Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks
Background: Hippocampus segmentation on magnetic resonance imaging is of key importance for the diagnosis, treatment decision and investigation of neuropsychiatric disorders. Automatic segmentation is an active research field, with many recent models using deep learning. Most current state-of-the ar...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2021-02-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844021003315 |
| _version_ | 1818879628818776064 |
|---|---|
| author | Diedre Carmo Bruna Silva Clarissa Yasuda Letícia Rittner Roberto Lotufo |
| author_facet | Diedre Carmo Bruna Silva Clarissa Yasuda Letícia Rittner Roberto Lotufo |
| author_sort | Diedre Carmo |
| collection | DOAJ |
| description | Background: Hippocampus segmentation on magnetic resonance imaging is of key importance for the diagnosis, treatment decision and investigation of neuropsychiatric disorders. Automatic segmentation is an active research field, with many recent models using deep learning. Most current state-of-the art hippocampus segmentation methods train their methods on healthy or Alzheimer's disease patients from public datasets. This raises the question whether these methods are capable of recognizing the hippocampus on a different domain, that of epilepsy patients with hippocampus resection.New Method: In this paper we present a state-of-the-art, open source, ready-to-use, deep learning based hippocampus segmentation method. It uses an extended 2D multi-orientation approach, with automatic pre-processing and orientation alignment. The methodology was developed and validated using HarP, a public Alzheimer's disease hippocampus segmentation dataset.Results and Comparisons: We test this methodology alongside other recent deep learning methods, in two domains: The HarP test set and an in-house epilepsy dataset, containing hippocampus resections, named HCUnicamp. We show that our method, while trained only in HarP, surpasses others from the literature in both the HarP test set and HCUnicamp in Dice. Additionally, Results from training and testing in HCUnicamp volumes are also reported separately, alongside comparisons between training and testing in epilepsy and Alzheimer's data and vice versa.Conclusion: Although current state-of-the-art methods, including our own, achieve upwards of 0.9 Dice in HarP, all tested methods, including our own, produced false positives in HCUnicamp resection regions, showing that there is still room for improvement for hippocampus segmentation methods when resection is involved. |
| first_indexed | 2024-12-19T14:33:06Z |
| format | Article |
| id | doaj.art-8485ec3fd5ef47839d3d0e1553054c6f |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-12-19T14:33:06Z |
| publishDate | 2021-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-8485ec3fd5ef47839d3d0e1553054c6f2022-12-21T20:17:22ZengElsevierHeliyon2405-84402021-02-0172e06226Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networksDiedre Carmo0Bruna Silva1Clarissa Yasuda2Letícia Rittner3Roberto Lotufo4School of Electrical and Computer Engineering, UNICAMP, Campinas, São Paulo, Brazil; Corresponding author.Faculty of Medical Sciences, UNICAMP, Campinas, São Paulo, BrazilFaculty of Medical Sciences, UNICAMP, Campinas, São Paulo, BrazilSchool of Electrical and Computer Engineering, UNICAMP, Campinas, São Paulo, BrazilSchool of Electrical and Computer Engineering, UNICAMP, Campinas, São Paulo, BrazilBackground: Hippocampus segmentation on magnetic resonance imaging is of key importance for the diagnosis, treatment decision and investigation of neuropsychiatric disorders. Automatic segmentation is an active research field, with many recent models using deep learning. Most current state-of-the art hippocampus segmentation methods train their methods on healthy or Alzheimer's disease patients from public datasets. This raises the question whether these methods are capable of recognizing the hippocampus on a different domain, that of epilepsy patients with hippocampus resection.New Method: In this paper we present a state-of-the-art, open source, ready-to-use, deep learning based hippocampus segmentation method. It uses an extended 2D multi-orientation approach, with automatic pre-processing and orientation alignment. The methodology was developed and validated using HarP, a public Alzheimer's disease hippocampus segmentation dataset.Results and Comparisons: We test this methodology alongside other recent deep learning methods, in two domains: The HarP test set and an in-house epilepsy dataset, containing hippocampus resections, named HCUnicamp. We show that our method, while trained only in HarP, surpasses others from the literature in both the HarP test set and HCUnicamp in Dice. Additionally, Results from training and testing in HCUnicamp volumes are also reported separately, alongside comparisons between training and testing in epilepsy and Alzheimer's data and vice versa.Conclusion: Although current state-of-the-art methods, including our own, achieve upwards of 0.9 Dice in HarP, all tested methods, including our own, produced false positives in HCUnicamp resection regions, showing that there is still room for improvement for hippocampus segmentation methods when resection is involved.http://www.sciencedirect.com/science/article/pii/S2405844021003315Deep learningHippocampus segmentationConvolutional neural networksAlzheimer's diseaseEpilepsy |
| spellingShingle | Diedre Carmo Bruna Silva Clarissa Yasuda Letícia Rittner Roberto Lotufo Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks Heliyon Deep learning Hippocampus segmentation Convolutional neural networks Alzheimer's disease Epilepsy |
| title | Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks |
| title_full | Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks |
| title_fullStr | Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks |
| title_full_unstemmed | Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks |
| title_short | Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks |
| title_sort | hippocampus segmentation on epilepsy and alzheimer s disease studies with multiple convolutional neural networks |
| topic | Deep learning Hippocampus segmentation Convolutional neural networks Alzheimer's disease Epilepsy |
| url | http://www.sciencedirect.com/science/article/pii/S2405844021003315 |
| work_keys_str_mv | AT diedrecarmo hippocampussegmentationonepilepsyandalzheimersdiseasestudieswithmultipleconvolutionalneuralnetworks AT brunasilva hippocampussegmentationonepilepsyandalzheimersdiseasestudieswithmultipleconvolutionalneuralnetworks AT clarissayasuda hippocampussegmentationonepilepsyandalzheimersdiseasestudieswithmultipleconvolutionalneuralnetworks AT leticiarittner hippocampussegmentationonepilepsyandalzheimersdiseasestudieswithmultipleconvolutionalneuralnetworks AT robertolotufo hippocampussegmentationonepilepsyandalzheimersdiseasestudieswithmultipleconvolutionalneuralnetworks |