Semi-supervised auto-segmentation method for pelvic organ-at-risk in magnetic resonance images based on deep-learning.

BACKGROUND AND PURPOSE: In radiotherapy, magnetic resonance (MR) imaging has higher contrast for soft tissues compared to computed tomography (CT) scanning and does not emit radiation. However, manual annotation of the deep learning-based automatic organ-at-risk (OAR) delineation algorithms is expensive, making the collection of large-high-quality annotated datasets a challenge. Therefore, we proposed the low-cost semi-supervised OAR segmentation method using small pelvic MR image annotations. METHODS: We trained a deep learning-based segmentation model using 116 sets of MR images from 116 patients. The bladder, femoral heads, rectum, and small intestine were selected as OAR regions. To generate the training set, we utilized a semi-supervised method and ensemble learning techniques. Additionally, we employed a post-processing algorithm to correct the self-annotation data. Both 2D and 3D auto-segmentation networks were evaluated for their performance. Furthermore, we evaluated the performance of semi-supervised method for 50 labeled data and only 10 labeled data. RESULTS: The Dice similarity coefficient (DSC) of the bladder, femoral heads, rectum and small intestine between segmentation results and reference masks is 0.954, 0.984, 0.908, 0.852 only using self-annotation and post-processing methods of 2D segmentation model. The DSC of corresponding OARs is 0.871, 0.975, 0.975, 0.783, 0.724 using 3D segmentation network, 0.896, 0.984, 0.890, 0.828 using 2D segmentation network and common supervised method. CONCLUSION: The outcomes of our study demonstrate that it is possible to train a multi-OAR segmentation model using small annotation samples and additional unlabeled data. To effectively annotate the dataset, ensemble learning and post-processing methods were employed. Additionally, when dealing with anisotropy and limited sample sizes, the 2D model outperformed the 3D model in terms of performance.

Deep learning-based low-dose CT for adaptive radiotherapy of abdominal and pelvic tumors.

The shape and position of abdominal and pelvic organs change greatly during radiotherapy, so image-guided radiation therapy (IGRT) is urgently needed. The world's first integrated CT-linac platform, equipped with fan beam CT (FBCT), can provide a diagnostic-quality FBCT for achieve adaptive radiotherapy (ART). However, CT scans will bring the risk of excessive scanning radiation dose. Reducing the tube current of the FBCT system can reduce the scanning dose, but it will lead to serious noise and artifacts in the reconstructed images. In this study, we proposed a deep learning method, Content-Noise Cycle-Consistent Generative Adversarial Network (CNCycle-GAN), to improve the image quality and CT value accuracy of low-dose FBCT images to meet the requirements of adaptive radiotherapy. We selected 76 patients with abdominal and pelvic tumors who received radiation therapy. The patients received one low-dose CT scan and one normal-dose CT scan in IGRT mode during different fractions of radiotherapy. The normal dose CT images (NDCT) and low dose CT images (LDCT) of 70 patients were used for network training, and the remaining 6 patients were used to validate the performance of the network. The quality of low-dose CT images after network restoration (RCT) were evaluated in three aspects: image quality, automatic delineation performance and dose calculation accuracy. Taking NDCT images as a reference, RCT images reduced MAE from 34.34 ± 5.91 to 20.25 ± 4.27, PSNR increased from 34.08 ± 1.49 to 37.23 ± 2.63, and SSIM increased from 0.92 ± 0.08 to 0.94 ± 0.07. The P value is less than 0.01 of the above performance indicators indicated that the difference were statistically significant. The Dice similarity coefficients (DCS) between the automatic delineation results of organs at risk such as bladder, femoral heads, and rectum on RCT and the results of manual delineation by doctors both reached 0.98. In terms of dose calculation accuracy, compared with the automatic planning based on LDCT, the difference in dose distribution between the automatic planning based on RCT and the automatic planning based on NDCT were smaller. Therefore, based on the integrated CT-linac platform, combined with deep learning technology, it provides clinical feasibility for the realization of low-dose FBCT adaptive radiotherapy for abdominal and pelvic tumors.

Robust whole slide image analysis for cervical cancer screening using deep learning.

Computer-assisted diagnosis is key for scaling up cervical cancer screening. However, current recognition algorithms perform poorly on whole slide image (WSI) analysis, fail to generalize for diverse staining and imaging, and show sub-optimal clinical-level verification. Here, we develop a progressive lesion cell recognition method combining low- and high-resolution WSIs to recommend lesion cells and a recurrent neural network-based WSI classification model to evaluate the lesion degree of WSIs. We train and validate our WSI analysis system on 3,545 patient-wise WSIs with 79,911 annotations from multiple hospitals and several imaging instruments. On multi-center independent test sets of 1,170 patient-wise WSIs, we achieve 93.5% Specificity and 95.1% Sensitivity for classifying slides, comparing favourably to the average performance of three independent cytopathologists, and obtain 88.5% true positive rate for highlighting the top 10 lesion cells on 447 positive slides. After deployment, our system recognizes a one giga-pixel WSI in about 1.5 min.

[Sparse-view CT image restoration via multiscale wavelet residual network].

OBJECTIVE: Sparse-view CT has the advantages of accelerated data collection and reduced radiation dose, but data missing arising from the data collection process causes serious streaking artifact and noise in the images reconstructed using the traditional filtering back projection algorithm (FBP). To solve this problem, we propose a multi-scale wavelet residual network (MWResNet) to restore sparse-view CT images. METHODS: The MWResNet was based on the combination of deep learning and traditional model in MWCNN, and the wavelet network was combined with the residual block to enhance the network's ability to embed image features and speed up network training. The network proposed herein was trained using the real spiral geometry CT image data, namely the Low-dose CT Grand Challenge dataset. The results of the proposed networks were visually and quantitatively compared to that by other existing networks, including the image restoration iterative residual convolution network (IRLNet), residual coding-decoding convolutional neural network (REDCNN) and the FBP convolutional neural network (FBPConvNet). RESULTS: The results demonstrated that the proposed method was superior to other competing methods in terms of visual inspection and quantitative comparison. CONCLUSIONS: The MWResNet network is an effective method for suppressing noise and artifacts and maintaining edges details in the sparse-view CT images.

[Sparse-view helical CT reconstruction based on tensor total generalized variation minimization].

OBJECTIVE: We propose a sparse-view helical CT iterative reconstruction algorithm based on projection of convex set tensor total generalized variation minimization (TTGV-POCS) to reduce the X-ray dose of helical CT scanning. METHODS: The three-dimensional volume data of helical CT reconstruction was viewed as the third-order tensor. The tensor generalized total variation (TTGV) was used to describe the structural sparsity of the three-dimensional image. The POCS iterative reconstruction framework was adopted to achieve a robust result of sparse-view helical CT reconstruction. The TTGV-POCS algorithm fully used the structural sparsity of first-order and second-order derivation and the correlation between the slices of helical CT image data to effectively suppress artifacts and noise in the image of sparse-view reconstruction and better preserve image edge information. RESULTS: The experimental results of XCAT phantom and patient scan data showed that the TTGVPOCS algorithm had better performance in reducing noise, removing artifacts and maintaining edges than the existing reconstruction algorithms. Comparison of the sparse-view reconstruction results of XCAT phantom data with 144 exposure views showed that the TTGV-POCS algorithm proposed herein increased the PSNR quantitative index by 9.17%-15.24% compared with the experimental comparison algorithm; the FSIM quantitative index was increased by 1.27%-9.30%. CONCLUSIONS: The TTGV-POCS algorithm can effectively improve the image quality of helical CT sparse-view reconstruction and reduce the radiation dose of helical CT examination to improve the clinical imaging diagnosis.

[Key technologies in digital breast tomosynthesis system:theory, design, and optimization].

OBJECTIVE: To develop a digital breast tomosynthesis (DBT) imaging system with optimizes imaging chain. METHODS: Based on 3D tomography and DBT imaging scanning, we analyzed the methods for projection data correction, geometric correction, projection enhancement, filter modulation, and image reconstruction, and established a hardware testing platform. In the experiment, the standard ACR phantom and high-resolution phantom were used to evaluate the system stability and noise level. The patient projection data of commercial equipment was used to test the effect of the imaging algorithm. RESULTS: In the high-resolution phantom study, the line pairs were clear without confusing artifacts in the images reconstructed with the geometric correction parameters. In ACR phantom study, the calcified foci, cysts, and fibrous structures were more clearly defined in the reconstructed images after filtering and modulation. The patient data study showed a high contrast between tissues, and the lesions were more clearly displayed in the reconstructed image. CONCLUSIONS: This DBT imaging system can be used for mammary tomography with an image quality comparable to that of commercial DBT systems to facilitate imaging diagnosis of breast diseases.

Non-rigid image registration with dynamic Gaussian component density and space curvature preservation.

Image registration plays an important role in military and civilian applications, such as natural disaster damage assessment, environmental monitoring, ground change detection and military damage assessment, etc. This work presents a new feature-based non-rigid image registration method. The main contributions of this work are: (i) a dynamic Gaussian component density is designed to better exploit available potential image information and provide sufficient inlier pairs for image transformation; (ii) a spatial structure preservation, which consists of an image transformation space curvature preservation and a local spatial structure constrain, is proposed to constrain the image transforming cost as well as the local structure of feature points during feature point set registration. The performances of the proposed method in multi-spectral natural images, lowaltitude aerial images and medical images against four types of nine state-of-the-art methods are tested where our method shows the best performances in most scenarios.

[Design and optimization of a cone-beam CT system for extremity imaging].

OBJECTIVE: To establish a cone beam computed tomography (ECBCT) system for high-resolution imaging of the extremities. METHODS: Based on three-dimensional X-Ray CT imaging and high-resolution flat plate detector technique, we constructed a physical model and a geometric model for ECBCT imaging, optimized the geometric calibration and image reconstruction methods, and established the scanner system. In the experiments, the pencil vase phantom, image quality (IQ) phantom and a swine feet were scanned using this imaging system to evaluate its effectiveness and stability. RESULTS: On the reconstructed image of the pencil vase phantom, the edges were well preserved with geometric calibrated parameters and no aliasing artifacts were observed. The reconstructed images of the IQ phantom showed a uniform distribution of the CT number, and the noise power spectra were stable in multiple scanning under the same condition. The reconstructed images of the swine feet had clearly displayed the bones with a good resolution. CONCLUSIONS: The ECBCT system can be used for highresolution imaging of the extremities to provide important imaging information to assist in the diagnosis of bone diseases.