Training With Uncertain Annotations for Semantic Segmentation of Basal Cell Carcinoma From Full-Field OCT Images
Semantic segmentation of basal cell carcinoma (BCC) from full-field optical coherence tomography (FF-OCT) images of human skin has received considerable attention in medical imaging. However, it is challenging for dermatopathologists to annotate the training data due to OCT's lack of color specificity. Very often, they are uncertain about the correctness of the annotations they made. In practice, annotations fraught with uncertainty profoundly impact the effectiveness of model training and hence the performance of BCC segmentation. To address this issue, we propose an approach to model training with uncertain annotations. The proposed approach includes a data selection strategy to mitigate the uncertainty of training data, a class expansion to consider sebaceous gland and hair follicle as additional classes to enhance the performance of BCC segmentation, and a self-supervised pre-training procedure to improve the initial weights of the segmentation model parameters. Furthermore, we develop three post-processing techniques to reduce the impact of speckle noise and image discontinuities on BCC segmentation. The mean Dice score of BCC of our model reaches 0.503±0.003, which, to the best of our knowledge, is the best performance to date for semantic segmentation of BCC from FF-OCT images.
| Medienart: |
E-Artikel |
|---|
| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
Zur Gesamtaufnahme - volume:43 |
|---|---|
| Enthalten in: |
IEEE transactions on medical imaging - 43(2024), 3 vom: 29. März, Seite 1060-1070 |
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Fu, Li-Wei [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| Anmerkungen: |
Date Completed 06.03.2024 Date Revised 06.03.2024 published: Print-Electronic Citation Status MEDLINE |
|---|
| doi: |
10.1109/TMI.2023.3327257 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
NLM363669760 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | NLM363669760 | ||
| 003 | DE-627 | ||
| 005 | 20240306232506.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 231226s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1109/TMI.2023.3327257 |2 doi | |
| 028 | 5 | 2 | |a pubmed24n1318.xml |
| 035 | |a (DE-627)NLM363669760 | ||
| 035 | |a (NLM)37874706 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Fu, Li-Wei |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Training With Uncertain Annotations for Semantic Segmentation of Basal Cell Carcinoma From Full-Field OCT Images |
| 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 06.03.2024 | ||
| 500 | |a Date Revised 06.03.2024 | ||
| 500 | |a published: Print-Electronic | ||
| 500 | |a Citation Status MEDLINE | ||
| 520 | |a Semantic segmentation of basal cell carcinoma (BCC) from full-field optical coherence tomography (FF-OCT) images of human skin has received considerable attention in medical imaging. However, it is challenging for dermatopathologists to annotate the training data due to OCT's lack of color specificity. Very often, they are uncertain about the correctness of the annotations they made. In practice, annotations fraught with uncertainty profoundly impact the effectiveness of model training and hence the performance of BCC segmentation. To address this issue, we propose an approach to model training with uncertain annotations. The proposed approach includes a data selection strategy to mitigate the uncertainty of training data, a class expansion to consider sebaceous gland and hair follicle as additional classes to enhance the performance of BCC segmentation, and a self-supervised pre-training procedure to improve the initial weights of the segmentation model parameters. Furthermore, we develop three post-processing techniques to reduce the impact of speckle noise and image discontinuities on BCC segmentation. The mean Dice score of BCC of our model reaches 0.503±0.003, which, to the best of our knowledge, is the best performance to date for semantic segmentation of BCC from FF-OCT images | ||
| 650 | 4 | |a Journal Article | |
| 700 | 1 | |a Liu, Chih-Hao |e verfasserin |4 aut | |
| 700 | 1 | |a Jain, Manu |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Chih-Shan Jason |e verfasserin |4 aut | |
| 700 | 1 | |a Wu, Yu-Hung |e verfasserin |4 aut | |
| 700 | 1 | |a Huang, Sheng-Lung |e verfasserin |4 aut | |
| 700 | 1 | |a Chen, Homer H |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t IEEE transactions on medical imaging |d 1982 |g 43(2024), 3 vom: 29. März, Seite 1060-1070 |w (DE-627)NLM082855269 |x 1558-254X |7 nnns |
| 773 | 1 | 8 | |g volume:43 |g year:2024 |g number:3 |g day:29 |g month:03 |g pages:1060-1070 |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1109/TMI.2023.3327257 |3 Volltext |
| 912 | |a GBV_USEFLAG_A | ||
| 912 | |a GBV_NLM | ||
| 951 | |a AR | ||
| 952 | |d 43 |j 2024 |e 3 |b 29 |c 03 |h 1060-1070 | ||