Abstracted/ Indexed in: Ulrich's International Periodical Directory, Google Scholar, SCIRUS, Genamics JournalSeek, EBSCO Information Services
Quarterly published in print and online "Inventi Impact: Biomedical Imaging" publishes high quality unpublished as well as high impact pre-published research and reviews catering to the needs of researchers and professionals from medical as well as engineering fields. The journal covers fundamental and translational research focused on medical imaging yielding to early detection, diagnostics, and therapy of diseases, as well as of understanding the life sciences. Areas included are: Imaging physics, Tomographic reconstruction algorithms (e.g. CT and MRI), Image processing, Picture archiving and communications systems (PACS), Image perception and observer performance, Ultrasonic imaging, Image-guided procedures etc.
Background Head and neck squamous cell carcinoma (HNSCC) represents the 6th leading cancer worldwide. In
most cases, patients present a locally advanced disease at diagnosis and non-surgical curative treatment is considered
the standard of care. Nowadays, [18F]FDG PET/CT is a validated tool in post-treatment evaluation, with a high level of
evidence. However, to standardize imaging response, several visual scales have been proposed with none of them
approved yet. The study’s aim is a head-to-head comparison between the diagnostic performance of the Hopkins
criteria, the Deauville score, and the new proposed Cuneo score, to establish their prognostic role. Secondly, we investigate
the possible value of semiquantitative analysis, evaluating SUVmax and ΔSUVmax of the lymph node with the
highest uptake on the restaging PET scan. Moreover, we also considered morphological features using the product of
diameters measured on the co-registered CT images to assess the added value of hybrid imaging.
Methods We performed a retrospective analysis on histologically proven HNSCC patients who underwent baseline
and response assessment [18F]FDG PET/CT. Post-treatment scans were reviewed according to Hopkins, Deauville, and
Cuneo criteria, assigning a score to the primary tumor site and lymph nodes. A per-patient final score for each scale
was chosen, corresponding to the highest score between the two sites. Diagnostic performance was then calculated
for each score considering any evidence of locoregional progression in the first 3 months as the gold standard. Survival
analysis was performed using the Kaplan–Meier method. SUVmax and its delta, as well as the product of diameters
of the lymph node with the highest uptake at post-treatment scan, if present, were calculated.
Results A total of 43 patients were finally included in the study. Sensitivity, specificity, PPV, NPV, and accuracy were
87%, 86%, 76%, 92%, and 86% for the Hopkins score, whereas 93%, 79%, 70%, 96%, and 84% for the Deauville score,
respectively. Conversely, the Cuneo score reached the highest specificity and PPV (93% and 78%, respectively) but the
lowest sensitivity (47%), NPV (76%), and accuracy (77%). Each scale significantly correlated with PFS and OS. The ROC
analysis of the combination of SUVmax and the product of diameters of the highest lymph node on the restaging PET
scan reached an AUC of 0.822. The multivariate analysis revealed the Cuneo criteria and the product of diameters as
prognostic factors for PFS.
Conclusions Each visual score statistically correlated with prognosis thus demonstrating the reliability of point-scale
criteria in HNSCC. The novel Cuneo score showed the highest specificity, but the lowest sensibility compared to Hopkins
and Deauville criteria. Furthermore, the combination of PET data with morphological features could support the
evaluation of equivocal cases....
Objectives: To measure phosphorus metabolites in human parotid glands by\n31P-MRS using three-dimensional chemical-shift imaging (3D-CSI), and ascertain\nwhether this method can capture changes in adenosine triphosphate\n(ATP) and phosphocreatine (PCr) levels due to saliva secretion. Study Design:\nThe parotid glands of 20 volunteers were assessed by 31P-MRS using\n3D-CSI on 3T MRI. After obtaining a first (baseline) measurement, the participants\ntook vitamin-C tablets and measurements were obtained twice\nmore, in a continuous manner....................
The registration of intraoperative ultrasound (US) images with preoperative magnetic resonance (MR) images is a challenging\r\nproblem due to the difference of information contained in each image modality. To overcome this difficulty, we introduce a new\r\nprobabilistic function based on the matching of cerebral hyperechogenic structures. In brain imaging, these structures are the\r\nliquid interfaces such as the cerebral falx and the sulci, and the lesions when the corresponding tissue is hyperechogenic. The\r\nregistration procedure is achieved by maximizing the joint probability for a voxel to be included in hyperechogenic structures in\r\nboth modalities. Experiments were carried out on real datasets acquired during neurosurgical procedures. The proposed validation\r\nframework is based on (i) visual assessment, (ii) manual expert estimations , and (iii) a robustness study. Results show that\r\nthe proposed method (i) is visually efficient, (ii) produces no statistically different registration accuracy compared to manualbased\r\nexpert registration, and (iii) converges robustly. Finally, the computation time required by our method is compatible with\r\nintraoperative use....
Skull stripping in brain magnetic resonance imaging (MRI) is an essential step to analyze\nimages of the brain. Although manual segmentation has the highest accuracy, it is a time-consuming\ntask. Therefore, various automatic segmentation algorithms of the brain in MRI have been devised\nand proposed previously. However, there is still no method that solves the entire brain extraction\nproblem satisfactorily for diverse datasets in a generic and robust way. To address these shortcomings\nof existing methods, we propose the use of a 3D-UNet for skull stripping in brain MRI. The 3D-UNet\nwas recently proposed and has been widely used for volumetric segmentation in medical images due\nto its outstanding performance. It is an extended version of the previously proposed 2D-UNet, which\nis based on a deep learning network, specifically, the convolutional neural network. We evaluated\n3D-UNet skull-stripping using a publicly available brain MRI dataset and compared the results with\nthree existing methods (BSE, ROBEX, and Kleesiekâ??s method; BSE and ROBEX are two conventional\nmethods, and Kleesiekâ??s method is based on deep learning). The 3D-UNet outperforms two typical\nmethods and shows comparable results with the specific deep learning-based algorithm, exhibiting a\nmean Dice coefficient of 0.9903, a sensitivity of 0.9853, and a specificity of 0.9953....
Background: Magnetic resonance cholangiopancreatography (MRCP) is an established technique for the evaluation\nof intra- and extrahepatic bile ducts in patients with known or suspected hepatobiliary disease. However, the ideal\nacquisition and reconstruction plane for optimal bile duct evaluation with 3D technique has not been evaluated.\nThe purpose of our study was to compare different acquisition and reconstruction planes of 3D-MRCP for bile duct\nassessment.\nMethods: 34 patients (17f/17 m, mean age 41y) referred for MRCP were included in this prospective IRB-approved\nstudy. Respiratory-triggered 3D-T2w-MRCP sequences were acquired in coronal and axial plane. Coronal and axial\nMIP were reconstructed based on each dataset (resulting in two coronal and two axial MIP, respectively). Three\nreaders in two sessions independently assessed the MIP, regarding visualization of bile ducts and image quality.\nResults were compared (Wilcoxon test). Intra- and interobserver variability were calculated (kappa-statistic).\nResults: In case of coronal data acquisition, visualization of bile duct segments was significantly better on coronal\nreconstructed MIP images as compared to axial reconstructed MIP (p < 0.05). Regarding visualization, coronal MIP of\nthe coronal acquisition were equal to coronal MIP of the axial acquisition (p > 0.05). Image quality of coronal and\naxial datasets did not differ significantly. Intra- and interobserver agreement regarding bile duct visualization were\nmoderate to excellent (?-range 0.55-1.00 and 0.42-0.85, respectively).\nConclusions: The results of our study suggest that for visualization and evaluation of intra- and extrahepatic bile\nduct segments reconstructed images in coronal orientation are preferable. The orientation of the primary dataset\n(coronal or axial) is negligibl...
Background: Hepatic angiomyolipoma is a rare benign mesenchymal tumor. We report an unusual case of a\npatient with multiple hepatic angiomyolipomas exhibiting high 18 F-fluorodeoxyglucose (FDG) uptake.\nCase presentation: A 29-year-old man with a medical history of tuberous sclerosis was admitted to our hospital for\nfever, vomiting, and weight loss. Abdominal dynamic computed tomography revealed faint hypervascular hepatic\ntumors in segments 5 (67 mm) and 6 (10 mm), with rapid washout and clear borders; however, the tumors exhibited\nno definite fatty density. Abdominal magnetic resonance imaging revealed that the hepatic lesions were slightly\nhypointense on T1-weighted imaging, slightly hyperintense on T2-weighted imaging, and hyperintense with no\napparent fat component on diffusion-weighted imaging. FDG-positron emission tomography (PET) imaging revealed\nhigh maximum standardized uptake values (SUVmax) of 6.27 (Segment 5) and 3.22 (Segment 6) in the hepatic\ntumors. A right hepatic lobectomy was performed, and part of the middle hepatic vein was also excised. Histological\nexamination revealed that these tumors were characterized by the background infiltration of numerous inflammatory\ncells, including spindle-shaped cells, and a resemblance to an inflammatory pseudotumor. Immunohistochemical\nevaluation revealed that the tumor stained positively for human melanoma black-45. The tumor was therefore considered\nan inflammatory pseudotumor-like angiomyolipoma. Although several case reports of hepatic angiomyolipoma\nhave been described or reviewed in the literature, only 3 have exhibited high 18 F-FDG uptake on PET imaging\nwith SUVmax ranging from 3.3Ã¢â?¬â??4.0. In this case, increased 18 F-FDG uptake is more likely to appear, particularly if\nthe inflammation is predominant.\nConclusion: Although literature regarding the role of 18 F-FDG-PET in hepatic angiomyolipoma diagnosis is limited\nand the diagnostic value of 18 F-FDG-PET has not yet been clearly defined, the possibility that hepatic angiomyolipoma\nmight exhibit high 18 F-FDG uptake should be considered....
Purpose: To compare a deep learning model with a radiomics model in differentiating high-grade (LR-3, LR-4, LR-5)
liver imaging reporting and data system (LI-RADS) liver tumors from low-grade (LR-1, LR-2) LI-RADS tumors based on
the contrast-enhanced magnetic resonance images.
Methods: Magnetic resonance imaging scans of 361 suspected hepatocellular carcinoma patients were retrospectively
reviewed. Lesion volume segmentation was manually performed by two radiologists, resulting in 426 lesions
from the training set and 83 lesions from the test set. The radiomics model was constructed using a support vector
machine (SVM) with pre-defined features, which was first selected using Chi-square test, followed by refining using
binary least absolute shrinkage and selection operator (LASSO) regression. The deep learning model was established
based on the DenseNet. Performance of the models was quantified by area under the receiver-operating characteristic
curve (AUC), accuracy, sensitivity, specificity and F1-score.
Results: A set of 8 most informative features was selected from 1049 features to train the SVM classifier. The AUCs
of the radiomics model were 0.857 (95% confidence interval [CI] 0.816–0.888) for the training set and 0.879 (95% CI
0.779–0.935) for the test set. The deep learning method achieved AUCs of 0.838 (95% CI 0.799–0.871) for the training
set and 0.717 (95% CI 0.601–0.814) for the test set. The performance difference between these two models was
assessed by t-test, which showed the results in both training and test sets were statistically significant.
Conclusion: The deep learning based model can be trained end-to-end with little extra domain knowledge, while
the radiomics model requires complex feature selection. However, this process makes the radiomics model achieve
better performance in this study with smaller computational cost and more potential on model interpretability....
Previous studies have investigated both structural and functional brain networks via graph-theoretical methods. However, there\r\nis an important issue that has not been adequately discussed before: what is the optimal theoretical graph model for describing\r\nthe structural networks of human brain? In this paper, we perform a comparative study to address this problem. Firstly, largescale\r\ncortical regions of interest (ROIs) are localized by recently developed and validated brain reference system named Dense\r\nIndividualized Common Connectivity-based Cortical Landmarks (DICCCOL) to address the limitations in the identification of\r\nthe brain network ROIs in previous studies. Then, we construct structural brain networks based on diffusion tensor imaging (DTI)\r\ndata. Afterwards, the global and local graph properties of the constructed structural brain networks are measured using the stateof-\r\nthe-art graph analysis algorithms and tools and are further compared with seven popular theoretical graph models. In addition,\r\nwe compare the topological properties between two graph models, namely, stickiness-index-based model (STICKY) and scale-free\r\ngene duplication model (SF-GD), that have higher similarity with the real structural brain networks in terms of global and local\r\ngraph properties. Our experimental results suggest that among the seven theoretical graphmodels compared in this study, STICKY\r\nand SF-GD models have better performances in characterizing the structural human brain network....
Increasing evidence suggests the utility of magnetic resonance imaging (MRI) as an\nimportant technique for the diagnosis of Alzheimerâ??s disease (AD) and for predicting the onset of this\nneurodegenerative disorder. In this study, we present a sophisticated machine learning (ML) model\nof great accuracy to diagnose the early stages of AD. A total of 373 MRI tests belonging to 150 subjects.............
Background. Atypical vascular pattern is one of the most important features by differentiating between benign and malignant\npigmented skin lesions. Detection and analysis of vascular structures is a necessary initial step for skin mole assessment; it is a\nprerequisite step to provide an accurate outcomefor thewidely used 7-point checklist diagnostic algorithm. Methods. In this research\nwe present a fully automated machine learning approach for segmenting vascular structures in dermoscopy colour images.The UNet\narchitecture is based on convolutional networks and designed for fast and precise segmentation of images. After preprocessing\nthe images are randomly divided into 146516 patches of 64 Ã? 64 pixels each. Results. On the independent validation dataset\nincluding 74 images our implemented method showed high segmentation accuracy. For the U-Net convolutional neural network,\nan average DSC of 0.84, sensitivity 0.85, and specificity 0.81 has been achieved. Conclusion. Vascular structures due to small size\nand similarity to other local structures create enormous difficulties during the segmentation and assessment process. The use of\nadvanced segmentation methods like deep learning, especially convolutional neural networks, has the potential to improve the\naccuracy of advanced local structure detection....
� Copyright©2013. Inventi Journals Pvt.Ltd. All Right Reserved.