Head and Neck Cancer Primary Tumor Auto Segmentation using Model Ensembling of Deep Learning in PET-CT Images

Naser, Mohamed A.; Wahid, Kareem A.; Dijk, Lisanne V. van; He, Renjie; Abobakr, Moamen; Dede, Cem; Mohamed, Abdallah S.R.; Fuller, Clifton D.

doi:10.1101/2021.10.14.21264953

Cited by 4 publications

(1 citation statement)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning (DL) has found wide success in a variety of domains for RT-related medical imaging applications such as target and OAR segmentation (6–11) and outcome prediction (12,13). One less routinely studied domain is synthetic image generation, i.e., mapping an input image to an output image.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Generation of Synthetic High-Resolution MRI from Low-Resolution MRI for Use in Head and Neck Cancer Adaptive Radiotherapy

Wahid

El-Habashy

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Quick, low contrast resolution magnetic resonance imaging (MRI) scans are typically acquired for daily MRI-guided radiotherapy setup. However, for patients with head and neck (HN) cancer, these images are often insufficient for discriminating target volumes and organs at risk (OARs). In this study, we investigated a deep learning (DL) approach to generate high-resolution synthetic images from low-resolution images. Methods: We used 108 unique HN image sets of paired 2-minute T2-weighted scans (2mMRI) and 6-minute T2-weighted scans (6mMRI). 90 image sets (~20,000 slices) were used to train a 2-dimensional generative adversarial DL model that utilized 2mMRI as input and 6mMRI as output. Eighteen image sets were used to test model performance. Similarity metrics, including the mean squared error (MSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR) were calculated between normalized synthetic 6mMRI and ground-truth 6mMRI for all test cases. In addition, a previously trained OAR DL auto-segmentation model was used to segment the right parotid gland, left parotid gland, and mandible on all test case images. Dice similarity coefficients (DSC) were calculated between 2mMRI and either ground-truth 6mMRI or synthetic 6mMRI for each OAR; two one-sided t-tests were applied between the ground-truth and synthetic 6mMRI to determine equivalence. Finally, a Turing test using paired ground-truth and synthetic 6mMRI was performed using three clinician observers; the percentage of images that were correctly identified was compared to random chance using proportion equivalence tests. Results: The median similarity metrics across the whole images were 0.19, 0.93, and 33.14 for MSE, SSIM, and PSNR, respectively. The median of DSCs comparing ground-truth vs. synthetic 6mMRI auto-segmented OARs were 0.84 vs. 0.83, 0.82 vs. 0.82, and 0.80 vs. 0.83 for the right parotid gland, left parotid gland, and mandible, respectively (equivalence p<0.05 for all OARs). The percent of images correctly identified was equivalent to chance (p<0.05 for all observers). Conclusions: Using 2mMRI inputs, we demonstrate that DL-generated synthetic 6mMRI outputs have high similarity to ground-truth 6mMRI. Our study facilitates the clinical incorporation of synthetic MRI in MRI-guided radiotherapy.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Generation of Synthetic High-Resolution MRI from Low-Resolution MRI for Use in Head and Neck Cancer Adaptive Radiotherapy

Wahid

El-Habashy

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Application of artificial intelligence for overall survival risk stratification in oropharyngeal carcinoma: A validation of ProgTOOL

Alabi¹,

Sjöblom²,

Carpén³

et al. 2023

International Journal of Medical Informatics

View full text Add to dashboard Cite

Deep Learning Auto-Segmentation of Cervical Neck Skeletal Muscle for Sarcopenia Analysis Using Pre-Therapy CT in Patients with Head and Neck Cancer

Naser

Wahid

Grossberg

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background/Purpose: Sarcopenia is a prognostic factor in patients with head and neck cancer (HNC). Sarcopenia can be determined using the skeletal muscle index (SMI) calculated from cervical neck SM segmentations. However, SM segmentation requires manual input, which is time-consuming and variable. Therefore, we developed a fully-automated approach to segment cervical vertebra SM. Materials/Methods: 390 HNC patients with corresponding contrast-enhanced computed tomography (CT) scans were utilized (300-training, 90-testing). Ground-truth single-slice SM segmentations at the C3 vertebra were manually generated. A multi-stage deep learning pipeline was developed, where a 3D ResUNet auto-segmented the C3 section (33 mm window), the middle slice of the section was auto-selected, and a 2D ResUNet auto-segmented the auto-selected slice. Both the 3D and 2D approaches trained five sub-models (5-fold cross-validation) and combined sub-model predictions on the test set using majority vote ensembling. Model performance was primarily determined using the Dice similarity coefficient (DSC). Predicted SMI was calculated using the auto-segmentation cross-sectional area. Finally, using established SMI cutoffs, we performed a Kaplan-Meier analysis to determine associations with overall survival. Results: Mean test set DSC of the 3D and 2D models were 0.96 and 0.95, respectively. Predicted SMI had high correlation to the ground-truth SMI in males and females (r>0.96). Predicted SMI stratified patients for overall survival in males (log-rank p = 0.01) but not females (log-rank p = 0.07), consistent with ground-truth SMI. Conclusion: We developed a high-performance, multi-stage, fully-automated approach to segment cervical vertebra SM. Our study is an essential step towards fully-automated sarcopenia-related decision-making.

show abstract

Head and Neck Cancer Primary Tumor Auto Segmentation using Model Ensembling of Deep Learning in PET-CT Images

Cited by 4 publications

References 22 publications

Deep-Learning-Based Generation of Synthetic High-Resolution MRI from Low-Resolution MRI for Use in Head and Neck Cancer Adaptive Radiotherapy

Deep-Learning-Based Generation of Synthetic High-Resolution MRI from Low-Resolution MRI for Use in Head and Neck Cancer Adaptive Radiotherapy

Application of artificial intelligence for overall survival risk stratification in oropharyngeal carcinoma: A validation of ProgTOOL

Deep Learning Auto-Segmentation of Cervical Neck Skeletal Muscle for Sarcopenia Analysis Using Pre-Therapy CT in Patients with Head and Neck Cancer

Contact Info

Product

Resources

About