Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions

Akkus, Zeynettin; Galimzianova, Alfiia; Hoogi, Assaf; Rubin, Daniel L.; Erickson, Bradley J.

doi:10.1007/s10278-017-9983-4

Cited by 896 publications

(621 citation statements)

References 60 publications

Supporting

Mentioning

606

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, automated tumour segmentation and evaluation may lead to an increased robustness and reliability due to reduced inter-reader bias [14]. As the tumour volume at primary diagnosis correlates with recurrence rates [1,12], a precise volumetric assessment could help to differentiate between meningioma grades.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI

et al. 2018

View full text Add to dashboard Cite

Objectives Magnetic resonance imaging (MRI) is the method of choice for imaging meningiomas. Volumetric assessment of meningiomas is highly relevant for therapy planning and monitoring. We used a multiparametric deep-learning model (DLM) on routine MRI data including images from diverse referring institutions to investigate DLM performance in automated detection and segmentation of meningiomas in comparison to manual segmentations. Methods We included 56 of 136 consecutive preoperative MRI datasets [T1/T2-weighted, T1-weighted contrast-enhanced (T1CE), FLAIR] of meningiomas that were treated surgically at the University Hospital Cologne and graded histologically as tumour grade I (n = 38) or grade II (n = 18). The DLM was trained on an independent dataset of 249 glioma cases and segmented different tumour classes as defined in the brain tumour image segmentation benchmark (BRATS benchmark). The DLM was based on the DeepMedic architecture. Results were compared to manual segmentations by two radiologists in a consensus reading in FLAIR and T1CE. T1-weighted contrast-enhanced MRI

show abstract

Section: Introductionmentioning

confidence: 99%

“…Further, pathologies such as brain tumours vary strongly in their presentation [5,14]. The technological advancements of deep-learning models (DLMs) led to significant improvements regarding the automated tumour detection and the technology is currently on the verge of being used in clinical routine [13,15,16].…”

Section: Introductionmentioning

confidence: 99%

Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI

et al. 2018

View full text Add to dashboard Cite

show abstract

“…More research is necessary to determine precisely whether the error reductions justify these databases, how they relate to regularized optimization, and how can it be optimized. It is also possible that other machine learning methods, such as convolutional neural networks (CNNs), 20 are more effective. This is provided that CNNs are developed for FE kernels, which were not available at the time of this research.…”

Section: Resultsmentioning

confidence: 99%

Inverse biomechanical modeling via machine learning and synthetic training data

Tolpadi

Stone

Carass

et al. 2018

Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling

View full text Add to dashboard Cite

The tongue’s deformation during speech can be measured using tagged magnetic resonance imaging, but there is no current method to directly measure the pattern of muscles that activate to produce a given motion. In this paper, the activation pattern of the tongue’s muscles is estimated by solving an inverse problem using a random forest. Examples describing different activation patterns and the resulting deformations are generated using a finite-element model of the tongue. These examples form training data for a random forest comprising 30 decision trees to estimate contractions in 262 contractile elements. The method was evaluated on data from tagged magnetic resonance data from actual speech and on simulated data mimicking flaps that might have resulted from glossectomy surgery. The estimation accuracy was modest (5.6% error), but it surpassed a semi-manual approach (8.1% error). The results suggest that a machine learning approach to contraction pattern estimation in the tongue is feasible, even in the presence of flaps.

show abstract

“…In addition, existing brain extraction algorithms focus on identifying the brain tissues from T1‐weighted (T1w) images, although there are many occasions that benefit from the characteristics of T2‐weighted (T2w) images: estimation of cerebrospinal fluid in quantitative evaluation of brain atrophy, pathologic studies of pediatric brains (pediatric MRI brain: normal or abnormal, that is the question), etc. More recently, deep learning‐based pediatric brain segmentation techniques have been proposed for brain extraction and segmentation . A dedicated 3D volumetric pediatric MR image analysis toolbox, called iBEAT, has been also introduced for image processing, skull extraction, tissue segmentation, and brain labeling.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, a brain extraction method for multislice T2w pediatric brain MR images is proposed in this study, based on the deep convolutional neural networks used for segmentation of medical images . More specifically, we adopted the dual frame (DF) U‐net architecture to enhance segmentation quality in boundary and small regions .…”

Section: Introductionmentioning

confidence: 99%

Pediatric brain extraction from T2‐weighted MR images using 3D dual frame U‐net and human connectome database

Kim

Chae

Han

2019

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Accurate extraction of brain tissues from magnetic resonance (MR) images is important in neuroradiology. However, brain extraction is more difficult for pediatric brains than for adult brains due to several factors including smaller brain sizes and lower tissue contrasts. In this work, we propose a brain extraction technique that utilizes dual frame (DF) 3D U‐net deep learning architecture and the human connectome project (HCP) database for multislice 2D pediatric T2‐weighted MR images with diseases. To improve segmentation accuracy in small pediatric brains with detailed boundary regions, DF 3D U‐net architecture was used. We pretrained networks with the HCP database to compensate for the limited amount of MR images and manual segmentation masks of pediatric patients. For quantitative analysis, we compared the brain extraction results of brain extraction tool, DF, and conventional 3D U‐net using the dice similarity coefficient (DSC), intersection of union (IoU), and boundary F1 (BF) scores; each deep learning architecture was evaluated with and without pretraining using the HCP. This study included 10 patients with diseases and all images were acquired using a PROPELLER MR sequence. Pretraining using the HCP database enhanced segmentation performance of the network, and the skip connections in the DF 3D U‐net could enhance the contour similarity of segmentation results. Experimental results showed that the proposed method increased the DSC, IoU, and BF scores by 0.8%, 1.6%, and 1.5%, respectively, compared with those of the conventional 3D U‐net without pretraining.

show abstract

Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions

Cited by 896 publications

References 60 publications

Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI

Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI

Inverse biomechanical modeling via machine learning and synthetic training data

Pediatric brain extraction from T2‐weighted MR images using 3D dual frame U‐net and human connectome database

Contact Info

Product

Resources

About