MHA-CoroCapsule : Multi-Head Attention Routing-Based Capsule Network for COVID-19 Chest X-Ray Image Classification
The outbreak of COVID-19 threatens the lives and property safety of countless people and brings a tremendous pressure to health care systems worldwide. The principal challenge in the fight against this disease is the lack of efficient detection methods. AI-assisted diagnosis based on deep learning can detect COVID-19 cases for chest X-ray images automatically, and also improve the accuracy and efficiency of doctors' diagnosis. However, large scale annotation of chest X-ray images is difficult because of limited resources and heavy burden on the medical system. To meet the challenge, we propose a capsule network model with multi-head attention routing algorithm, called MHA-CoroCapsule, to provide fast and accurate diagnostics for COVID-19 diseases from chest X-ray images. The MHA-CoroCapsule consists of convolutional layers, two capsule layers, and a non-iterative, parameterized multi-head attention routing algorithm is used to quantify the relationship between the two capsule layers. The experiments are performed on a combined dataset constituted by two publicly available datasets including normal, non-COVID pneumonia and COVID-19 images. The model achieves the accuracy of 97.28%, recall of 97.36%, and precision of 97.38% even with a limited number of samples. The experimental results demonstrate that, contrary to the transfer learning and deep feature extraction approaches, the proposed MHA-CoroCapsule has an encouraging performance with fewer trainable parameters and does not require pretraining and plenty of training samples.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2022 |
|---|---|
| Erschienen: |
2022 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:41 |
|---|---|
| Enthalten in: |
IEEE transactions on medical imaging - 41(2022), 5 vom: 09. Mai, Seite 1208-1218 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Li, Fudong [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 04.05.2022 Date Revised 26.05.2022 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1109/TMI.2021.3134270 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM334191114 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM334191114 | ||
| 003 | DE-627 | ||
| 005 | 20231225223201.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2022 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TMI.2021.3134270 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1113.xml |
| 035 | |a (DE-627)NLM334191114 | ||
| 035 | |a (NLM)34882550 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Li, Fudong |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a MHA-CoroCapsule |b Multi-Head Attention Routing-Based Capsule Network for COVID-19 Chest X-Ray Image Classification |
| 264 | 1 | |c 2022 | |
| 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 04.05.2022 | ||
| 500 | |a Date Revised 26.05.2022 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a The outbreak of COVID-19 threatens the lives and property safety of countless people and brings a tremendous pressure to health care systems worldwide. The principal challenge in the fight against this disease is the lack of efficient detection methods. AI-assisted diagnosis based on deep learning can detect COVID-19 cases for chest X-ray images automatically, and also improve the accuracy and efficiency of doctors' diagnosis. However, large scale annotation of chest X-ray images is difficult because of limited resources and heavy burden on the medical system. To meet the challenge, we propose a capsule network model with multi-head attention routing algorithm, called MHA-CoroCapsule, to provide fast and accurate diagnostics for COVID-19 diseases from chest X-ray images. The MHA-CoroCapsule consists of convolutional layers, two capsule layers, and a non-iterative, parameterized multi-head attention routing algorithm is used to quantify the relationship between the two capsule layers. The experiments are performed on a combined dataset constituted by two publicly available datasets including normal, non-COVID pneumonia and COVID-19 images. The model achieves the accuracy of 97.28%, recall of 97.36%, and precision of 97.38% even with a limited number of samples. The experimental results demonstrate that, contrary to the transfer learning and deep feature extraction approaches, the proposed MHA-CoroCapsule has an encouraging performance with fewer trainable parameters and does not require pretraining and plenty of training samples | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a Research Support, Non-U.S. Gov't | |
| 700 | 1 | |a Lu, Xingyu |e verfasserin |4 aut | |
| 700 | 1 | |a Yuan, Jianjun |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on medical imaging |d 1982 |g 41(2022), 5 vom: 09. Mai, Seite 1208-1218 |w (DE-627)NLM082855269 |x 1558-254X |7 nnns |
| 773 | 1 | 8 | |g volume:41 |g year:2022 |g number:5 |g day:09 |g month:05 |g pages:1208-1218 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TMI.2021.3134270 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 41 |j 2022 |e 5 |b 09 |c 05 |h 1208-1218 | ||