LESION SEARCH WITH SELF-SUPERVISED LEARNING

Kristin Qi; Jiali Cheng; Daniel Haehn

LESION SEARCH WITH SELF-SUPERVISED LEARNING

Kristin Qi
, Jiali Cheng
, Daniel Haehn

Computer Science

University of Massachusetts Boston
University of Massachusetts Lowell

Research output: Contribution to conference › Paper › peer-review

Abstract

Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians’ interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a generalized-mean (GeM) pooling followed by L2 normalization to classify lesion types and retrieve similar images before clinicians’ analysis. Results have shown improved performance. We additionally build an open-source application for image analysis and retrieval. The application is easy to integrate, relieving manual efforts and suggesting the potential to support clinicians’ everyday activities.

Original language	English
State	Published - 2023
Event	1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023 - Kigali, Rwanda Duration: May 5 2023 → May 5 2023

Conference

Conference	1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023
Country/Territory	Rwanda
City	Kigali
Period	5/5/23 → 5/5/23

ASJC Scopus Subject Areas

Linguistics and Language
Language and Linguistics
Computer Science Applications
Education

Cite this

@conference{76d0ddc7985045a9a195d29b384a5a8d,

title = "LESION SEARCH WITH SELF-SUPERVISED LEARNING",

abstract = "Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians{\textquoteright} interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a generalized-mean (GeM) pooling followed by L2 normalization to classify lesion types and retrieve similar images before clinicians{\textquoteright} analysis. Results have shown improved performance. We additionally build an open-source application for image analysis and retrieval. The application is easy to integrate, relieving manual efforts and suggesting the potential to support clinicians{\textquoteright} everyday activities.",

author = "Kristin Qi and Jiali Cheng and Daniel Haehn",

note = "Publisher Copyright: {\textcopyright} 2023 1st Tiny Papers Track at ICLR 2023 - Tiny Papers @ ICLR 2023. All rights reserved.; 1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023 ; Conference date: 05-05-2023 Through 05-05-2023",

year = "2023",

language = "English",

}

TY - CONF

T1 - LESION SEARCH WITH SELF-SUPERVISED LEARNING

AU - Qi, Kristin

AU - Cheng, Jiali

AU - Haehn, Daniel

PY - 2023

Y1 - 2023

N2 - Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians’ interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a generalized-mean (GeM) pooling followed by L2 normalization to classify lesion types and retrieve similar images before clinicians’ analysis. Results have shown improved performance. We additionally build an open-source application for image analysis and retrieval. The application is easy to integrate, relieving manual efforts and suggesting the potential to support clinicians’ everyday activities.

AB - Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians’ interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a generalized-mean (GeM) pooling followed by L2 normalization to classify lesion types and retrieve similar images before clinicians’ analysis. Results have shown improved performance. We additionally build an open-source application for image analysis and retrieval. The application is easy to integrate, relieving manual efforts and suggesting the potential to support clinicians’ everyday activities.

UR - https://www.scopus.com/pages/publications/105026748498

UR - https://www.scopus.com/pages/publications/105026748498#tab=citedBy

M3 - Paper

AN - SCOPUS:105026748498

T2 - 1st Tiny Papers at 11th International Conference on Learning Representations, Tiny Papers @ ICLR 2023

Y2 - 5 May 2023 through 5 May 2023

ER -

LESION SEARCH WITH SELF-SUPERVISED LEARNING

Abstract

Conference

ASJC Scopus Subject Areas

Other files and links

Fingerprint

Cite this