
PHAIR Consortium
@phairconsortium
The Pancreatobiliary and Hepatic Artificial Intelligence Research (PHAIR) Consortium. Focusing on clinically relevant and applicable AI tools voor HPB disease.
ID: 1621491924006838276
http://phair-consortium.com 03-02-2023 12:53:21
29 Tweet
78 Followers
13 Following

Excited to be a part of the PHAIR Consortium NYU Langone Health NYU Langone General Surgery Residency!! Looking forward to the work that comes out of this group

#EAHPBA2023 E-AHPBA External validation of #radiomics preoperative fistula๐ง risk score (RAD-FRS) for Whipple ๐ช ! FIRST externally validated model of its kind โ Similar AUC to (ua)FRS in pre-op setting โ Great work by Ewout Ingwersen, Jacqueline Bereska and PHAIR Consortium!


#EAHPBA2023 E-AHPBA Segmentation model for ๐ฌ residual pancreatic cancer following neoadjuvant therapy (ISGPP-2)! Model based on 528 pt, 14 centers, 7 countries๐ณ๐ฑ๐บ๐ธ๐ฉ๐ช๐ณ๐ด๐น๐ท๐ฐ๐ท๐ฆ๐บ, 4 scanner types! Validated with by-scanner internal-external cross-validation ๐! F1 score of 0.78!


Now ESGAR #ESGAR2023 Externally valid #radiomics preoperative fistula risk score (RAD-FRS) for Whipple! FIRST externally valid model of its kind โ Similar AUC (0.81) to (ua)FRS (0.79) in preop setting โ Great work Ewout Ingwersen, Jacqueline Bereska and PHAIR Consortium!


ESGAR #esgar2023 PHAIR Consortium lead Inez Verpalen presents: ๐๏ธ #ArtificialIntelligence based Assessment of Vascular Involvement and Resectability ๐ชon CT in patients with PDAC Segmentation ๐ธ below! Great work Jacqueline Bereska Boris Janssen and PHAIR Consortium โ๏ธ


EPC-Europ Pancr Club #EPC2023 Boris Janssen on behalf of PHAIR Consortium! AI residual cancer burden (RCB) to evaluate impact of NAT in resected pancreatic cancer! RCB ๐ฌ NAT vs. upfront: 2.2 vs. 10.3 mm2 p<0.0001 Survival ๐ Above vs. below median RCB: 24 vs. 30 months. p=0.018



The future of IPMN management ๐ will be based on two pillars ๐๏ธ Biomarkers and AI ๐ค Twelve AI based models to assess the risk of malignancy already exist! ๐ข Methodological quality and reliability still to be improvedโฆ letโs work on it!! ๐ read ๐academic.oup.com/bjs/advance-arโฆ


๐ข: Alberto Balduzzi Boris Janssen and PHAIR Consortium in BJS ๐ 12 imaging-based AI models to predict malignancy of IPMN ๐ Methodologically suboptimal ๐ Methodologically robust prospective studies incl. non-surgical patients required! Read: academic.oup.com/bjs/advance-arโฆ


This week ๐ณ๐ฑ Inez Verpalen Jacqueline Bereska etc. from Amsterdam UMC visit ๐ณ๐ดร smund A. Fretland Knut Jรธrgen Labori in the Oslounivsykehus! External validation of a CRLM CT segmentation model! ๐ธ Discussions on imaging-based response evaluation to neoadjuvant therapy in both liver and pancreas! ๐


Last week radiogist Hรฅvard Bjรธrke Jenssen from ๐ณ๐ดOslounivsykehus visited the ๐ณ๐ฑ @AmsterdamUMC HPB team! Sharing and aligning HPB CT segmentation โ๏ธ strategies with Yung Nio, Jacqueline Bereska Inez Verpalen and others! ๐ธ Visit finalized with the annual @AmsterdamUMC HPB BBQ!


The first ever Radiomics ๐พ preoperative fistula risk score !!! Development ๐ณ๐ฑ and external validation ๐ฎ๐น ๐ณ The radiomics-based preop FRS performed similarly to the existing scores ( ROC 0.8) ๐ช Great added value considering only CT derived data! academic.oup.com/bjsopen/articlโฆ


Now in BJS Open! Externally valid #radiomics pre-op fistula risk score (RAD-FRS) for Whipple! ๐ฎ๐น๐ณ๐ฑ FIRST externally valid model โ Similar AUC (0.81) to (ua)FRS (0.79) in preop setting ๐ท ๐ Ewout Ingwersen, Jacqueline Bereska and PHAIR Consortium! academic.oup.com/bjsopen/articlโฆ

