BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:242746
DTSTAMP:20260915T081256Z
DTSTART;TZID=America/New_York:20260924T160000
DTEND;TZID=America/New_York:20260924T165000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/ece-graduate-seminar-
 lecture-speaker-xinming-huang-ece-department-wpi
SUMMARY:ECE Graduate Seminar Lecture\, Speaker: Xinming Huang\, ECE Departm
 ent\, WPI
DESCRIPTION:Title:\nAI Algorithms for Skin Cancer Detection: From Convoluti
 onal Networks to Vision Transformers\nAbstract:\nArtificial intelligence h
 as shown substantial promise for improving the accuracy\, consistency\, an
 d scalability of skin cancer screening. This talk presents our recent work
  on deep learning algorithms for automated skin lesion analysis\, with a p
 articular focus on dermoscopic images. We will discuss the development of 
 an ensemble-based classification framework that achieved third place in th
 e ISIC MILK10K Challenge\, illustrating how model architecture\, data augm
 entation\, training strategy\, and model fusion can improve performance on
  large and heterogeneous dermatologic image datasets.\nWe will also presen
 t our work on vision transformer (ViT)-based melanoma classification\, pub
 lished in Cancers. Unlike conventional convolutional neural networks\, vis
 ion transformers use self-attention to capture both local lesion character
 istics and longer-range spatial relationships across an image. Our results
  demonstrate the potential of transformer-based architectures for discrimi
 nating melanoma from benign skin lesions and provide insights into their a
 dvantages and limitations.\nBeyond benchmark classification\, we will disc
 uss the challenges involved in translating AI algorithms into practical sk
 in cancer screening systems\, including image resolution\, lesion size\, d
 ataset bias\, model generalizability\, explainability\, and clinical workf
 low integration. These results illustrate both the rapid progress of AI-ba
 sed dermatologic image analysis and the opportunities for developing techn
 ologies capable of detecting skin cancers at early stages.\n\n\nImage\n  \
 n\n\n\nSpeaker:\nXinming Huang\nProfessor\, ECE Department\, WPI\nBio:\nXi
 nming Huang is a Professor of Electrical and Computer Engineering at Worce
 ster Polytechnic Institute (WPI) and Director of the Embedded Computing La
 boratory. His research interests include machine learning\, computer visio
 n\, embedded design\, and edge computing. His recent work focuses on AI al
 gorithms for applications\, including automated driving\, wireless communi
 cations\, and digital health.\nHost: John McNeill
END:VEVENT
END:VCALENDAR