Search

In this study, we proposed a computer-aided diagnosis (CADx) framework under dual-energy spectral CT (DECT), which operates directly on the transmission data in the pre-log domain, called CADxDE, to explore the spectral information for lesion diagnosis. The CADxDE includes material identification and machine learning (ML) based CADx. Benefits from DECT’s capability of performing virtual monoenergetic imaging with the identified materials, the responses of different tissue types (e.g., muscle, water, and fat) in lesions at each energy can be explored by ML for CADx. Without losing essential factors in the DECT scan, a pre-log domain model-based iterative reconstruction is adopted to obtain decomposed material images, which are then used to generate the virtual monoenergetic images (VMIs) at selected n energies. While these VMIs have the same anatomy, their contrast distribution patterns contain rich information along with the n energies for tissue characterization. Thus, a corresponding ML-based CADx is developed to exploit the energy-enhanced tissue features for differentiating malignant from benign lesions. Specifically, an original image-driven multi-channel three-dimensional convolutional neural network (CNN) and extracted lesion feature-based ML CADx methods are developed to show the feasibility of CADxDE. Results from three pathologically proven clinical datasets showed 4.01% to 14.25% higher AUC (area under the receiver operating characteristic curve) scores than the scores of both the conventional DECT data (high and low energy spectrum separately) and the conventional CT data. The mean gain > 9.13% in AUC scores indicated that the energy spectral-enhanced tissue features from CADxDE have great potential to improve lesion diagnosis performance.

Cisplatin, the most widely used platinum-based anticancer drug, often causes progressive and irreversible sensorineural hearing loss in cancer patients. However, the precise mechanism underlying cisplatin-associated ototoxicity is still unclear. Nicotinamide adenine dinucleotide (NAD+), a co-substrate for the sirtuin family and PARPs, has emerged as a potent therapeutic molecular target in various diseases. In our investigates, we observed that NAD+ level was changed in the cochlear explants of mice treated with cisplatin. Supplementation of a specific inhibitor (TES-1025) of α-amino-β-carboxymuconate-e-semialdehyde decarboxylase (ACMSD), a rate-limiting enzyme of NAD+de novo synthesis pathway, promoted SIRT1 activity, increased mtDNA contents and enhanced AMPK expression, thus significantly reducing hair cells loss and deformation. The protection was blocked by EX527, a specific SIRT1 inhibitor. Meanwhile, the use of NMN, a precursor of NAD+ salvage synthesis pathway, had shown beneficial effect on hair cell under cisplatin administration, effectively suppressing PARP1. In vivo experiments confirmed the hair cell protection of NAD+ modulators in cisplatin treated mice and zebrafish. In conclusion, we demonstrated that modulation of NAD+ biosynthesis via the de novo synthesis pathway and the salvage synthesis pathway could both prevent ototoxicity of cisplatin. These results suggested that direct modulation of cellular NAD+ levels could be a promising therapeutic approach for protection of hearing from cisplatin-induced ototoxicity.

Cisplatin is an antitumor drug that is widely used for the treatment of various solid tumors. Unfortunately, patients are often troubled by serious side effects, especially hearing loss. Up to now, there have been no clear and effective measures to prevent cisplatin-induced ototoxicity in clinical use. We explored the role of autophagy and the efficacy of metformin in cisplatin-induced ototoxicity in cells, zebrafish, and mice. Furthermore, the underlying molecular mechanism of how metformin affects cisplatin-induced ototoxicity was examined. In in vitro experiments, autophagy levels in HEI-OC1 cells were assessed using fluorescence and Western blot analyses. In in vivo experiments, whether metformin had a protective effect against cisplatin ototoxicity was validated in zebrafish and C57BL/6 mice. The results showed that cisplatin induced autophagy activation in HEI-OC1 cells. Metformin exerted antagonistic effects against cisplatin ototoxicity in HEI-OC1 cells, zebrafish, and mice. Notably, metformin activated autophagy and increased the expression levels of the adenosine monophosphate-activated protein kinase (AMPK) and the transcription factor Forkhead box protein O3 (FOXO3a), whereas cells with AMPK silencing displayed otherwise. Our findings indicate that metformin alleviates cisplatin-induced ototoxicity possibly through AMPK/FOXO3a-mediated autophagy machinery. This study underpins further researches on the prevention and treatment of cisplatin ototoxicity.NEW & NOTEWORTHY Cisplatin is an antitumor drug that is widely used for the treatment of various solid tumors. Up to now, there have been no clear and effective measures to prevent cisplatin-induced ototoxicity in clinical use. We investigated the protective effect of metformin on cisplatin ototoxicity in vitro and in vivo. Our findings indicate that metformin alleviates cisplatin-induced ototoxicity possibly through AMPK/FOXO3a-mediated autophagy machinery. This study underpins further researches on the prevention and treatment of cisplatin ototoxicity.

Pancreatoscopy plays a significant role in the diagnosis and treatment of pancreatic diseases. However, the risk of pancreatoscopy is remarkably greater than that of other endoscopic procedures, such as gastroscopy and bronchoscopy, owing to its severe invasiveness. In comparison, virtual pancreatoscopy (VP) has shown notable advantages. However, because of the low resolution of current computed tomography (CT) technology and the small diameter of the pancreatic duct, VP has limited clinical use. In this study, an optimal path algorithm and super-resolution technique are investigated for the development of an open-source software platform for VP based on 3D Slicer. The proposed segmentation of the pancreatic duct from the abdominal CT images reached an average Dice coefficient of 0.85 with a standard deviation of 0.04. Owing to the excellent segmentation performance, a fly-through visualization of both the inside and outside of the duct was successfully reconstructed, thereby demonstrating the feasibility of VP. In addition, a quantitative analysis of the wall thickness and topology of the duct provides more insight into pancreatic diseases than a fly-through visualization. The entire VP system developed in this study is available at https://github.com/gaoyi/VirtualEndoscopy.git.

Photon-counting spectral computed tomography (CT) is capable of material characterization and can improve diagnostic performance over traditional clinical CT. However, it suffers from photon count starving for each individual energy channel which may cause severe artifacts in the reconstructed images. Furthermore, since the images in different energy channels describe the same object, there are high correlations among different channels. To make full use of the inter-channel correlations and minimize the count starving effect while maintaining clinically meaningful texture information, this paper combines a region-specific texture model with a low-rank correlation descriptor as an a priori regularization to explore a superior texture preserving Bayesian reconstruction of spectral CT. Specifically, the inter-channel correlations are characterized by the low-rank representation, and the inner-channel regional textures are modeled by a texture preserving Markov random field. In other words, this paper integrates the spectral and spatial information into a unified Bayesian reconstruction framework. The widely-used Split-Bregman algorithm is employed to minimize the objective function because of the non-differentiable property of the low-rank representation. To evaluate the tissue texture preserving performance of the proposed method for each channel, three references are built for comparison: one is the traditional CT image from energy integration detection. The second one is spectral images from dual-energy CT. The third one is individual channels images from custom-made photon-counting spectral CT. As expected, the proposed method produced promising results in terms of not only preserving texture features but also suppressing image noise in each channel, comparing to existing methods of total variation (TV), low-rank TV and tensor dictionary learning, by both visual inspection and quantitative indexes of root mean square error, peak signal to noise ratio, structural similarity and feature similarity.

Accurately classifying colorectal polyps, or differentiating malignant from benign ones, has a significant clinical impact on early detection and identifying optimal treatment of colorectal cancer. Convolution neural network (CNN) has shown great potential in recognizing different objects (e.g. human faces) from multiple slice (or color) images, a task similar to the polyp differentiation, given a large learning database. This study explores the potential of CNN learning from multiple slice (or feature) images to differentiate malignant from benign polyps from a relatively small database with pathological ground truth, including 32 malignant and 31 benign polyps represented by volumetric computed tomographic (CT) images. The feature image in this investigation is the gray-level co-occurrence matrix (GLCM). For each volumetric polyp, there are 13 GLCMs, computed from each of the 13 directions through the polyp volume. For comparison purpose, the CNN learning is also applied to the multi-slice CT images of the volumetric polyps. The comparison study is further extended to include Random Forest (RF) classification of the Haralick texture features (derived from the GLCMs). From the relatively small database, this study achieved scores of 0.91/0.93 (two-fold/leave-one-out evaluations) AUC (area under curve of the receiver operating characteristics) by using the CNN on the GLCMs, while the RF reached 0.84/0.86 AUC on the Haralick features and the CNN rendered 0.79/0.80 AUC on the multiple-slice CT images. The presented CNN learning from the GLCMs can relieve the challenge associated with relatively small database, improve the classification performance over the CNN on the raw CT images and the RF on the Haralick features, and have the potential to perform the clinical task of differentiating malignant from benign polyps with pathological ground truth.

Perfusion computed tomography (PCT) is critical in detecting cerebral ischemic lesions. PCT examination with low-dose scans can effectively reduce radiation exposure to patients at the cost of degraded images with severe noise, and artifacts. Tensor total variation (TTV) models are powerful tools that can encode the regional continuous structures underlying a PCT object. In a TTV model, the sparsity structures of the contrast-medium concentration (CMC) across PCT frames are assumed to be isotropic with identical, and independent distribution. However, this assumption is inconsistent with practical PCT tasks wherein the sparsity has evident variations, and correlations. Such modeling deviation hampers the performance of TTV-based PCT reconstructions. To address this issue, we developed a novel c ontrast- m edium a nisotropy- a ware t ensor t otal v ariation (CMAA-TTV) model to describe the intrinsic anisotropy sparsity of the CMC in PCT imaging tasks. Instead of directly on the difference matrices, the CMAA-TTV model characterizes sparsity on a low-rank subspace of the difference matrices which are calculated from the input data adaptively, thus naturally encoding the intrinsic variant, and correlated anisotropy sparsity structures of the CMC. We further proposed a robust, and efficient PCT reconstruction algorithm to improve low-dose PCT reconstruction performance using the CMAA-TTV model. Experimental studies using a digital brain perfusion phantom, patient data with low-dose simulation, and clinical patient data were performed to validate the effectiveness of the presented algorithm. The results demonstrate that the CMAA-TTV algorithm can achieve noticeable improvements over state-of-the-art methods in low-dose PCT reconstruction tasks.

Most penalized maximum likelihood methods for tomographic image reconstruction based on Bayes’ law include a freely adjustable hyperparameter to balance the data fidelity term and the prior/penalty term for a specific noise–resolution tradeoff. The hyperparameter is determined empirically via a trial-and-error fashion in many applications, which then selects the optimal result from multiple iterative reconstructions. These penalized methods are not only time-consuming by their iterative nature, but also require manual adjustment. This study aims to investigate a theory-based strategy for Bayesian image reconstruction without a freely adjustable hyperparameter, to substantially save time and computational resources. The Bayesian image reconstruction problem is formulated by two probability density functions (PDFs), one for the data fidelity term and the other for the prior term. When formulating these PDFs, we introduce two parameters. While these two parameters ensure the PDFs completely describe the data and prior terms, they cannot be determined by the acquired data; thus, they are called complete but unobservable parameters. Estimating these two parameters becomes possible under the conditional expectation and maximization for the image reconstruction, given the acquired data and the PDFs. This leads to an iterative algorithm, which jointly estimates the two parameters and computes the to-be reconstructed image by maximizing a posteriori probability, denoted as joint-parameter-Bayes. In addition to the theoretical formulation, comprehensive simulation experiments are performed to analyze the stopping criterion of the iterative joint-parameter-Bayes method. Finally, given the data, an optimal reconstruction is obtained without any freely adjustable hyperparameter by satisfying the PDF condition for both the data likelihood and the prior probability, and by satisfying the stopping criterion. Moreover, the stability of joint-parameter-Bayes is investigated through factors such as initialization, the PDF specification, and renormalization in an iterative manner. Both phantom simulation and clinical patient data results show that joint-parameter-Bayes can provide comparable reconstructed image quality compared to the conventional methods, but with much less reconstruction time. To see the response of the algorithm to different types of noise, three common noise models are introduced to the simulation data, including white Gaussian noise to post-log sinogram data, Poisson-like signal-dependent noise to post-log sinogram data and Poisson noise to the pre-log transmission data. The experimental outcomes of the white Gaussian noise reveal that the two parameters estimated by the joint-parameter-Bayes method agree well with simulations. It is observed that the parameter introduced to satisfy the prior’s PDF is more sensitive to stopping the iteration process for all three noise models. A stability investigation showed that the initial image by filtered back projection is very robust. Clinical patient data demonstrated the effectiveness of the proposed joint-parameter-Bayes and stopping criterion.

Texture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

Objective: As an effective lesion heterogeneity depiction, texture information extracted from computed tomography has become increasingly important in polyp classification. However, variation and redundancy among multiple texture descriptors render a challenging task of integrating them into a general characterization. Considering these two problems, this work proposes an adaptive learning model to integrate multi-scale texture features. Methods: To mitigate feature variation, the whole feature set is geometrically split into several independent subsets that are ranked by a learning evaluation measure after preliminary classifications. To reduce feature redundancy, a bottom-up hierarchical learning framework is proposed to ensure monotonic increase of classification performance while integrating these ranked sets selectively. Two types of classifiers, traditional (random forest + support vector machine)- and convolutional neural network (CNN)-based, are employed to perform the polyp classification under the proposed framework with extended Haralick measures and gray-level co-occurrence matrix (GLCM) as inputs, respectively. Experimental results are based on a retrospective dataset of 63 polyp masses (defined as greater than 3 cm in largest diameter), including 32 adenocarcinomas and 31 benign adenomas, from adult patients undergoing first-time computed tomography colonography and who had corresponding histopathology of the detected masses. Results: We evaluate the performance of the proposed models by the area under the curve (AUC) of the receiver operating characteristic curve. The proposed models show encouraging performances of an AUC score of 0.925 with the traditional classification method and an AUC score of 0.902 with CNN. The proposed adaptive learning framework significantly outperforms nine well-established classification methods, including six traditional methods and three deep learning ones with a large margin. Conclusions: The proposed adaptive learning model can combat the challenges of feature variation through a multiscale grouping of feature inputs, and the feature redundancy through a hierarchal sorting of these feature groups. The improved classification performance against comparative models demonstrated the feasibility and utility of this adaptive learning procedure for feature integration.

Textures have become widely adopted as an essential tool for lesion detection and classification through analysis of the lesion heterogeneities. In this study, higher order derivative images are being employed to combat the challenge of the poor contrast across similar tissue types among certain imaging modalities. To make good use of the derivative information, a novel concept of vector texture is firstly introduced to construct and extract several types of polyp descriptors. Two widely used differential operators, i.e., the gradient operator and Hessian operator, are utilized to generate the first and second order derivative images. These derivative volumetric images are used to produce two angle-based and two vector-based (including both angle and magnitude) textures. Next, a vector-based co-occurrence matrix is proposed to extract texture features which are fed to a random forest classifier to perform polyp classifications. To evaluate the performance of our method, experiments are implemented over a private colorectal polyp dataset obtained from computed tomographic colonography. We compare our method with four existing state-of-the-art methods and find that our method can outperform those competing methods over 4%-13% evaluated by the area under the receiver operating characteristics curves.

The current standardized scheme for interpreting MRI requires a high level of expertise and exhibits a significant degree of inter-reader and intra-reader variability. An automated prostate cancer (PCa) classification can improve the ability of MRI to assess the spectrum of PCa. The purpose of the study was to evaluate the performance of a texture-based deep learning model (Textured-DL) for differentiating between clinically significant PCa (csPCa) and non-csPCa and to compare the Textured-DL with Prostate Imaging Reporting and Data System (PI-RADS)-based classification (PI-RADS-CLA), where a threshold of PI-RADS ≥ 4, representing highly suspicious lesions for csPCa, was applied. The study cohort included 402 patients (60% (n = 239) of patients for training, 10% (n = 42) for validation, and 30% (n = 121) for testing) with 3T multiparametric MRI matched with whole-mount histopathology after radical prostatectomy. For a given suspicious prostate lesion, the volumetric patches of T2-Weighted MRI and apparent diffusion coefficient images were cropped and used as the input to Textured-DL, consisting of a 3D gray-level co-occurrence matrix extractor and a CNN. PI-RADS-CLA by an expert reader served as a baseline to compare classification performance with Textured-DL in differentiating csPCa from non-csPCa. Sensitivity and specificity comparisons were performed using Mcnemar’s test. Bootstrapping with 1000 samples was performed to estimate the 95% confidence interval (CI) for AUC. CIs of sensitivity and specificity were calculated by the Wald method. The Textured-DL model achieved an AUC of 0.85 (CI [0.79, 0.91]), which was significantly higher than the PI-RADS-CLA (AUC of 0.73 (CI [0.65, 0.80]), p &lt, 0.05) for PCa classification, and the specificity was significantly different between Textured-DL and PI-RADS-CLA (0.70 (CI [0.59, 0.82]) vs. 0.47 (CI [0.35, 0.59]), 0.05). In sub-analyses, Textured-DL demonstrated significantly higher specificities in the peripheral zone (PZ) and solitary tumor lesions compared to the PI-RADS-CLA (0.78 (CI [0.66, 0.90]) vs. 0.42 (CI [0.28, 0.57]), 0.75 (CI [0.54, 0.96]) vs. 0.38 [0.14, 0.61], all p values &lt, 0.05). Moreover, Textured-DL demonstrated a high negative predictive value of 92% while maintaining a high positive predictive value of 58% among the lesions with a PI-RADS score of 3. In conclusion, the Textured-DL model was superior to the PI-RADS-CLA in the classification of PCa. In addition, Textured-DL demonstrated superior performance in the specificities for the peripheral zone and solitary tumors compared with PI-RADS-based risk assessment.

Objective: Current studies still find insufficient evidence to support the routine use of repetitive transcranial magnetic stimulation (rTMS) in tinnitus. This study aimed to assess response of tinnitus to treatment with rTMS and identify factors influencing the overall response. Methods: Between January 2016 and May 2017, 199 tinnitus patients were identified from a retrospective review of the electronic patient record at the Sun Yat-sen Memorial Hospital. All patients received rTMS treatment. Their clinicodemographic profile and outcomes, including the tinnitus handicap inventory (THI) and visual analog scale (VAS) scores, were extracted for analysis. Results: Regarding the THI results, 62.3% of all patients responded to rTMS. The analysis of the VAS score revealed an overall response rate of 66.3%. Both percentages were close to the patient’s subjective assessment result, of 63.8%. Patients with tinnitus of less than 1-week duration had the highest response rate to rTMS in terms of either THI/VAS scores or the patient’s subjective assessment of symptoms. Tinnitus duration was recognized as a factor influencing the overall response to the treatment. Conclusions: Repetitive transcranial magnetic stimulation treatment is effective for patients with tinnitus, but its efficacy is affected by tinnitus duration. Tinnitus patients are advised to attend for rTMS as soon as possible since therapy was more effective in those with a shorter duration of disease of less than 1 week.

Computer aided detection (CADe) of pulmonary nodules plays an important role in assisting radiologists’ diagnosis and alleviating interpretation burden for lung cancer. Current CADe systems, aiming at simulating radiologists’ examination procedure, are built upon computer tomography (CT) images with feature extraction for detection and diagnosis. Human visual perception in CT image is reconstructed from sinogram, which is the original raw data acquired from CT scanner. In this work, different from the conventional image based CADe system, we propose a novel sinogram based CADe system in which the full projection information is used to explore additional effective features of nodules in the sinogram domain. Facing the challenges of limited research in this concept and unknown effective features in the sinogram domain, we design a new CADe system that utilizes the self-learning power of the convolutional neural network to learn and extract effective features from sinogram. The proposed system was validated on 208 patient cases from the publicly available online Lung Image Database Consortium database, with each case having at least one juxtapleural nodule annotation. Experimental results demonstrated that our proposed method obtained a value of 0.91 of the area under the curve (AUC) of receiver operating characteristic based on sinogram alone, comparing to 0.89 based on CT image alone. Moreover, a combination of sinogram and CT image could further improve the value of AUC to 0.92. This study indicates that pulmonary nodule detection in the sinogram domain is feasible with deep learning.

BACKGROUND Preoperative prediction of bladder cancer (BCa) recurrence risk is critical for individualized clinical management of BCa patients. PURPOSE To develop and validate a nomogram based on radiomics and clinical predictors for personalized prediction of the first 2 years (TFTY) recurrence risk. STUDY TYPE Retrospective. POPULATION Preoperative MRI datasets of 71 BCa patients (34 recurrent) were collected, and divided into training (n = 50) and validation cohorts (n = 21). FIELD STRENGTH/SEQUENCE 3.0T MRI/T2 -weighted (T2 W), multi-b-value diffusion-weighted (DW), and dynamic contrast-enhanced (DCE) sequences. ASSESSMENT Radiomics features were extracted from the T2 W, DW, apparent diffusion coefficient, and DCE images. A Rad_Score model was constructed using the support vector machine-based recursive feature elimination approach and a logistic regression model. Combined with the important clinical factors, including age, gender, grade, and muscle-invasive status (MIS) of the archived lesion, tumor size and number, surgery, and image signs like stalk and submucosal linear enhancement, a radiomics-clinical nomogram was developed, and its performance was evaluated in the training and the validation cohorts. The potential clinical usefulness was analyzed by the decision curve. STATISTICAL TESTS Univariate and multivariate analyses were performed to explore the independent predictors for BCa recurrence prediction. RESULTS Of the 1872 features, the 32 with the highest area under the curve (AUC) of receiver operating characteristic were selected for the Rad_Score calculation. The nomogram developed by two independent predictors, MIS and Rad_Score, showed good performance in the training (accuracy 88%, AUC 0.915, P << 0.01) and validation cohorts (accuracy 80.95%, AUC 0.838, P = 0.009). The decision curve exhibited when the risk threshold was larger than 0.3, more benefit was observed by using the radiomics-clinical nomogram than using the radiomics or clinical model alone. DATA CONCLUSION The proposed radiomics-clinical nomogram has potential in the preoperative prediction of TFTY BCa recurrence. LEVEL OF EVIDENCE 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2019;50:1893-1904.

Rationale and Objectives To (1) apply a quantitative volumetric textural analysis (VTA) to colorectal masses at CT colonography (CTC) for the differentiation of malignant and benign lesions and to (2) compare VTA with human performance. Materials and Methods A validated, quantitative VTA method was applied to 63 pathologically proven colorectal masses (mean size, 4.2 cm; range, 3–8 cm) at noncontrast CTC in 59 adults (mean age, 66.5 years; range, 45.9–91.6 years). Fifty-one percent (32/63) of the masses were invasive adenocarcinoma, and the remaining 49% (31/63) were large benign adenomas. Three readers with CTC experience independently assessed the likelihood of malignancy using a 5-point scale (1 = definitely benign, 2 = probably benign, 3 = indeterminate, 4 = probably malignant, 5 = definitely malignant). Areas under the curve (AUCs) and accuracy levels were compared. Results VTA achieved optimal sensitivity of 83.6% vs 91.7% for human readers (P = .034), with specificities of 87.5% and 77.4%, respectively (P = .007). No significant difference in overall accuracy was seen between VTA and human readers (85.5% vs 84.7%, P = .753). The AUC for differentiating benign and malignant lesions was 0.936 for VTA and 0.917 for human readers. Intraclass correlation coefficient among the human readers was 0.76, indicating good to excellent agreement. Conclusion VTA demonstrates excellent performance for distinguishing benign from malignant colorectal masses (≥3 cm) at CTC, comparable yet potentially complementary to experienced human performance.

Segmenting intensity inhomogeneous images is a challenging task for both local and global methods. Some hybrid methods have great advantages over the traditional methods in inhomogeneous image segmentation. In this paper, a new hybrid method is presented, which incorporates image gradient, local environment and global information into a framework, called adaptive-weighting active contour model. The energy or level set functions in the framework mainly include two parts: a global term and local term. The global term aims to enhance the image contrast, and it can also accelerate the convergence rate when minimizing the energy function. The local term integrates fractional order differentiation, fractional order gradient magnitude, and difference image information into the well-known local Chan–Vese model, which has been shown to be effective and efficient in modeling the local information. The local term can also enhance low frequency information and improve the inhomogeneous image segmentation. An adaptive weighting strategy is proposed to balance the actions of the global and local terms automatically. When minimizing the level set functions, regularization can be imposed by applying Gaussian filtering to ensure smoothness in the evolution process. In addition, a corresponding stopping criterion is proposed to ensure the evolving curve automatically stops on true boundaries of objects. Dice similarity coefficient is employed as the comparative quantitative measures for the segmented results. Experiments on synthetic images as well as real images are performed to demonstrate the segmentation accuracy and computational efficiency of the presented hybrid method.

Screening is an effective way to detect lung cancer early and can improve the survival rate significantly. The low-dose computed tomography (LdCT) is demanding for lung screening to ensure the exam radiation as low as reasonably possible. The statistical image reconstruction has shown great advantages in LdCT imaging, where many types of priors can be used as constrain for optimal images. The tissue-specific Markov random field (MRF) type texture prior (MRFt) was proposed in our previous work to address the clinical related texture information. For the chest scans, four tissue texture were extracted from regions of lung, bone, fat and muscle respectively. In this work, we focus on the region of interest, i.e. lung for the lung cancer screening. The quantitative texture analysis of normal and abnormal lung tissue was performed to address the following issues of the proposed MRFt model: (1) a more comprehensive understanding of the lung tissue texture (2) what MRF prior we should use for the abnormal lung tissue. Experiments results showed that normal lung tissue has texture similarity among different subjects. The robust similarity among humans laid the feasibility of building the lung tissue database for the LdCT imaging which has no previous FdCT scans. Different abnormal lung tissue varies significantly. There is no way to get the prior knowledge of lung nodules until the CT exam was performed.

Dual energy CT (DECT) expands applications of CT imaging in its capability to acquire two datasets, one at high and the other at low energy, and produce decomposed material images of the scanned objects. Bayesian theory applied for statistical DECT reconstruction has shown great potential for giving the accurate decomposed material fraction images directly from projection measurements. It provides a natural framework to include various kinds of prior information for improved image reconstruction with its optimal selected hyper parameter by a trial-error style. To eliminate the cumbersome style, in this work, we propose a parameter-free Bayesian reconstruction algorithm for DECT (PfBR-DE). In our approach, the physical meaning of the hyper parameter can be interpreted as the ratio of the data variance α and the prior tolerance σ by formulating the probability distribution functions of the data fidelity and prior expectation. With an alternative optimization scheme, the data variance, prior tolerance and decomposed material images can be jointly estimated. Experimental results with the abdomen phantom demonstrate the PfBR-DE method can obtain the comparable quantity decomposed material images with the conventional methods without freely adjustable hyper parameter.

Malignant lesions have a high tendency to invade their surrounding environment compared to benign ones. This paper proposes a dynamic lesion model and explores the 2nd order derivatives at each image voxel, which reflect the rate of change of image intensity, as a quantitative measure of the tendency. The 2nd order derivatives at each image voxel are usually represented by the Hessian matrix, but it is difficult to quantify a matrix field (or image) through the lesion space as a measure of the tendency. We conjecture that the three eigenvalues contain important information of the Hessian matrix and are chosen as the surrogate representation of the Hessian matrix. By treating the three eigenvalues as a vector, called Hessian vector, which is defined in a local coordinate formed by three orthogonal Hessian eigenvectors and further adapting the gray level occurrence computing method to extract the vector texture descriptors (or measures) from the Hessian vector, a quantitative presentation for the dynamic lesion model is completed. The vector texture descriptors were applied to differentiate malignant from benign lesions from two pathologically proven datasets: colon polyps and lung nodules. The classification results not only outperform four state-of-the-art methods but also three radiologist experts.

Cisplatin, the most widely used platinum-based anticancer drug, often causes progressive and irreversible sensorineural hearing loss in cancer patients. However, the precise mechanism underlying cisplatin-associated ototoxicity is still unclear. Nicotinamide adenine dinucleotide (NAD

Extracting effective texture features from computed tomographic colonography (CTC) and merging them to form a much powerful descriptor are two critical challenges in computer-aided detection (CADe) and diagnosis (CADx). In this paper, we introduce multi-scaling analysis into grey level co-occurrence matrix (GLCM) to construct texture features from different image domains, i.e. intensity, gradient and curvature. Thus, nine texture descriptors are generated and form a descriptor pool sorted by AUC (area under the curve of receiver operating characteristics) scores. Then an adaptive feature merging method is designed and implemented in a binary tree framework where every layer consists of two nodes, i.e. the baseline descriptor and its complement which are always the first two descriptors in the descriptor pool. Their merging will be performed using forward stepwise method where some complementary variables with gains in classification are preserved. After feature merging, the descriptor pool will be updated by removing the two candidates and adding the new baseline descriptor. This procedure will be performed iteratively until the final descriptor is obtained. Obviously, this is a greedy procedure which guarantees the monotonicity of the classification. Experimental outcomes testify the effectiveness of this method and the proposed method outperforms the pre-merging descriptor over 4% by AUC scores.

Although Bayesian theory has been successfully applied for count-limited medical image reconstruction in the past two decades, its wide applications in clinic has been hampered by its hyperparameter ${\beta}$ , which is traditionally determined by a trial-error style. To eliminate the cumbersome style, this work aims to present a selection method by mimicking the physical model of cooling down the temperature adaptively for an economic high-quality crystal. From the basic Bayes' law, the physical meaning of hyperparameter can be interpreted as the ratio of the data uncertainty (or variance ${\alpha}$ ) and the prior tolerance (or ${\sigma}$ ) by formulating the probability distribution functions (FDFs) of the data fidelity and prior expectation. Inspired by this idea, the prior tolerance ${\sigma}$ can be treated as the temperature of the texture patterns, and ${\beta}$ can be adjusted according to different texture pattern status by satisfying the condition of each PDF in the Bayes' Law during the iteration. In Simulated phantom study, realistic Poisson noise added to the pre-log transmission data model was used. Both phantom simulation and clinical patient data results show that the proposed method can provide comparable reconstructed image quality comparing to the conventional methods but with much less reconstruction time. It is observed that the parameter introduced to satisfy the prior's PDF is more sensitive to stop the iteration process.

Computed tomography (CT) of COVID-19 manifests a relatively global effect through the whole lungs, like peripheral ground glass, consolidation, reticular pattern, nodules etc. This characteristic effect renders the difficulties in differentiating COVID-19 from the normal body or other lung diseases by CT. This work presents a novel method to relieve the difficulties by reducing the global effect through the 3D whole lung volume into 2D-like domain. The hypothesis is that the lung tissue shares the similar anatomic structure within a small lung sub-volume for normal subjects. Therefore, the anatomic land-markers along the z-axis, denoted as Lung Marks are used to eliminate axial variable. Our experiments indicated that 30 Lung Marks are sufficient to eliminate the axial variable. The method computes texture measures from each 2D-like volumetric data and maps the measures on to the corresponding Lung Mark, resulting in a profile along the z-axis. The difference of the profiles between two different abnormalities is the proposed sensitive merit to differentiate COVID-19 cases from others in CT images. 48 COVID-19 cases and 48 normal screening cases were used to test the effectiveness of the proposed sensitive merit. Intensity and gradient based texture descriptors were computed from each axial cross image at the corresponding Lung Mark along the z-axis. Euclidean, Jaccard and Dice distances are calculated to generate the profiles of the proposed sensitive merit. Consistent results are observed across texture descriptor types and distance types in the texture measure between the normal and COVID-19 subjects. Uneven Profiles demonstrate the variation along the z-axis. With Lung Mark, the variation of texture descriptor has been reduced prominently. The Gradient based descriptor is more sensitive. Individual Haralick features analysis shows the 2nd and 10th dimensions are most distinguishable.

Dual energy computed tomography (DECT) expands applications of CT imaging in its capability to acquire two datasets, one at high and the other at low energies, and produces decomposed material images. Instead of being viewed simultaneously, the produced two series images are most often fused into a single optimum contrast image for disease diagnosis using a blending technique with a ratio of the two datasets. However, current existing methods apply blending technique on the individual reconstructed CT images, which suffer from beam hardening artifacts. Furthermore, how to select a reasonable ratio to improve the contrast resolution remains a practical problem in current DECT application. In order to alleviate the above two issues, we proposed an adaptive optimum contrast image acquisition strategy and demonstrated its success in improving our previous spectrum estimation-guided DECT (SEG-DECT) reconstruction. Specifically, the proposed strategy takes x-ray spectrum information into consideration to reconstruct the basis material density images by the SEG-DECT method to eliminate the effect of beam hardening. Furthermore, based on the statistical properties of the decomposed material images, an adaptive nonlinear blending technique is incorporated in the reconstruction of an optimum contrast CT image. Numerical experiments with the XCAT phantom containing a lesion showed that the proposed method significantly improves both the contrast-to-noise ratio and quality of fused CT images.

Data preparation for any machine learning process is of utmost importance to produce consistent and robust results. The challenges faced with identifying the colon polyps in computed tomographic colonography (CTC) images are that some polyps do not have a definite outline, some are coated by oral tag material due to poor preparation, and the intra-variation when multiple contributors work on the same dataset. This study aims to relieve the challenge by an iterative user-driven procedure, which starts by an expert to draw the initial borders of the colon polyps (or VOIs), followed by using computer aided classification (CAC) on an adequately grouped VOIs to find outliers. Then the expert examines the outliers for refining the VOIs and the CAC is repeated on the refined VOIs. This iterative procedure is repeated until a threshold is satisfied. The expert-driven CAC procedure was validated by experiments using three datasets. One small dataset containing 87 large polyp masses, and two large datasets containing 726 and 563 polyp masses varying in size from medium and small. Of the dataset with 87 polyps, 63 VOIs were constructed previously by three experts as the baseline, including 31 benign and 32 malignant. The remaining 24 (12 benign and 12 malignant) were added after going through the expert-driven CAC procedure (i.e. only one expert). The two large datasets had multiple contributors and each dataset could be split into several subgroups and cross validated using the highest performing subgroup as the baseline. The cross validation was performed using the grey-level co-occurrence measures of the VOIs, two-fold validation, and random forest classifier. The AUC score on the large polyp dataset remained the same as that of the baseline when the 24 new VOIs were added using the expert-driven CAC procedure, while varied by 4% if the procedure was not used. The AUC score on the medium and small polyp datasets had nominal increases up to 2% after expert-driven CAC procedure. Upon further examination on the-up-to 2% variation, the causes include flat small polyps and small polyps being submerged and/or surrounded by oral tagging materials. These causes of up to 2% variation are CTC data specific and acceptable. In conclusion, expert-driven CAC is important for large database construction. Key words: ML, Database, Colon polyps, CTC, CAC.

Background Although the clinical efficacy and safety of repetitive transcranial magnetic stimulation (rTMS) in the treatment of chronic tinnitus have been frequently examined, the results remain contradictory. Therefore, we performed a systematic review and meta-analysed clinical trials examining the effects of rTMS to evaluate its clinical efficacy and safety. Methods Studies of rTMS for chronic tinnitus were retrieved from PubMed, Embase, and Cochrane Library through April 2020. Review Manager 5.3 software was employed for data synthesis, and Stata 13.0 software was used for analyses of publication bias and sensitivity. Results Twenty-nine randomized studies involving 1228 chronic tinnitus patients were included. Compared with sham-rTMS, rTMS exhibited significant improvements in the tinnitus handicap inventory (THI) scores at 1 week (mean difference [MD]: − 7.92, 95% confidence interval [CI]: − 14.18, − 1.66), 1 month (MD: -8.52, 95% CI: − 12.49, − 4.55), and 6 months (MD: -6.53, 95% CI: − 11.406, − 1.66) post intervention; there were significant mean changes in THI scores at 1 month (MD: -14.86, 95% CI: − 21.42, − 8.29) and 6 months (MD: -16.37, 95% CI: − 20.64, − 12.11) post intervention, and the tinnitus questionnaire (TQ) score at 1 week post intervention (MD: -8.54, 95% CI: − 15.56, − 1.52). Nonsignificant efficacy of rTMS was found regarding the THI score 2 weeks post intervention (MD: -1.51, 95% CI: − 13.42, − 10.40); the mean change in TQ scores 1 month post intervention (MD: -3.67, 95% CI: − 8.56, 1.22); TQ scores 1 (MD: -8.97, 95% CI: − 20.41, 2.48) and 6 months (MD: -7.02, 95% CI: − 18.18, 4.13) post intervention; and adverse events (odds ratios [OR]: 1.11, 95% CI: 0.51, 2.42). Egger’s and Begg’s tests indicated no publication bias (P = 0.925). Conclusion This meta-analysis demonstrated that rTMS is effective for chronic tinnitus; however, its safety needs more validation. Restrained by the insufficient number of included studies and the small sample size, more large randomized double-blind multi-centre trials are needed for further verification.

Background:Although the clinical efficacy and safety of repeated transcranial magnetic stimulation(rTMS)on the treatment of chronic tinnitushave been frequently reported, the results remain controversial.Therefore, its relatedclinical efficacy and safety were systematically evaluated and meta-classified in this study.Methods:Literature on repeated transcranial magnetic stimulation(rTMS)on chronic tinnitus was retrieved in PubMed, Embase and Cochrane Library due April 2020.Review Manager 5.3 software was appliedto data synthesis, and Stata 13.0 software was adopted for analyses of publication bias and sensitivity.Results:A total of 29randomized studies with 1,228 patients were included. Compared with sham rTMS, rTMSshowed statistical significance in tinnitus handicap inventory(THI) scores 1 week after intervention (MD-7.92, 95% condidence interval [CI] -14.18,-1.66), THI scores 1month after intervention (MD-8.52, 95% CI -12.49,-4.55),THI scores 6months after intervention (MD-6.53, 95% CI -11.406,-1.66), TQ scores 1 week after intervention (MD-8.54, 95% CI -15.56,-1.52),mean change in THI scores 1month after intervention(MD-14.86, 95% CI -21.42,-8.29) and mean change in THI scores 6months after intervention(MD-16.37, 95% CI -20.64,-12.11) .There was no statistical difference between rTMS and sham rTMS in THI scores 2 week after intervention (MD-1.51, 95% CI -13.42,-10.40),tinnitus questionnaire(TQ) scores 1 month after intervention (MD-8.97, 95% CI -20.41,2.48),TQ scores 6 months after intervention (MD-7.02, 95% CI -18.18,4.13) , mean change in TQ scores 1months after intervention(MD-3.67, 95% CI -8.56,1.22) and adverse events (OR 1.11, 95% CI 0.51,2.42).Egger's and Begg's testsindicatedno publication bias(P= 0.925).Conclusion:It was demonstrated that rTMS on chronic tinnitus has certain clinical curative effect and high safety,however, due to the lack of included studies and the small sample size, more large-sample, multi-center, randomized double-blind trials are needed for further verification.

PURPOSE: Tissue texture has been recognized as biomarkers for various clinical tasks. In computed tomography (CT) image reconstruction, it is important but challenging to preserve the texture when lowering X-ray exposure from full- toward low-/ultralow-dose level. Therefore, this paper aims to explore the texture-dose relationship by one tissue-specific pre-log Bayesian CT reconstruction algorithm. METHODS: To enhance the texture in ultralow-dose CT (ULdCT) reconstruction, this paper presents a Bayesian type algorithm, where shifted Poisson model is adapted to describe the statistical properties of pre-log data and a tissue-specific Markov random field (MRF) prior is used to incorporate tissue texture from previous full dose CT, thus called SP-MRFt algorithm. Utilizing the SP-MRFt algorithm, we investigated tissue texture degradation as a function of dose levels from full dose (100mAs/120kVp) to ultralow dose (1mAs/120kVp) by introducing a quantitative texture-based evaluation metrics. RESULTS: Experimental results show the SP-MRFt algorithm outperforms conventional filtered back projection (FBP) and post-log domain penalized weighted least square MRFt (PWLS-MRFt) in terms of noise suppression and texture preservation. Comparable results are also obtained with shifted Poisson model with 7×7 Huber MRF weights (SP-Huber7). The SP-MRFt is a reasonably good tool to investigate the texture-dose relationship approaching the ultra-low dose end. The investigation on texture-dose relationship shows that the quantified texture measures drop monotonically as dose level decreases, and interestingly a turning point is observed on the texture-dose response curve. CONCLUSIONS: This important observation implies that there exists a minimum dose level, at which a given CT scanner (hardware configuration and image reconstruction software) can achieve without compromising clinical tasks. Moreover, the experiment results show that the variance of electronic noise has higher impact than the mean to the texture-dose relationship.

In this article, we introduce a deformation independent model to solve the shape and posture changing issue for polyp characterization in computer-aided diagnosis (CADx) via CT colonography. After volumetric data parameterization in a four-dimensional space, the first fundamental form (FFF) is employed to construct the polyp model which contains several excellent properties such as locality, symmetry, orientation robustness, shift and isometric invariance. In consideration of the scaling effects, gray level co-occurrence matrix (GLCM) is utilized to remove the scaling factor and extract texture descriptors. As a symmetrical square tensor, however, it is difficult to put the FFF into GLCM directly. To solve this problem, we perform matrix decomposition on FFF to extract its eigenvalues and eigenvectors which are used to construct three metric images as the input of GLCM. Then Haralick measures extracted from GLCM are applied to construct texture descriptors which are fed to a random forest classifier to perform polyp classification. Experiments show that the proposed method obtains an encouraging classification performance with area under the curve of receiver operating characteristics (AUC score) of 95.3% which is a significant improvement comparing with five existing methods.

Machine learning, especially convolutional neural network (CNN) approach has been successfully applied in noise suppression in natural image. However, shifting from natural image to medical image filed remains challenging due to specific difficulties such as training samples limitation, clinically meaningful image quality requirement and so on. To address this challenge, one possible solution is to incorporate our human prior knowledge into the machine learning model to better benefit its power. Therefore, in this work, we propose one prior knowledge driven machine learning based approach for positron emission tomography (PET) sinogram data denoising. Two main properties of PET sinogram data were considered in CNN architecture design, which are the Poisson statistics of the data and different correlation strength in the detector and view directions. Specially, for the statistical property, the sparse non-local method was used. For the correlation property, separate convolution was applied in two directions respectively. Experimental results showed the proposed model outperform the CNN model without prior knowledge. Results also demonstrate our insight of applying human knowledge strength the power of machine learning in medical imaging field.

Colorectal cancer (CRC) remains one of the leading causes of cancer deaths today. Since precancerous colorectal polyps slowly progress into cancer, screening methods are highly effective in reducing the overall mortality rate of CRC by removing them before developing into later stages. The two current screening modalities, optical colonoscopy (OC) and virtual tomographic colonography (CTC), are both effective at detecting polyps, but the diagnostic performance from each has lagged behind detection. In this paper, we propose a texture analysis-based approach for integrating the complementary information from these two screening modalities. We use a set of well-established texture features including gray-level co-occurrence matrix features, gray-level run-length matrix features, local binary pattern features, first order histogram features, and more. To maximize the amount of textures extracted to examine the tissue heterogeneities between polyp pathologies, these textures are also computed on the higher order derivative images of the CTC polyp images and on the Hue/Saturation/Value color-space of the optical polyp images. The dataset used consisted of 165 polyps taken from 113 patients who underwent standard clinical prep prior to the procedures. Patients first had the CTC scan followed by the OC procedure, where the polyps where registered between imaging modalities and were pathologically confirmed for ground truth. Using a random forest classifier with a greedy feature selection algorithm, we find that the combination of using both CTC and OC texture features can improve the diagnostic performance by area under the receiver operating characteristic (AUC) score by upwards of 3%.

Photon-counting spectral computed tomography (PCCT) reconstructs multiple energy-channel images to describe the same object, where there exists a strong correlation among all channels. In addition, reconstruction of each energychannel image suffers photon count starving problem. To make full use of the correlation among different channels to suppress the data noise and enhance the tissue texture in reconstructing each energy-channel image, this paper proposed a tensor convolutional neural network (TCNN) architecture to learn a tissue-specific texture prior for PCCT reconstruction. Specifically, we first model the spatial texture prior information in each individual channel using a convolution neural network, and then extract the correlation information among different energy channels by merging the multi-channel networks. Finally, we integrate the TCNN as a prior into Bayesian reconstruction framework. To evaluate the tissue texture preserving performance of the proposed method for each channel, a vivid clinical phantom which can simulate the real tissue textures was employed. The improvement associated with TCNN is remarkable relative to simultaneous algebraic reconstruction technique (SART) and tensor dictionary learning (TDL) based reconstruction. The proposed method produced promising results in terms of not only preserving texture feature but also suppressing image noise in each channel. The proposed method outperforms the competing methods in both visual inspection and quantitative indexes of root mean square error (RMSE), peak signal to noise ratio (PSNR), structural similarity (SSIM) and feature similarity (FSIM).

Deep learning such as Convolutional Neural Network (CNN) has demonstrated its superior in the field of image analysis. However, in the medical imaging field, deep learning faces more challenges for tumor classification in computer-aided diagnosis due to uncertainties of lesions including their size, scaling factor, rotation, shapes, etc. Thus, instead of feeding raw images, texture-based CNN model has been designed to classify the objects with their good attributes. For example, gray level co-occurrence matrix (GLCM) can be chosen as the descriptor of the texture pattern for many good properties such as uniform size, shape invariance, scaling invariance. However, there are many different texture metrics to measure the different texture patterns. Thus, an effective and efficient integration model is essential to further improve the classification performance from different texture patterns. In this paper, we proposed a multi-channel texture-based CNN model to effectively integrate intensity, gradient and curvature texture patterns together for differentiating the malignant from benign polyps. Performance was evaluated by the merit of area under the curve of receiver operating characteristics (AUC). Around 0.3~4.8% improvement has been observed by combining different texture patterns together. Finally, classification performance of AUC=86.7% has been achieved for a polyp mass dataset of 87 samples, which obtains 1.8% improvement compared with a state-of-the-art method. The results indicate that texture information from different metrics could be fused and classified with a better classification performance. It also sheds lights that data integration is important and indispensable to pursuit improvement in classification task.

This study explores an automatic diagnosis method to predict unnecessary nodule biopsy from a small, unbalanced, and pathologically proven database. The automatic diagnosis method is based on a convolutional neural network (CNN) model. Because of the small and unbalanced samples, the presented method aims to improve the transfer learning capability via the VGG16 architecture and optimize the related transfer learning parameters. For comparison purpose, a traditional machine learning method is implemented, which extracts the texture features and classifies the features by support vector machine (SVM). The database includes 68 biopsied nodules, 16 are pathologically proven benign and the remaining 52 are malignant. To consider the volumetric data by the CNN model, each image slice from each nodule volume is selected randomly until all image slices of each nodule are utilized. The leave-one-out and 10-folder cross validations are applied to train and test the randomly selected 68 image slices (one image slice from one nodule) in each experiment, respectively. The averages over all the experimental outcomes are the final results. The experiments revealed that the features from both the medical and the natural images share the similarity of focusing on simpler and less-abstract objects, leading to the conclusion that not the more the transfer convolutional layers, the better the classification results. Transfer learning from other larger datasets can supply additional information to small and unbalanced datasets to improve the classification performance. The presented method has shown the potential to adapt CNN architecture to improve the prediction of unnecessary nodule biopsy from small, unbalanced, and pathologically proven volumetric dataset.

Additional file 1. Primary parameters of the imaging sequences and the details of the feature information.

Background Non-invasive discrimination between lung squamous cell carcinoma (LUSC) and lung adenocarcinoma (LUAD) subtypes of non-small-cell lung cancer (NSCLC) could be very beneficial to the patients unfit for the invasive diagnostic procedures. The aim of this study was to investigate the feasibility of utilizing the multimodal magnetic resonance imaging (MRI) radiomics and clinical features in classifying NSCLC. This retrospective study involved 148 eligible patients with postoperative pathologically confirmed NSCLC. The study was conducted in three steps: (1) feature extraction was performed using the online freely available package with the multimodal MRI data; (2) feature selection was performed using the Student’s t test and support vector machine (SVM)-based recursive feature elimination method with the training cohort (n = 100), and the performance of these selected features was evaluated using both the training and the validation cohorts (n = 48) with a non-linear SVM classifier; (3) a Radscore model was then generated using logistic regression algorithm; (4) Integrating the Radscore with the semantic clinical features, a radiomics–clinical nomogram was developed, and its overall performance was evaluated with both cohorts. Results Thirteen optimal features achieved favorable discrimination performance with both cohorts, with area under the curve (AUC) of 0.819 and 0.824, respectively. The radiomics–clinical nomogram integrating the Radscore with the independent clinical predictors exhibited more favorable discriminative power, with AUC improved to 0.901 and 0.872 in both cohorts, respectively. The Hosmer–Lemeshow test and decision curve analysis results furtherly showed good predictive precision and clinical usefulness of the nomogram. Conclusion Non-invasive histological subtype stratification of NSCLC can be done favorably using multimodal MRI radiomics features. Integrating the radiomics features with the clinical features could further improve the performance of the histological subtype stratification in patients with NSCLC.

Localizing and characterizing clinically-significant lung nodules, a potential precursor to lung cancer, at the lowest achievable radiation dose is demanded to minimize the stochastic radiation effects from x-ray computed tomography (CT). A minimal dose level is heavily dependent on the image reconstruction algorithms and clinical task, in which the tissue texture always plays an important role. This study aims to investigate the dependence through a task-based evaluation at multiple dose levels and variable textures in reconstructions with prospective patient studies. 133 patients with a suspicious pulmonary nodule scheduled for biopsy were recruited and the data was acquired at120kVp with three different dose levels of 100, 40 and 20mAs. Three reconstruction algorithms were implemented: analytical filtered back-projection (FBP) with optimal noise filtering; statistical Markov random field (MRF) model with optimal Huber weighting (MRF-H) for piecewise smooth reconstruction; and tissue-specific texture model (MRF-T) for texture preserved statistical reconstruction. Experienced thoracic radiologists reviewed and scored all images at random, blind to the CT dose and reconstruction algorithms. The radiologists identified the nodules in each image including the 133 biopsy target nodules and 66 other non-target nodules. For target nodule characterization, only MRF-T at 40mAs showed no statistically significant difference from FBP at 100mAs. For localizing both the target nodules and the non-target nodules, some as small as 3mm, MRF-T at 40 and 20mAs levels showed no statistically significant difference from FBP at 100mAs, respectively. MRF-H and FBP at 40 and 20mAs levels performed statistically differently from FBP at 100mAs. This investigation concluded that (1) the textures in the MRF-T reconstructions improves both the tasks of localizing and characterizing nodules at low dose CT and (2) the task of characterizing nodules is more challenging than the task of localizing nodules and needs more dose or enhanced textures from reconstruction.

Accurate segmentation and volumetric analysis of colon wall is essential to advance computer-aided detection (CAD) of colonic polyps in computed tomography colonography (CTC). Due to their limited geometric information, detection of flat polyps is very difficult in both optical colonoscopy and CTC. In this paper, we present a new framework of segmentation and volumetric analysis of colon wall for improving detection of flat polyps. First, partial volume (PV) effects around the inner mucous membrane of the colon were reserved through our PV based electronic colon cleansing. PV information was further used to guide colon wall segmentation as well as to establish the starting point of iso-potential surfaces for colon wall thickness measures. Then, we employed a dual level set competition model to simultaneously segment both inner and outer colon wall by taking into account the mutual interference between two borders. We further conducted volumetric analysis of the dynamic colon wall information and built four layer of iso-potential surfaces which represent the intrinsic anatomical information of colon wall. We built a unique point-to-point path starting from the very beginning of the mucous membrane of the colon. As flat polyps are plaque-like lesions raised less than 3mm from the colonic mucosa layer, inclusion of PV effects shall bring us the fine information about flat polyps, thus improving the detection performance. The proposed framework was validated on patient CTC scans with flat polyps. Experimental results demonstrated that the framework is very promising towards detection of colonic flat polyps via CTC.

Clinical colonoscopy is the gold standard for polyp detection and resection in clinic. A main challenge in the polyp identification by deep learning is the limited patients number. In this paper, we discussed the usage of various image layers which provide and emphasize different image information in the polyp recognition and polyp classification. The results showed that comparing with the intensity image in RGB color space, the gradient images and images in chromaticity color space may provide more critical character to the deep learning model, and achieve a better performance with small training dataset.