Privacy risks of whole-slide image sharing in digital pathology

Holub, Petr; Müller, Heimo; Bíl, Tomáš; Pireddu, Luca; Plass, Markus; Praßer, Fabian; Schlünder, Irene; Zatloukal, Kurt; Nenutil, Rudolf; Brázdil, Tomǎš

doi:10.1038/s41467-023-37991-y

Cited by 14 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As WSI deals with large amounts of sensitive patient information, strong data privacy policies, encryption, and access control are indispensable. Differential privacy methods such as encryption and federated learning protect individual privacy while allowing accurate data analysis ( 87 - 89 ).…”

Section: Discussionmentioning

confidence: 99%

Digital pathology, deep learning, and cancer: a narrative review

Williams Jr,

Graifman,

Hussain

et al. 2024

Transl Cancer Res

View full text Add to dashboard Cite

Background and Objective Cancer is a leading cause of morbidity and mortality worldwide. The emergence of digital pathology and deep learning technologies signifies a transformative era in healthcare. These technologies can enhance cancer detection, streamline operations, and bolster patient care. A substantial gap exists between the development phase of deep learning models in controlled laboratory environments and their translations into clinical practice. This narrative review evaluates the current landscape of deep learning and digital pathology, analyzing the factors influencing model development and implementation into clinical practice. Methods We searched multiple databases, including Web of Science, Arxiv, MedRxiv, BioRxiv, Embase, PubMed, DBLP, Google Scholar, IEEE Xplore, Semantic Scholar, and Cochrane, targeting articles on whole slide imaging and deep learning published from 2014 and 2023. Out of 776 articles identified based on inclusion criteria, we selected 36 papers for the analysis. Key Content and Findings Most articles in this review focus on the in-laboratory phase of deep learning model development, a critical stage in the deep learning lifecycle. Challenges arise during model development and their integration into clinical practice. Notably, lab performance metrics may not always match real-world clinical outcomes. As technology advances and regulations evolve, we expect more clinical trials to bridge this performance gap and validate deep learning models’ effectiveness in clinical care. High clinical accuracy is vital for informed decision-making throughout a patient’s cancer care. Conclusions Deep learning technology can enhance cancer detection, clinical workflows, and patient care. Challenges may arise during model development. The deep learning lifecycle involves data preprocessing, model development, and clinical implementation. Achieving health equity requires including diverse patient groups and eliminating bias during implementation. While model development is integral, most articles focus on the pre-deployment phase. Future longitudinal studies are crucial for validating models in real-world settings post-deployment. A collaborative approach among computational pathologists, technologists, industry, and healthcare providers is essential for driving adoption in clinical settings.

show abstract

Section: Discussionmentioning

confidence: 99%

Digital pathology, deep learning, and cancer: a narrative review

Williams Jr,

Graifman,

Hussain

et al. 2024

Transl Cancer Res

View full text Add to dashboard Cite

show abstract

“…WSI belongs to a specific data category, as a digital slide is just an image of high resolution in gigapixels or tens of gigapixels reflecting the detailed structure of tissue samples obtained, processed, cut, stained, and scanned in the laboratory. From this perspective, WSI could be categorized as low-risk data ( 39 ). However, the scan of the histological specimen can be labeled with a patient identifier and also linked to clinical or laboratory data, so WSI should be considered as sensitive as other clinical data.…”

Section: Ethical Requirements For Privacy Protection When Using Dp Toolsmentioning

confidence: 99%

Digital pathology implementation in cancer diagnostics: towards informed decision-making

Sulaieva,

Dudin,

Koshyk

et al. 2024

Front. Digit. Health

View full text Add to dashboard Cite

Digital pathology (DP) has become a part of the cancer healthcare system, creating additional value for cancer patients. DP implementation in clinical practice provides plenty of benefits but also harbors hidden ethical challenges affecting physician-patient relationships. This paper addresses the ethical obligation to transform the physician-patient relationship for informed and responsible decision-making when using artificial intelligence (AI)-based tools for cancer diagnostics. DP application allows to improve the performance of the Human-AI Team shifting focus from AI challenges towards the Augmented Human Intelligence (AHI) benefits. AHI enhances analytical sensitivity and empowers pathologists to deliver accurate diagnoses and assess predictive biomarkers for further personalized treatment of cancer patients. At the same time, patients’ right to know about using AI tools, their accuracy, strengths and limitations, measures for privacy protection, acceptance of privacy concerns and legal protection defines the duty of physicians to provide the relevant information about AHI-based solutions to patients and the community for building transparency, understanding and trust, respecting patients' autonomy and empowering informed decision-making in oncology.

show abstract

“…When transmitting data, an attacker could modify certain values in the transmitted data, leading to false diagnoses or illegal access to data. Solutions such as authentication or data encryption should be used to eliminate these potential risks [9][10][11]. This research area is addressed by the authors in their article [9], in which they present a solution they have developed to enable the transmission of digitized pathology samples over the network with a lower risk factor.…”

Section: Network Data Streaming In Different Areas Of Digital Medicinementioning

confidence: 99%

Real-Time Network Video Data Streaming in Digital Medicine

Vincze,

Molnar,

Kozlovszky

2023

Computers

View full text Add to dashboard Cite

Today, the use of digital medicine is becoming more and more common in medicine. With the use of digital medicine, health data can be shared, processed, and visualized using computer algorithms. One of the problems currently facing digital medicine is the rapid transmission of large amounts of data and their appropriate visualization, even in 3D. Advances in technology offer the possibility to use new image processing, networking, and visualization solutions for the evaluation of medical samples. Because of the resolution of the samples, it is not uncommon that it takes a long time for them to be analyzed, processed, and shared. This is no different for 3D visualization. In order to be able to display digitalized medical samples in 3D at high resolution, a computer with computing power that is not necessarily available to doctors and researchers is needed. COVID-19 has shown that everyday work must continue even when there is a physical distance between the participants. Real-time network streaming can provide a solution to this, by creating a 3D environment that can be shared between doctors/researchers in which the sample being examined can be visualized. In order for this 3D environment to be available to everyone, it must also be usable on devices that do not have high computing capacity. Our goal was to design a general-purpose solution that would allow users to visualize large amounts of medical imaging data in 3D, regardless of the computational capacity of the device they are using. With the solution presented in this paper, our goal was to create a 3D environment for physicians and researchers to collaboratively evaluate 3D medical samples in an interdisciplinary way.

show abstract

Privacy risks of whole-slide image sharing in digital pathology

Cited by 14 publications

References 33 publications

Digital pathology, deep learning, and cancer: a narrative review

Digital pathology, deep learning, and cancer: a narrative review

Digital pathology implementation in cancer diagnostics: towards informed decision-making

Real-Time Network Video Data Streaming in Digital Medicine

Contact Info

Product

Resources

About