Weakly-supervised lesion analysis with a CNN-based framework for COVID-19
Creative Commons Attribution license..
Objective.Lesions of COVID-19 can be clearly visualized using chest CT images, and hence provide valuable evidence for clinicians when making a diagnosis. However, due to the variety of COVID-19 lesions and the complexity of the manual delineation procedure, automatic analysis of lesions with unknown and diverse types from a CT image remains a challenging task. In this paper we propose a weakly-supervised framework for this task requiring only a series of normal and abnormal CT images without the need for annotations of the specific locations and types of lesions.Approach.A deep learning-based diagnosis branch is employed for classification of the CT image and then a lesion identification branch is leveraged to capture multiple types of lesions.Main Results.Our framework is verified on publicly available datasets and CT data collected from 13 patients of the First Affiliated Hospital of Shantou University Medical College, China. The results show that the proposed framework can achieve state-of-the-art diagnosis prediction, and the extracted lesion features are capable of distinguishing between lesions showing ground glass opacity and consolidation.Significance.The proposed approach integrates COVID-19 positive diagnosis and lesion analysis into a unified framework without extra pixel-wise supervision. Further exploration also demonstrates that this framework has the potential to discover lesion types that have not been reported and can potentially be generalized to lesion detection of other chest-based diseases.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2021 |
|---|---|
| Erschienen: |
2021 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:66 |
|---|---|
| Enthalten in: |
Physics in medicine and biology - 66(2021), 24 vom: 31. Dez. |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Wu, Kaichao [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
COVID-19 |
|---|
| Anmerkungen: |
Date Completed 10.01.2022 Date Revised 10.01.2022 published: Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1088/1361-6560/ac4316 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM334421535 |
|---|
| LEADER | 01000naa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM334421535 | ||
| 003 | DE-627 | ||
| 005 | 20231225223651.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231225s2021 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1088/1361-6560/ac4316 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1114.xml |
| 035 | |a (DE-627)NLM334421535 | ||
| 035 | |a (NLM)34905733 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Wu, Kaichao |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Weakly-supervised lesion analysis with a CNN-based framework for COVID-19 |
| 264 | 1 | |c 2021 | |
| 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 10.01.2022 | ||
| 500 | |a Date Revised 10.01.2022 | ||
| 500 | |a published: Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Creative Commons Attribution license. | ||
| 520 | |a Objective.Lesions of COVID-19 can be clearly visualized using chest CT images, and hence provide valuable evidence for clinicians when making a diagnosis. However, due to the variety of COVID-19 lesions and the complexity of the manual delineation procedure, automatic analysis of lesions with unknown and diverse types from a CT image remains a challenging task. In this paper we propose a weakly-supervised framework for this task requiring only a series of normal and abnormal CT images without the need for annotations of the specific locations and types of lesions.Approach.A deep learning-based diagnosis branch is employed for classification of the CT image and then a lesion identification branch is leveraged to capture multiple types of lesions.Main Results.Our framework is verified on publicly available datasets and CT data collected from 13 patients of the First Affiliated Hospital of Shantou University Medical College, China. The results show that the proposed framework can achieve state-of-the-art diagnosis prediction, and the extracted lesion features are capable of distinguishing between lesions showing ground glass opacity and consolidation.Significance.The proposed approach integrates COVID-19 positive diagnosis and lesion analysis into a unified framework without extra pixel-wise supervision. Further exploration also demonstrates that this framework has the potential to discover lesion types that have not been reported and can potentially be generalized to lesion detection of other chest-based diseases | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a COVID-19 | |
| 650 | 4 | |a GGO | |
| 650 | 4 | |a chest CT image | |
| 650 | 4 | |a lesion identification | |
| 650 | 4 | |a weakly-supervised | |
| 700 | 1 | |a Jelfs, Beth |e verfasserin |4 aut | |
| 700 | 1 | |a Ma, Xiangyuan |e verfasserin |4 aut | |
| 700 | 1 | |a Ke, Ruitian |e verfasserin |4 aut | |
| 700 | 1 | |a Tan, Xuerui |e verfasserin |4 aut | |
| 700 | 1 | |a Fang, Qiang |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Physics in medicine and biology |d 1956 |g 66(2021), 24 vom: 31. Dez. |w (DE-627)NLM000336505 |x 1361-6560 |7 nnns |
| 773 | 1 | 8 | |g volume:66 |g year:2021 |g number:24 |g day:31 |g month:12 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1088/1361-6560/ac4316 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 66 |j 2021 |e 24 |b 31 |c 12 | ||