BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Integrating Radiomics and Explainable Methods: Paving the Way for 
 Transparent and Interpretable Medical Imaging Analysis - Francesco Prinzi\
 , University of Palermo
DTSTART:20230519T160000Z
DTEND:20230519T170000Z
UID:TALK201361@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Although data-driven Artificial Intelligence (AI) methods have
  played a crucial role in recent years\, their actual implementation in me
 dicine still poses numerous challenges. The lack of transparency has foste
 red skepticism among physicians and patients towards these emerging techno
 logies. Notably\, the US Federal Trade Commission emphasizes the importanc
 e of transparency\, explainability\, fairness\, and other ethical consider
 ations in the use of AI tools. Additionally\, under the GDPR\, individuals
  have the right to receive an explanation regarding the predictions made b
 y AI systems.\nIn response to these concerns\, several post-hoc explanatio
 n methods have been proposed to elucidate the deep features extracted by n
 eural networks\, including Convolutional Neural Networks\, Graph Neural Ne
 tworks\, and Vision Transformers. However\, these methods have exhibited l
 imitations in effectively correlating predictions with clinical justificat
 ions.\nRecently\, particularly in the field of radiological medical imagin
 g\, Radiomics has emerged as a powerful tool for feature extraction. Unlik
 e deep features\, radiomic features are derived through mathematical formu
 las applied to the images\, enabling the extraction and quantification of 
 various image characteristics such as texture\, pattern\, and statistical 
 measurements of regions of interest. Radiomic workflows offer several adva
 ntages over deep feature extraction\, including the ability to work with s
 mall datasets (a common scenario in the medical field). Moreover\, the inh
 erent interpretability of radiomic features is well-established\, as each 
 feature carries a known meaning.\nThe combination of Radiomics and explain
 able-by-design methods holds great promise in advancing the transparency a
 nd interpretability of AI applications in medical imaging.
LOCATION:Lecture Theatre 2
END:VEVENT
END:VCALENDAR