4.6 Article

Deep Learning-based Non-rigid Image Registration for High-dose Rate Brachytherapy in Inter-fraction Cervical Cancer

Related references

Note: Only part of the references are listed.
Article Engineering, Electrical & Electronic

COLI-Net: Deep learning-assisted fully automated COVID-19 lung and infection pneumonia lesion detection and segmentation from chest computed tomography images

Isaac Shiri et al.

Summary: This study proposes an automated deep learning method for whole lung and COVID-19 pneumonia lesion detection and segmentation. By evaluating on an external dataset, the accuracy of lung and lesion segmentation was high, with various quantitative metrics used to assess the segmentation performance.

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Robust-Deep: A Method for Increasing Brain Imaging Datasets to Improve Deep Learning Models' Performance and Robustness

Amirhossein Sanaat et al.

Summary: A small dataset can negatively impact the performance of deep neural networks (DNNs) in medical imaging research. To overcome the challenge of gathering large clinical databases, researchers proposed an analytical method for generating a large realistic/diverse dataset. They utilized a classical technique called Laplacian blending to create natural presentations and implemented a modified ResNet DNN for image-to-image translation tasks. The quantitative analysis showed that the proposed model improved the performance of the DNNs and produced higher quality images with lower quantitative bias and variance.

JOURNAL OF DIGITAL IMAGING (2022)

Article Biology

Unsupervised pseudo CT generation using heterogenous multicentric CT/MR images and CycleGAN: Dosimetric assessment for 3D conformal radiotherapy

Amir Jabbarpour et al.

Summary: This study investigates the feasibility of using a cycle generative adversarial network (CycleGAN) to generate pseudo CT (pCT) images from magnetic resonance imaging (MRI). The results show that the CycleGAN model using masked T2 images achieved better performance. The dosimetric assessment using T1-weighted MR images reveals minimal differences in dose volume histogram (DVH) between CT and pCT images.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Article Multidisciplinary Sciences

Clinical target segmentation using a novel deep neural network: double attention Res-U-Net

Vahid Ashkani Chenarlogh et al.

Summary: The study introduces the Double Attention Res-U-Net architecture for medical image segmentation and achieves high Dice and Jaccard coefficients on different datasets.

SCIENTIFIC REPORTS (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Automatic cardiac evaluations using a deep video object segmentation network

Nasim Sirjani et al.

Summary: This study utilized the EchoRCNN method to accurately measure cardiac volume and function using neural network technology, including segmentation of the left and right ventricle regions and estimation of key parameters, providing important insights for clinical diagnosis.

INSIGHTS INTO IMAGING (2022)

Article Radiology, Nuclear Medicine & Medical Imaging

Deep learning-based fully automated Z-axis coverage range definition from scout scans to eliminate overscanning in chest CT imaging

Yazdan Salimi et al.

Summary: Despite the prevalence of chest CT in the clinic, concerns about unoptimized protocols delivering high radiation doses to patients still remain. This study aimed to assess the additional radiation dose associated with overscanning in chest CT and to develop an automated deep learning-assisted scan range selection technique to reduce radiation dose to patients. The DL-based approach resulted in errors of 0.08 +/- 1.46 and - 1.5 +/- 4.1 mm in superior and inferior directions, respectively, demonstrating a reduction in unnecessary radiation exposure to patients.

INSIGHTS INTO IMAGING (2021)

Article Biology

Personalized brachytherapy dose reconstruction using deep learning

Azadeh Akhavanallaf et al.

Summary: The study introduced a personalized brachytherapy dosimetry approach based on deep learning, which improves accuracy while avoiding the computational burden of Monte Carlo calculations and simplifications of TG-43. Experimental results showed that this method exhibited comparable performance to the Monte Carlo method in dose prediction.

COMPUTERS IN BIOLOGY AND MEDICINE (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Automatic fetal biometry prediction using a novel deep convolutional network architecture

Mostafa Ghelich Oghli et al.

Summary: This study introduces an Attention MFP-Unet network that incorporates attention gates for automatic segmentation and measurement of fetal biometric parameters, showing superior performance compared to existing state-of-the-art approaches.

PHYSICA MEDICA-EUROPEAN JOURNAL OF MEDICAL PHYSICS (2021)

Article Oncology

Deep learning-based auto-segmentation of organs at risk in high-dose rate brachytherapy of cervical cancer

Reza Mohammadi et al.

Summary: This study proposed a method for automatic contouring of organs at risk in high-dose rate brachytherapy using a deep convolutional neural network. By analyzing images of 113 patients with cervical cancer, the method demonstrated excellent accuracy and consistency in segmenting the bladder, rectum, and sigmoid.

RADIOTHERAPY AND ONCOLOGY (2021)

Article Computer Science, Artificial Intelligence

A deep learning framework for unsupervised affine and deformable image registration

Bob D. de Vos et al.

MEDICAL IMAGE ANALYSIS (2019)

Article Oncology

Cancer statistics, 2019

Rebecca L. Siegel et al.

CA-A CANCER JOURNAL FOR CLINICIANS (2019)

Proceedings Paper Optics

Deformable image registration using convolutional neural networks

Koen A. J. Eppenhof et al.

MEDICAL IMAGING 2018: IMAGE PROCESSING (2018)

Proceedings Paper Computer Science, Theory & Methods

End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network

Bob D. de Vos et al.

DEEP LEARNING IN MEDICAL IMAGE ANALYSIS AND MULTIMODAL LEARNING FOR CLINICAL DECISION SUPPORT (2017)

Article Engineering, Biomedical

Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

Guorong Wu et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2016)

Article Computer Science, Interdisciplinary Applications

A CNN Regression Approach for Real-Time 2D/3D Registration

Shun Miao et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2016)

Editorial Material Oncology

Uncertainties in image guided adaptive cervix cancer brachytherapy: Impact on planning and prescription

Kari Tanderup et al.

RADIOTHERAPY AND ONCOLOGY (2013)

Review Oncology

Locally advanced cervical cancer: what is the standard of care?

Zeina Al-Mansour et al.

CURRENT OPINION IN ONCOLOGY (2010)

Article Oncology

CERVIX REGRESSION AND MOTION DURING THE COURSE OF EXTERNAL BEAM CHEMORADIATION FOR CERVICAL CANCER

Beth M. Beadle et al.

INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS (2009)