Visual interpretability of bioimaging deep learning models

Oded Rotem; Assaf Zaritsky

doi:10.1038/s41592-024-02322-6

Visual interpretability of bioimaging deep learning models

Oded Rotem, Assaf Zaritsky

Department of Software and Information Systems Engineering

Ben-Gurion University of the Negev

Research output: Contribution to journal › Comment/debate

Abstract

The success of deep learning in analyzing bioimages comes at the expense of biologically meaningful interpretations. We review the state of the art of explainable artificial intelligence (XAI) in bioimaging and discuss its potential in hypothesis generation and data-driven discovery.

Original language	American English
Pages (from-to)	1394-1397
Number of pages	4
Journal	Nature Methods
Volume	21
Issue number	8
DOIs	https://doi.org/10.1038/s41592-024-02322-6
State	Published - 1 Aug 2024

All Science Journal Classification (ASJC) codes

Biotechnology
Biochemistry
Molecular Biology
Cell Biology

Access to Document

10.1038/s41592-024-02322-6

Cite this

@article{dd28e7dab1f341a3a367956e62f8e5aa,

title = "Visual interpretability of bioimaging deep learning models",

abstract = "The success of deep learning in analyzing bioimages comes at the expense of biologically meaningful interpretations. We review the state of the art of explainable artificial intelligence (XAI) in bioimaging and discuss its potential in hypothesis generation and data-driven discovery.",

author = "Oded Rotem and Assaf Zaritsky",

note = "Publisher Copyright: {\textcopyright} Springer Nature America, Inc. 2024.",

year = "2024",

month = aug,

day = "1",

doi = "10.1038/s41592-024-02322-6",

language = "American English",

volume = "21",

pages = "1394--1397",

journal = "Nature Methods",

issn = "1548-7091",

publisher = "Nature Research",

number = "8",

}

TY - JOUR

T1 - Visual interpretability of bioimaging deep learning models

AU - Rotem, Oded

AU - Zaritsky, Assaf

PY - 2024/8/1

Y1 - 2024/8/1

N2 - The success of deep learning in analyzing bioimages comes at the expense of biologically meaningful interpretations. We review the state of the art of explainable artificial intelligence (XAI) in bioimaging and discuss its potential in hypothesis generation and data-driven discovery.

AB - The success of deep learning in analyzing bioimages comes at the expense of biologically meaningful interpretations. We review the state of the art of explainable artificial intelligence (XAI) in bioimaging and discuss its potential in hypothesis generation and data-driven discovery.

UR - http://www.scopus.com/inward/record.url?scp=85200741706&partnerID=8YFLogxK

U2 - 10.1038/s41592-024-02322-6

DO - 10.1038/s41592-024-02322-6

M3 - Comment/debate

C2 - 39122948

SN - 1548-7091

VL - 21

SP - 1394

EP - 1397

JO - Nature Methods

JF - Nature Methods

IS - 8

ER -

Visual interpretability of bioimaging deep learning models

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this