BEGIN:VCALENDAR
VERSION:2.0
PRODID:www.dresden-science-calendar.de
METHOD:PUBLISH
CALSCALE:GREGORIAN
X-MICROSOFT-CALSCALE:GREGORIAN
X-WR-TIMEZONE:Europe/Berlin
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
DTSTART:19810329T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;INTERVAL=1;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:DSC-22098
DTSTART;TZID=Europe/Berlin:20250708T150000
SEQUENCE:1751953088
TRANSP:OPAQUE
DTEND;TZID=Europe/Berlin:20250708T160000
URL:https://www.dresden-science-calendar.de/calendar/de/detail/22098
LOCATION:IFW\, Helmholtzstraße 2001069 Dresden
SUMMARY:Stamp: Sounding out Malignancy: AI-Assisted Acoustic Sensing for Re
 al-Time Tumour Detection in Brain Surgery
CLASS:PUBLIC
DESCRIPTION:Speaker: Dr. Melanie Stamp\nInstitute of Speaker: The Universit
 y of Melbourne\, FEIT Infrastructure Team | Faculty of Engineering and Inf
 ormation Tech\nTopics:\n\n Location:\n  Name: IFW (B3E.26\, IFW Dresden)\n
   Street: Helmholtzstraße 20\n  City: 01069 Dresden\n  Phone: \n  Fax: \n
 Description: Brain tumours pose a significant challenge in modern neurosur
 gery due to their invasive nature and the high recurrence rate of over 30%
 \, often resulting from malignant cells infiltrating healthy brain tissue.
  Current intraoperative techniques lack the real-time precision needed to 
 differentiate between neoplastic and non-neoplastic tissues\, leading to i
 ncomplete tumour resections and increased risks of neurological complicati
 ons. Our research addresses this gap by integrating AI-assisted surface ac
 oustic wave (SAW) sensors into surgical tools for real-time mechanical pro
 perty analysis during brain surgery. Acoustic sensing technology enables r
 eal-time\, non-invasive differentiation between tumorous and non-neoplasti
 c tissues by leveraging their mechanical property differences\, as tumours
  typically exhibit greater stiffness. In our study\, we combine high-frequ
 ency SAW sensors with AI algorithms to analyse and classify mechanical res
 ponses in GelMA hydrogel tissue models. Experimental results indicate that
  SAW sensors can sensitively detect stiffness changes\; softer materials s
 how greater wave attenuation. When applied to tumour tissue\, we observe t
 hat stiffer tumours produce stronger SAW reflections compared to healthy b
 rain tissue\, providing immediate feedback suitable for intraoperative use
 . Our findings demonstrate that SAW sensors can detect subtle mechanical c
 hanges without damaging tissue\, offering a key advantage over traditional
  diagnostic techniques. The integration of AI enhances classification accu
 racy\, enabling more precise tumour resections. This approach addresses a 
 critical gap in surgical diagnostics\, improving the ability to delineate 
 tumour margins and reduce recurrence rates\, ultimately contributing to sa
 fer\, more effective neurosurgery and improved patient recovery.
DTSTAMP:20260715T073754Z
CREATED:20250701T053846Z
LAST-MODIFIED:20250708T053808Z
END:VEVENT
END:VCALENDAR