Research Presentation Sessions: Imaging Informatics / Artificial Intelligence and Machine Learning

RPS 1305 - Artificial intelligence (AI) in chest imaging: part 2

Lectures

1
Introduction by the moderator

Introduction by the moderator

02:00Guillaume Chassagnon, Paris / FR

2
Overall survival prediction for stage II and stage III non-small cell lung cancer patients using a graph-based deep learning algorithm

Overall survival prediction for stage II and stage III non-small cell lung cancer patients using a graph-based deep learning algorithm

08:00Varut Vardhanabhuti, Hong Kong / HK

3
A laboratory-medicine-like approach to the analysis of unremarkable chest radiographs using artificial intelligence

A laboratory-medicine-like approach to the analysis of unremarkable chest radiographs using artificial intelligence

08:00Thomas Weikert, Basel / CH

4
Deep learning universal lesion segmentation for automated RECIST measurements on CT: comparison to manual assessment by radiologists

Deep learning universal lesion segmentation for automated RECIST measurements on CT: comparison to manual assessment by radiologists

08:00Max De Grauw, Velp (GE) / NL

5
Lightweight techniques to improve generalisability of U-Net based segmentations of lung lobes

Lightweight techniques to improve generalisability of U-Net based segmentations of lung lobes

08:00Armin Dadras, Offenbach / DE

6
Development and validation of a machine learning based CADx designed to improve patient management in lung cancer screening programmes

Development and validation of a machine learning based CADx designed to improve patient management in lung cancer screening programmes

08:00Charles Voyton, Valbonne / FR

7
First performance evaluation of an artificial intelligence-based computer aided detection system for pulmonary nodule evaluation in dual source photon-counting detector CT at different low dose levels

First performance evaluation of an artificial intelligence-based computer aided detection system for pulmonary nodule evaluation in dual source photon-counting detector CT at different low dose levels

08:00Lisa Jungblut, Zürich / CH

8
Reducing clinical chest X-ray reading times by using artificial intelligence to stratify worklists into normal/abnormal categories

Reducing clinical chest X-ray reading times by using artificial intelligence to stratify worklists into normal/abnormal categories

08:00K.F.M. Hergaarden, Leiden / NL

9
Development of a deep learning-based model for chest X-ray quality assessment

Development of a deep learning-based model for chest X-ray quality assessment

08:00Rémi Khansa, Taissy / FR

10
AI model uncertainty for detecting pneumothorax on chest radiographs is a strong predictor for annotator confidence

AI model uncertainty for detecting pneumothorax on chest radiographs is a strong predictor for annotator confidence

08:00Omar Hertgers, Den Haag / NL

11
Impact of a content-based image retrieval system on the interpretation of chest CTs of patients with diffuse parenchymal lung disease

Impact of a content-based image retrieval system on the interpretation of chest CTs of patients with diffuse parenchymal lung disease

08:00Sebastian Röhrich, Vienna / AT

12
CAD significantly increases the accuracy of pulmonary nodule detection in both concurrent and second reader paradigms

CAD significantly increases the accuracy of pulmonary nodule detection in both concurrent and second reader paradigms

08:00Yiyuan Zhao, Chesterbrook / US