Three-dimensional U-Net Convolutional Neural Network for Detection and Segmentation of Intracranial Metastases

Rudie, Jeffrey D.; Weiß, David; Colby, John B.; Rauschecker, Andreas M.; Laguna, Benjamin; Braunstein, Steve; Sugrue, Leo P.; Hess, Christopher P.; Villanueva-Meyer, Javier

doi:10.1148/ryai.2021200204

Cited by 40 publications

(61 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results corroborate previous studies that deep learning is effective in medical image segmentation. 21–23,27,28 This study also replicated the results of prior studies showing that U-Nets can segment brain images with high accuracy. 23,27 Our results also corroborate a previous study that showed the effectiveness of 2D CapsNets for segmenting biomedical images, outperforming other deep learning models including U-Nets.…”

Section: Discussionsupporting

confidence: 85%

“…Our results corroborate previous studies that deep learning is effective in medical image segmentation. [20][21][22]26,27 Multiple prior studies have shown the success of U-Nets in biomedical image segmentation. 20,22,27 The 3D U-Net that we coded in this study also showed strong performance in segmenting brain MRIs.…”

Section: Discussionmentioning

confidence: 99%

“…The U-Net is considered among the highest-performing segmentation algorithms in diagnostic imaging. [20][21][22][23] The U-Net has shown strong auto-segmentation accuracy across a variety of different imaging modalities and anatomic structures. [21][22][23][24][25][26] Figure 1.B shows the architecture of our 3D U-Net.…”

Section: D U-netmentioning

confidence: 99%

“…[20][21][22][23] The U-Net has shown strong auto-segmentation accuracy across a variety of different imaging modalities and anatomic structures. [21][22][23][24][25][26] Figure 1.B shows the architecture of our 3D U-Net. The input image undergoes 64 convolutions (3×3×3) to generate 64 feature maps.…”

Section: D U-netmentioning

confidence: 99%

See 3 more Smart Citations

3D Capsule Networks for Brain Image Segmentation

Avesta

Hui

Krumholz

et al. 2022

Preprint

View full text Add to dashboard Cite

INTRODUCTION: Segmenting brain structures around a tumor on brain images is important for radiotherapy and surgical planning. Current auto-segmentation methods often fail to segment brain anatomy when it is distorted by tumors. OBJECTIVE: To develop and validate 3D capsule networks (CapsNets) that can segment brain structures with novel spatial features that were not represented in the training data. Methods: We developed, trained, and tested 3D CapsNets using 3430 brain MRIs acquired in a multi-institutional study. We compared our CapsNets with U-Nets using multiple performance measures, including accuracy in segmenting various brain structures, segmenting brain structures with spatial features not represented in the training data, performance when the models are trained using limited data, memory requirements, and computation times. RESULTS: 3D CapsNets can segment third ventricle, thalamus, and hippocampus with Dice scores of 94%, 94%, and 91%, respectively. 3D CapsNets outperform 3D U-Nets in segmenting brain structures that were not represented in the training data, with Dice scores more than 30% higher. 3D CapsNets are also remarkably smaller models compared to 3D U-Nets, with 93% fewer trainable parameters. This led to faster convergence of 3D CapsNets during training, making them faster to train compared to U-Nets. The two models were equally fast during testing. CONCLUSION: 3D CapsNets can segment brain structures with high accuracy, outperform U-Nets in segmenting brain structures with features that were not represented during training, and are remarkably more efficient compared to U-Nets, achieving similar results while their size is one order of magnitude smaller.

show abstract

Section: Discussionsupporting

confidence: 85%

Section: Discussionmentioning

confidence: 99%

Section: D U-netmentioning

confidence: 99%

Section: D U-netmentioning

confidence: 99%

See 2 more Smart Citations

3D Capsule Networks for Brain Image Segmentation

Avesta

Hui

Krumholz

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Along with the development of artificial intelligence (AI), quantitative data from CT and ordinary MR images, such as T1, T2, and T1-contrast-enhanced, and fluid-attenuated inversion recovery (FLAIR) images could be extracted and processed by machine learning or deep learning algorithms ( Lambin et al, 2012 ; Chang et al, 2019 ). State-of-the-art neural networks could select shape, texture, and gray level of tumors for predicting tumor classification ( Lee et al, 2020 ; Chakrabarty et al, 2021 ), segmentation ( Tang et al, 2020 ; Rudie et al, 2021 ), grading ( Naser and Deen, 2020 ), and even molecular parameters ( Bangalore Yogananda et al, 2020 ; Choi et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

Alternations and Applications of the Structural and Functional Connectome in Gliomas: A Mini-Review

Chen

Teng

et al. 2022

Front. Neurosci.

View full text Add to dashboard Cite

In the central nervous system, gliomas are the most common, but complex primary tumors. Genome-based molecular and clinical studies have revealed different classifications and subtypes of gliomas. Neuroradiological approaches have non-invasively provided a macroscopic view for surgical resection and therapeutic effects. The connectome is a structural map of a physical object, the brain, which raises issues of spatial scale and definition, and it is calculated through diffusion magnetic resonance imaging (MRI) and functional MRI. In this study, we reviewed the basic principles and attributes of the structural and functional connectome, followed by the alternations of connectomes and their influences on glioma. To extend the applications of connectome, we demonstrated that a series of multi-center projects still need to be conducted to systemically investigate the connectome and the structural–functional coupling of glioma. Additionally, the brain–computer interface based on accurate connectome could provide more precise structural and functional data, which are significant for surgery and postoperative recovery. Besides, integrating the data from different sources, including connectome and other omics information, and their processing with artificial intelligence, together with validated biological and clinical findings will be significant for the development of a personalized surgical strategy.

show abstract

Automated Detection of Brain Metastases on T1‐Weighted MRI Using a Convolutional Neural Network: Impact of Volume Aware Loss and Sampling Strategy

Chartrand¹,

Emiliani²,

Pawlowski³

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Detection of brain metastases (BM) and segmentation for treatment planning could be optimized with machine learning methods. Convolutional neural networks (CNNs) are promising, but their trade‐offs between sensitivity and precision frequently lead to missing small lesions. Hypothesis Combining volume aware (VA) loss function and sampling strategy could improve BM detection sensitivity. Study Type Retrospective. Population A total of 530 radiation oncology patients (55% women) were split into a training/validation set (433 patients/1460 BM) and an independent test set (97 patients/296 BM). Field Strength/Sequence 1.5 T and 3 T, contrast‐enhanced three‐dimensional (3D) T1‐weighted fast gradient echo sequences. Assessment Ground truth masks were based on radiotherapy treatment planning contours reviewed by experts. A U‐Net inspired model was trained. Three loss functions (Dice, Dice + boundary, and VA) and two sampling methods (label and VA) were compared. Results were reported with Dice scores, volumetric error, lesion detection sensitivity, and precision. A detected voxel within the ground truth constituted a true positive. Statistical Tests McNemar's exact test to compare detected lesions between models. Pearson's correlation coefficient and Bland–Altman analysis to compare volume agreement between predicted and ground truth volumes. Statistical significance was set at P ≤ 0.05. Results Combining VA loss and VA sampling performed best with an overall sensitivity of 91% and precision of 81%. For BM in the 2.5–6 mm estimated sphere diameter range, VA loss reduced false negatives by 58% and VA sampling reduced it further by 30%. In the same range, the boundary loss achieved the highest precision at 81%, but a low sensitivity (24%) and a 31% Dice loss. Data Conclusion Considering BM size in the loss and sampling function of CNN may increase the detection sensitivity regarding small BM. Our pipeline relying on a single contrast‐enhanced T1‐weighted MRI sequence could reach a detection sensitivity of 91%, with an average of only 0.66 false positives per scan. Evidence Level 3 Technical Efficacy Stage 2

show abstract

Three-dimensional U-Net Convolutional Neural Network for Detection and Segmentation of Intracranial Metastases

Cited by 40 publications

References 21 publications

3D Capsule Networks for Brain Image Segmentation

3D Capsule Networks for Brain Image Segmentation

Alternations and Applications of the Structural and Functional Connectome in Gliomas: A Mini-Review

Automated Detection of Brain Metastases on T1‐Weighted MRI Using a Convolutional Neural Network: Impact of Volume Aware Loss and Sampling Strategy

Contact Info

Product

Resources

About