Fast and Precise Hippocampus Segmentation Through Deep Convolutional Neural Network Ensembles and Transfer Learning

Ataloglou, Dimitrios; Dimou, Anastasios; Zarpalas, Dimitrios; Daras, Petros

doi:10.1007/s12021-019-09417-y

Cited by 58 publications

(43 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Looking at these recent works, one can confirm the segmentation potential of the U-Net architecture, including the idea of an ensemble of 2D U-Nets instead of using a single 3D one, as we [25], some simultaneous recent work [7,18], or even works in other segmentation problems [26] presented. In this paper, some of those methods were reproduced for comparison purposes in our in-house dataset, namely [7,8], including a 3D UNet architecture test from [9].…”

Section: Hippocampus Segmentation With Deep Learningmentioning

confidence: 53%

“…Lately, a more time efficient approach appeared in the literature, namely the use of such atlases as training volumes for CNNs. Deep learning methods can achieve similar overlap metrics while predicting results in a matter of seconds per volume [7,8,15,16,17,18,19].…”

Section: Hippocampus Segmentation With Deep Learningmentioning

confidence: 99%

“…Ataloglou et al [18] recently displayed another case of fusion of multiple CNN outputs, specialized into axial, coronal and sagittal orientations, into a final hippocampus segmentation. They used U-Net like CNNs specialized in each orientation, followed by error correction CNNs, and a final average fusion of the results.…”

Section: Hippocampus Segmentation With Deep Learningmentioning

confidence: 99%

See 2 more Smart Citations

Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks

Carmo

Silva

Initiative

et al. 2021

Heliyon

View full text Add to dashboard Cite

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 preprocessing 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.

show abstract

Section: Hippocampus Segmentation With Deep Learningmentioning

confidence: 53%

Section: Hippocampus Segmentation With Deep Learningmentioning

confidence: 99%

Section: Hippocampus Segmentation With Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks

Carmo

Silva

Initiative

et al. 2021

Heliyon

View full text Add to dashboard Cite

show abstract

“…First, we segmented the hippocampus region for each subject's T1 image, which was used to mask the hippocampus region of FA, MD, and MK maps after some preprocessing (Figures 1, 2). Deep segmented CNN was employed to perform the segmentation which was trained by Ataloglou et al (2019). Then, because it contains T1 and segmented hippocampus images, the EADC-ADNI HarP dataset 2 was used to fine-tune the network and segment the hippocampus region of T1 image for each subject.…”

Section: Data Preprocessingmentioning

confidence: 99%

Identifying Epilepsy Based on Deep Learning Using DKI Images

Huang

Kang

et al. 2020

Front. Hum. Neurosci.

View full text Add to dashboard Cite

“…Since then, deep learning methods have been employed for the task in various variations. [8][9][10][11] In the RT application, CT-only auto-contouring could simplify the clinical workflow by removing the need for an MR scan during treatment planning and for additional steps such as MR/CT registration. Zhao et al 12 proposed to perform whole brain segmentation including the hippocampus by generating synthetic MR from CT images with deep learning, then applying MR-based segmentation algorithms from literature.…”

mentioning

confidence: 99%

Hippocampus segmentation in CT using deep learning: impact of MR versus CT-based training contours

et al. 2020

View full text Add to dashboard Cite

. Purpose: Hippocampus contouring for radiotherapy planning is performed on MR image data due to poor anatomical visibility on computed tomography (CT) data. Deep learning methods for direct CT hippocampus auto-segmentation exist, but use MR-based training contours. We investigate if these can be replaced by CT-based contours without loss in segmentation performance. This would remove the MR not only from inference but also from training. Approach: The hippocampus was contoured by medical experts on MR and CT data of 45 patients. Convolutional neural networks (CNNs) for hippocampus segmentation on CT were trained on CT-based or propagated MR-based contours. In both cases, their predictions were evaluated against the MR-based contours considered as the ground truth. Performance was measured using several metrics, including Dice score, surface distances, and contour Dice score. Bayesian dropout was used to estimate model uncertainty. Results: CNNs trained on propagated MR contours (median Dice 0.67) significantly outperform those trained on CT contours (0.59) and also experts contouring manually on CT (0.59). Differences between the latter two are not significant. Training on MR contours results in lower model uncertainty than training on CT contours. All contouring methods (manual or CNN) on CT perform significantly worse than a CNN segmenting the hippocampus directly on MR (median Dice 0.76). Additional data augmentation by rigid transformations improves the quantitative results but the difference remains significant. Conclusions: CT-based training contours for CT hippocampus segmentation cannot replace propagated MR-based contours without significant loss in performance. However, if MR-based contours are used, the resulting segmentations outperform experts in contouring the hippocampus on CT.

show abstract

Fast and Precise Hippocampus Segmentation Through Deep Convolutional Neural Network Ensembles and Transfer Learning

Cited by 58 publications

References 65 publications

Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks

Hippocampus segmentation on epilepsy and Alzheimer's disease studies with multiple convolutional neural networks

Identifying Epilepsy Based on Deep Learning Using DKI Images

Hippocampus segmentation in CT using deep learning: impact of MR versus CT-based training contours

Contact Info

Product

Resources

About