Universal lesion detection in CT scans using neural network ensembles

Tarun Mattikalli; Tejas Sudharshan Mathai; Ronald M. Summers

doi:10.1117/12.2612660

4 April 2022 Universal lesion detection in CT scans using neural network ensembles

Tarun Mattikalli, Tejas Sudharshan Mathai, Ronald M. Summers

Proceedings Volume 12033, Medical Imaging 2022: Computer-Aided Diagnosis; 120333D (2022) https://doi.org/10.1117/12.2612660
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Abstract

In clinical practice, radiologists are reliant on the lesion size when distinguishing metastatic from non-metastatic lesions. A prerequisite for lesion sizing is their detection, as it promotes the downstream assessment of tumor spread. However, lesions vary in their size and appearance in CT scans, and radiologists often miss small lesions during a busy clinical day. To overcome these challenges, we propose the use of state-of-the-art detection neural networks to flag suspicious lesions present in the NIH DeepLesion dataset for sizing. Additionally, we incorporate a bounding box fusion technique to minimize false positives (FP) and improve detection accuracy. Finally, to resemble clinical usage, we constructed an ensemble of the best detection models to localize lesions for sizing with a precision of 65.17% and sensitivity of 91.67% at 4 FP per image. Our results improve upon or maintain the performance of current state-of-the-art methods for lesion detection in challenging CT scans.

Conference Presentation

Citation Download Citation

Tarun Mattikalli, Tejas Sudharshan Mathai, and Ronald M. Summers "Universal lesion detection in CT scans using neural network ensembles", Proc. SPIE 12033, Medical Imaging 2022: Computer-Aided Diagnosis, 120333D (4 April 2022); https://doi.org/10.1117/12.2612660

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES + PRESENTATION

DOWNLOAD PAPER SAVE TO MY LIBRARY

WATCH
PRESENTATION

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Computed tomography

Neural networks

Tumors

Computer aided diagnosis and therapy

Machine learning

Object recognition

RELATED CONTENT

Identifying an optimal machine learning generated image marker to predict...
Proceedings of SPIE (April 04 2022)

Weakly supervised deep learning of interstitial lung disease types on...
Proceedings of SPIE (March 13 2019)

Applying a radiomics approach to predict prognosis of lung cancer...
Proceedings of SPIE (March 24 2016)

Lung nodule malignancy prediction using multi-task convolutional neural network
Proceedings of SPIE (March 03 2017)

Pelvic artery calcification detection on CT scans using convolutional neural...
Proceedings of SPIE (March 03 2017)

Lung lesion detection in FDG PET CT with Gaussian process...
Proceedings of SPIE (March 03 2017)

A novel feature reduction method to improve performance of machine...
Proceedings of SPIE (February 15 2021)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years