No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Revolutionizing Healthcare Advances in AI-Driven Medical Imaging for Precision Diagnosis
ResearchGate has not been able to resolve any citations for this publication.
Data versioning in machine learning is of paramount importance as it ensures the reproducibility, transparency, and reliability of ML models. In the dynamic landscape of ML research, where models heavily rely on diverse datasets, data versioning plays a crucial role in maintaining consistency throughout the ML pipeline. By tracking changes in datasets over time and aligning machine learning models with specific versions of data, researchers can reproduce experiments, verify results, and address challenges related to data quality, collaboration, and model training. Effective data versioning practices contribute to the robustness of ML workflows, fostering trust in model outcomes and supporting advancements in the field.
Cloud computing represents a transformative approach to delivering IT services via an interconnected network of servers, collectively referred to as the "Cloud." This virtualized environment seamlessly integrates networks, servers, applications, storage, and services, facilitating convenient access for users with minimal administrative overhead. This comprehensive review article centers on two fundamental pillars of cloud computing: virtualization and containerization. It examines their groundbreaking influence on resource management and deployment efficiency. Additionally, the paper explores upcoming trends and challenges expected to shape the cloud computing landscape from 2025 to 2030.An emphasis is placed on the anticipated adoption of hybrid and multi-cloud strategies, providing organizations with tailored solutions while reducing the risks associated with vendor lock-in. The emergence of edge computing is highlighted as a key solution to address latency concerns and foster a competitive environment for the Internet of Things (IoT). Furthermore, the integration of artificial intelligence (AI) and machine learning within cloud frameworks is poised to unlock new avenues of innovation and optimization, propelling digital transformation. The article underscores the critical need for enhanced security measures to protect sensitive data and ensure user privacy. Ongoing price competitions among cloud providers and heightened regulatory scrutiny are also examined, underscoring the dynamic nature of cloud computing. By offering insights into the past, present, and future trajectory of cloud computing, this article affirms its pivotal role in driving digital innovation and empowering organizations to thrive in an interconnected world. In conclusion, the article provides recommendations for businesses to leverage emerging technologies and effectively navigate evolving challenges in the realm of cloud computing.
On average, a drug or a treatment is effective in only about half of patients who take it. These patients need to try several until they find one that is effective at the cost of side effects associated with every treatment. The ultimate goal of precision medicine is to provide a treatment best suited for every individual. Sequencing technologies have now made genome means ics data available in abundance to be used towards this goal. In this project, we will specifically focus on cancer. Most cancer patients get a particular treatment based on the cancer type and the stage, though different individuals will react differently to a treatment. It is now well established that genetic mutations cause cancer growth and spreading and importantly, these mutations are different in individual patients. The aim of this project is to use genomic data to allow for better stratification of cancer patients, to predict the treatment most likely to work. Specifically, the project will use a machine learning approach to classify cancer and suggest medicine. The whole work is divided into two parts, one is predicting cancer using several machine learning classification techniques and then suggesting medicine.
This article explores the with a specific focus on how predictive analytics and decision support systems are revolutionizing patient care. Predictive analytics enable early disease prevention and diagnosis by iden outcomes and cost treatment plans, leveraging individual patient data for tailored interventions that enhance efficacy and m enhance diagnostic accuracy, providing rapid and precise assessments. Decision support systems, powered by AI, streamline healthcare workflows by offering real based on patient making. Remote patient monitoring, facilitated by AI, allows for proactive healthcare interventions by tracking vital signs and identifying potential health issues in real time. The article also discusses challenges and ethical considerations associated with AI integration in healthcare, emphasizing the importance of responsible deployment and regulatory frameworks. The comprehensive exploration underscores how AI is not only transforming pa .
Artificial intelligence (AI) has the potential to completely change how healthcare is delivered, revolutionizing the healthcare sector. Precision diagnosis, proactive disease prevention, personalised treatment plans, real-time monitoring and intervention, improved medical imaging, streamlined healthcare workflows, ethical considerations, and the potential future implications of AI in healthcare are all explored in this paper. The first section describes how precision diagnosis using AI technologies is improving diagnostic accuracy. Personalised treatment regimens and earlier disease detection are made possible by machine learning algorithms' analysis of enormous volumes of patient data. Additionally, AI makes it possible to actively prevent disease by using predictive analytics to identify those who are most likely to develop a particular condition, enabling early intervention and tailored preventive actions. The second segment focuses on how AI is transforming therapeutic approaches. AI algorithms create individualised treatment regimens by analyzing patient data, including genetics, biomarkers, and information on therapy response. This maximizes treatment efficacy and minimizes side effects. Additionally, wearable technology and remote monitoring devices powered by AI allow for real-time monitoring and intervention, improving patient safety and lowering hospital readmissions. Examines how AI has affected medical imaging. Radiologists' efficiency and accuracy in identifying anomalies are increased by deep learning algorithms' analysis of complicated medical pictures like CT scans and MRIs. As a result, diagnoses are made more quickly and accurately, allowing for quicker interventions and better patient outcomes. The fourth chapter examines how AI streamlines medical procedures. Administrative responsibilities are reduced and errors are minimized by automating operations like appointment scheduling and documentation. By offering timely support and triaging symptoms, intelligent catboats and virtual assistants increase patient involvement and happiness. The fifth segment talks with ethical issues related to AI in healthcare. In order to create and use AI algorithms responsibly, patient privacy, data security, and bias mitigation are essential. Fair and equitable healthcare practices must be ensured by ethical standards and legal requirements. The abstract wraps off with a preview of the potential effects of AI on healthcare delivery in the future. Emerging medical technologies including telemedicine, robotics, predictive analytics, and AI-assisted surgery show immense promise for revolutionizing the industry. To overcome obstacles, maximize advantages, and guarantee a human-centric approach in the integration of AI in healthcare, cooperation between healthcare practitioners, technologists, policymakers, and ethicists is essential.
Skin cancer continues to remain one of the major healthcare issues across the globe. If diagnosed early, skin cancer can be treated successfully. While early diagnosis is paramount for an effective cure for cancer, the current process requires the involvement of skin cancer specialists, which makes it an expensive procedure and not easily available and affordable in developing countries. This dearth of skin cancer specialists has given rise to the need to develop automated diagnosis systems. In this context, Artificial Intelligence (AI)-based methods have been proposed. These systems can assist in the early detection of skin cancer and can consequently lower its morbidity, and, in turn, alleviate the mortality rate associated with it. Machine learning and deep learning are branches of AI that deal with statistical modeling and inference, which progressively learn from data fed into them to predict desired objectives and characteristics. This survey focuses on Machine Learning and Deep Learning techniques deployed in the field of skin cancer diagnosis, while maintaining a balance between both techniques. A comparison is made to widely used datasets and prevalent review papers, discussing automated skin cancer diagnosis. The study also discusses the insights and lessons yielded by the prior works. The survey culminates with future direction and scope, which will subsequently help in addressing the challenges faced within automated skin cancer diagnosis.
Machine learning and AI have the potential to change almost every facet of human life; medical imaging and data interpretation is no exception to this rule. This article discusses current and potential uses of machine learning and artificial intelligence in cardiology, diagnostic imaging, and much more, as well as guidance for physicians on critical elements of AI and ML. Based on what it can do, AI is currently in the initial development stages and is divided into two categories, weak and strong AI. The research paper explores the capabilities of ANI, otherwise known as weak AI, in the medical field. Predictive modeling fundamentals important in cardiology are first reviewed, including feature selection and modern implementation of machine learning combined with hard-coded programming. Second, it analyzes several performances in cardiology and relevant disciplines and discusses some of the most popular supervised learning & implementation methods. Third, it shows how unsupervised learning, including deep understanding, may allow precision cardiology and enhance patient outcomes. It presents examples from both general care and cardiovascular medicine as background.
Radiation therapy is one of the key cancer treatment options. To avoid adverse effects in the healthy tissue, the treatment plan needs to be based on accurate anatomical models of the patient. In this work, an automatic segmentation solution for both female breasts and the heart is constructed using deep learning. Our newly developed deep neural networks perform better than the current state-of-the-art neural networks while improving inference speed by an order of magnitude. While manual segmentation by clinicians takes around 20 min, our automatic segmentation takes less than a second with an average of 3 min manual correction time. Thus, our proposed solution can have a huge impact on the workload of clinical staff and on the standardization of care.
One of the most promising areas of health innovation is the application of artificial intelligence (AI), primarily in medical imaging. This article provides basic definitions of terms such as “machine/deep learning” and analyses the integration of AI into radiology. Publications on AI have drastically increased from about 100–150 per year in 2007–2008 to 700–800 per year in 2016–2017. Magnetic resonance imaging and computed tomography collectively account for more than 50% of current articles. Neuroradiology appears in about one-third of the papers, followed by musculoskeletal, cardiovascular, breast, urogenital, lung/thorax, and abdomen, each representing 6–9% of articles. With an irreversible increase in the amount of data and the possibility to use AI to identify findings either detectable or not by the human eye, radiology is now moving from a subjective perceptual skill to a more objective science. Radiologists, who were on the forefront of the digital era in medicine, can guide the introduction of AI into healthcare. Yet, they will not be replaced because radiology includes communication of diagnosis, consideration of patient’s values and preferences, medical judgment, quality assurance, education, policy-making, and interventional procedures. The higher efficiency provided by AI will allow radiologists to perform more value-added tasks, becoming more visible to patients and playing a vital role in multidisciplinary clinical teams.
The goals of this review paper on deep learning (DL) in medical imaging and radiation therapy are to (a) summarize what has been achieved to date; (b) identify common and unique challenges, and strategies that researchers have taken to address these challenges; and (c) identify some of the promising avenues for the future both in terms of applications as well as technical innovations. We introduce the general principles of DL and convolutional neural networks, survey five major areas of application of DL in medical imaging and radiation therapy, identify common themes, discuss methods for dataset expansion, and conclude by summarizing lessons learned, remaining challenges, and future directions.
Explainable Artificial Intelligence (XAI) is paramount for building trust and understanding in machine learning models, particularly in complex domains. Traditional XAI methods face challenges when applied to neural networks evolved through Neuro-Evolutionary Algorithms (NEAs), limiting their effectiveness in providing transparent insights into model decision-making processes. This research introduces a novel framework that integrates NEAs with XAI techniques, aiming to enhance the explainability of evolved neural network architectures. By combining the adaptability of neuro-evolution with interpretability-focused methodologies, the proposed approach addresses the inherent opacity of evolved models. This article presents an in-depth exploration of the framework's principles, detailing its application to neural network evolution and the incorporation of state-of-the-art XAI techniques. Experimental results showcase the effectiveness of the neuro-evolutionary XAI framework in producing models that not only exhibit high performance but also offer interpretable and transparent decision-making processes. The findings highlight the potential of neuro-evolutionary approaches in advancing the field of XAI, paving the way for more trustworthy and understandable AI systems in complex applications. As artificial intelligence (AI) and machine learning (ML) increasingly infiltrate critical domains, the lack of explainability in complex models creates concerns about accountability, trust, and fairness. Explainable AI (XAI) seeks to address this issue by understanding how models make decisions and providing insights into their reasoning. This research delves into a promising avenue within XAI: neuro-evolutionary approaches. Inspired by the brain's learning mechanisms, neuro-evolutionary algorithms offer unique capabilities for tackling explainability challenges.
This review offers insight into AI’s current and future contributions to medical image analysis. The article highlights the challenges associated with manual image interpretation and introduces AI methodologies, including machine learning and deep learning. It explores AI’s applications in image segmentation, classification, registration, and reconstruction across various modalities like X-ray, computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound.
Medical image analysis is vital in modern healthcare, facilitating disease diagnosis, treatment, and monitoring. Integrating artificial intelligence (AI) techniques, particularly deep learning, has revolutionized this field.
Recent advancements are discussed, such as generative adversarial networks (GANs), transfer learning, and federated learning. The review assesses the advantages and limitations of AI in medical image analysis, underscoring the importance of interpretability, robustness, and generalizability in clinical practice. Ethical considerations related to data privacy, bias, and regulatory aspects are also examined.
The article concludes by exploring future directions, including personalized medicine, multi-modal fusion, real-time analysis, and seamless integration with electronic health records (EHRs).
This comprehensive review delineates artificial intelligence’s current and prospective role in medical image analysis. With implications for researchers, clinicians, and policymakers, it underscores AI’s transformative potential in enhancing patient care.
In the rapidly evolving landscape of transportation technology, the advent of autonomous vehicles (AVs) promises transformative benefits in terms of safety, efficiency, and mobility. However, with this promise comes the critical imperative of ensuring robust cybersecurity measures to safeguard AVs against potential threats and vulnerabilities. This research article delves into the development of comprehensive cybersecurity frameworks tailored specifically to autonomous vehicle systems, with a particular focus on securing onboard systems, communication networks, and data privacy within smart city ecosystems. The introduction contextualizes the significance of AV technology and underscores the pivotal role of cybersecurity in ensuring its safe integration into smart city environments. Recognizing the multifaceted nature of cybersecurity challenges facing AVs, the research delineates the scope of the investigation, aiming to provide actionable insights and strategies for mitigating risks across various domains. The first section examines the challenges inherent in securing autonomous vehicle systems, identifying vulnerabilities within onboard components such as sensors, controllers, and actuators. It further elucidates the risks posed by potential cyberattacks targeting communication networks connecting AVs to each other and to urban infrastructure. Additionally, the section highlights the privacy concerns associated with the collection, storage, and sharing of sensitive data generated by AVs. This work is licensed under CC BY-NC-SA 4.0. Building upon an analysis of existing cybersecurity frameworks applicable to AVs, the research proposes a comprehensive cybersecurity framework tailored to the unique requirements of autonomous vehicles operating within smart city environments. Drawing from established principles of cybersecurity and risk management, the framework integrates proactive measures such as threat modeling, risk assessment, and mitigation strategies, with a focus on real-time monitoring and incident response capabilities. Subsequent sections delve into specific strategies for securing onboard systems, encompassing authentication mechanisms, access control protocols, and intrusion detection/prevention systems. Moreover, the research explores encryption techniques and network security measures to protect communication networks, emphasizing the importance of resilience against emerging threats such as denial-of-service attacks. Addressing the paramount concern of data privacy, the framework advocates for the minimization of data collection, adoption of anonymization techniques, and adherence to relevant privacy regulations to safeguard user privacy in AV operations. Furthermore, the research elucidates the challenges and opportunities associated with integrating AVs into existing smart city ecosystems, emphasizing the need for seamless coordination with urban mobility systems and collaboration with IoT devices and platforms. By analyzing case studies and practical implementations of cybersecurity frameworks in autonomous vehicle fleets, the research offers valuable insights and best practices derived from real-world deployments. Finally, the conclusion summarizes key findings and outlines future research directions aimed at further enhancing the cybersecurity posture of autonomous vehicles in smart city environments. This research article provides a comprehensive examination of cybersecurity frameworks for autonomous vehicle systems, offering actionable strategies and insights to address the evolving challenges of securing AVs within smart city ecosystems.
Public Key Infrastructure (PKI) serves as a foundational element in the realm of securing Vehicle-to-Everything (V2X) communication networks. Its primary objective is to uphold the authenticity, confidentiality, and integrity of data exchanged within these networks. Despite its pivotal role, deploying and effectively managing PKI within V2X environments presents a host of formidable challenges. This article delves into the complexities surrounding PKI deployment specifically tailored to V2X networks, shedding light on the hurdles encountered and presenting innovative solutions to circumvent these obstacles. One of the foremost challenges plaguing the implementation of PKI in V2X networks revolves around scalability. As the network expands to accommodate a burgeoning number of connected vehicles and infrastructure components, traditional PKI architectures often struggle to scale in tandem. This scalability conundrum necessitates a reevaluation of existing architectural paradigms to ensure that PKI infrastructures can seamlessly adapt to the ever-evolving demands of V2X environments. Moreover, certificate management emerges as a significant stumbling block in the effective administration of PKI within V2X networks. The intricate web of certificates required to authenticate various entities, including vehicles, roadside units (RSUs), and traffic management systems, poses a formidable logistical challenge. The issuance, revocation, and renewal of certificates must be orchestrated with precision to maintain the integrity of the PKI ecosystem while simultaneously mitigating the risk of security breaches. This work is licensed under CC BY-NC-SA 4.0. View complete license here Furthermore, establishing trusted authorities within the V2X ecosystem presents yet another layer of complexity. The delineation of trust hierarchies and the designation of entities tasked with certificate issuance and validation necessitate meticulous planning and coordination. Without a cohesive framework governing the roles and responsibilities of these trusted authorities, the integrity of the entire PKI infrastructure may be compromised, leaving V2X networks vulnerable to exploitation. In light of these challenges, this research article proposes a multifaceted approach aimed at alleviating the inherent complexities associated with PKI deployment in V2X networks. By exploring innovative solutions tailored to address scalability issues, certificate management complexities, and the establishment of trusted authorities, this article seeks to pave the way for the seamless integration of PKI within the burgeoning domain of V2X communication networks. Through collaborative efforts and a steadfast commitment to innovation, the V2X community can surmount these challenges and usher in a new era of secure and resilient V2X communication.
Technological tools can redesign traditional approaches to radiology education, for example, with simulation cases and via computer-generated feedback. In this study, we investigated the use of an AI-powered, Bayesian inference-based clinical decision support (CDS) software to provide automated “real-time” feedback to trainees during interpretation of clinical and simulation brain MRI examinations. Radiology trainees participated in sessions in which they interpreted 3 brain MRIs: two cases from a routine clinical worklist (one without and one with CDS) and a teaching file-based simulation case with CDS. The CDS software required trainees to input imaging features and differential diagnoses, after which inferred diagnoses were displayed, and the case was reviewed with an attending neuroradiologist. An observer timed each case, including time spent on education, and trainees completed a survey rating their confidence in their findings and the educational value of the case. Ten trainees reviewed 75 brain MRI examinations during 25 reading sessions. Trainees had slightly lower confidence in their findings and diagnosis and rated the educational value slightly higher for simulation cases with CDS compared to clinical cases without CDS (p < 0.05). There were no significant differences in ratings of clinical cases with or without CDS. No differences in overall timing were found among the reading scenarios. Simulation cases with “CDS-provided feedback” may improve the educational value of interpreting imaging studies at a workstation without adding additional time. Further investigation will help drive innovation in trainee education, which may be particularly relevant in this era of increasing remote work and asynchronous attending review.
Model-based approaches for image reconstruction, analysis, and interpretation have made significant progress over the past decades. Many of these approaches are based on either mathematical, physical, or biological models. A challenge for these approaches is the modeling of the underlying processes (e.g., the physics of image acquisition or the patho-physiology of a disease) with appropriate levels of detail and realism. With the availability of large amounts of imaging data and machine learning (in particular deep learning) techniques, data-driven approaches have become more widespread for use in different tasks in reconstruction, analysis, and interpretation. These approaches learn statistical models directly from labeled or unlabeled image data and have been shown to be very powerful for extracting clinically useful information from medical imaging. While these data-driven approaches often outperform traditional model-based approaches, their clinical deployment often poses challenges in terms of robustness, generalization ability, and interpretability. In this article, we discuss what developments have motivated the shift from model-based approaches toward data-driven strategies and what potential problems are associated with the move toward purely data-driven approaches, in particular deep learning. We also discuss some of the open challenges for data-driven approaches, e.g., generalization to new unseen data (e.g., transfer learning), robustness to adversarial attacks, and interpretability. Finally, we conclude with a discussion on how these approaches may lead to the development of more closely coupled imaging pipelines that are optimized in an end-to-end fashion.
In recent years, there has been enormous interest in applying artificial intelligence (AI) to radiology. Although some of this interest may have been driven by exaggerated expectations that the technology can outperform radiologists in some tasks, there is a growing body of evidence that illustrates its limitations in medical imaging. The true potential of the technique probably lies somewhere in the middle, and AI will ultimately play a key role in medical imaging in the future. The limitless power of computers makes AI an ideal candidate to provide the standardization, consistency, and dependability needed to support radiologists in their mission to provide excellent patient care. However, important roadblocks currently limit the expansion of this field in medical imaging. This article reviews some of the challenges and potential solutions to advance the field forward, with focus on the experience gained by hosting image-based competitions.
Artificial intelligence (AI) has been heralded as the next big wave in the computing revolution and touted as a transformative technology for many industries including health care. In radiology, considerable excitement and anxiety are associated with the promise of AI and its potential to disrupt the practice of the radiologist. Radiology has often served as the gateway for medical technological advancements, and AI will likely be no different. We present a brief overview of AI advancements that have driven recent interest, offer a review of the current literature, and examine the most likely ways that AI will change radiology in the coming years.
BACKGROUND: Non-contrast head CT scan is the current standard for initial imaging of patients with head trauma or stroke symptoms. We aimed to develop and validate a set of deep learning algorithms for automated detection of the following key findings from these scans: intracranial haemorrhage and its types (ie, intraparenchymal, intraventricular, subdural, extradural, and subarachnoid); calvarial fractures; midline shift; and mass effect. METHODS: We retrospectively collected a dataset containing 313 318 head CT scans together with their clinical reports from around 20 centres in India between Jan 1, 2011, and June 1, 2017. A randomly selected part of this dataset (Qure25k dataset) was used for validation and the rest was used to develop algorithms. An additional validation dataset (CQ500 dataset) was collected in two batches from centres that were different from those used for the development and Qure25k datasets. We excluded postoperative scans and scans of patients younger than 7 years. The original clinical radiology report and consensus of three independent radiologists were considered as gold standard for the Qure25k and CQ500 datasets, respectively. Areas under the receiver operating characteristic curves (AUCs) were primarily used to assess the algorithms. FINDINGS: The Qure25k dataset contained 21 095 scans (mean age 43 years; 9030 [43%] female patients), and the CQ500 dataset consisted of 214 scans in the first batch (mean age 43 years; 94 [44%] female patients) and 277 scans in the second batch (mean age 52 years; 84 [30%] female patients). On the Qure25k dataset, the algorithms achieved an AUC of 0·92 (95% CI 0·91-0·93) for detecting intracranial haemorrhage (0·90 [0·89-0·91] for intraparenchymal, 0·96 [0·94-0·97] for intraventricular, 0·92 [0·90-0·93] for subdural, 0·93 [0·91-0·95] for extradural, and 0·90 [0·89-0·92] for subarachnoid). On the CQ500 dataset, AUC was 0·94 (0·92-0·97) for intracranial haemorrhage (0·95 [0·93-0·98], 0·93 [0·87-1·00], 0·95 [0·91-0·99], 0·97 [0·91-1·00], and 0·96 [0·92-0·99], respectively). AUCs on the Qure25k dataset were 0·92 (0·91-0·94) for calvarial fractures, 0·93 (0·91-0·94) for midline shift, and 0·86 (0·85-0·87) for mass effect, while AUCs on the CQ500 dataset were 0·96 (0·92-1·00), 0·97 (0·94-1·00), and 0·92 (0·89-0·95), respectively. INTERPRETATION: Our results show that deep learning algorithms can accurately identify head CT scan abnormalities requiring urgent attention, opening up the possibility to use these algorithms to automate the triage process.Qure.ai.
Artificial intelligence (AI) algorithms, particularly deep learning, have demonstrated remarkable progress in image-recognition tasks. Methods ranging from convolutional neural networks to variational autoencoders have found myriad applications in the medical image analysis field, propelling it forward at a rapid pace. Historically, in radiology practice, trained physicians visually assessed medical images for the detection, characterization and monitoring of diseases. AI methods excel at automatically recognizing complex patterns in imaging data and providing quantitative, rather than qualitative, assessments of radiographic characteristics. In this Opinion article, we establish a general understanding of AI methods, particularly those pertaining to image-based tasks. We explore how these methods could impact multiple facets of radiology, with a general focus on applications in oncology, and demonstrate ways in which these methods are advancing the field. Finally, we discuss the challenges facing clinical implementation and provide our perspective on how the domain could be advanced. Full text: https://rdcu.be/O1xz
AI applications in robotics, diagnostic image analysis and precision medicine: Current limitations, future trends, guidelines on CAD systems for medicine
- T Habuza
- A N Navaz
- F Hashim
- F Alnajjar
- N Zaki
- M A Serhani
- Y Statsenko
Habuza, T., Navaz, A. N., Hashim, F., Alnajjar, F.,
Zaki, N., Serhani, M. A., & Statsenko, Y. (2021). AI
applications in robotics, diagnostic image analysis and
precision medicine: Current limitations, future trends,
guidelines on CAD systems for medicine. Informatics
in
Medicine
Unlocked,
24,
100596.
https://doi.org/10.1016/j.imu.2021.100596
Automatic magnetic resonance prostate segmentation by deep learning with holistically nested networks
- R R H L N L L T B G W M E P T P P C P M M S R Cheng
R. R. H. L. N. L. L. T. B. G. W. M. E. P. T. P. P. C. P.
M. M. S. R. Cheng, "Automatic magnetic resonance
prostate segmentation by deep learning with
holistically nested networks," J. Med. Imaging, vol. 4,
p. 041302, 2017.