Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images
In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/7/10/200 |
| _version_ | 1797514238017667072 |
|---|---|
| author | Andrik Rampun Deborah Jarvis Paul D. Griffiths Reyer Zwiggelaar Bryan W. Scotney Paul A. Armitage |
| author_facet | Andrik Rampun Deborah Jarvis Paul D. Griffiths Reyer Zwiggelaar Bryan W. Scotney Paul A. Armitage |
| author_sort | Andrik Rampun |
| collection | DOAJ |
| description | In this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively. |
| first_indexed | 2024-03-10T06:28:47Z |
| format | Article |
| id | doaj.art-4cd159ae98bc409fac4e046260e6aec6 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-10T06:28:47Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-4cd159ae98bc409fac4e046260e6aec62023-11-22T18:44:11ZengMDPI AGJournal of Imaging2313-433X2021-10-0171020010.3390/jimaging7100200Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR ImagesAndrik Rampun0Deborah Jarvis1Paul D. Griffiths2Reyer Zwiggelaar3Bryan W. Scotney4Paul A. Armitage5Academic Unit of Radiology, Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Sheffield S10 2RX, UKAcademic Unit of Radiology, Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Sheffield S10 2RX, UKAcademic Unit of Radiology, Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Sheffield S10 2RX, UKDepartment of Computer Science, Aberystwyth University, Wales SY23 3DB, UKSchool of Computing, Ulster University, Jordanstown, County Antrim BT37 0QB, Northern Ireland, UKAcademic Unit of Radiology, Department of Infection, Immunity & Cardiovascular Disease, University of Sheffield, Sheffield S10 2RX, UKIn this work, we develop the Single-Input Multi-Output U-Net (SIMOU-Net), a hybrid network for foetal brain segmentation inspired by the original U-Net fused with the holistically nested edge detection (HED) network. The SIMOU-Net is similar to the original U-Net but it has a deeper architecture and takes account of the features extracted from each side output. It acts similar to an ensemble neural network, however, instead of averaging the outputs from several independently trained models, which is computationally expensive, our approach combines outputs from a single network to reduce the variance of predications and generalization errors. Experimental results using 200 normal foetal brains consisting of over 11,500 2D images produced Dice and Jaccard coefficients of 94.2 ± 5.9% and 88.7 ± 6.9%, respectively. We further tested the proposed network on 54 abnormal cases (over 3500 images) and achieved Dice and Jaccard coefficients of 91.2 ± 6.8% and 85.7 ± 6.6%, respectively.https://www.mdpi.com/2313-433X/7/10/200foetal brain segmentationMRIU-NetHED networkdeep learningconvolutional neural network |
| spellingShingle | Andrik Rampun Deborah Jarvis Paul D. Griffiths Reyer Zwiggelaar Bryan W. Scotney Paul A. Armitage Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images Journal of Imaging foetal brain segmentation MRI U-Net HED network deep learning convolutional neural network |
| title | Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images |
| title_full | Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images |
| title_fullStr | Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images |
| title_full_unstemmed | Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images |
| title_short | Single-Input Multi-Output U-Net for Automated 2D Foetal Brain Segmentation of MR Images |
| title_sort | single input multi output u net for automated 2d foetal brain segmentation of mr images |
| topic | foetal brain segmentation MRI U-Net HED network deep learning convolutional neural network |
| url | https://www.mdpi.com/2313-433X/7/10/200 |
| work_keys_str_mv | AT andrikrampun singleinputmultioutputunetforautomated2dfoetalbrainsegmentationofmrimages AT deborahjarvis singleinputmultioutputunetforautomated2dfoetalbrainsegmentationofmrimages AT pauldgriffiths singleinputmultioutputunetforautomated2dfoetalbrainsegmentationofmrimages AT reyerzwiggelaar singleinputmultioutputunetforautomated2dfoetalbrainsegmentationofmrimages AT bryanwscotney singleinputmultioutputunetforautomated2dfoetalbrainsegmentationofmrimages AT paulaarmitage singleinputmultioutputunetforautomated2dfoetalbrainsegmentationofmrimages |