HAL-IA : A Hybrid Active Learning framework using Interactive Annotation for medical image segmentation
Copyright © 2023 Elsevier B.V. All rights reserved..
High performance of deep learning models on medical image segmentation greatly relies on large amount of pixel-wise annotated data, yet annotations are costly to collect. How to obtain high accuracy segmentation labels of medical images with limited cost (e.g. time) becomes an urgent problem. Active learning can reduce the annotation cost of image segmentation, but it faces three challenges: the cold start problem, an effective sample selection strategy for segmentation task and the burden of manual annotation. In this work, we propose a Hybrid Active Learning framework using Interactive Annotation (HAL-IA) for medical image segmentation, which reduces the annotation cost both in decreasing the amount of the annotated images and simplifying the annotation process. Specifically, we propose a novel hybrid sample selection strategy to select the most valuable samples for segmentation model performance improvement. This strategy combines pixel entropy, regional consistency and image diversity to ensure that the selected samples have high uncertainty and diversity. In addition, we propose a warm-start initialization strategy to build the initial annotated dataset to avoid the cold-start problem. To simplify the manual annotation process, we propose an interactive annotation module with suggested superpixels to obtain pixel-wise label with several clicks. We validate our proposed framework with extensive segmentation experiments on four medical image datasets. Experimental results showed that the proposed framework achieves high accuracy pixel-wise annotations and models with less labeled data and fewer interactions, outperforming other state-of-the-art methods. Our method can help physicians efficiently obtain accurate medical image segmentation results for clinical analysis and diagnosis.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2023 |
|---|---|
| Erschienen: |
2023 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:88 |
|---|---|
| Enthalten in: |
Medical image analysis - 88(2023) vom: 15. Aug., Seite 102862 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Li, Xiaokang [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Active learning |
|---|
| Anmerkungen: |
Date Completed 05.10.2023 Date Revised 05.10.2023 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1016/j.media.2023.102862 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM357970705 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM357970705 | ||
| 003 | DE-627 | ||
| 005 | 20231226073737.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1016/j.media.2023.102862 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1193.xml |
| 035 | |a (DE-627)NLM357970705 | ||
| 035 | |a (NLM)37295312 | ||
| 035 | |a (PII)S1361-8415(23)00122-6 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Li, Xiaokang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a HAL-IA |b A Hybrid Active Learning framework using Interactive Annotation for medical image segmentation |
| 264 | 1 | |c 2023 | |
| 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 05.10.2023 | ||
| 500 | |a Date Revised 05.10.2023 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Copyright © 2023 Elsevier B.V. All rights reserved. | ||
| 520 | |a High performance of deep learning models on medical image segmentation greatly relies on large amount of pixel-wise annotated data, yet annotations are costly to collect. How to obtain high accuracy segmentation labels of medical images with limited cost (e.g. time) becomes an urgent problem. Active learning can reduce the annotation cost of image segmentation, but it faces three challenges: the cold start problem, an effective sample selection strategy for segmentation task and the burden of manual annotation. In this work, we propose a Hybrid Active Learning framework using Interactive Annotation (HAL-IA) for medical image segmentation, which reduces the annotation cost both in decreasing the amount of the annotated images and simplifying the annotation process. Specifically, we propose a novel hybrid sample selection strategy to select the most valuable samples for segmentation model performance improvement. This strategy combines pixel entropy, regional consistency and image diversity to ensure that the selected samples have high uncertainty and diversity. In addition, we propose a warm-start initialization strategy to build the initial annotated dataset to avoid the cold-start problem. To simplify the manual annotation process, we propose an interactive annotation module with suggested superpixels to obtain pixel-wise label with several clicks. We validate our proposed framework with extensive segmentation experiments on four medical image datasets. Experimental results showed that the proposed framework achieves high accuracy pixel-wise annotations and models with less labeled data and fewer interactions, outperforming other state-of-the-art methods. Our method can help physicians efficiently obtain accurate medical image segmentation results for clinical analysis and diagnosis | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 650 | 4 | |a Active learning | |
| 650 | 4 | |a Annotation cost reduction | |
| 650 | 4 | |a Interactive segmentation | |
| 650 | 4 | |a Medical image segmentation | |
| 650 | 4 | |a Region consistency | |
| 700 | 1 | |a Xia, Menghua |e verfasserin |4 aut | |
| 700 | 1 | |a Jiao, Jing |e verfasserin |4 aut | |
| 700 | 1 | |a Zhou, Shichong |e verfasserin |4 aut | |
| 700 | 1 | |a Chang, Cai |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Yuanyuan |e verfasserin |4 aut | |
| 700 | 1 | |a Guo, Yi |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medical image analysis |d 1996 |g 88(2023) vom: 15. Aug., Seite 102862 |w (DE-627)NLM096527188 |x 1361-8423 |7 nnns |
| 773 | 1 | 8 | |g volume:88 |g year:2023 |g day:15 |g month:08 |g pages:102862 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.media.2023.102862 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 88 |j 2023 |b 15 |c 08 |h 102862 | ||