Few-shot segmentation framework for lung nodules via an optimized active contour model
© 2024 American Association of Physicists in Medicine..
BACKGROUND: Accurate segmentation of lung nodules is crucial for the early diagnosis and treatment of lung cancer in clinical practice. However, the similarity between lung nodules and surrounding tissues has made their segmentation a longstanding challenge.
PURPOSE: Existing deep learning and active contour models each have their limitations. This paper aims to integrate the strengths of both approaches while mitigating their respective shortcomings.
METHODS: In this paper, we propose a few-shot segmentation framework that combines a deep neural network with an active contour model. We introduce heat kernel convolutions and high-order total variation into the active contour model and solve the challenging nonsmooth optimization problem using the alternating direction method of multipliers. Additionally, we use the presegmentation results obtained from training a deep neural network on a small sample set as the initial contours for our optimized active contour model, addressing the difficulty of manually setting the initial contours.
RESULTS: We compared our proposed method with state-of-the-art methods for segmentation effectiveness using clinical computed tomography (CT) images acquired from two different hospitals and the publicly available LIDC dataset. The results demonstrate that our proposed method achieved outstanding segmentation performance according to both visual and quantitative indicators.
CONCLUSION: Our approach utilizes the output of few-shot network training as prior information, avoiding the need to select the initial contour in the active contour model. Additionally, it provides mathematical interpretability to the deep learning, reducing its dependency on the quantity of training samples.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:51 |
|---|---|
| Enthalten in: |
Medical physics - 51(2024), 4 vom: 06. Apr., Seite 2788-2805 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Yang, Lin [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
Computed tomography |
|---|
| Anmerkungen: |
Date Completed 05.04.2024 Date Revised 05.04.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1002/mp.16933 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM366801562 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM366801562 | ||
| 003 | DE-627 | ||
| 005 | 20240405233349.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 240114s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1002/mp.16933 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1366.xml |
| 035 | |a (DE-627)NLM366801562 | ||
| 035 | |a (NLM)38189528 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Yang, Lin |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Few-shot segmentation framework for lung nodules via an optimized active contour model |
| 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 05.04.2024 | ||
| 500 | |a Date Revised 05.04.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a © 2024 American Association of Physicists in Medicine. | ||
| 520 | |a BACKGROUND: Accurate segmentation of lung nodules is crucial for the early diagnosis and treatment of lung cancer in clinical practice. However, the similarity between lung nodules and surrounding tissues has made their segmentation a longstanding challenge | ||
| 520 | |a PURPOSE: Existing deep learning and active contour models each have their limitations. This paper aims to integrate the strengths of both approaches while mitigating their respective shortcomings | ||
| 520 | |a METHODS: In this paper, we propose a few-shot segmentation framework that combines a deep neural network with an active contour model. We introduce heat kernel convolutions and high-order total variation into the active contour model and solve the challenging nonsmooth optimization problem using the alternating direction method of multipliers. Additionally, we use the presegmentation results obtained from training a deep neural network on a small sample set as the initial contours for our optimized active contour model, addressing the difficulty of manually setting the initial contours | ||
| 520 | |a RESULTS: We compared our proposed method with state-of-the-art methods for segmentation effectiveness using clinical computed tomography (CT) images acquired from two different hospitals and the publicly available LIDC dataset. The results demonstrate that our proposed method achieved outstanding segmentation performance according to both visual and quantitative indicators | ||
| 520 | |a CONCLUSION: Our approach utilizes the output of few-shot network training as prior information, avoiding the need to select the initial contour in the active contour model. Additionally, it provides mathematical interpretability to the deep learning, reducing its dependency on the quantity of training samples | ||
| 650 | 4 | |a Journal Article | |
| 650 | 4 | |a computed tomography | |
| 650 | 4 | |a few‐shot segmentation framework | |
| 650 | 4 | |a lung nodule | |
| 650 | 4 | |a optimized active contour model | |
| 700 | 1 | |a Shao, Dan |e verfasserin |4 aut | |
| 700 | 1 | |a Huang, Zhenxing |e verfasserin |4 aut | |
| 700 | 1 | |a Geng, Mengxiao |e verfasserin |4 aut | |
| 700 | 1 | |a Zhang, Na |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Long |e verfasserin |4 aut | |
| 700 | 1 | |a Wang, Xi |e verfasserin |4 aut | |
| 700 | 1 | |a Liang, Dong |e verfasserin |4 aut | |
| 700 | 1 | |a Pang, Zhi-Feng |e verfasserin |4 aut | |
| 700 | 1 | |a Hu, Zhanli |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Medical physics |d 1974 |g 51(2024), 4 vom: 06. Apr., Seite 2788-2805 |w (DE-627)NLM000294748 |x 2473-4209 |7 nnns |
| 773 | 1 | 8 | |g volume:51 |g year:2024 |g number:4 |g day:06 |g month:04 |g pages:2788-2805 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1002/mp.16933 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 51 |j 2024 |e 4 |b 06 |c 04 |h 2788-2805 | ||