Figure 3 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group

Figure 3 from Predicting Molecular Subtype and Survival of Rhabdomyosarcoma Patients Using Deep Learning of H&E Images: A Report from the Children's Oncology Group

<p><i>TP53</i> gene mutation prediction from H&E images. <b>A,</b> Workflow for deep learning of <i>TP53</i> mutations from FN-RMS WSIs. <b>B</b> and <b>C,</b> Representative (<b>B</b>) H&E images and (<b>C&l...

Full description

Saved in:
Bibliographic Details
Main Author: David Milewski (15050643) (author)
Other Authors: Hyun Jung (15050646) (author), G. Thomas Brown (15050649) (author), Yanling Liu (15050652) (author), Ben Somerville (15050655) (author), Curtis Lisle (15050658) (author), Marc Ladanyi (15050661) (author), Erin R. Rudzinski (15050664) (author), Hyoyoung Choo-Wosoba (15050667) (author), Donald A. Barkauskas (15050670) (author), Tammy Lo (15050673) (author), David Hall (15050676) (author), Corinne M. Linardic (15050679) (author), Jun S. Wei (14955721) (author), Hsien-Chao Chou (14955718) (author), Stephen X. Skapek (15050682) (author), Rajkumar Venkatramani (15050685) (author), Peter K. Bode (15050688) (author), Seth M. Steinberg (15043179) (author), George Zaki (15050691) (author), Igor B. Kuznetsov (15050694) (author), Douglas S. Hawkins (15050697) (author), Jack F. Shern (14938001) (author), Jack Collins (15050700) (author), Javed Khan (15046967) (author)
Published: 2025
Subjects:
Cancer
Cancer Detection and Diagnosis
Methods and Technology
Biomarkers
Prognostic biomarkers
Computational Methods
Artificial intelligence & machine learning
Pediatric Cancers
Sarcomas
Soft-tissue sarcoma
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<p><i>TP53</i> gene mutation prediction from H&E images. <b>A,</b> Workflow for deep learning of <i>TP53</i> mutations from FN-RMS WSIs. <b>B</b> and <b>C,</b> Representative (<b>B</b>) H&E images and (<b>C</b>) class activation maps of a TP53 wild-type tumor and a tumor with a TP53 p.P278T mutation (VAF = 0.474). <b>D,</b> Confusion matrix for predictions on a test dataset. Micro F1, Macro F1, and Matthew's correlation coefficient shown below. <b>E,</b> Performance statistics for <i>TP53</i> mutation prediction. <b>F,</b> Average ROC curve for <i>TP53</i> mutation prediction using holdout test data. <b>G,</b> Dot plot of <i>TP53</i> mutant samples (<i>n</i> = 15) showing relationship between <i>TP53</i> mutation VAF and A.I. positive prediction probability. Statistical analysis was performed using the Mann–Whitney <i>U</i> test.</p>

Similar Items