Wyniki wyszukiwania - BazTech

1

Multi-stage fully convolutional network for precise prostate segmentation in ultrasound images

Feng Yujie, Atabansi Chukwuemeka Clinton, Nie Jing, Liu Haijun, Zhou Hang, Zhao Huai, Hong Ruixia, Li Fang, Zhou Xichuan

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 3

586--602

EN

Prostate cancer is one of the most commonly diagnosed non-cutaneous malignant tumors and the sixth major cause of cancer-related death generally found in men globally. Automatic segmentation of prostate regions has a wide range of applications in prostate cancer diagnosis and treatment. It is challenging to extract powerful spatial features for precise prostate segmentation methods due to the wide variation in prostate size, shape, and histopathologic heterogeneity among patients. Most of the existing CNN-based architectures often produce unsatisfactory results and inaccurate boundaries in prostate segmentation, which are caused by inadequate discriminative feature maps and the limited amount of spatial information. To address these issues, we propose a novel deep learning technique called Multi-Stage FCN architecture for 2D prostate segmentation that captures more precise spatial information and accurate prostate boundaries. In addition, a new prostate ultrasound image dataset known as CCH-TRUSPS was collected from Chongqing University Cancer Hospital, including prostate ultrasound images of various prostate cancer architectures. We evaluate our method on the CCH-TRUSPS dataset and the publicly available Multi-site T2-weighted MRI dataset using five commonly used metrics for medical image analysis. When compared to other CNN-based methods on the CCH-TRUSPS test set, our Multi-Stage FCN achieves the highest and best binary accuracy of 99.15%, the DSC score of 94.90%, the IoU score of 89.80%, the precision of 94.67%, and the recall of 96.49%. The statistical and visual results demonstrate that our approach outperforms previous CNN-based techniques in all ramifications and can be used for the clinical diagnosis of prostate cancer.

2

Double-image encryption scheme based on the phase-truncated multiple-parameter Fresnel transform

Zhou Ling, Zhou Hang, Ma Yan, Zhou Nan-Run

Optica Applicata

|

2022

|

Vol. 52, nr 2

163--177

EN

A double-image encryption algorithm is proposed with the phase-truncated multiple-parameter Fresnel transform. Firstly, the pixel positions of two plaintext images are scrambled and then the results are merged into one image with the scrambling operation. Subsequently, the resulting image is encrypted by phase truncation and phase reservation in the multiple-parameter Fresnel transform domain. The phase information is scrambled by the affine transform and then recombined with the amplitude information. The final encryption image is obtained with the pixel scrambling and diffusion methods to further enhance the security of the image encryption system, where the scrambling and diffusion operations are based on logistic map, logistic-sine system and 2D logistic-adjusted-sine map. The image encryption scheme is robust against the common attacks due to the nonlinear properties of diffusion and phase truncation. Numerical simulation results verify the performance and the security of the proposed double-image algorithm based on the phase-truncated multiple-parameter Fresnel transform.

3

Double-image encryption algorithm based on discrete fractional angular transform and fractional Fourier transform

Qiu Tian, Dai Wei-Hua, Chen Su-Hua, Zhou Hang, Gong Li-Hua

Optica Applicata

|

2022

|

Vol. 52, nr 4

669--684

EN

By combining fractional Fourier transform with discrete fractional angular transform, a double-image encryption algorithm is designed. The discrete cosine transform is performed on two grayscale images to generate a spectrum image, and then the generated spectrum image is compressed into an image with Zigzag scanning. The compressed image is processed with the discrete fractional angular transform, and then fractional Fourier transform and double random phase coding are executed on the image. The DNA operation controlled by chaotic system is introduced to change the pixel values. Finally, the ciphertext image is obtained through bit-level permutation and pixel adaptive diffusion. The statistical information of the plaintext images is employed as the input of the SHA-256 to calculate the initial conditions of the chaotic map. Simulation experiments demonstrate that the double-image encryption algorithm can effectively reduce the correlation among adjacent pixels of the plaintext images.

4

An analysis model for the temperature and residual stress of tunnel liner exposed to fire

Qiao Rujia, Shao Zhushan, Yuan Yuan, Zhou Hang, Guo Yinbo

Archives of Civil and Mechanical Engineering

|

2021

|

Vol. 21, no. 4

388--398

EN

The temperature and stress analysis of tunnel liner is the basis of the damage assessment of the tunnel, and it is also have a great significance to tunnel fire protection design. In this study, a thermo-mechanical coupling model is derived to study the temperature and stresses of tunnel liner under the RABT fire curve. In contrast to consideration the effects of flame impingement on the heated surface only, the heat transfer coefficient (HTC) of the heated surface of tunnel liner is considered in the proposed model. The applicability of theoretical method is verified by comparing with the fire tests. According to maximum temperature experienced and material degradation, the residual stress of tunnel liner after fire is discussed, which could provide the basic for the damage assessment after fire. Contributions of the HTC of tunnel liner on the temperature and stresses were quantitatively described. This theoretical model explains the temperature and residual stress evolution of tunnel liner under fire when considering the effect of HTC, which provides a theoretical basis for the tunnel fire proofing.