Bi-parametric magnetic resonance imaging based radiomics for the identification of benign and malignant prostate lesions: cross-vendor validation.

The purpose of this study was to develop Bi-parametric Magnetic Resonance Imaging (BP-MRI) based radiomics models for differentiation between benign and malignant prostate lesions, and to cross-vendor validate the generalization ability of the models. The prebiopsy BP-MRI data (T2-Weighted Image [T2WI] and the Apparent Diffusion Coefficient [ADC]) of 459 patients with clinical suspicion of prostate cancer were acquired using two scanners from different vendors. The prostate biopsies are the reference standard for diagnosing benign and malignant prostate lesions. The training set was 168 patients' data from Siemens (Vendor 1), and the inner test set was 70 patients' data from the same vendor. The external test set was 221 patients' data from GE (Vendor 2). The lesion Region of Interest (ROI) was manually delineated by experienced radiologists. A total of 851 radiomics features including shape, first-order statistical, texture, and wavelet features were extracted from ROI in T2WI and ADC, respectively. Two feature-ranking methods (Minimum Redundancy Maximum Relevance [MRMR] and Wilcoxon Rank-Sum Test [WRST]) and three classifiers (Random Forest [RF], Support Vector Machine [SVM], and the Least Absolute Shrinkage and Selection Operator [LASSO] regression) were investigated for their efficacy in building single-parametric radiomics signatures. A biparametric radiomics model was built by combining the optimal single-parametric radiomics signatures. A comprehensive diagnosis model was built by combining the biparametric radiomics model with age and Prostate Specific Antigen (PSA) value using multivariable logistic regression. All models were built in the training set and independently validated in the inner and external test sets, and the performances of models in the diagnosis of benign and malignant prostate lesions were quantified by the Area Under the Receiver Operating Characteristic Curve (AUC). The mean AUCs of the inner and external test sets were calculated for each model. The non-inferiority test was used to test if the AUC of model in external test was not inferior to the AUC of model in inner test. Combining MRMR and LASSO produced the best-performing single-parametric radiomics signatures with the highest mean AUC of 0.673 for T2WI (inner test AUC = 0.729 vs. external test AUC = 0.616, p = 0.569) and the highest mean AUC of 0.810 for ADC (inner test AUC = 0.822 vs. external test AUC = 0.797, p = 0.102). The biparametric radiomics model produced a mean AUC of 0.833 (inner test AUC = 0.867 vs. external test AUC = 0.798, p = 0.051). The comprehensive diagnosis model had an improved mean AUC of 0.911 (inner test AUC = 0.935 vs. external test AUC = 0.886, p = 0.010). The comprehensive diagnosis model for differentiating benign from malignant prostate lesions was accurate and generalizable.

The safety of thymic vein sealing with ultrasonic energy in video-assisted thoracoscopic surgery thymectomy.

BACKGROUND: The key for conducting thymectomy by thoracoscope is the treatment of thymic veins, as they are the most common source of bleeding. The traditional treatment is to cut off the distal and proximal vessels after Ham-Lock clamping. Our team found that it is safe and reliable to use ultrasonic energy to cut off thymic veins in previous open operations. This study aimed to investigate the feasibility and safety of thymic vein sealing with ultrasonic energy in video-assisted thoracoscopic surgery (VATS) thymectomy. METHODS: A total of 169 patients with or without thymic tumors who underwent thymectomy by thoracoscope were enrolled in the study. Among them, group A, with 89 patients, underwent thoracoscopic thymic vein resection by Ham-Lock, and group B, with 80 patients, did so by ultrasonic energy. The groups were compared in terms of the characteristics of patients, tumors, and perioperative period. RESULTS: There were no significant differences in patients' characteristics between the two groups (P>0.05). There was no significant difference between the two groups in blood transfusion, operation time, drainage, and hospitalization (P>0.05). There were no deaths, secondary operation and post-operative blood transfusion, and no serious complications leading to prolonged hospitalization. One patient in group A was converted to thoracotomy due to left anonymous venous hemorrhage, and one patient in group B had thymic venous hemorrhage, but the hemorrhage was successfully stopped under thoracoscope. CONCLUSIONS: In VATS thymectomy (with or without thymic tumors), there is no significant difference in the treatment of thymic veins between Ham-Lock clipping and ultrasonic energy in conversion to open surgery in regards to thymic venous hemorrhage, postoperative drainage, blood transfusion, operation time, drainage, and hospital stay. Use of ultrasonic energy is a safe and reliable method for thymic vein disconnection.

Preoperative radiomic signature based on multiparametric magnetic resonance imaging for noninvasive evaluation of biological characteristics in rectal cancer.

OBJECTIVES: To develop and validate radiomic models in evaluating biological characteristics of rectal cancer based on multiparametric magnetic resonance imaging (MP-MRI). METHODS: This study consisted of 345 patients with rectal cancer who underwent MP-MRI. We focused on evaluating five postoperative confirmed characteristics: lymph node (LN) metastasis, tumor differentiation, fraction of Ki-67-positive tumor cells, human epidermal growth factor receptor 2 (HER-2), and KRAS-2 gene mutation status. Data from 197 patients were used to develop the biological characteristics evaluation models. Radiomic features were extracted from MP-MRI and then refined for reproducibility and redundancy. The refined features were investigated for usefulness in building radiomic signatures by using two feature-ranking methods (MRMR and WLCX) and three classifiers (RF, SVM, and LASSO). Multivariable logistic regression was used to build an integrated evaluation model combining radiomic signatures and clinical characteristics. The performance was evaluated using an independent validation dataset comprising 148 patients. RESULTS: The MRMR and LASSO regression produced the best-performing radiomic signatures for evaluating HER-2, LN metastasis, tumor differentiation, and KRAS-2 gene status, with AUC values of 0.696 (95% CI, 0.610-0.782), 0.677 (95% CI, 0.591-0.763), 0.720 (95% CI, 0.621-0.819), and 0.651 (95% CI, 0.539-0.763), respectively. The best-performing signatures for evaluating Ki-67 produced an AUC value of 0.699 (95% CI, 0.611-0.786), and it was developed by WLCX and RF algorithm. The integrated evaluation model incorporating radiomic signature and MRI-reported LN status had improved AUC of 0.697 (95% CI, 0.612-0.781). CONCLUSION: Radiomic signatures based on MP-MRI have potential to noninvasively evaluate the biological characteristics of rectal cancer. KEY POINTS: • Radiomic features were extracted from MP-MRI images of the rectal tumor. • The proposed radiomic signatures demonstrated discrimination ability in identifying the histopathological, immunohistochemical, and genetic characteristics of rectal cancer. • All MRI sequences were important and could provide complementary information in radiomic analysis.

A fast iteration approach to undersampled cone-beam CT reconstruction.

BACKGROUND: Due to large dimensional matrix multiplications, the existing iterative algorithms for cone beam computed tomography (CBCT) reconstruction often face problems of heavy computational workload and large volume of memory usage. OBJECTIVE: This study proposes and tests an iterative algorithm of 3DA-TVAL3 for fast reconstruction of CBCT images using undersampled measurement data and the reduced amount of computer memories. METHODS: In order to reduce computational workload and computer memories based on the sparsity of the CBCT measurement matrix, the proposed iterative algorithm applies elementwise scalar multiplications in the iterative computation to search for optimal solution. Through a number of tests on three different CT data sets with different number of projections, the reconstruction performance of the proposed algorithm is compared with that of two accelerated iterative algorithms and the conventional FDK algorithm. RESULTS: The visual and quantitative evaluations using the normalized mean square error, peak signal to noise ratio and structural similarity metrics demonstrated the faster computational time and the higher image quality of using the proposed 3DA-TVAL3 algorithm than using other conventional algorithms under comparison. CONCLUSIONS: The proposed 3DA-TVAL3 algorithm can perform efficient and fast computation of CBCT reconstruction using the reduced amount of computer memories.

An adaptive multiscale anisotropic diffusion regularized image reconstruction method for digital breast tomosynthesis.

As a special case of tomography, digital breast tomosynthesis (DBT) can realize quasi-3D image reconstruction for breast lesion detection from few-view and limited-angle projection data. For DBT image reconstruction, iterative algorithms are needed to suppress artifacts due to undersampling, and adaptive regularizations are necessary for preserving the edges of masses and calcifications. This paper presents a novel reconstruction method by regularizing projection onto convex sets (POCS) with multiscale Tikhonov-total variation (MTTV). The regularization, known as adaptive multiscale anisotropic diffusion, is able to preserve edges to a considerable extent and selectively suppress noise without introducing artifacts. The proposed method is referred to as MTTV-POCS and is evaluated quantitatively using 3D numerical breast and Shepp-Logan phantoms as well as two clinical volume images acquired from an advanced DBT machine. Experimental results show that the proposed method has better performance in metrics of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) over two existing methods: adaptive-steepest-descent-POCS (ASD-POCS) and selective-diffusion regularized simultaneous algebraic reconstruction technique (SD-SART). As indicated by the results, the proposed method is applicable to DBT for high-quality image reconstruction.

GATE Monte Carlo simulation of dose distribution using MapReduce in a cloud computing environment.

The GATE Monte Carlo simulation platform has good application prospects of treatment planning and quality assurance. However, accurate dose calculation using GATE is time consuming. The purpose of this study is to implement a novel cloud computing method for accurate GATE Monte Carlo simulation of dose distribution using MapReduce. An Amazon Machine Image installed with Hadoop and GATE is created to set up Hadoop clusters on Amazon Elastic Compute Cloud (EC2). Macros, the input files for GATE, are split into a number of self-contained sub-macros. Through Hadoop Streaming, the sub-macros are executed by GATE in Map tasks and the sub-results are aggregated into final outputs in Reduce tasks. As an evaluation, GATE simulations were performed in a cubical water phantom for X-ray photons of 6 and 18 MeV. The parallel simulation on the cloud computing platform is as accurate as the single-threaded simulation on a local server and the simulation correctness is not affected by the failure of some worker nodes. The cloud-based simulation time is approximately inversely proportional to the number of worker nodes. For the simulation of 10 million photons on a cluster with 64 worker nodes, time decreases of 41× and 32× were achieved compared to the single worker node case and the single-threaded case, respectively. The test of Hadoop's fault tolerance showed that the simulation correctness was not affected by the failure of some worker nodes. The results verify that the proposed method provides a feasible cloud computing solution for GATE.

Patient specific respiratory motion modeling using a limited number of 3D lung CT images.

To build a patient specific respiratory motion model with a low dose, a novel method was proposed that uses a limited number of 3D lung CT volumes with an external respiratory signal. 4D lung CT volumes were acquired for patients with in vitro labeling on the upper abdominal surface. Meanwhile, 3D coordinates of in vitro labeling were measured as external respiratory signals. A sequential correspondence between the 4D lung CT and the external respiratory signal was built using the distance correlation method, and a 3D displacement for every registration control point in the CT volumes with respect to time can be obtained by the 4D lung CT deformable registration. A temporal fitting was performed for every registration control point displacements and an external respiratory signal in the anterior-posterior direction respectively to draw their fitting curves. Finally, a linear regression was used to fit the corresponding samples of the control point displacement fitting curves and the external respiratory signal fitting curve to finish the pulmonary respiration modeling. Compared to a B-spline-based method using the respiratory signal phase, the proposed method is highly advantageous as it offers comparable modeling accuracy and target modeling error (TME); while at the same time, the proposed method requires 70% less 3D lung CTs. When using a similar amount of 3D lung CT data, the mean of the proposed method's TME is smaller than the mean of the PCA (principle component analysis)-based methods' TMEs. The results indicate that the proposed method is successful in striking a balance between modeling accuracy and number of 3D lung CT volumes.

[A technology of real-time image compression for convex grating imaging spectrometer].

The huge amount of convex grating imaging spectrometer image data brings much pressure to data transmission and storage, so the image must be compressed in real time. Firstly, the image characteristics were analyzed according to the imaging principle, and the compression approach to removing spatial correlation and spectral correlation was achieved; Secondly, the compression algorithms were analyzed and the 3-D compression scheme of one-order linear compression in spectral dimension and JPEG2000 compression in spatial dimension was proposed. Finally, a real-time compression system based on FPGA and ADV212 was designed, in which FPGA was used for logic control and implementation of prediction algorithm, and ADV212 was used for JPEG2000 compression. The analysis result shows that the system has the ability of lossless and lossy compression, enabling real-time image compression.