Journal of X-Ray Science and Technology - Volume 31, issue 5

Authors: Ghani, Muhammad Usman | Makeev, Andrey | Manus, Joseph A. | Glick, Stephen J. | Ghammraoui, Bahaa

Article Type: Research Article

Abstract: BACKGROUND: Geometric calibration is essential in developing a reliable computed tomography (CT) system. It involves estimating the geometry under which the angular projections are acquired. Geometric calibration of cone beam CTs employing small area detectors, such as currently available photon counting detectors (PCDs), is challenging when using traditional-based methods due to detectors’ limited areas. OBJECTIVE: This study presented an empirical method for the geometric calibration of small area PCD-based cone beam CT systems. METHODS: Unlike the traditional methods, we developed an iterative optimization procedure to determine geometric parameters using the reconstructed images of small metal ball …bearings (BBs) embedded in a custom-built phantom. An objective function incorporating the sphericities and symmetries of the embedded BBs was defined to assess performance of the reconstruction algorithm with the given initial estimated set of geometric parameters. The optimal parameter values were those which minimized the objective function. The TIGRE toolbox was employed for fast tomographic reconstruction. To evaluate the proposed method, computer simulations were carried out using various numbers of spheres placed in various locations. Furthermore, efficacy of the method was experimentally assessed using a custom-made benchtop PCD-based cone beam CT. RESULTS: Computer simulations validated the accuracy and reproducibility of the proposed method. The precise estimation of the geometric parameters of the benchtop revealed high-quality imaging in CT reconstruction of a breast phantom. Within the phantom, the cylindrical holes, fibers, and speck groups were imaged in high fidelity. The CNR analysis further revealed the quantitative improvements of the reconstruction performed with the estimated parameters using the proposed method. CONCLUSION: Apart from the computational cost, we concluded that the method was easy to implement and robust. Show more

Keywords: Geometric calibration, sphericity, symmetry, photon counting detectors, cone beam CTs

DOI: 10.3233/XST-230007

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 865-877, 2023

Authors: Lee, Jumin | Lee, Min-Jin | Kim, Bong-Seog | Hong, Helen

Article Type: Research Article

Abstract: BACKGROUND: It is often difficult to automatically segment lung tumors due to the large tumor size variation ranging from less than 1 cm to greater than 7 cm depending on the T-stage. OBJECTIVE: This study aims to accurately segment lung tumors of various sizes using a consistency learning-based multi-scale dual-attention network (CL-MSDA-Net). METHODS: To avoid under- and over-segmentation caused by different ratios of lung tumors and surrounding structures in the input patch according to the size of the lung tumor, a size-invariant patch is generated by normalizing the ratio to the average size of the lung tumors used …for the training. Two input patches, a size-invariant patch and size-variant patch are trained on a consistency learning-based network consisting of dual branches that share weights to generate a similar output for each branch with consistency loss. The network of each branch has a multi-scale dual-attention module that learns image features of different scales and uses channel and spatial attention to enhance the scale-attention ability to segment lung tumors of different sizes. RESULTS: In experiments with hospital datasets, CL-MSDA-Net showed an F1-score of 80.49%, recall of 79.06%, and precision of 86.78%. This resulted in 3.91%, 3.38%, and 2.95% higher F1-scores than the results of U-Net, U-Net with a multi-scale module, and U-Net with a multi-scale dual-attention module, respectively. In experiments with the NSCLC-Radiomics datasets, CL-MSDA-Net showed an F1-score of 71.7%, recall of 68.24%, and precision of 79.33%. This resulted in 3.66%, 3.38%, and 3.13% higher F1-scores than the results of U-Net, U-Net with a multi-scale module, and U-Net with a multi-scale dual-attention module, respectively. CONCLUSIONS: CL-MSDA-Net improves the segmentation performance on average for tumors of all sizes with significant improvements especially for small sized tumors. Show more

Keywords: Chest CT, lung tumor segmentation, deep learning, size normalization, consistency learning

DOI: 10.3233/XST-230003

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 879-892, 2023

Authors: Fauzi, Adam | Yueniwati, Yuyun | Naba, Agus | Rahayu, Rachmi Fauziah

Article Type: Research Article

Abstract: BACKGROUND: Malignant Primary Brain Tumor (MPBT) and Metastatic Brain Tumor (MBT) are the most common types of brain tumors, which require different management approaches. Magnetic Resonance Imaging (MRI) is the most frequently used modality for assessing the presence of these tumors. The utilization of Deep Learning (DL) is expected to assist clinicians in classifying MPBT and MBT more effectively. OBJECTIVE: This study aims to examine the influence of MRI sequences on the classification performance of DL techniques for distinguishing between MPBT and MBT and analyze the results from a medical perspective. METHODS: Total 1,360 images performed …from 4 different MRI sequences were collected and preprocessed. VGG19 and ResNet101 models were trained and evaluated using consistent parameters. The performance of the models was assessed using accuracy, sensitivity, and other precision metrics based on a confusion matrix analysis. RESULTS: The ResNet101 model achieves the highest accuracy of 83% for MPBT classification, correctly identifying 90 out of 102 images. The VGG19 model achieves an accuracy of 81% for MBT classification, accurately classifying 86 out of 102 images. T2 sequence shows the highest sensitivity for MPBT, while T1C and T1 sequences exhibit the highest sensitivity for MBT. CONCLUSIONS: DL models, particularly ResNet101 and VGG19, demonstrate promising performance in classifying MPBT and MBT based on MRI images. The choice of MRI sequence can impact the sensitivity of tumor detection. These findings contribute to the advancement of DL-based brain tumor classification and its potential in improving patient outcomes and healthcare efficiency. Show more

Keywords: Deep learning, brain tumor classification, MRI Sequences, malignant primary brain tumor, metastatic brain tumor

DOI: 10.3233/XST-230046

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 893-914, 2023

Authors: Wang, Shubin | Liu, Yi | Zhang, Pengcheng | Chen, Ping | Li, Zhiyuan | Yan, Rongbiao | Li, Shu | Hou, Ruifeng | Gui, Zhiguo

Article Type: Research Article

Abstract: BACKGROUND: Low-dose CT (LDCT) images usually contain serious noise and artifacts, which weaken the readability of the image. OBJECTIVE: To solve this problem, we propose a compound feature attention network with edge enhancement for LDCT denoising (CFAN-Net), which consists of an edge-enhanced module and a proposed compound feature attention block (CFAB). METHODS: The edge enhancement module extracts edge details with the trainable Sobel convolution. CFAB consists of an interactive feature learning module (IFLM), a multi-scale feature fusion module (MFFM), and a joint attention module (JAB), which removes noise from LDCT images in a coarse-to-fine manner. First, …in IFLM, the noise is initially removed by cross-latitude interactive judgment learning. Second, in MFFM, multi-scale and pixel attention are integrated to explore fine noise removal. Finally, in JAB, we focus on key information, extract useful features, and improve the efficiency of network learning. To construct a high-quality image, we repeat the above operation by cascading CFAB. RESULTS: By applying CFAN-Net to process the 2016 NIH AAPM-Mayo LDCT challenge test dataset, experiments show that the peak signal-to-noise ratio value is 33.9692 and the structural similarity value is 0.9198. CONCLUSIONS: Compared with several existing LDCT denoising algorithms, CFAN-Net effectively preserves the texture of CT images while removing noise and artifacts. Show more

Keywords: LDCT, edge enhancement, interactive feature learning, multi-scale feature fusion, joint attention

DOI: 10.3233/XST-230064

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 915-933, 2023

Authors: Zhang, Ruyi | Hu, Yiwei | Zhang, Kai | Lan, Guanhua | Peng, Liang | Zhu, Yabin | Qian, Wei | Yao, Yudong

Article Type: Research Article

Abstract: BACKGROUND: C-arm fluoroscopy, as an effective diagnosis and treatment method for spine surgery, can help doctors perform surgery procedures more precisely. In clinical surgery, the surgeon often determines the specific surgical location by comparing C-arm X-ray images with digital radiography (DR) images. However, this heavily relies on the doctor’s experience. OBJECTIVE: In this study, we design a framework for automatic vertebrae detection as well as vertebral segment matching (VDVM) for the identification of vertebrae in C-arm X-ray images. METHODS: The proposed VDVM framework is mainly divided into two parts: vertebra detection and vertebra matching. In the …first part, a data preprocessing method is used to improve the image quality of C-arm X-ray images and DR images. The YOLOv3 model is then used to detect the vertebrae, and the vertebral regions are extracted based on their position. In the second part, the Mobile-Unet model is first used to segment the vertebrae contour of the C-arm X-ray image and DR image based on vertebral regions respectively. The inclination angle of the contour is then calculated using the minimum bounding rectangle and corrected accordingly. Finally, a multi-vertebra strategy is applied to measure the visual information fidelity for the vertebral region, and the vertebrae are matched based on the measured results. RESULTS: We use 382 C-arm X-ray images and 203 full length X-ray images to train the vertebra detection model, and achieve a mAP of 0.87 in the test dataset of 31 C-arm X-ray images and 0.96 in the test dataset of 31 lumbar DR images. Finally, we achieve a vertebral segment matching accuracy of 0.733 on 31 C-arm X-ray images. CONCLUSIONS: A VDVM framework is proposed, which performs well for the detection of vertebrae and achieves good results in vertebral segment matching. Show more

Keywords: C-arm X-ray image, DR image, deep learning, image identification

DOI: 10.3233/XST-230025

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 935-949, 2023

Authors: Jigmeddorj, Vanchinkhuu | Jamsranjav, Erdenetogtokh | Baatar, Duurenbuyan | Kinjo, Yasuhito | Ito, Atsushi | Shiina, Tatsuo

Article Type: Research Article

Abstract: BACKGROUND: The soft X-ray projection microscope has been developed for high resolution imaging of hydrated bio-specimens. Image blurring due to X-ray diffraction can be corrected by an iteration procedure. The correction is not efficient enough for all images, especially for low contrast chromosome images. OBJECTIVE: The purpose of this study is to improve X-ray imaging techniques using a finer pinhole and reducing capture time, as well as to improve image correction methods. A method of specimen staining prior to the imaging was tested in order to capture images with high contrasts. The efficiency of the iteration procedure and …its combined version with an image enhancement method was also assessed. METHODS: In image correction, we used the iteration procedure and its combined version with an image enhancement technique. To capture higher contrast images, we stained chromosome specimens with the Platinum blue (Pt-blue) prior to the imaging. RESULTS: The iteration procedure combined with image enhancement corrected the chromosome images with 329 or lower magnification effectively. Using the Pt-blue staining for the chromosome, images with high contrast have been captured and successfully corrected. CONCLUSIONS: The image enhancement technique combining contrast enhancement and noise removal together was effective to obtain higher contrast images. As a result, the chromosome images with 329 or lower times magnification were corrected effectively. With Pt-blue staining, chromosome images with contrasts of 2.5 times higher than unstained case could be captured and corrected by the iteration procedure. Show more

Keywords: Soft X-ray projection microscopy, imaging, Pt-blue, image correction, iteration procedure, contrast enhancement, chromosome, grayscale value

DOI: 10.3233/XST-230056

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 951-964, 2023

Authors: Tang, Hui | Li, Tian | Lin, Yu Bing | Li, Yu | Bao, Xu Dong

Article Type: Research Article

Abstract: Digital tomosynthesis (DTS) technology has attracted much attention in the field of nondestructive testing of printed circuit boards (PCB) due to its high resolution and suitability to thin slab objects. However, the traditional DTS iterative algorithm is computationally demanding, and its real-time processing of high-resolution and large volume reconstruction is infeasible. To address this issue, we in this study propose a multiple multi-resolution algorithm, including two multi-resolution strategies: volume domain multi-resolution and projection domain multi-resolution. The first multi-resolution scheme employs a LeNet-based classification network to divide the roughly reconstructed low-resolution volume into two sub-volumes namely, (1) the region of interest …(ROI) with welding layers that necessitates high-resolution reconstruction, and (2) the remaining volume with unimportant information which can be reconstructed in low-resolution. When X-rays in adjacent projection angles pass through many identical voxels, information redundancy is prevalent between the adjacent image projections. Therefore, the second multi-resolution scheme divides the projections into non-overlapping subsets, using only one subset for each iteration. The proposed algorithm is evaluated using both the simulated and real image data. The results demonstrate that the proposed algorithm is approximately 6.5 times faster than the full-resolution DTS iterative reconstruction algorithm without compromising image reconstruction quality. Show more

Keywords: Multi-resolution, tomosynthesis, LeNet, PCB, iterative image reconstruction

DOI: 10.3233/XST-230047

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 965-979, 2023

Authors: Zhao, Tianhu | Qi, Shouliang | Yue, Yong | Zhang, Baihua | Li, Jingxu | Wen, Yanhua | Yao, Yudong | Qian, Wei | Guan, Yubao

Article Type: Research Article

Abstract: BACKGROUND: Pulmonary granulomatous nodules (GN) with spiculation or lobulation have a similar morphological appearance to solid lung adenocarcinoma (SADC) under computed tomography (CT). However, these two kinds of solid pulmonary nodules (SPN) have different malignancies and are sometimes misdiagnosed. OBJECTIVE: This study aims to predict malignancies of SPNs by a deep learning model automatically. METHODS: A chimeric label with self-supervised learning (CLSSL) is proposed to pre-train a ResNet-based network (CLSSL-ResNet) for distinguishing isolated atypical GN from SADC in CT images. The malignancy, rotation, and morphology labels are integrated into a chimeric label and utilized to pre-train …a ResNet50. The pre-trained ResNet50 is then transferred and fine-tuned to predict the malignancy of SPN. Two image datasets of 428 subjects (Dataset1, 307; Dataset2, 121) from different hospitals are collected. Dataset1 is divided into training, validation, and test data by a ratio of 7:1:2 to develop the model. Dataset2 is utilized as an external validation dataset. RESULTS: CLSSL-ResNet achieves an area under the ROC curve (AUC) of 0.944 and an accuracy (ACC) of 91.3%, which was much higher than that of the consensus of two experienced chest radiologists (77.3%). CLSSL-ResNet also outperforms other self-supervised learning models and many counterparts of other backbone networks. In Dataset2, AUC and ACC of CLSSL-ResNet are 0.923 and 89.3%, respectively. Additionally, the ablation experiment result indicates higher efficiency of the chimeric label. CONCLUSION: CLSSL with morphology labels can increase the ability of feature representation by deep networks. As a non-invasive method, CLSSL-ResNet can distinguish GN from SADC via CT images and may support clinical diagnoses after further validation. Show more

Keywords: Lung adenocarcinoma, granulomatous nodules, chimeric label, self-supervised learning, deep learning, classification

DOI: 10.3233/XST-230063

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 981-999, 2023

Authors: Huang, Yuting | Wu, Ketong | Liu, Yang | Li, Dan | Lai, Haiyang | Peng, Tao | Wan, Yuan | Zhang, Bo

Article Type: Research Article

Abstract: BACKGROUND: Microwave ablation (MWA) is becoming an effective therapy for inoperable pulmonary metastases from colorectal cancer (CRC). However, it is unclear whether the primary tumor location affects survival after MWA. OBJECTIVE: This study aims to investigate the survival outcomes and prognostic factors of MWA based on different primary origins between colon and rectal cancer. METHODS: Patients who underwent MWA for pulmonary metastases from 2014 to 2021 were reviewed. Differences in survival outcomes between colon and rectal cancer were analyzed with the Kaplan-Meier method and log-rank tests. The prognostic factors between groups were then evaluated by univariable …and multivariable Cox regression analyses. RESULTS: A total of 118 patients with 154 pulmonary metastases from CRC were treated in 140 MWA sessions. Rectal cancer had a higher proportion with seventy (59.32% ) than colon cancer with forty-eight (40.68% ). The average maximum diameter of pulmonary metastases from rectal cancer (1.09 cm) was greater than that of colon cancer (0.89 cm; p  = 0.026). The median follow-up was 18.53 months (range 1.10 – 60.63 months). The disease-free survival (DFS) and overall survival (OS) in colon and rectal cancer groups were 25.97 vs 11.90 months (p  = 0.405), and 60.63 vs 53.87 months (p  = 0.149), respectively. Multivariate analyses showed that only age was an independent prognostic factor in patients with rectal cancer (HR = 3.70, 95% CI: 1.28 – 10.72, p  = 0.023), while none in colon cancer. CONCLUSIONS: Primary CRC location has no impact on survival for patients with pulmonary metastases after MWA, while a disparate prognostic factor exists between colon and rectal cancer. Show more

Keywords: Pulmonary metastases, colorectal cancer, microwave ablation, primary tumor, prognosis

DOI: 10.3233/XST-230078

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 1001-1011, 2023

Authors: Rostami, Aram | Neto, Aluisio Jose De Castro | Paloor, Satheesh Prasad | Khalid, Abdul Sattar | Hammoud, Rabih

Article Type: Research Article

Abstract: Background: Accurate and fast dose calculation is crucial in modern radiation therapy. Four dose calculation algorithms (AAA, AXB, CCC, and MC) are available in Varian Eclipse and RaySearch Laboratories RayStation Treatment Planning Systems (TPSs). Objectives: This study aims to evaluate and compare dosimetric accuracy of the four dose calculation algorithms applying to homogeneous and heterogeneous media, VMAT plans (based on AAPM TG-119 test cases), and the surface and buildup regions. Methods: The four algorithms are assessed in homogeneous (IAEA-TECDOCE 1540) and heterogeneous (IAEA-TECDOC 1583) media. Dosimetric evaluation accuracy for VMAT plans is then analyzed, along with …the evaluation of the accuracy of algorithms applying to the surface and buildup regions. Results: Tests conducted in homogeneous media revealed that all algorithms exhibit dose deviations within 5% for various conditions, with pass rates exceeding 95% based on recommended tolerances. Additionally, the tests conducted in heterogeneous media demonstrate high pass rates for all algorithms, with a 100% pass rate observed for 6 MV and mostly 100% pass rate for 15 MV, except for CCC, which achieves a pass rate of 94%. The results of gamma index pass rate (GIPR) for dose calculation algorithms in IMRT fields show that GIPR (3% /3 mm) for all four algorithms in all evaluated tests based on TG119, are greater than 97%. The results of the algorithm testing for the accuracy of superficial dose reveal variations in dose differences, ranging from –11.9% to 7.03% for 15 MV and –9.5% to 3.3% for 6 MV, respectively. It is noteworthy that the AXB and MC algorithms demonstrate relatively lower discrepancies compared to the other algorithms. Conclusions: This study shows that generally, two dose calculation algorithms (AXB and MC) that calculate dose in medium have better accuracy than other two dose calculation algorithms (CCC and AAA) that calculate dose to water. Show more

Keywords: Treatment Planning System (TPS), Anisotropic Analytical Algorithm (AAA), Acuros (AXB), collapsed cone convolution (CCC), Monte Carlo (MC).

DOI: 10.3233/XST-230079

Citation: Journal of X-Ray Science and Technology, vol. 31, no. 5, pp. 1013-1033, 2023