclei in histological images based on the principles of persistent homology. More specifically, an abstract simplicial homology approach for image segmentation is established. Essentially, the approach deals with the persistence of disconnected sets in the image, thus identifying salient regions that express patterns of persistence. By introducing an image representation based on topological features, the task of segmentation is less dependent on variations of color or texture. This results in a novel approach that generalizes well and provides stable performance. The method conceptualizes regions of interest (cell nuclei) pertinent to their topological features in a successful manner. The time cost of the proposed approach is lower-bounded by an almost linear behavior and upper-bounded by O(n2) in a worst-case scenario. Time complexity matches a quasilinear behavior which is O(n1+ɛ) for ε < 1. Images acquired from histological sections of liver tissue are used as a case study to demonstrate the effectiveness of the approach. The histological landscape consists of hepatocytes and non-parenchymal cells. The accuracy of the proposed methodology is verified against an automated workflow created by the output of a conventional filter bank (validated by experts) and the supervised training of a random forest classifier. The results are obtained on a per-object basis. The proposed workflow successfully detected both hepatocyte and non-parenchymal cell nuclei with an accuracy of 84.6%, and hepatocyte cell nuclei only with an accuracy of 86.2%. A public histological dataset with supplied ground-truth data is also used for evaluating the performance of the proposed approach (accuracy: 94.5%). Further validations are carried out with a publicly available dataset and ground-truth data from the Gland Segmentation in Colon Histology Images Challenge (GlaS) contest. The proposed method is useful for obtaining unsupervised robust initial segmentations that can be further integrated in image/data processing and management pipelines. The development of a fully automated system supporting a human expert provides tangible benefits in the context of clinical decision-making.

Competitive Algorithms for Coevolving Both Game Content and AI. A Case Study: &lt;italic&gt;Planet Wars&lt;/italic&gt;

The classical approach of competitive coevolution (CC) applied in games tries to exploit an arms race between coevolving populations that belong to the same species (or at least to the same biotic niche), namely strategies, rules, tracks for racing, or any other. This paper proposes the coevolution of entities belonging to different realms (namely biotic and abiotic) via a competitive approach. More precisely, we aim to coevolutionarily optimize both virtual players and game content. From a general perspective, our proposal can be viewed as a method of procedural content generation combined with a technique for generating game AI. This approach can not only help game designers in game creation but also generate content personalized to both specific players’ profiles and game designer’s objectives (e.g., create content that favors novice players over skillful players). As a case study we use Planet Wars , the real-time strategy (RTS) game associated with the 2010 Google AI Challenge contest, and demonstrate (via an empirical study) the validity of our approach.