Ultrasound Image Synthesis Using Generative AI for Lung Consolidation Detection

Developing reliable healthcare AI models requires training with representative and diverse data. In imbalanced datasets, model performance tends to plateau on the more prevalent classes while remaining low on less common cases. To overcome this limitation, we propose DiffUltra, the first generative AI technique capable of synthesizing realistic Lung Ultrasound (LUS) images with extensive lesion variability. Specifically, we condition the generative AI by the introduced Lesion-anatomy Bank, which captures the lesion's structural and positional properties from real patient data to guide the image synthesis. We demonstrate that DiffUltra improves consolidation detection by 5.6% in AP compared to the models trained solely on real patient data. More importantly, DiffUltra increases data diversity and prevalence of rare cases, leading to a 25% AP improvement in detecting rare instances such as large lung consolidations, which make up only 10% of the dataset.

Authors

Institutions

Publication Details

Published
2025-04-14
DOI
https://doi.org/10.1109/isbi60581.2025.10980728
Primary Topic
Lung Cancer Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Ultrasound Image Synthesis Using Generative AI for Lung Consolidation Detection

Maria A. Parker, Alvin Chen, Jochen Kruecker, Jeffrey W. Shupp et al.
Lung Cancer Diagnosis and Treatment
article

Ultrasound Image Synthesis Using Generative AI for Lung Consolidation Detection

Maria A. Parker, Alvin Chen, Jochen Kruecker, Jeffrey W. Shupp, Cristiana Baloescu, David Kessler, Mohsen Zahiri, Yu-Cheng Chou, Nikolai Schnittke, Bryson Hicks, Cynthia R. Gregory, Naveen Balaraju, Li Chen, Shubham Patil, Christopher L. Moore, Balasundar I. Raju, Kenton W. Gregory, Gary Y. Li
article en

Abstract

Developing reliable healthcare AI models requires training with representative and diverse data. In imbalanced datasets, model performance tends to plateau on the more prevalent classes while remaining low on less common cases. To overcome this limitation, we propose DiffUltra, the first generative AI technique capable of synthesizing realistic Lung Ultrasound (LUS) images with extensive lesion variability. Specifically, we condition the generative AI by the introduced Lesion-anatomy Bank, which captures the lesion's structural and positional properties from real patient data to guide the image synthesis. We demonstrate that DiffUltra improves consolidation detection by 5.6% in AP compared to the models trained solely on real patient data. More importantly, DiffUltra increases data diversity and prevalence of rare cases, leading to a 25% AP improvement in detecting rare instances such as large lung consolidations, which make up only 10% of the dataset.

MedStar Washington Hospital Center (US), Johns Hopkins University (US), Oregon Health & Science University (US), Yale University (US), Philips (Spain) (ES), Columbia College (CA), Royal College of Physicians (GB), Columbia University (US)
U.S. Department of Health and Human Services, Biomedical Advanced Research and Development Authority
Openalex Percentile: Top 83%
Lung Cancer Diagnosis and Treatment
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.