Reducing Overtreatment of Indeterminate Thyroid Nodules Using a Multimodal Deep Learning Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Athreya, Shreeram, Melehy, Andrew, Suthahar, Sujit Silas Armstrong, Ivezić, Vedrana, Radhachandran, Ashwath, Sant, Vivek, Moleta, Chace, Zheng, Henry, Patel, Maitraya, Masamed, Rinat, Arnold, Corey W., Speier, William
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910624154386432
author Athreya, Shreeram
Melehy, Andrew
Suthahar, Sujit Silas Armstrong
Ivezić, Vedrana
Radhachandran, Ashwath
Sant, Vivek
Moleta, Chace
Zheng, Henry
Patel, Maitraya
Masamed, Rinat
Arnold, Corey W.
Speier, William
author_facet Athreya, Shreeram
Melehy, Andrew
Suthahar, Sujit Silas Armstrong
Ivezić, Vedrana
Radhachandran, Ashwath
Sant, Vivek
Moleta, Chace
Zheng, Henry
Patel, Maitraya
Masamed, Rinat
Arnold, Corey W.
Speier, William
contents Objective: Molecular testing (MT) classifies cytologically indeterminate thyroid nodules as benign or malignant with high sensitivity but low positive predictive value (PPV), only using molecular profiles, ignoring ultrasound (US) imaging and biopsy. We address this limitation by applying attention multiple instance learning (AMIL) to US images. Methods: We retrospectively reviewed 333 patients with indeterminate thyroid nodules at UCLA medical center (259 benign, 74 malignant). A multi-modal deep learning AMIL model was developed, combining US images and MT to classify the nodules as benign or malignant and enhance the malignancy risk stratification of MT. Results: The final AMIL model matched MT sensitivity (0.946) while significantly improving PPV (0.477 vs 0.448 for MT alone), indicating fewer false positives while maintaining high sensitivity. Conclusion: Our approach reduces false positives compared to MT while maintaining the same ability to identify positive cases, potentially reducing unnecessary benign thyroid resections in patients with indeterminate nodules.
format Preprint
id arxiv_https___arxiv_org_abs_2409_19171
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reducing Overtreatment of Indeterminate Thyroid Nodules Using a Multimodal Deep Learning Model
Athreya, Shreeram
Melehy, Andrew
Suthahar, Sujit Silas Armstrong
Ivezić, Vedrana
Radhachandran, Ashwath
Sant, Vivek
Moleta, Chace
Zheng, Henry
Patel, Maitraya
Masamed, Rinat
Arnold, Corey W.
Speier, William
Quantitative Methods
Machine Learning
Image and Video Processing
Objective: Molecular testing (MT) classifies cytologically indeterminate thyroid nodules as benign or malignant with high sensitivity but low positive predictive value (PPV), only using molecular profiles, ignoring ultrasound (US) imaging and biopsy. We address this limitation by applying attention multiple instance learning (AMIL) to US images. Methods: We retrospectively reviewed 333 patients with indeterminate thyroid nodules at UCLA medical center (259 benign, 74 malignant). A multi-modal deep learning AMIL model was developed, combining US images and MT to classify the nodules as benign or malignant and enhance the malignancy risk stratification of MT. Results: The final AMIL model matched MT sensitivity (0.946) while significantly improving PPV (0.477 vs 0.448 for MT alone), indicating fewer false positives while maintaining high sensitivity. Conclusion: Our approach reduces false positives compared to MT while maintaining the same ability to identify positive cases, potentially reducing unnecessary benign thyroid resections in patients with indeterminate nodules.
title Reducing Overtreatment of Indeterminate Thyroid Nodules Using a Multimodal Deep Learning Model
topic Quantitative Methods
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2409.19171