Cross-scale multi-instance learning for pathological image diagnosis
Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved..
Analyzing high resolution whole slide images (WSIs) with regard to information across multiple scales poses a significant challenge in digital pathology. Multi-instance learning (MIL) is a common solution for working with high resolution images by classifying bags of objects (i.e. sets of smaller image patches). However, such processing is typically performed at a single scale (e.g., 20× magnification) of WSIs, disregarding the vital inter-scale information that is key to diagnoses by human pathologists. In this study, we propose a novel cross-scale MIL algorithm to explicitly aggregate inter-scale relationships into a single MIL network for pathological image diagnosis. The contribution of this paper is three-fold: (1) A novel cross-scale MIL (CS-MIL) algorithm that integrates the multi-scale information and the inter-scale relationships is proposed; (2) A toy dataset with scale-specific morphological features is created and released to examine and visualize differential cross-scale attention; (3) Superior performance on both in-house and public datasets is demonstrated by our simple cross-scale MIL strategy. The official implementation is publicly available at https://github.com/hrlblab/CS-MIL.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:94 |
---|---|
Enthalten in: |
Medical image analysis - 94(2024) vom: 01. Apr., Seite 103124 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Deng, Ruining [VerfasserIn] |
---|
Links: |
---|
Themen: |
Attention mechanism |
---|
Anmerkungen: |
Date Completed 16.04.2024 Date Revised 25.04.2024 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.media.2024.103124 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM369181557 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM369181557 | ||
003 | DE-627 | ||
005 | 20240425233023.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240302s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.media.2024.103124 |2 doi | |
028 | 5 | 2 | |a pubmed24n1386.xml |
035 | |a (DE-627)NLM369181557 | ||
035 | |a (NLM)38428271 | ||
035 | |a (PII)S1361-8415(24)00049-5 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Deng, Ruining |e verfasserin |4 aut | |
245 | 1 | 0 | |a Cross-scale multi-instance learning for pathological image diagnosis |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 16.04.2024 | ||
500 | |a Date Revised 25.04.2024 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2024 The Author(s). Published by Elsevier B.V. All rights reserved. | ||
520 | |a Analyzing high resolution whole slide images (WSIs) with regard to information across multiple scales poses a significant challenge in digital pathology. Multi-instance learning (MIL) is a common solution for working with high resolution images by classifying bags of objects (i.e. sets of smaller image patches). However, such processing is typically performed at a single scale (e.g., 20× magnification) of WSIs, disregarding the vital inter-scale information that is key to diagnoses by human pathologists. In this study, we propose a novel cross-scale MIL algorithm to explicitly aggregate inter-scale relationships into a single MIL network for pathological image diagnosis. The contribution of this paper is three-fold: (1) A novel cross-scale MIL (CS-MIL) algorithm that integrates the multi-scale information and the inter-scale relationships is proposed; (2) A toy dataset with scale-specific morphological features is created and released to examine and visualize differential cross-scale attention; (3) Superior performance on both in-house and public datasets is demonstrated by our simple cross-scale MIL strategy. The official implementation is publicly available at https://github.com/hrlblab/CS-MIL | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Attention mechanism | |
650 | 4 | |a Multi-instance learning | |
650 | 4 | |a Multi-scale | |
650 | 4 | |a Pathology | |
700 | 1 | |a Cui, Can |e verfasserin |4 aut | |
700 | 1 | |a Remedios, Lucas W |e verfasserin |4 aut | |
700 | 1 | |a Bao, Shunxing |e verfasserin |4 aut | |
700 | 1 | |a Womick, R Michael |e verfasserin |4 aut | |
700 | 1 | |a Chiron, Sophie |e verfasserin |4 aut | |
700 | 1 | |a Li, Jia |e verfasserin |4 aut | |
700 | 1 | |a Roland, Joseph T |e verfasserin |4 aut | |
700 | 1 | |a Lau, Ken S |e verfasserin |4 aut | |
700 | 1 | |a Liu, Qi |e verfasserin |4 aut | |
700 | 1 | |a Wilson, Keith T |e verfasserin |4 aut | |
700 | 1 | |a Wang, Yaohong |e verfasserin |4 aut | |
700 | 1 | |a Coburn, Lori A |e verfasserin |4 aut | |
700 | 1 | |a Landman, Bennett A |e verfasserin |4 aut | |
700 | 1 | |a Huo, Yuankai |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Medical image analysis |d 1996 |g 94(2024) vom: 01. Apr., Seite 103124 |w (DE-627)NLM096527188 |x 1361-8423 |7 nnns |
773 | 1 | 8 | |g volume:94 |g year:2024 |g day:01 |g month:04 |g pages:103124 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.media.2024.103124 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 94 |j 2024 |b 01 |c 04 |h 103124 |