A deep learning method for automatic segmentation of the bony orbit in MRI and CT images

Hamwood, Jared; Schmutz, Beat; Collins, Michael J.; Allenby, Mark C.; Alonso‐Caneiro, David

doi:10.1038/s41598-021-93227-3

Cited by 41 publications

(34 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Firstly, the manual segmentation is performed by MRI experts, which is a tedious and complex task, but accurate, while the accurate and straightforward software does automatic segmentation due to developments in artificial intelligence. It is also worth mentioning that the MRI experts first label the datasets used for automatic segmentation ( 41 ). The evaluation metrics used for brain tumor segmentation are DSC, accuracy, sensitivity, and precision ( 42 ).…”

Section: Resultsmentioning

confidence: 99%

A Sequential Machine Learning-cum-Attention Mechanism for Effective Segmentation of Brain Tumor

et al. 2022

View full text Add to dashboard Cite

Magnetic resonance imaging is the most generally utilized imaging methodology that permits radiologists to look inside the cerebrum using radio waves and magnets for tumor identification. However, it is tedious and complex to identify the tumorous and nontumorous regions due to the complexity in the tumorous region. Therefore, reliable and automatic segmentation and prediction are necessary for the segmentation of brain tumors. This paper proposes a reliable and efficient neural network variant, i.e., an attention-based convolutional neural network for brain tumor segmentation. Specifically, an encoder part of the UNET is a pre-trained VGG19 network followed by the adjacent decoder parts with an attention gate for segmentation noise induction and a denoising mechanism for avoiding overfitting. The dataset we are using for segmentation is BRATS’20, which comprises four different MRI modalities and one target mask file. The abovementioned algorithm resulted in a dice similarity coefficient of 0.83, 0.86, and 0.90 for enhancing, core, and whole tumors, respectively.

show abstract

Section: Resultsmentioning

confidence: 99%

A Sequential Machine Learning-cum-Attention Mechanism for Effective Segmentation of Brain Tumor

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Orbital MRI examination is free of ionizing radiation damage and is superior in revealing soft tissue. Compared with MRI examinations, CT images are noisier (Hamwood et al, 2021). Therefore, the traditional UNet algorithm is better suited to training with CT images because it extracts rich feature scales and can effectively filter local noise (Pan et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

“…Furthermore, AI can segment bony structures from orbital CT/MRI images. Hamwood et al (2021) developed a DL system for the segmentation of bony regions from orbital CT/MRI images that exhibited excellent efficiency, particularly in terms of computational time. Li et al (2022a) extracted bony orbit features and analyzed Asian aging characteristics through the popular deep CNN (DCNN) model.…”

Section: Sabatesmentioning

confidence: 99%

“…Li et al (2022a) extracted bony orbit features and analyzed Asian aging characteristics through the popular deep CNN (DCNN) model. Some commercial software can also automatically segment orbital regions from CT images (Hamwood et al, 2021). In addition, using AI-based technology, irregular soft tissues, such as fat and abscesses, have been reliably segmented from orbital CT/MRI images.…”

Section: Sabatesmentioning

confidence: 99%

See 1 more Smart Citation

Orbital and eyelid diseases: The next breakthrough in artificial intelligence?

Bao

Sun

Zhan

et al. 2022

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

Orbital and eyelid disorders affect normal visual functions and facial appearance, and precise oculoplastic and reconstructive surgeries are crucial. Artificial intelligence (AI) network models exhibit a remarkable ability to analyze large sets of medical images to locate lesions. Currently, AI-based technology can automatically diagnose and grade orbital and eyelid diseases, such as thyroid-associated ophthalmopathy (TAO), as well as measure eyelid morphological parameters based on external ocular photographs to assist surgical strategies. The various types of imaging data for orbital and eyelid diseases provide a large amount of training data for network models, which might be the next breakthrough in AI-related research. This paper retrospectively summarizes different imaging data aspects addressed in AI-related research on orbital and eyelid diseases, and discusses the advantages and limitations of this research field.

show abstract

“…Various autosegmentation methods that have historically been applied to computed tomography (CT) images have shown promise on MRI [6], including deformable image registration (DIR)based structure propagation [4,7], atlas-based autosegmentation [8][9][10], and deep learning [11][12][13]. While several studies have shown that deep learning can improve organ-at-risk (OAR) segmentation accuracy compared to atlas-based autosegmentation on CT for head and neck [14][15][16] and other treatment sites [17][18][19][20], to our knowledge, only a single study thus far has directly compared these methods on MRI for any treatment site [21].…”

Section: Introductionmentioning

confidence: 99%

Investigation of Autosegmentation Techniques on T2-Weighted MRI for Off-line Dose Reconstruction in MR-Linac Adapt to Position Workflow for Head and Neck Cancers

McDonald

Cárdenas

O’Connell

et al. 2021

Preprint

View full text Add to dashboard Cite

Purpose: In order to accurately accumulate delivered dose for head and neck cancer patients treated with the Adapt to Position workflow on the 1.5T magnetic resonance imaging (MRI)-linear accelerator (MR-linac), the low-resolution T2-weighted MRIs used for daily setup must be segmented to enable reconstruction of the delivered dose at each fraction. In this study, our goal is to evaluate various autosegmentation methods for head and neck organs at risk (OARs) on on-board setup MRIs from the MR-linac for off-line reconstruction of delivered dose. Methods: Seven OARs (parotid glands, submandibular glands, mandible, spinal cord, and brainstem) were contoured on 43 images by seven observers each. Ground truth contours were generated using a simultaneous truth and performance level estimation (STAPLE) algorithm. 20 autosegmentation methods were evaluated in ADMIRE: 1-9) atlas-based autosegmentation using a population atlas library (PAL) of 5/10/15 patients with STAPLE, patch fusion (PF), random forest (RF) for label fusion; 10-19) autosegmentation using images from a patient's 1-4 prior fractions (individualized patient prior (IPP)) using STAPLE/PF/RF; 20) deep learning (DL) (3D ResUNet trained on 43 ground truth structure sets plus 45 contoured by one observer). Execution time was measured for each method. Autosegmented structures were compared to ground truth structures using the Dice similarity coefficient, mean surface distance, Hausdorff distance, and Jaccard index. For each metric and OAR, performance was compared to the inter-observer variability using Dunn's test with control. Methods were compared pairwise using the Steel-Dwass test for each metric pooled across all OARs. Further dosimetric analysis was performed on three high-performing autosegmentation methods (DL, IPP with RF and 4 fractions (IPP_RF_4), IPP with 1 fraction (IPP_1)), and one low-performing (PAL with STAPLE and 5 atlases (PAL_ST_5)). For five patients, delivered doses from clinical plans were recalculated on setup images with ground truth and autosegmented structure sets. Differences in maximum and mean dose to each structure between the ground truth and autosegmented structures were calculated and correlated with geometric metrics. Results: DL and IPP methods performed best overall, all significantly outperforming inter-observer variability and with no significant difference between methods in pairwise comparison. PAL methods performed worst overall; most were not significantly different from the inter-observer variability or from each other. DL was the fastest method (33 seconds per case) and PAL methods the slowest (3.7 - 13.8 minutes per case). Execution time increased with number of prior fractions/atlases for IPP and PAL. For DL, IPP_1, and IPP_RF_4, the majority (95%) of dose differences were within 250 cGy from ground truth, but outlier differences up to 785 cGy occurred. Dose differences were much higher for PAL_ST_5, with outlier differences up to 1920 cGy. Dose differences showed weak but significant correlations with all geometric metrics (R2 between 0.030 and 0.314). Conclusions: The autosegmentation methods offering the best combination of performance and execution time are DL and IPP_1. Dose reconstruction on on-board T2-weighted MRIs is feasible with autosegmented structures with minimal dosimetric variation from ground truth, but contours should be visually inspected prior to dose reconstruction in an end-to-end dose accumulation workflow.

show abstract

A deep learning method for automatic segmentation of the bony orbit in MRI and CT images

Cited by 41 publications

References 44 publications

A Sequential Machine Learning-cum-Attention Mechanism for Effective Segmentation of Brain Tumor

A Sequential Machine Learning-cum-Attention Mechanism for Effective Segmentation of Brain Tumor

Orbital and eyelid diseases: The next breakthrough in artificial intelligence?

Investigation of Autosegmentation Techniques on T2-Weighted MRI for Off-line Dose Reconstruction in MR-Linac Adapt to Position Workflow for Head and Neck Cancers

Contact Info

Product

Resources

About