BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
DTSTART:20260308T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261101T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20261028T193946Z
UID:898E8FCC-A97C-4E06-8576-7CF91C52882A
DTSTART;TZID=America/New_York:20261028T140000
DTEND;TZID=America/New_York:20261028T150000
DESCRIPTION:Skin cancer is the most common cancer in the United States of A
 merica (USA). Skin cancer is a significant public health problem\; it can 
 affect anyone\, regardless of skin color\, gender\, and age. Further\, it 
 is a leading cause of death worldwide. The deadliest and most severe form 
 of skin cancer is called Melanoma.\n\nSkilled doctors typically diagnose m
 elanoma (including BCC\, SCC\, and actinic keratosis) through visual\, com
 puter vision\, and data-driven techniques. However\, these approaches rely
  on dermoscopy results and match them with medical knowledge. Moreover\, h
 uman subjectivity strongly influences this process\, making it inconsisten
 t in some cases. Therefore\, we need to develop computer- and data-driven 
 technologies that can identify and classify melanoma and other skin cancer
 s at very early stages. Therefore\, to achieve efficient\, effective\, and
  accurate early-stage melanoma identification and classification\, this ta
 lk traces computer vision and data science (AI) applications and presents 
 discussions and results using deep neural network-based algorithms\, Visio
 n-Language Models (VLMs)\, multi-agent architectures\, and human-in-the-lo
 op architectures. It then compares the performance metrics of these algori
 thms and outlines future directions. The talk also covers survivorship amo
 ng melanoma survivors\, associated risk scores\, and strategies to thrive 
 in personal\, professional\, and social life.\n\nSpeaker(s): Avi\, \n\nVir
 tual: https://events.vtools.ieee.org/m/587365
LOCATION:Virtual: https://events.vtools.ieee.org/m/587365
ORGANIZER:tan@fdu.edu
SEQUENCE:112
SUMMARY:Optimizing Skin Cancer Screening and Melanoma Survivorship
URL;VALUE=URI:https://events.vtools.ieee.org/m/587365
X-ALT-DESC:Description: <br /><p class="MsoNormal" style="text-align: justi
 fy\; margin: 0in 49.5pt .0001pt .75in\;"><span style="mso-fareast-font-fam
 ily: Calibri\; color: black\; mso-themecolor: text1\;">Skin cancer is the 
 most common cancer in the United States of America (USA). Skin cancer is a
  significant public health problem\; it can affect anyone\, regardless of 
 skin color\, gender\, and age.<span style="mso-spacerun: yes\;">&nbsp\; </
 span>Further\, it is a leading cause of death worldwide. The deadliest and
  most severe form of skin cancer is called Melanoma.</span></p>\n<p class=
 "MsoNormal" style="text-align: justify\; margin: 0in 49.5pt .0001pt .75in\
 ;"><span style="mso-fareast-font-family: Calibri\; color: black\; mso-them
 ecolor: text1\;">&nbsp\;</span></p>\n<p class="MsoNormal" style="text-alig
 n: justify\; margin: 0in 49.5pt .0001pt .75in\;"><span style="mso-fareast-
 font-family: Calibri\; color: black\; mso-themecolor: text1\;">Skilled doc
 tors typically diagnose melanoma (including BCC\, SCC\, and actinic kerato
 sis) through visual\, computer vision\, and data-driven techniques. Howeve
 r\, these approaches rely on dermoscopy results and match them with medica
 l knowledge. Moreover\, human subjectivity strongly influences this proces
 s\, making it inconsistent in some cases. Therefore\, we need to develop c
 omputer- and data-driven technologies that can identify and classify melan
 oma and other skin cancers at very early stages. Therefore\, to achieve ef
 ficient\, effective\, and accurate early-stage melanoma identification and
  classification\, this talk traces computer vision and data science (AI) a
 pplications and presents discussions and results using deep neural network
 -based algorithms\, Vision-Language Models (VLMs)\, multi-agent architectu
 res\, and human-in-the-loop architectures. It then compares the performanc
 e metrics of these algorithms and outlines future directions. The talk als
 o covers survivorship among melanoma survivors\, associated risk scores\, 
 and strategies to thrive in personal\, professional\, and social life. </s
 pan></p>
END:VEVENT
END:VCALENDAR