Computed Tomography Image Fusion Research Articles

Advanced hybrid attention-based deep learning network with heuristic algorithm for adaptive CT and PET image fusion in lung cancer detection

Lung cancer is one of the most deadly diseases in the world. Lung cancer detection can save the patient's life. Despite being the best imaging tool in the medical sector, clinicians find it challenging to interpret and detect cancer from Computed Tomography (CT) scan data. One of the most effective ways for the diagnosis of certain malignancies like lung tumours is Positron Emission Tomography (PET) imaging. So many diagnosis models have been implemented nowadays to diagnose various diseases. Early lung cancer identification is very important for predicting the severity level of lung cancer in cancer patients. To explore the effective model, an image fusion-based detection model is proposed for lung cancer detection using an improved heuristic algorithm of the deep learning model. Firstly, the PET and CT images are gathered from the internet. Further, these two collected images are fused for further process by using the Adaptive Dilated Convolution Neural Network (AD-CNN), in which the hyperparameters are tuned by the Modified Initial Velocity-based Capuchin Search Algorithm (MIV-CapSA). Subsequently, the abnormal regions are segmented by influencing the TransUnet3+. Finally, the segmented images are fed into the Hybrid Attention-based Deep Networks (HADN) model, encompassed with Mobilenet and Shufflenet. Therefore, the effectiveness of the novel detection model is analyzed using various metrics compared with traditional approaches. At last, the outcome evinces that it aids in early basic detection to treat the patients effectively.

Investigation of Medical Image Technology Based on Big Data Neuroscience in Exercise Rehabilitation.

The purpose of this article is to combine the functional information of CT images with the anatomical and soft tissue information of MRI through image fusion technology, providing more detailed information for rehabilitation treatment and thus providing a scientific basis for clinical applications and better training plans. In this paper, functional brain imaging technology combining CT (computed tomography) and MRI (magnetic resonance imaging) was used for image fusion, and SURF (accelerated robust feature) feature points of images were extracted. In this study, 40 patients with mild and moderate closed traumatic brain injury admitted to the rehabilitation department of a rehabilitation center from 2018 to 2022 were selected as the research objects. Compared with using only CT images and MRI images for brain injury diagnosis, the fusion image had a higher detection rate of abnormal brain injury diagnosis, with a detection rate of 97.5%. When using fused images for the diagnosis of abnormal brain injury, the patient's exercise rehabilitation effect was better. CT and MRI image fusion technology had a high diagnostic accuracy for brain injury, which could timely guide doctors in determining exercise rehabilitation plans and help improve the effectiveness of patient exercise rehabilitation.

Enhancing preoperative diagnosis of microvascular invasion in hepatocellular carcinoma: domain-adaptation fusion of multi-phase CT images

ObjectivesIn patients with hepatocellular carcinoma (HCC), accurately predicting the preoperative microvascular invasion (MVI) status is crucial for improving survival rates. This study proposes a multi-modal domain-adaptive fusion model based on deep learning methods to predict the preoperative MVI status in HCC.Materials and methodsFrom January 2008 to May 2022, we collected 163 cases of HCC from our institution and 42 cases from another medical facility, with each case including Computed Tomography (CT) images from the pre-contrast phase (PCP), arterial phase (AP), and portal venous phase (PVP). We divided our institution’s dataset (n=163) into training (n=119) and test sets (n=44) in an approximate 7:3 ratio. Additionally, we included cases from another institution (n=42) as an external validation set (test1 set). We constructed three single-modality models, a simple concatenated multi-modal model, two current state-of-the-art image fusion model and a multi-modal domain-adaptive fusion model (M-DAFM) based on deep learning methods. We evaluated and analyzed the performance of these constructed models in predicting preoperative MVI using the area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), and net reclassification improvement (NRI) methods.ResultsIn comparison with all models, M-DAFM achieved the highest AUC values across the three datasets (0.8013 for the training set, 0.7839 for the test set, and 0.7454 for the test1 set). Notably, in the test set, M-DAFM’s Decision Curve Analysis (DCA) curves consistently demonstrated favorable or optimal net benefits within the 0-0.65 threshold probability range. Additionally, the Net Reclassification Improvement (NRI) values between M-DAFM and the three single-modal models, as well as the simple concatenation model, were all greater than 0 (all p < 0.05). Similarly, the NRI values between M-DAFM and the two current state-of-the-art image fusion models were also greater than 0. These findings collectively indicate that M-DAFM effectively integrates valuable information from multi-phase CT images, thereby enhancing the model’s preoperative predictive performance for MVI.ConclusionThe M-DAFM proposed in this study presents an innovative approach to improve the preoperative predictive performance of MVI.

A three-layer decomposition method based on structural texture perception for fusion of CT and MRI images

The fusion of computed tomography (CT) images and magnetic resonance imaging (MRI) images has made essential contribution to clinical diagnosis because of its ability of complementary visual information enhancement and redundancy elimination. However, some methods that involve upsampling and downsampling operations may lose information during image processing, which affects the fusion results. In this paper, a medical image fusion algorithm based on structural texture perception is proposed. The proposed method demonstrates enhanced performance in preserving both detailed texture information and energy information of source images. First, the source image is decomposed into a signal strength layer, a base layer, and a texture layer based on the proposed three-layer decomposition framework. Then, the signal strength layers are fused using a saliency detection method based on iterative least squares. The texture layer is fused using the principle of spatial frequency maximization. For the fusion of the base layer, a non-linear function is designed to calculate the fusion weights. Finally, the final fusion result is obtained through image reconstruction. The proposed algorithm is compared with nine state-of-the-art fusion algorithms to verify its superiority. Experimental results show that the proposed method can effectively preserve the intensity information of CT images and the detailed texture of MRI images.

Using computed tomography fusion imaging as learning data for sonographer training in identification of left ventricular endocardial boundaries

BackgroundWe hypothesized that if computed tomography (CT) images were used as learning data, we could overcome volume underestimation by echocardiography, improving the accuracy of left ventricular (LV) volume measurements. MethodsWe utilized a fusion imaging modality consisting of echocardiography with superimposed CT images for 37 consecutive patients to identify the endocardial boundary. We compared LV volumes obtained with and without CT learning trace-lines (TLs). Furthermore, 3D echocardiography was used to compare LV volumes obtained with and without CT learning for endocardial identification. The mean difference between the echocardiography and CT-derived LV volumes and the coefficient of variation were compared pre- and post-learning. Bland–Altman analysis was used to assess the differences in LV volume (mL) obtained from the 2D pre-learning TL and 3D post-learning TL. ResultsThe post-learning TL was located closer to the epicardium than the pre-learning TL. This trend was particularly pronounced in the lateral and the anterior wall. The post-learning TL was along the inner side of the high echoic layer in the basal-lateral wall in the four-chamber view. CT fusion imaging determined that the difference in LV volume between 2D echocardiography and CT was small (−25.6 ± 14.4 mL before learning, −6.9 ± 11.5 mL after learning) and that CT learning improved the coefficient of variation (10.9 % before learning, 7.8 % after learning). Significant improvements were observed during 3D echocardiography; the difference in LV volume between 3D echocardiography and CT was slight (−20.5 ± 15.1 mL before learning, 3.8 ± 15.7 mL after learning), and the coefficient of variation improved (11.5 % before learning, 9.3 % after learning). ConclusionsDifferences between the LV volumes obtained using CT and echocardiography either disappeared or were reduced after CT fusion imaging. Fusion imaging is useful in training regimens for accurate LV volume quantification using echocardiography and may contribute to quality control.

Brain Tumor Classification Using Image Fusion and EFPA-SVM Classifier

An accurate and early diagnosis of brain tumors based on medical imaging modalities is of great interest because brain tumors are a harmful threat to a person’s health worldwide. Several medical imaging techniques have been used to analyze brain tumors, including computed tomography (CT) and magnetic resonance imaging (MRI). CT provides information about dense tissues, whereas MRI gives information about soft tissues. However, the fusion of CT and MRI images has little effect on enhancing the accuracy of the diagnosis of brain tumors. Therefore, machine learning methods have been adopted to diagnose brain tumors in recent years. This paper intends to develop a novel scheme to detect and classify brain tumors based on fused CT and MRI images. The proposed approach starts with preprocessing the images to reduce the noise. Then, fusion rules are applied to get the fused image, and a segmentation algorithm is employed to isolate the tumor region from the background to isolate the tumor region. Finally, a machine learning classifier classified the brain images into benign and malignant tumors. Computing statistical measures evaluate the classification potential of the proposed scheme. Experimental outcomes are provided, and the Enhanced Flower Pollination Algorithm (EFPA) system shows that it outperforms other brain tumor classification methods considered for comparison.

Cone Beam Computed Tomography Image Fusion with Cross Sectional Images for Percutaneous Renal Tumor Ablation: Preliminary Data.

Percutaneous ablative treatments in the kidney are now standard options for local cancer therapy. Multimodality image guidance, combining two 3D image sets, may improve procedural images and interventional strategies. We aimed to assess the value of intra-procedural cone beam computed tomography (CBCT) with magnetic resonance (MR) or CT imaging fusion technique in the guidance of percutaneous microwave ablation (MWA) of renal neoplasms. Fifteen patients (eight males, seven females, median age 65 years, median lesion size 20 mm) underwent percutaneous MWA for 15 renal tumors. All the procedures were performed in a dedicated angiography room setting; CBCT ablation planning capabilities included multimodality image fusion. Preoperative contrast-enhanced CT was available in 12 patients, whereas magnetic resonance imaging in the remaining. All patients were considered inoperable due to comorbidities, advanced age, and/or refusal to undergo surgery. Exclusion criteria were: tumors visible at unenhanced CBCT, metastatic disease, and uncorrected coagulopathy. Technical success and technical effectiveness were calculated. Procedural time, complications and recurrences were registered. MWA under CBCT-guidance with fusion technique was technically successful in 14 out of 15 cases (93%). The median procedural time was 45 min. No procedure-related complications were reported. No enhancing tissue was visualized in the area of ablation at 1-month follow-up. All 15 cases were recurrence-free at last follow-up assessment (median follow-up of 12 months); no cancer-specific deaths were registered. CBCT-CT/MR image fusion is technically feasible and safe in achieving correct targeting and complete ablation of renal lesions. This approach bears the potential to overcome most of the limitations of unenhanced CBCT guidance alone; larger series are needed to validate this technique.

Step-by-Step Stereotactic Radiotherapy Planning of Glomus Jugulare: A Guide to Radiation Oncologists—Dr Kanhu’s ROSE (Radiation Oncology from Simulation to Execution)

Background Glomus jugulare is a rare, slow-growing tumor that arise within the jugular foramen of the temporal bone. In the past, surgery was the primary modality of treatment for glomus Jugulare, but it leads to many complications and increased mortality. Radiotherapy was indicated in adjuvant setting in post-operative residual disease. But, with the advent of highly conformal radiation planning, stereotactic radiosurgery (SRS), is now one of the main modalities of radiation treatment in glomus jugulare. Objective To describe the procedural steps for radiation planning of SRS of glomus jugulare. Methods The step-by-step procedure for stereotactic planning of glomus jugulare has been described using a clinical scenario of glomus jugulare. Results The stereotactic radiation planning of glomus jugulare starts with the basic history and relevant clinical evaluation, that is, visual testing. Computed tomography (CT) scan and magnetic resonance imaging (MRI) of the brain is the imaging modality of choice. The radiation planning of glomus jugulare starts with CT simulation. MRI of brain should be done in the prescribed format to achieve uniformity in radiation planning. After CT and MRI image fusion, contouring of target, organs at risk (OAR) and radiation planning should be done. The plan evaluation includes target and OAR coverage index, conformity, homogeneity and gradient index, and beam arrangement. After radiation plan evaluation, treatment is delivered after quality assurance and dry run. Conclusion The paper highlights the sequential process of radiation planning for SRS in glomus jugulare—starting from simulation, planning, evaluation of plan, and treatment.

Where Position Matters—Deep-Learning–Driven Normalization and Coregistration of Computed Tomography in the Postoperative Analysis of Deep Brain Stimulation

IntroductionRecent developments in the postoperative evaluation of deep brain stimulation surgery on the group level warrant the detection of achieved electrode positions based on postoperative imaging. Computed tomography (CT) is a frequently used imaging modality, but because of its idiosyncrasies (high spatial accuracy at low soft tissue resolution), it has not been sufficient for the parallel determination of electrode position and details of the surrounding brain anatomy (nuclei). The common solution is rigid fusion of CT images and magnetic resonance (MR) images, which have much better soft tissue contrast and allow accurate normalization into template spaces. Here, we explored a deep-learning approach to directly relate positions (usually the lead position) in postoperative CT images to the native anatomy of the midbrain and group space. Materials and MethodsDeep learning is used to create derived tissue contrasts (white matter, gray matter, cerebrospinal fluid, brainstem nuclei) based on the CT image; that is, a convolution neural network (CNN) takes solely the raw CT image as input and outputs several tissue probability maps. The ground truth is based on coregistrations with MR contrasts. The tissue probability maps are then used to either rigidly coregister or normalize the CT image in a deformable way to group space. The CNN was trained in 220 patients and tested in a set of 80 patients. ResultsRigorous validation of such an approach is difficult because of the lack of ground truth. We examined the agreements between the classical and proposed approaches and considered the spread of implantation locations across a group of identically implanted subjects, which serves as an indicator of the accuracy of the lead localization procedure. The proposed procedure agrees well with current magnetic resonance imaging–based techniques, and the spread is comparable or even lower. ConclusionsPostoperative CT imaging alone is sufficient for accurate localization of the midbrain nuclei and normalization to the group space. In the context of group analysis, it seems sufficient to have a single postoperative CT image of good quality for inclusion. The proposed approach will allow researchers and clinicians to include cases that were not previously suitable for analysis.

Predictive Value of Ablative Margin Assessment After Microwave Ablation for Local Tumor Progression in Medium and Large Hepatocellular Carcinoma: Computed Tomography-Computed Tomography Image Fusion Method Versus Side-by-Side Method.

This study aimed to explore the feasibility and predictive value for local tumor progression (LTP) of the computed tomography (CT)-CT image fusion method versus side-by-side method to assess ablative margin (AM) in hepatocellular carcinoma ≥3 cm in diameter. We selected patients with hepatocellular carcinoma ≥3 cm in diameter who underwent microwave ablation and had complete tumor ablation. We used the CT-CT image fusion method and side-by-side method to assess AM separately and divided the lesions into 3 groups: group I, minimum ablative margin (min-AM) <0 mm (the ablation zone did not fully cover the tumor); group II, 0 mm ≤ min-AM <5 mm; and group III, min-AM ≥5 mm. A total of 71 patients involving 71 lesions were included. The κ coefficient for the agreement between the CT-CT image fusion method and the side-by-side method in assessing min-AM was 0.14 (P = 0.028). Cumulative LTP rate was significantly different between groups by min-AM from the CT-CT image fusion method (P < 0.05) but not by min-AM from the side-by-side method (P = 0.807). Seventeen of the 20 LTP lesions were located at min-AM on fused CT images, with consistency rate of 85%. Compared with the side-by-side method, the CT-CT image fusion method is more accurate in assessing the AM of eccentrically ablated lesions and shows better predictive value for LTP. The min-AM based on CT-CT image fusion assessment is an important influencing factor for LTP.

Intraoperative Fusion Imaging During Transcarotid Artery Revascularization

BackgroundTranscarotid artery revascularization (TCAR) with reverse-flow neuroprotection has emerged as an alternative to transfemoral carotid artery stenting and carotid endarterectomy. However, it requires fluoroscopic guidance, exposing patient and surgeon to radiation. Although computed tomography (CT) fusion-guided EVAR has been demonstrated to significantly decrease this radiation risk, not much is known about similar outcomes for TCAR. The purpose of this study is to evaluate outcomes at a single institution utilizing CT fusion-guided imaging during TCAR compared to regional TCAR cases in the Vascular Quality Initiative (VQI) registry without CT fusion imaging.MethodsA retrospective analysis was conducted of data collected from all patients undergoing TCAR with CT fusion-guided imaging (TCAR-F) at our hospital (Figure) and TCAR patients within the VQI database. Primary outcomes included total operative time, dose area product, fluoroscopy time, contrast use, and flow-reversal time. Demographics and preoperative risk factors were also assessed in both groups. Continuous outcomes were compared using Welch’s t test. Categorical outcomes were compared using Fisher’s exact test.ResultsA total of 30 TCAR-F cases (January 2019 to May 2022) at our institution were compared against the regional VQI dataset (n = 2,535). TCAR-F cases had lower dose area product (5.67 Gy.cm2 vs 93.1 Gy.cm2; P < .0001), fluoroscopic time (8.07 minutes vs 16.4 minutes; P < .0001), and contrast use (13.49 mL vs 76.7 mL; P < .0001) as compared to regional averages of the same. TCAR-F cases had longer total operative time (117.3 minutes vs 80.9 minutes; P < .0001) and flow-reversal time (14.4 minutes vs 11.7 minutes; P = .025) than regional cases.Conclusions BackgroundTranscarotid artery revascularization (TCAR) with reverse-flow neuroprotection has emerged as an alternative to transfemoral carotid artery stenting and carotid endarterectomy. However, it requires fluoroscopic guidance, exposing patient and surgeon to radiation. Although computed tomography (CT) fusion-guided EVAR has been demonstrated to significantly decrease this radiation risk, not much is known about similar outcomes for TCAR. The purpose of this study is to evaluate outcomes at a single institution utilizing CT fusion-guided imaging during TCAR compared to regional TCAR cases in the Vascular Quality Initiative (VQI) registry without CT fusion imaging. Transcarotid artery revascularization (TCAR) with reverse-flow neuroprotection has emerged as an alternative to transfemoral carotid artery stenting and carotid endarterectomy. However, it requires fluoroscopic guidance, exposing patient and surgeon to radiation. Although computed tomography (CT) fusion-guided EVAR has been demonstrated to significantly decrease this radiation risk, not much is known about similar outcomes for TCAR. The purpose of this study is to evaluate outcomes at a single institution utilizing CT fusion-guided imaging during TCAR compared to regional TCAR cases in the Vascular Quality Initiative (VQI) registry without CT fusion imaging. MethodsA retrospective analysis was conducted of data collected from all patients undergoing TCAR with CT fusion-guided imaging (TCAR-F) at our hospital (Figure) and TCAR patients within the VQI database. Primary outcomes included total operative time, dose area product, fluoroscopy time, contrast use, and flow-reversal time. Demographics and preoperative risk factors were also assessed in both groups. Continuous outcomes were compared using Welch’s t test. Categorical outcomes were compared using Fisher’s exact test. A retrospective analysis was conducted of data collected from all patients undergoing TCAR with CT fusion-guided imaging (TCAR-F) at our hospital (Figure) and TCAR patients within the VQI database. Primary outcomes included total operative time, dose area product, fluoroscopy time, contrast use, and flow-reversal time. Demographics and preoperative risk factors were also assessed in both groups. Continuous outcomes were compared using Welch’s t test. Categorical outcomes were compared using Fisher’s exact test. ResultsA total of 30 TCAR-F cases (January 2019 to May 2022) at our institution were compared against the regional VQI dataset (n = 2,535). TCAR-F cases had lower dose area product (5.67 Gy.cm2 vs 93.1 Gy.cm2; P < .0001), fluoroscopic time (8.07 minutes vs 16.4 minutes; P < .0001), and contrast use (13.49 mL vs 76.7 mL; P < .0001) as compared to regional averages of the same. TCAR-F cases had longer total operative time (117.3 minutes vs 80.9 minutes; P < .0001) and flow-reversal time (14.4 minutes vs 11.7 minutes; P = .025) than regional cases. A total of 30 TCAR-F cases (January 2019 to May 2022) at our institution were compared against the regional VQI dataset (n = 2,535). TCAR-F cases had lower dose area product (5.67 Gy.cm2 vs 93.1 Gy.cm2; P < .0001), fluoroscopic time (8.07 minutes vs 16.4 minutes; P < .0001), and contrast use (13.49 mL vs 76.7 mL; P < .0001) as compared to regional averages of the same. TCAR-F cases had longer total operative time (117.3 minutes vs 80.9 minutes; P < .0001) and flow-reversal time (14.4 minutes vs 11.7 minutes; P = .025) than regional cases. Conclusions

Fusion of CT images and clinical variables based on deep learning for predicting invasiveness risk of stage I lung adenocarcinoma.

To develop a novel multimodal data fusion model by incorporating computed tomography (CT) images and clinical variables based on deep learning for predicting the invasiveness risk of stage I lung adenocarcinoma that manifests as ground-glass nodules (GGNs) and compare the diagnostic performance of it with that of radiologists. A total of 1946 patients with solitary and histopathologically confirmed GGNs with maximum diameter less than 3cm were retrospectively enrolled. The training dataset containing 1704 GGNs was augmented by resampling, scaling, random cropping, and so forth, to generate new training data. A multimodal data fusion model based on residual learning architecture and two multilayer perceptron with attention mechanism combining CT images with patient general data and serum tumor markers was built. The distance-based confidence scores (DCS) were calculated and compared among multimodal data models with different combinations. An observer study was conducted and the prediction performance of the fusion algorithms was compared with that of the two radiologists by an independent testing dataset with 242 GGNs. Among the whole GGNs, 606 GGNs are confirmed as invasive adenocarcinoma (IA) and 1340 are non-IA. The proposed novel multimodal data fusion model combining CT images, patient general data, and serum tumor markers achieved the highest accuracy (88.5%), area under a ROC curve (0.957), F1 (81.5%), F1weighted (81.9%), and Matthews correlation coefficient (73.2%) for classifying between IA and non-IA GGNs, which was even better than the senior radiologist's performance (accuracy, 86.1%). In addition, the DCSs for multimodal data suggested that CT image had a stronger influence (0.9540) quantitatively than general data (0.6726) or tumor marker (0.6971). This study demonstrated that the feasibility of integrating different types of data including CT images and clinical variables, and the multimodal data fusion model yielded higher performance for distinguishing IA from non-IA GGNs.

Dual-layer spectral CT fusion imaging for lung biopsies: more accurate targets, diagnostic samplings, and biomarker information?

The increasingly widespread use of computed tomography (CT) has increased the number of detected lung lesions, which are then subjected to needle biopsy to obtain histopathological diagnosis. Obtaining high-quality biopsy specimens is fundamental for diagnosis and biomolecular characterisation that guide therapy decision-making. In order to obtain samples with high diagnostic potential, fusion imaging techniques, such as fusion between positron emission tomography and CT, have been introduced to target the biopsy where there more viable neoplastic cells can be sampled. Nowadays, dual-layer spectral CT represents a novel technology enabling an increased tissue characterisation. In particular, Z-effective images, i.e., colour-coded images based on the effective atomic number of tissue components, provide a higher level of discrimination than usual imaged based on x-ray attenuation in Hounsfield units and offer the potential of a better tissue characterisation. Our hypothesis is based on the future use of data provided by spectral CT, in particular by Z-effective images, as a guide for appropriate biopsy sampling for histopathological and biomolecular characterisation in the era of patient tailored-therapy.

A Novel MRI And CT Image Fusion Based on Discrete Wavelet Transform and Principal Component Analysis for Enhanced Clinical Diagnosis

A large percentage of healthcare resources, including imaging tools, like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) have been dedicated to the management of affected patients in this pandemic of Coronavirus disease 2019 (COVID-19). The diagnostic modalities in medical research are improving at a rapid pace with an objective to acquire maximum information with as little data as possible without any artifacts. That is where image fusion comes into the picture. It is a technique of merging source medical pictures to maximize the necessary information. CT is generally used for bony structures, whereas MRI is more appropriate for soft tissues. A fusion of MRI and CT images would lead to enhancement of the overall image quality while giving comprehensive information, at the same time artifacts are also eliminated. Image fusion methods are applied in medical science and various other sectors. Several image processing techniques are used in medical diagnostics, like Principal Component analysis (PCA), Intensity-Hue-Saturation, Discrete Wavelet Transform (DWT), and others. This study suggests an image fusion algorithm utilising the principal component averaging and the DWT along with the performance analysis of the fusion of the MRI and CT images of brain. The technique used in our study significantly enhances the image quality in terms of various fusion performance measures that helps the medical practitioners to diagnose any infection and aids in its treatment.&#x0D;

The Role of Fusion Technique of Computed Tomography and Non-echo-planar Diffusion-weighted Imaging in the Evaluation of Surgical Cholesteatoma Localization.

Objective:In recent years, the fusion of computed tomography (CT) and non-echo-planar diffusion-weighted magnetic resonance imaging (non- EPI DWI) has been preferred in cholesteatoma localizations. This study aimed to investigate the role of CT and non-EPI DWI fusion imaging in cholesteatoma localizations.Methods:This retrospective study included 39 patients who underwent chronic otitis media operation [mean age of 35.10±15.33 years (18-67 years), 64.1% female, and 35.9% male] and had preoperative high-resolution temporal bone CT and non-EPI DWI examinations. Images were sent to the Advantage Workstation VolumeShare 7 for fusion. These selected images were fused on the workstation and were manually corrected by the radiologist. The sensitivity, specificity, positive and negative predictive values, and diagnostic accuracies of fused images of CT and non-EPI DWI were evaluated according to anatomic cholesteatoma localizations based on surgical data.Results:The sensitivity, specificity, positive and negative predictive values, and diagnostic accuracies of non-EPI DWI for detecting cholesteatomas were 97.14%, 75.00%, 97.14%, 75.00%, and 94.87%, respectively. Three true-negative, one false-positive, and one false-negative case were observed according to surgical results in detecting the presence of a cholesteatoma with non-EPI DWI. Moderate agreement was determined between the surgical and radiological results in detecting the presence of a cholesteatoma (k=0.721). Detecting the lesion of localization on the fused images compared to surgical found an almost perfect agreement in the mastoid antrum (k=0.948), strong agreement in the hypotympanum and mastoid cells (k=0.894), moderate agreement in the epitympanum (k=0.653), and weak agreement in those in the mesotympanum (k=0.540).Conclusions:The surgeons’ determinations are supported by the guidance of temporal CT and non-EPI DWI fused images. Therefore, preferring the fusion imaging technique could increase the quality of life by reducing unnecessary operations.

Recent Advances in the Clinical Application of Adrenal Vein Sampling.

We reviewed clinical research investigating the applications of adrenal vein sampling (AVS). AVS could be applied not only to primary aldosteronism (PA) but also to other endocrine diseases, such as adrenocorticotropic hormone (ACTH) independent Cushing syndrome (AICS) and hyperandrogenemia (HA). However, the AVS protocol requires improvements to increase its success rate. Using the computed tomography image fusion, coaxial guidewire technique, and fast intraprocedural cortisol testing (CCF) technique could improve the success rate of catheterization in AVS for PA. ACTH loading could be considered in medical centers with a low selectivity of AVS for PA but is not essential in those with mature AVS technology. The continuous infusion method should be recommended for ACTH stimulation in AVS for PA to reduce adverse events. AVS has not been routinely recommended before management decisions in AICS, but several studies verified that AVS was useful in finding out the source of excess cortisol, especially for distinguishing unilateral from bilateral disease. However, it is necessary to reassess the results of AVS in AICS with the use of reference hormones to fully normalize cortisol levels. In addition, it is essential to determine the optimal model that combines AVS results and mass size to guide the selection of surgical plans, including identifying the dominant gland and presenting the option of staged adrenalectomy, to minimize the impact of bilateral resection. For HA, AVS combined with ovarian intravenous sampling to locate excess androgens could be considered when imaging results are equivocal.

Radiofrequency ablation using real-time ultrasonography-computed tomography fusion imaging improves treatment outcomes for T1a renal cell carcinoma: Comparison with laparoscopic partial nephrectomy.

PurposeTo determine whether real-time ultrasonography–computed tomography (US-CT) fusion imaging can improve technical feasibility versus B-mode US and provide comparable outcomes of radiofrequency ablation (RFA) for T1a renal cell carcinoma (RCC) compared with laparoscopic partial nephrectomy (LPN).Materials and MethodsBetween June 2013 and August 2016, biopsy- or pathologically confirmed stage T1a RCCs were retrospectively reviewed. Of these, 39 cases were included in the RFA group, and 46 cases were included in the LPN group. In the RFA group, we evaluated tumor visibility and technical feasibility before RFA on a four-point scale on B-mode US and US-CT fusion images. After RFA, hospital days, creatinine value, complications, and disease-free survival rate were compared between the two groups. All results were analyzed by use of the Mann–Whitney U-test and Kaplan–Meier method.ResultsCompared with B-mode US alone, real-time US-CT fusion significantly improved the tumor visibility score and overall mean technical feasibility grade (p<0.001). The 5-year disease-free survival rate was 97.4% and 97.8% in the RFA and LPN groups, respectively, and there was no statistically significant difference between groups (p=0.1). Mean periprocedural creatinine levels were significantly lower in the RFA group than in the LPN group. The number of hospital days was shorter in the RFA group. Minor complications were present in 5.1% of the RFA group and 13.0% of the LPN group, with no major complications.ConclusionsUS-CT fusion-image-guided RFA improved tumor visibility scores and overall mean technical validity and resulted in a comparable disease-free survival rate to LPN.

Analysis of Discrete Wavelet Transforms Variants for the Fusion of CT and MRI Images

Background: Medical image fusion methods are applied to a wide assortment of medical fields, for example, computer-assisted diagnosis, telemedicine, radiation treatment, preoperative planning, and so forth. Computed Tomography (CT) is utilized to scan the bone structure, while Magnetic Resonance Imaging (MRI) is utilized to examine the soft tissues of the cerebrum. The fusion of the images obtained from the two modalities helps radiologists diagnose the abnormalities in the brain and localize the position of the abnormality concerning the bone. Methods: Multimodal medical image fusion procedure contributes to the decrease of information vulnerability and improves the clinical diagnosis exactness. The motive is to protect salient features from multiple source images to produce an upgraded fused image. The CT-MRI image fusion study made it conceivable to analyze the two modalities straightforwardly. Several states of the art techniques are available for the fusion of CT &amp; MRI images. The discrete wavelet transform (DWT) is one of the widely used transformation techniques for the fusion of images. However, the efficacy of utilization of the variants of wavelet filters for the decomposition of the images, which may improve the image fusion quality, has not been studied in detail. Therefore the objective of this study is to assess the utility of wavelet families for the fusion of CT and MRI images. In this paper investigation on the efficacy of 8 wavelet families (120 family members) on the visual quality of the fused CT &amp; MRI image has been performed. Further, to strengthen the quality of the fused image, two quantitative performance evaluation parameters, namely classical and gradient information, have been calculated. Results: Experimental results demonstrate that amongst the 120 wavelet family members (8 wavelet families), db1, rbio1.1, and Haar wavelets have outperformed other wavelet family members in both qualitative and quantitative analysis. Conclusion: Quantitative and qualitative analysis shows that the fused image may help radiologists diagnose the abnormalities in the brain and localize the position of the abnormality concerning the bone more easily. For further improvement in the fused results, methods based on deep learning may be tested in the future.

Fusion of CT and MR Liver Images Using Multiresolution Analysis Methods

There are various medical imaging techniques such as Computed Tomography (CT) and Magnetic Resonance (MR) techniques. Both techniques give complex features of the region to be imaged. This study proposes an approach that uses Multiresolution Analysis (MRA) methods to fuse CT and MR liver images to obtain as detailed images as possible for medical diagnostic purposes. The transform coefficients are obtained by applying MRA methods to the images. Images are combined by applying 3 different fusion rules to these transform coefficients. Peak Signal to Noise Rate (PSNR), Structural Similarity Index Measure (SSIM) and Mean Square Error (MSE) values are calculated to evaluate the fused images. When comparing the methods, the best result was obtained using complex-valued curvelet transform.

Utilization of image interpolation and fusion in brain tumor segmentation.

Brain tumor is a mass of anomalous cells in the brain. Medical imagining techniques have a vital role in the diagnosis of brain tumors. Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) techniques are the most popular techniques to localize the tumor area. Brain tumor segmentation is very important for the diagnosis of tumors. In this paper, we introduce a framework to perform brain tumor segmentation, and then localize the region of the tumor, accurately. The proposed framework begins with the fusion of MR and CT images by the Non-Sub-Sampled Shearlet Transform (NSST) with the aid of the Modified Central Force Optimization (MCFO) to get the optimum fusion result from the quality metrics perspective. After that, image interpolation is applied to obtain a High-Resolution (HR) image from the Low-Resolution (LR) ones. The objective of the interpolation process is to enrich the details of the fusion result prior to segmentation. Finally, the threshold and the watershed segmentation are applied sequentially to localize the tumor region, clearly. The proposed framework enhances the efficiency of segmentation to help the specialists diagnose brain tumors.