Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks
The quantification of new or enlarged lesions from follow-up MRI scans is an important surrogate of clinical disease activity in patients with multiple sclerosis (MS). Not only is manual segmentation time consuming, but inter-rater variability is high. Currently, only a few fully automated methods a...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2020-01-01
|
| Series: | NeuroImage: Clinical |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158220302825 |
| _version_ | 1818390220906692608 |
|---|---|
| author | Julia Krüger Roland Opfer Nils Gessert Ann-Christin Ostwaldt Praveena Manogaran Hagen H. Kitzler Alexander Schlaefer Sven Schippling |
| author_facet | Julia Krüger Roland Opfer Nils Gessert Ann-Christin Ostwaldt Praveena Manogaran Hagen H. Kitzler Alexander Schlaefer Sven Schippling |
| author_sort | Julia Krüger |
| collection | DOAJ |
| description | The quantification of new or enlarged lesions from follow-up MRI scans is an important surrogate of clinical disease activity in patients with multiple sclerosis (MS). Not only is manual segmentation time consuming, but inter-rater variability is high. Currently, only a few fully automated methods are available. We address this gap in the field by employing a 3D convolutional neural network (CNN) with encoder-decoder architecture for fully automatic longitudinal lesion segmentation.Input data consist of two fluid attenuated inversion recovery (FLAIR) images (baseline and follow-up) per patient. Each image is entered into the encoder and the feature maps are concatenated and then fed into the decoder. The output is a 3D mask indicating new or enlarged lesions (compared to the baseline scan). The proposed method was trained on 1809 single point and 1444 longitudinal patient data sets and then validated on 185 independent longitudinal data sets from two different scanners. From the two validation data sets, manual segmentations were available from three experienced raters, respectively. The performance of the proposed method was compared to the open source Lesion Segmentation Toolbox (LST), which is a current state-of-art longitudinal lesion segmentation method.The mean lesion-wise inter-rater sensitivity was 62%, while the mean inter-rater number of false positive (FP) findings was 0.41 lesions per case. The two validated algorithms showed a mean sensitivity of 60% (CNN), 46% (LST) and a mean FP of 0.48 (CNN), 1.86 (LST) per case. Sensitivity and number of FP were not significantly different (p < 0.05) between the CNN and manual raters.New or enlarged lesions counted by the CNN algorithm appeared to be comparable with manual expert ratings. The proposed algorithm seems to outperform currently available approaches, particularly LST. The high inter-rater variability in case of manual segmentation indicates the complexity of identifying new or enlarged lesions. An automated CNN-based approach can quickly provide an independent and deterministic assessment of new or enlarged lesions from baseline to follow-up scans with acceptable reliability. |
| first_indexed | 2024-12-14T04:54:10Z |
| format | Article |
| id | doaj.art-23911af55b254b5fb632e45f1589d55d |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-12-14T04:54:10Z |
| publishDate | 2020-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-23911af55b254b5fb632e45f1589d55d2022-12-21T23:16:27ZengElsevierNeuroImage: Clinical2213-15822020-01-0128102445Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networksJulia Krüger0Roland Opfer1Nils Gessert2Ann-Christin Ostwaldt3Praveena Manogaran4Hagen H. Kitzler5Alexander Schlaefer6Sven Schippling7jung diagnostics GmbH, Hamburg, Germany; Corresponding author.jung diagnostics GmbH, Hamburg, GermanyInstitute of Medical Technology, Hamburg University of Technology, Germanyjung diagnostics GmbH, Hamburg, GermanyNeuroimmunology and Multiple Sclerosis Research, Department of Neurology, University Hospital Zurich and University of Zurich, Switzerland; Department of Information Technology and Electrical Engineering, Swiss Federal Institute of Technology, Zurich, SwitzerlandInstitute of Diagnostic and Interventional Neuroradiology, University Hospital Carl Gustav Carus, Technische Universität Dresden, GermanyInstitute of Medical Technology, Hamburg University of Technology, GermanyNeuroimmunology and Multiple Sclerosis Research, Department of Neurology, University Hospital Zurich and University of Zurich, Switzerland; Neuroscience Center Zurich, University of Zurich and Federal Institute of Technology (ETH), Zurich, SwitzerlandThe quantification of new or enlarged lesions from follow-up MRI scans is an important surrogate of clinical disease activity in patients with multiple sclerosis (MS). Not only is manual segmentation time consuming, but inter-rater variability is high. Currently, only a few fully automated methods are available. We address this gap in the field by employing a 3D convolutional neural network (CNN) with encoder-decoder architecture for fully automatic longitudinal lesion segmentation.Input data consist of two fluid attenuated inversion recovery (FLAIR) images (baseline and follow-up) per patient. Each image is entered into the encoder and the feature maps are concatenated and then fed into the decoder. The output is a 3D mask indicating new or enlarged lesions (compared to the baseline scan). The proposed method was trained on 1809 single point and 1444 longitudinal patient data sets and then validated on 185 independent longitudinal data sets from two different scanners. From the two validation data sets, manual segmentations were available from three experienced raters, respectively. The performance of the proposed method was compared to the open source Lesion Segmentation Toolbox (LST), which is a current state-of-art longitudinal lesion segmentation method.The mean lesion-wise inter-rater sensitivity was 62%, while the mean inter-rater number of false positive (FP) findings was 0.41 lesions per case. The two validated algorithms showed a mean sensitivity of 60% (CNN), 46% (LST) and a mean FP of 0.48 (CNN), 1.86 (LST) per case. Sensitivity and number of FP were not significantly different (p < 0.05) between the CNN and manual raters.New or enlarged lesions counted by the CNN algorithm appeared to be comparable with manual expert ratings. The proposed algorithm seems to outperform currently available approaches, particularly LST. The high inter-rater variability in case of manual segmentation indicates the complexity of identifying new or enlarged lesions. An automated CNN-based approach can quickly provide an independent and deterministic assessment of new or enlarged lesions from baseline to follow-up scans with acceptable reliability.http://www.sciencedirect.com/science/article/pii/S2213158220302825Multiple sclerosisLesion activityConvolutional neural networkU-netLesion segmentation |
| spellingShingle | Julia Krüger Roland Opfer Nils Gessert Ann-Christin Ostwaldt Praveena Manogaran Hagen H. Kitzler Alexander Schlaefer Sven Schippling Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks NeuroImage: Clinical Multiple sclerosis Lesion activity Convolutional neural network U-net Lesion segmentation |
| title | Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks |
| title_full | Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks |
| title_fullStr | Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks |
| title_full_unstemmed | Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks |
| title_short | Fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3D convolutional neural networks |
| title_sort | fully automated longitudinal segmentation of new or enlarged multiple sclerosis lesions using 3d convolutional neural networks |
| topic | Multiple sclerosis Lesion activity Convolutional neural network U-net Lesion segmentation |
| url | http://www.sciencedirect.com/science/article/pii/S2213158220302825 |
| work_keys_str_mv | AT juliakruger fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks AT rolandopfer fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks AT nilsgessert fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks AT annchristinostwaldt fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks AT praveenamanogaran fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks AT hagenhkitzler fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks AT alexanderschlaefer fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks AT svenschippling fullyautomatedlongitudinalsegmentationofneworenlargedmultiplesclerosislesionsusing3dconvolutionalneuralnetworks |