Ralph Deters

Mayra Samaniego, Sara Hosseinzadeh Kassani, Cristian Espana et al.

Computer-Aided Diagnosis (CAD) systems have emerged to support clinicians in interpreting medical images. CAD systems are traditionally combined with artificial intelligence (AI), computer vision, and data augmentation to evaluate suspicious structures in medical images. This evaluation generates vast amounts of data. Traditional CAD systems belong to a single institution and handle data access management centrally. However, the advent of CAD systems for research among multiple institutions demands distributed access management. This research proposes a blockchain-based solution to enable distributed data access management in CAD systems. This solution has been developed as a distributed application (DApp) using Ethereum in a consortium network.

Sara Rouhani, Rafael Belchior, Rui S. Cruz et al.

Auditing provides an essential security control in computer systems, by keeping track of all access attempts, including both legitimate and illegal access attempts. This phase can be useful to the context of audits, where eventual misbehaving parties can be held accountable. Blockchain technology can provide trusted auditability required for access control systems. In this paper, we propose a distributed \ac{ABAC} system based on blockchain to provide trusted auditing of access attempts. Besides auditability, our system presents a level of transparency that both access requestors and resource owners can benefit from it. We present a system architecture with an implementation based on Hyperledger Fabric, achieving high efficiency and low computational overhead. The proposed solution is validated through a use case of independent digital libraries. Detailed performance analysis of our implementation is presented, taking into account different consensus mechanisms and databases. The experimental evaluation shows that our presented system can process 5,000 access control requests with the send rate of 200 per second and a latency of 0.3 seconds.

Sara Hosseinzadeh Kassani, Peyman Hosseinzadeh Kassani, Michal J. Wesolowski et al.

Colorectal cancer is the third most common cancer-related death after lung cancer and breast cancer worldwide. The risk of developing colorectal cancer could be reduced by early diagnosis of polyps during a colonoscopy. Computer-aided diagnosis systems have the potential to be applied for polyp screening and reduce the number of missing polyps. In this paper, we compare the performance of different deep learning architectures as feature extractors, i.e. ResNet, DenseNet, InceptionV3, InceptionResNetV2 and SE-ResNeXt in the encoder part of a U-Net architecture. We validated the performance of presented ensemble models on the CVC-Clinic (GIANA 2018) dataset. The DenseNet169 feature extractor combined with U-Net architecture outperformed the other counterparts and achieved an accuracy of 99.15\%, Dice similarity coefficient of 90.87%, and Jaccard index of 83.82%.

Sara Hosseinzadeh Kassani, Peyman Hosseinzadeh Kassasni, Michal J. Wesolowski et al.

The newly identified Coronavirus pneumonia, subsequently termed COVID-19, is highly transmittable and pathogenic with no clinically approved antiviral drug or vaccine available for treatment. The most common symptoms of COVID-19 are dry cough, sore throat, and fever. Symptoms can progress to a severe form of pneumonia with critical complications, including septic shock, pulmonary edema, acute respiratory distress syndrome and multi-organ failure. While medical imaging is not currently recommended in Canada for primary diagnosis of COVID-19, computer-aided diagnosis systems could assist in the early detection of COVID-19 abnormalities and help to monitor the progression of the disease, potentially reduce mortality rates. In this study, we compare popular deep learning-based feature extraction frameworks for automatic COVID-19 classification. To obtain the most accurate feature, which is an essential component of learning, MobileNet, DenseNet, Xception, ResNet, InceptionV3, InceptionResNetV2, VGGNet, NASNet were chosen amongst a pool of deep convolutional neural networks. The extracted features were then fed into several machine learning classifiers to classify subjects as either a case of COVID-19 or a control. This approach avoided task-specific data pre-processing methods to support a better generalization ability for unseen data. The performance of the proposed method was validated on a publicly available COVID-19 dataset of chest X-ray and CT images. The DenseNet121 feature extractor with Bagging tree classifier achieved the best performance with 99% classification accuracy. The second-best learner was a hybrid of the a ResNet50 feature extractor trained by LightGBM with an accuracy of 98%.

Sara Hosseinzadeh Kassani, Peyman Hosseinzadeh Kassani, Michal J. Wesolowski et al.

Breast cancer is one of the leading causes of death across the world in women. Early diagnosis of this type of cancer is critical for treatment and patient care. Computer-aided detection (CAD) systems using convolutional neural networks (CNN) could assist in the classification of abnormalities. In this study, we proposed an ensemble deep learning-based approach for automatic binary classification of breast histology images. The proposed ensemble model adapts three pre-trained CNNs, namely VGG19, MobileNet, and DenseNet. The ensemble model is used for the feature representation and extraction steps. The extracted features are then fed into a multi-layer perceptron classifier to carry out the classification task. Various pre-processing and CNN tuning techniques such as stain-normalization, data augmentation, hyperparameter tuning, and fine-tuning are used to train the model. The proposed method is validated on four publicly available benchmark datasets, i.e., ICIAR, BreakHis, PatchCamelyon, and Bioimaging. The proposed multi-model ensemble method obtains better predictions than single classifiers and machine learning algorithms with accuracies of 98.13%, 95.00%, 94.64% and 83.10% for BreakHis, ICIAR, PatchCamelyon and Bioimaging datasets, respectively.

Sara Hosseinzadeh Kassani, Peyman Hosseinzadeh kassani, Michal J. Wesolowski et al.

Automatic detection of leukemic B-lymphoblast cancer in microscopic images is very challenging due to the complicated nature of histopathological structures. To tackle this issue, an automatic and robust diagnostic system is required for early detection and treatment. In this paper, an automated deep learning-based method is proposed to distinguish between immature leukemic blasts and normal cells. The proposed deep learning based hybrid method, which is enriched by different data augmentation techniques, is able to extract high-level features from input images. Results demonstrate that the proposed model yields better prediction than individual models for Leukemic B-lymphoblast classification with 96.17% overall accuracy, 95.17% sensitivity and 98.58% specificity. Fusing the features extracted from intermediate layers, our approach has the potential to improve the overall classification performance.

Sara Hosseinzadeh Kassani, Peyman Hosseinzadeh Kassani, Michal J. Wesolowski et al.

Breast cancer is one of the most common causes of cancer-related death in women worldwide. Early and accurate diagnosis of breast cancer may significantly increase the survival rate of patients. In this study, we aim to develop a fully automatic, deep learning-based, method using descriptor features extracted by Deep Convolutional Neural Network (DCNN) models and pooling operation for the classification of hematoxylin and eosin stain (H&E) histological breast cancer images provided as a part of the International Conference on Image Analysis and Recognition (ICIAR) 2018 Grand Challenge on BreAst Cancer Histology (BACH) Images. Different data augmentation methods are applied to optimize the DCNN performance. We also investigated the efficacy of different stain normalization methods as a pre-processing step. The proposed network architecture using a pre-trained Xception model yields 92.50% average classification accuracy.

Mayra Samaniego, Cristian Espana, Ralph Deters

IoT systems have enabled ubiquitous communication in physical spaces, making them smart Nowadays, there is an emerging concern about evaluating suspicious transactions in smart spaces. Suspicious transactions might have a logical structure, but they are not correct under the present contextual information of smart spaces. This research reviews suspicious transactions in smart spaces and evaluates the characteristics of blockchain technology to manage them. Additionally, this research presents a blockchain-based system model with the novel idea of iContracts (interactive contracts) to enable contextual evaluation through proof-of-provenance to detect suspicious transactions in smart spaces.

Mayra Samaniego, Ralph Deters

With the advent of blockchain technology, some management tasks of IoT networks can be moved from central systems to distributed validation authorities. Cloud-centric blockchain implementations for IoT have shown satisfactory performance. However, some features of blockchain are not necessary for IoT. For instance, a competitive consensus. This research presents the idea of customizing and encapsulating the features of blockchain into software-defined components to host them on edge devices. Thus, blockchain resources can be provisioned by edge devices (e-miners) working together closer to the things layer in a cooperative manner. This research uses Edison SoC as e-miners to test the software-defined blockchain components.

Ajay Kumar Shrestha, Ralph Deters, Julita Vassileva

The tremendous technological advancement in the last few decades has brought many enterprises to collaborate in a better way while making intelligent decisions. The use of Information Technology tools in obtaining data of people's everyday life from various autonomous data sources allowing unrestricted access to user data has emerged as an important practical issue and has given rise to legal implications. Various innovative models for data sharing and management have privacy and centrality issues. To alleviate these limitations, we have incorporated blockchain in user modeling. In this paper, we constructed a decentralized data sharing architecture with MultiChain blockchain in the travel domain, which is also applicable to other similar domains including education, health, and sports. Businesses that operate in the tourism industries including travel and tour agencies, hotels and resorts, shopping malls are connected to the MultiChain and they share their user profile data via stream in the MultiChain. The paper presents the hotel booking service for an imaginary hotel as one of the enterprise nodes, which collects user profile data with proper validation and will allow users to decide which of their data to be shared thus ensuring user control over their data and the preservation of privacy. The data from the repository is converted into an open data format while sharing via stream in the blockchain so that other enterprise nodes, after receiving the data, can easily convert them and store into their own repositories. The paper presents an evaluation of the performance of the model by measuring the latency and memory consumption with three test scenarios that mostly affect the user experience. The node responded quickly in all of these cases.

Sara Rouhani, Ralph Deters

Access to the system resources. The current access control systems face many problems, such as the presence of the third-party, inefficiency, and lack of privacy. These problems can be addressed by blockchain, the technology that received major attention in recent years and has many potentials. In this study, we overview the problems of the current access control systems, and then, we explain how blockchain can help to solve them. We also present an overview of access control studies and proposed platforms in different domains. This paper presents the state of the art and the challenges of blockchain-based access control systems.

Vahid Pourheidari, Sara Rouhani, Ralph deters

Many studies have been done to improve the performance of centrally controlled business processes and enhance the integration between different parties of these collaborations. However, the most serious issues of collaborative business processes remained unsolved in these studies, lack of trust and divided data on various confidential ledgers. Blockchain technology has enormous potential to become a new substantial integration method for untrusted collaborative businesses. Using the governing consensus mechanism, blockchain eliminates the necessity of the trusted third party. It provides a distributed shared ledger which facilitates the job of the process monitoring for the parties. The smart contract, as a crucial tool, is used to define the guaranteed autonomous programs. In addition, the privacy of the data can be ensured by using a permissioned blockchain that handles the access control because in this way, only verifiable participants can have access to the state of the business process and its related information. In this study, the applicability of execution of a real-word untrusted business process on the permissioned blockchain is investigated. Moreover, we determine the advantages of using the permissioned access-controller blockchain as the infrastructure for the collaborative business processes, through implementing the process of Order Processing on the Hyperledger Fabric blockchain platform.

Sara Rouhani, Vahid Pourheidari, Ralph Deters

Using blockchain as a decentralized backend infrastructure has grabbed the attention of many startups entrepreneurs and developers. Blockchain records transactions permanently and protects them from undesirable tampering. It provides a reliable tamper-proof database which can be considered as a trustable source for tracking the previous system state. In this paper, we present our access control application based on Hyperledger Fabric Blockchain and Hyperledger Composer to control access to physical places. The system components and modular architecture are illustrated, and we have extracted metadata include historian transactions details arising from our demo test. Finally, the performance metrics and resources consumption are provided using Hyperledger Caliper, a benchmark framework for measuring Hyperledger blockchains performance.

Sara Hosseinzadeh Kassani, Ralph Deters

The Semantic Web, an extension of the current web, provides a common framework that makes data machine understandable and also allows data to be shared and reused across various applications. Resource Description Framework (RDF), a graph-based data model for describing things (entities), facilitates data integration. Due to the explosion of the amount of RDF data, developing tools to support processing and answering of complex queries over the integrated data has become challenging. To overcome this challenge in query processing in semantic data integration frameworks, we provide a view layer inserted between the heterogeneous data sources and user interface layer while ensuring only authorized users are allowed access to the information. The view layer must provide a support in terms of access, integration, querying, management of data sources in a multi-user environment.

Uchi Ugobame Uchibeke, Sara Hosseinzadeh Kassani, Kevin A. Schneider et al.

In recent years, the advancement in modern technologies has experienced an explosion of huge data sets being captured and recorded in different fields, but also given rise to concerns the security and protection of data storage, transmission, processing, and access to data. The blockchain is a distributed ledger that records transactions in a secure, flexible, verifiable and permanent way. Transactions in a blockchain can be an exchange of an asset, the execution of the terms of a smart contract, or an update to a record. In this paper, we have developed a blockchain access control ecosystem that gives asset owners the sovereign right to effectively manage access control of large data sets and protect against data breaches. The Linux Foundation's Hyperledger Fabric blockchain is used to run the business network while the Hyperledger composer tool is used to implement the smart contracts or transaction processing functions that run on the blockchain network.