Dongguk University

This method enables medical digital twins to achieve 98% accuracy in breast cancer prediction, even under adversarial attacks SEOUL, South Korea, April 11, 2025 /PRNewswire/ -- Medical digital twins are virtual models of the human body that can help predict diseases with high accuracy. However, they are vulnerable to cyberattacks that can manipulate data and lead to incorrect diagnoses. To address this, researchers from Dongguk University developed the Wavelet-Based Adversarial Training (WBAD) defense system. Tested on a breast cancer diagnostic model, WBAD restored accuracy to 98% against attacks, ensuring safer and more reliable medical digital twins for healthcare applications. Continue Reading WBAD combines wavelet denoising to remove high-frequency noise from input images and adversarial training to recognize and resist adversarial inputs A digital twin is an exact virtual copy of a real-world system. Built using real-time data, they provide a platform to test, simulate, and optimize the performance of their physical counterpart. In healthcare, medical digital twins can create virtual models of biological systems to predict diseases or test medical treatments. However, medical digital twins are susceptible to adversarial attacks, where small, intentional modifications to input data can mislead the system into making incorrect predictions, such as false cancer diagnoses, posing significant risks to the safety of patients. To counter these threats, a research team from Dongguk University, Republic of Korea, and Oregon State University, USA, led by Professor Insoo Sohn, has proposed a novel defense algorithm: Wavelet-Based Adversarial Training (WBAD). Their approach, which aims to protect medical digital twins against cyberattacks, was made available online on October 11, 2024, and is published in volume 115 of the March 2025 issue of the journal Information Fusion. "We present the first study within Digital Twin Security to propose a secure medical digital twin system, which features a novel two-stage defense mechanism against cyberattacks. This mechanism is based on wavelet denoising and adversarial training," says Professor Insoo Sohn, from Dongguk University, the corresponding author of the study. The researchers tested their defense system on a digital twin designed to diagnose breast cancer using thermography images. Thermography detects temperature variations in the body, with tumors often appearing as hotter regions due to increased blood flow and metabolic activity. Their model processes these images using Discrete Wavelet Transform, which extracts essential features to create Initial Feature Point Images. These features are then fed into a machine learning classifier trained on a dataset of 1,837 breast images (both healthy and cancerous), to distinguish between normal and tumorous tissue. Initially, the model achieved 92% accuracy in predicting breast cancer. However, when subjected to three types of adversarial attacks—Fast Gradient Sign Method, Projected Gradient Descent, and Carlini & Wagner attacks—its accuracy dropped drastically to just 5%, exposing its vulnerability to adversarial manipulations. To counter these threats, the researchers introduced a two-layer defense mechanism. The first layer, wavelet denoising, is applied during the image preprocessing stage. Adversarial attacks typically introduce high-frequency noise into input data to mislead the model. Wavelet denoising applies soft thresholding to remove this noise while preserving the low-frequency features of the image. To further improve the model's resilience, the researchers added an adversarial training step, which trains the machine learning model to recognize and resist adversarial inputs. This two-step defense strategy proved highly effective, with the model achieving 98% accuracy against FGSM attacks, 93% against PGD attacks, and 90% against C&W attacks. "Our results demonstrate a transformative approach to medical digital twin security, providing a comprehensive and effective defense against cyberattacks and leading to enhanced system functionality and reliability," says Prof. Sohn. Reference Title of original paper: Adversarial robust image processing in medical digital twin Journal: Information Fusion DOI: 10.1016/j.inffus.2024.102728 Website: Media Contact: Sunggeun Cho 82 2-2260-3069 [email protected] SOURCE Dongguk University WANT YOUR COMPANY'S NEWS FEATURED ON PRNEWSWIRE.COM? 440k+ Newsrooms & Influencers 9k+ Digital Media Outlets 270k+ Journalists Opted In GET STARTED

Installation Marks the Second ZAP-X System in Korea to Offer the Latest Advance in Non-Surgical Brain Tumor Care GOYANG-SI, South Korea--(BUSINESS WIRE)-- ZAP Surgical Systems, Inc., a global leader in surgical robotics, proudly announces the completion of first patient treatments at Dongguk University Ilsan Hospital using the ZAP-X® Gyroscopic Radiosurgery® platform. This marks the second installation of the ZAP-X system in Korea, signifying a substantial advancement in providing cutting-edge medical care to patients in the Asia-Pacific region. This press release features multimedia. View the full release here: The Vault-Free, Cobalt-Free ZAP-X® Gyroscopic Radiosurgery® Platform at Dongguk University Ilsan Hospital (interior view). (Photo: Business Wire) Stereotactic radiosurgery (SRS) provides a non-invasive and painless treatment option for treating many primary and metastatic brain tumors, as well as other conditions of the head and neck. With outcomes equivalent or superior to traditional open surgeries, SRS typically involves only one to five brief outpatient visits, allowing patients to often resume normal activities on the same day. Historically, the hospital’s radiosurgery patients were treated in the Radiation Oncology department using multi-purpose radiation delivery systems typically employed for breast, lung, and prostate cancers. However, with the addition of the ZAP-X platform, the Neurosurgery department at Dongguk University Ilsan Hospital will now independently lead cranial SRS treatments. The ZAP-X system is exclusively optimized for cranial, head, and neck applications, helping to ensure the highest precision and minimize potential radiation exposure to healthy critical anatomy. Located 60 minutes from Seoul's Incheon International Airport, Dongguk University Ilsan Hospital is a renowned medical institution founded by Dongguk University. With 33 departments, 47 specialized clinics, and 11 specialized centers, the hospital is committed to delivering exceptional patient care through the latest innovations and advanced technology. The ZAP-X system's ground-breaking design utilizes gyroscopic mobility to precisely focus high-dose radiation on targeted tumors from thousands of potential angles, maximizing the preservation of healthy brain tissue and patient cognitive function. Further, its vault-free and cobalt-free features eliminate the requirement for expensive shielded radiation treatment rooms and the management of radioactive isotopes. Dr. Seung-yeob Yang, Professor of Neurosurgery at Dongguk University Ilsan Hospital expressed his enthusiasm, stating, "The ZAP-X system represents a meaningful advancement in our ability to treat primary and metastatic brain tumors, as well as functional disorders such as trigeminal neuralgia. Its precision and non-invasive nature allow us to provide our patients with the best possible care while minimizing side effects and patient downtime." “Together with superior technical capabilities, the ZAP-X platform offered significant advantages over traditional radiation delivery systems. Also, ZAP-X eliminated the need to construct a shielded radiation bunker and allowed for easy installation in our existing outpatient Neurosurgery department,” added Dr. Yang. About ZAP Surgical Systems, Inc. ZAP Surgical Systems, Inc. designs and manufactures the ZAP-X® Gyroscopic Radiosurgery® platform. ZAP was founded in 2014 by Dr. John R. Adler. In addition to being CEO of ZAP, Dr. Adler is Emeritus Dorothy & TK Chan Professor of Neurosurgery and Radiation Oncology at Stanford University. Dr. Adler is also renowned as the inventor of the CyberKnife® system and founder of Accuray, Inc. The ZAP-X platform incorporates a unique vault-free design that typically eliminates the need for costly shielded treatment rooms. ZAP-X also utilizes a modern linear accelerator to eliminate legacy use of Cobalt-60. Learn more at ZAP Surgical and follow us on LinkedIn. View source version on businesswire.com: Contacts Mark Arnold, ZAP Surgical Systems, Inc. Senior Vice President, Marketing +1 650 492 7797, ext. 101 Email: info@zapsurgical.com Source: ZAP Surgical Systems, Inc. Smart Multimedia Gallery Photo The Vault-Free, Cobalt-Free ZAP-X® Gyroscopic Radiosurgery® Platform at Dongguk University Ilsan Hospital (interior view). (Photo: Business Wire) Photo The Vault-Free, Cobalt-Free ZAP-X® Gyroscopic Radiosurgery® Platform at Dongguk University Ilsan Hospital (exterior view). (Photo: Business Wire) Logo View this news release and multimedia online at:

The study found that using the combination of low PSi and SR had high predictability for mortality 180 days after cardiac arrest Masimo SedLine brain function monitoring. (Credit: Business Wire) Masimo announced that the combination of two SedLine parameters, including patient state index (PSi) and suppression ratio (SR), has shown high predictability for mortality 180 days after cardiac arrest. Dr Tae Youn Kim and colleagues at the Dongguk University College of Medicine and Yonsei University College of Medicine in Korea assessed the potential of two parameters offered by Masimo SedLine brain function monitoring for the prediction of neurological outcomes and long-term survival in post-cardiac arrest ICU patients. Researchers used a multi-modal approach to assess the prognostic accuracy of the two Masimo SedLine parameters as predictors of neurological outcomes, both alone and in combination. The team selected PSi as it is widely used in anesthesiology to determine the degree of procedural sedation, while SR was selected to estimate the percentage of EEG suppression. PSi is derived from EEG. Masimo recruited 103 adult patients between January 2017 and August 2020 who experienced a non-traumatic out-of-hospital cardiac arrest and successfully resuscitated after CPR. They were given targeted temperature management during their ICU stay. Masimo SedLine was used to continuously monitor PSi and SR immediately after ICU admission until 24 hours after return of spontaneous circulation (ROSC). Both parameters have been recorded at one hour intervals Pittsburgh Brain Stem Score (PBSS) and Cerebral Performance Category (CPC) were used to categorise the neurological outcomes. According to the company, the researchers noticed that using either PSi or SR alone had good predictability for poor neurological outcome and the combination of low PSi and SR had high predictability for mortality 180 days after cardiac arrest. The researchers concluded that PSi and SR are good predictors for early neuro-prognostication in post-cardiac arrest patients, said the company. The SedLine brain function monitoring system secured approval from the US Food and Drug Administration (FDA) in January 2018. Featuring an advanced signal processing engine, the system is designed to provide clinicians with a complete picture of the brain.