High-resolution CT image retrieval using sparse convolutional neural network

Lei, Yang; Xu, Dong; Zhou, Zhengyang; Higgins, Kristin; Dong, Xue; Liu, Tian; Shim, Hyunsuk; Mao, Hui; Yang, Xiaofeng

doi:10.1117/12.2292891

Cited by 4 publications

(1 citation statement)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers have proposed that, combining pixel information of different scales can extract the best size information; some researchers believe that, reducing the size of the convolution kernel can improve the running speed of the neural network. [7][8][9][10] The CT image reconstruction algorithm can effectively remove image noise and improve image quality, assisting physicians in diagnosing diseases. With the rapid development of deep learning, many deep learning networks are used to process CT images.…”

Section: Resultsmentioning

confidence: 99%

Deep Learning Algorithm Based on Analysis the Effect of Posterior Cervical Vertebral Canal Decompression Angioplasty in the Treatment of Ossification of Posterior Longitudinal Ligament of Cervical Spine by CT Image

Liu¹,

Kong²

2021

Pak J Med Sci

View full text Add to dashboard Cite

Original Article Deep learning algorithm based on analyzing the effect of posterior cervical vertebral canal decompression angioplastyin the treatment of ossification of posterior longitudinalligament of cervical spine by CT image Yang Liu1, Jianjun Kong2 ABSTRACTObjective: The paper uses the convolutional neural network algorithm in the deep learning algorithm to explore the therapeutic effect of surgical treatment of hyperextension injuries associated with ossification of the posterior longitudinal ligament of the cervical spine. Methods: In this retrospectively analyzed study 27 patients with hyperextension injury of the posterior longitudinal ligament of the cervical spine were selected from our hospital between August 2018 to July 2020. It included 21 males and 6 females; aged 36-79 years, with an average of 55.9 years. Results: Follow-up time of patients was 3-39 months, with an average of 17.4 months. The JOA score after surgery was significantly better than that before surgery (P﹤0.01), which was statistically significant; the improvement of JOA in patients undergoing anterior therapy was better than that in patients undergoing posterior therapy, which was statistically significant; the JOA improved in patients with minor violent injuries. The situation is significantly better than severe violent injuries, with statistical significance. The rate of postoperative JOA improvement was significantly correlated with the degree of nerve function retention of the injured spinal cord before surgery (P﹤0.01), and there was no significant correlation between the degree of spinal stenosis caused by ossification and the postoperative JOA improvement of patients.Conclusion: Convolutional neural network algorithm in the deep learning algorithm based on the cervical spine posterior longitudinal ligament ossification hyperextension injury was significantly improved after surgery. The less preoperative neurological damage, the postoperative neurological function, the degree of improvement, there was no significant correlation between the degree of spinal stenosis and the improvement of postoperative spinal cord function. For patients with ossification of the posterior longitudinal ligament, if there are neurological symptoms, early surgical treatment is recommended to relieve the compression, so as to prevent irreversible neurological damage caused by trauma. KEYWORDS: Cervical spine, Ossification of posterior longitudinal ligament, Hyperextension injury, Spinal stenosis rate, JOA improvement rate. doi: https://doi.org/10.12669/pjms.37.6-WIT.4857How to cite this:Liu Y, Kong J. Deep learning algorithm based on analyzing the effect of posterior cervical vertebral canal decompression angioplasty in the treatment of ossification of posterior longitudinal ligament of cervical spine by CT image. Pak J Med Sci. 2021;37(6):1630-1635. doi: https://doi.org/10.12669/pjms.37.6-WIT.4857 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

show abstract

Section: Resultsmentioning

confidence: 99%

Deep Learning Algorithm Based on Analysis the Effect of Posterior Cervical Vertebral Canal Decompression Angioplasty in the Treatment of Ossification of Posterior Longitudinal Ligament of Cervical Spine by CT Image

Liu¹,

Kong²

2021

Pak J Med Sci

View full text Add to dashboard Cite

show abstract

A performance comparison of convolutional neural network‐based image denoising methods: The effect of loss functions on low‐dose CT images

et al. 2019

View full text Add to dashboard Cite

Purpose Convolutional neural network (CNN)‐based image denoising techniques have shown promising results in low‐dose CT denoising. However, CNN often introduces blurring in denoised images when trained with a widely used pixel‐level loss function. Perceptual loss and adversarial loss have been proposed recently to further improve the image denoising performance. In this paper, we investigate the effect of different loss functions on image denoising performance using task‐based image quality assessment methods for various signals and dose levels. Methods We used a modified version of U‐net that was effective at reducing the correlated noise in CT images. The loss functions used for comparison were two pixel‐level losses (i.e., the mean‐squared error and the mean absolute error), Visual Geometry Group network‐based perceptual loss (VGG loss), adversarial loss used to train the Wasserstein generative adversarial network with gradient penalty (WGAN‐GP), and their weighted summation. Each image denoising method was applied to reconstructed images and sinogram images independently and validated using the extended cardiac‐torso (XCAT) simulation and Mayo Clinic datasets. In the XCAT simulation, we generated fan‐beam CT datasets with four different dose levels (25%, 50%, 75%, and 100% of a normal‐dose level) using 10 XCAT phantoms and inserted signals in a test set. The signals had two different shapes (spherical and spiculated), sizes (4 and 12 mm), and contrast levels (60 and 160 HU). To evaluate signal detectability, we used a detection task SNR (tSNR) calculated from a non‐prewhitening model observer with an eye filter. We also measured the noise power spectrum (NPS) and modulation transfer function (MTF) to compare the noise and signal transfer properties. Results Compared to CNNs without VGG loss, VGG‐loss‐based CNNs achieved a more similar tSNR to that of the normal‐dose CT for all signals at different dose levels except for a small signal at the 25% dose level. For a low‐contrast signal at 25% or 50% dose, adding other losses to the VGG loss showed more improved performance than only using VGG loss. The NPS shapes from VGG‐loss‐based CNN closely matched that of normal‐dose CT images while CNN without VGG loss overly reduced the mid‐high‐frequency noise power at all dose levels. MTF also showed VGG‐loss‐based CNN with better‐preserved high resolution for all dose and contrast levels. It is also observed that additional WGAN‐GP loss helps improve the noise and signal transfer properties of VGG‐loss‐based CNN. Conclusions The evaluation results using tSNR, NPS, and MTF indicate that VGG‐loss‐based CNNs are more effective than those without VGG loss for natural denoising of low‐dose images and WGAN‐GP loss improves the denoising performance of VGG‐loss‐based CNNs, which corresponds with the qualitative evaluation.

show abstract

A review of deep learning based methods for medical image multi-organ segmentation

et al. 2021

Self Cite

View full text Add to dashboard Cite

Deep learning has revolutionized image processing and achieved the-state-of-art performance in many medical image segmentation tasks. Many deep learning-based methods have been published to segment different parts of the body for different medical applications. It is necessary to summarize the current state of development for deep learning in the field of medical image segmentation. In this paper, we aim to provide a comprehensive review with a focus on multi-organ image segmentation, which is crucial for radiotherapy where the tumor and organs-at-risk need to be contoured for treatment planning. We grouped the surveyed methods into two broad categories which are 'pixel-wise classification' and 'end-to-end segmentation'. Each category was divided into subgroups according to their network design. For each type, we listed the surveyed works, highlighted important contributions and identified specific challenges. Following the detailed review, we discussed the achievements, shortcomings and future potentials of each category. To enable direct comparison, we listed the performance of the surveyed works that used thoracic and head-and-neck benchmark datasets.

show abstract

High-resolution CT image retrieval using sparse convolutional neural network

Cited by 4 publications

References 23 publications

Deep Learning Algorithm Based on Analysis the Effect of Posterior Cervical Vertebral Canal Decompression Angioplasty in the Treatment of Ossification of Posterior Longitudinal Ligament of Cervical Spine by CT Image

Deep Learning Algorithm Based on Analysis the Effect of Posterior Cervical Vertebral Canal Decompression Angioplasty in the Treatment of Ossification of Posterior Longitudinal Ligament of Cervical Spine by CT Image

A performance comparison of convolutional neural network‐based image denoising methods: The effect of loss functions on low‐dose CT images

A review of deep learning based methods for medical image multi-organ segmentation

Contact Info

Product

Resources

About