A radiomics approach to the diagnosis of femoroacetabular impingement.

Introduction: Femoroacetabular Impingement (FAI) is a hip pathology characterized by impingement of the femoral head-neck junction against the acetabular rim, due to abnormalities in bone morphology. FAI is normally diagnosed by manual evaluation of morphologic features on magnetic resonance imaging (MRI). In this study, we assess, for the first time, the feasibility of using radiomics to detect FAI by automatically extracting quantitative features from images. Material and methods: 17 patients diagnosed with monolateral FAI underwent pre-surgical MR imaging, including a 3D Dixon sequence of the pelvis. An expert radiologist drew regions of interest on the water-only Dixon images outlining femur and acetabulum in both impingement (IJ) and healthy joints (HJ). 182 radiomic features were extracted for each hip. The dataset numerosity was increased by 60 times with an ad-hoc data augmentation tool. Features were subdivided by type and region in 24 subsets. For each, a univariate ANOVA F-value analysis was applied to find the 5 features most correlated with IJ based on p-value, for a total of 48 subsets. For each subset, a K-nearest neighbor model was trained to differentiate between IJ and HJ using the values of the radiomic features in the subset as input. The training was repeated 100 times, randomly subdividing the data with 75%/25% training/testing. Results: The texture-based gray level features yielded the highest prediction max accuracy (0.972) with the smallest subset of features. This suggests that the gray image values are more homogeneously distributed in the HJ in comparison to IJ, which could be due to stress-related inflammation resulting from impingement. Conclusions: We showed that radiomics can automatically distinguish IJ from HJ using water-only Dixon MRI. To our knowledge, this is the first application of radiomics for FAI diagnosis. We reported an accuracy greater than 97%, which is higher than the 90% accuracy for detecting FAI reported for standard diagnostic tests (90%). Our proposed radiomic analysis could be combined with methods for automated joint segmentation to rapidly identify patients with FAI, avoiding time-consuming radiological measurements of bone morphology.

Relevance of apparent diffusion coefficient features for a radiomics-based prediction of response to induction chemotherapy in sinonasal cancer.

In this paper, several radiomics-based predictive models of response to induction chemotherapy (IC) in sinonasal cancers (SNCs) are built and tested. Models were built as a combination of radiomic features extracted from three types of MRI images: T1-weighted images, T2-weighted images and apparent diffusion coefficient (ADC) maps. Fifty patients (aged 54 ± 12 years, 41 men) were included in this study. Patients were classified according to their response to IC (25 responders and 25 nonresponders). Not all types of images were acquired for all of the patients: 49 had T1-weighted images, 50 had T2-weighted images and 34 had ADC maps. Only in a subset of 33 patients were all three types of image acquired. Eighty-nine radiomic features were extracted from the MRI images. Dimensionality reduction was performed by using principal component analysis (PCA) and by selecting only the three main components. Different algorithms (trees ensemble, K-nearest neighbors, support vector machine, naïve Bayes) were used to classify the patients as either responders or nonresponders. Several radiomic models (either monomodality or multimodality obtained by a combination of T1-weighted, T2-weighted and ADC images) were developed and the performance was assessed through 100 iterations of train and test split. The area under the curve (AUC) of the models ranged from 0.56 to 0.78. Trees ensemble, support vector machine and naïve Bayes performed similarly, but in all cases ADC-based models performed better. Trees ensemble gave the highest AUC (0.78 for the T1-weighted+T2-weighted+ADC model) and was used for further analyses. For trees ensemble, the models based on ADC features performed better than those models that did not use those features (P < 0.02 for one-tail Hanley test, AUC range 0.68-0.78 vs 0.56-0.69) except the T1-weighted+ADC model (AUC 0.71 vs 0.69, nonsignificant differences). The results suggest the relevance of ADC-based radiomics for prediction of response to IC in SNCs.

Seeking a Widely Adoptable Practical Standard to Estimate Signal-to-Noise Ratio in Magnetic Resonance Imaging for Multiple-Coil Reconstructions.

BACKGROUND: Signal-to-noise ratio (SNR) is used to evaluate the performance of magnetic resonance (MR) imaging systems. Accurate and consistent estimations are needed to routinely use SNR to assess coils and image reconstruction techniques. PURPOSE: To identify a reliable and practical method for SNR estimation in multiple-coil reconstructions. STUDY TYPE: Technical evaluation and comparison. SUBJECTS/PHANTOM: A uniform phantom and four healthy volunteers: 35, 38, 39 y/o males, 25 y/o female. FIELD STRENGTH/SEQUENCE: Two-dimensional multislice gradient-echo pulse sequence at 3 T and 7 T. ASSESSMENT: Reference-standard SNR was calculated from 100 multiple replicas. Six SNR methods were compared against it: difference image (DI), analytic array combination (AC), pseudo-multiple-replica (PMR), generalized pseudo-replica (GPR), smoothed image subtraction (SIS), and DI with temporal instability correction (TIC). The assessment was repeated for different multiple-coil reconstructions. STATISTICAL TESTS: SNR methods were evaluated in terms of relative deviation (RD) and normalized mutual information (NMI) with respect to the reference-standard, using a linear regression (0.05 significance level) to assess how different factors affect accuracy. RESULTS: Average RD (phantom) for DI, AC, PMR, GPR, SIS, and TIC was 7.9%, 6%, 6.7%, 10.1%, 40%, and 14.6%, respectively. RD increased with acceleration. SNR maps with AC were the most similar to the reference standard (NMI = 0.358). Considering all brain regions of interest, average RD for all SNR methods varied 96% among volunteers but remained approximately 10% for AC, PMR, and GPR, whereas it was more than 30% for DI, SIS, and TIC. RD was mainly affected by image reconstruction (beta = 12) for AC and SNR entropy for SIS (beta = 19). DATA CONCLUSION: AC provided accurate and robust SNR estimation. PMR and GPR are more generally applicable than AC. DI and TIC should be used only at low acceleration factors, when an additional noise-only scan cannot be acquired. SIS is a single-acquisition alternative to DI for generalized autocalibrating partial parallel acquisition (GRAPPA) reconstructions. EVIDENCE LEVEL: 1 TECHNICAL EFFICACY: Stage 1.

Retrospective study of late radiation-induced damages after focal radiotherapy for childhood brain tumors.

PURPOSE: To study a robust and reproducible procedure to investigate a relation between focal brain radiotherapy (RT) low doses, neurocognitive impairment and late White Matter and Gray Matter alterations, as shown by Diffusion Tensor Imaging (DTI), in children. METHODS AND MATERIALS: Forty-five patients (23 males and 22 females, median age at RT 6.2 years, median age at evaluations 11.1 years) who had received focal RT for brain tumors were recruited for DTI exams and neurocognitive tests. Patients' brains were parceled in 116 regions of interest (ROIs) using an available segmented atlas. After the development of an ad hoc, home-made, multimodal and highly deformable registration framework, we collected mean RT doses and DTI metrics values for each ROI. The pattern of association between cognitive scores or domains and dose or DTI values was assessed in each ROI through both considering and excluding ROIs with mean doses higher than 75% of the prescription. Subsequently, a preliminary threshold value of dose discriminating patients with and without neurocognitive impairment was selected for the most relevant associations. RESULTS: The workflow allowed us to identify 10 ROIs where RT dose and DTI metrics were significantly associated with cognitive tests results (p<0.05). In 5/10 ROIs, RT dose and cognitive tests were associated with p<0.01 and preliminary RT threshold dose values, implying a possible cognitive or neuropsychological damage, were calculated. The analysis of domains showed that the most involved one was the "school-related activities". CONCLUSION: This analysis, despite being conducted on a retrospective cohort of children, shows that the identification of critical brain structures and respective radiation dose thresholds is achievable by combining, with appropriate methodological tools, the large amount of data arising from different sources. This supported the design of a prospective study to gain stronger evidence.

A multi-metric registration strategy for the alignment of longitudinal brain images in pediatric oncology.

Survival of pediatric patients with brain tumor has increased over the past 20 years, and increasing evidence of iatrogenic toxicities has been reported. In follow-ups, images are acquired at different time points where substantial changes of brain morphology occur, due to childhood physiological development and treatment effects. To address the image registration complexity, we propose two multi-metric approaches (Mplus, Mdot), combining mutual information (MI) and normalized gradient field filter (NGF). The registration performance of the proposed metrics was assessed on a simulated dataset (Brainweb) and compared with those obtained by MI and NGF separately, using mean magnitude and mean angular errors. The most promising metric (Mplus) was then selected and tested on a retrospective dataset comprising 45 pediatric patients who underwent focal radiotherapy for brain cancer. The quality of the realignment was scored by a radiation oncologist using a perceived misalignment metric (PM). All patients but one were assessed as PM ≤ 2 (good alignment), but the remaining one, severely affected by hydrocephalus and pneumocephalus at the first MRI acquisition, scored PM = 5 (unacceptable). These preliminary findings suggest that Mplus might improve the registration accuracy in complex applications such as pediatric oncology, when data are acquired throughout the years of follow-up, and is worth investigating. Graphical abstract Graphical abstract showing the clinical workflow of the overall registration procedure including the three rigid steps, the fourth deformable step, the reference MRI and the registered MRI as well as the contoured ROIs. The registration performance is assessed by means of the Perceived Misalignment score (PM).

Application of an OCT-based 3D reconstruction framework to the hemodynamic assessment of an ulcerated coronary artery plaque.

The rupture of a vulnerable plaque, known as ulceration, is the most common cause of myocardial infarction. It can be recognized by angiographic features, such as prolonged intraluminal filling and delayed clearance of the contrast liquid. The diagnosis of such an event is an open challenge due to the limited angiographic resolution and acquisition frequency. The treatment of ulcerated plaques is an open discussion, due to the high heterogeneity and the lack of evidences that support particular strategies. Therefore, the therapeutic decision should follow a detailed investigation with angiography and intravascular imaging, such as optical coherence tomography (OCT), to locate the lesion, besides its geometric features and the lumen occlusion severity. The aim of this study is the application of a framework for the in-silico analysis of the disrupted hemodynamics due to an ulcerated lesion. The study employed a validated OCT-based reconstruction methodology and computational fluid dynamics (CFD) simulations for the computation of local hemodynamic quantities, such as wall shear stress. The reported findings, such as disrupted pre-operative flow conditions, proved the applicability of the developed framework for CFD analyses on complicated patient-specific anatomies that feature ulcerated plaques. The prediction of lesion expansion and the clinical decision making can benefit from a reliable computation of wall shear stress distributions that result from the peculiar anatomy of the lesion. The application of intravascular OCT imaging, high fidelity 3D reconstructions and CFD simulations might guide the treatment of such pathology.

Automatic segmentation of optical coherence tomography pullbacks of coronary arteries treated with bioresorbable vascular scaffolds: Application to hemodynamics modeling.

BACKGROUND / OBJECTIVES: Automatic algorithms for stent struts segmentation in optical coherence tomography (OCT) images of coronary arteries have been developed over the years, particularly with application on metallic stents. The aim of this study is three-fold: (1) to develop and to validate a segmentation algorithm for the detection of both lumen contours and polymeric bioresorbable scaffold struts from 8-bit OCT images, (2) to develop a method for automatic OCT pullback quality assessment, and (3) to demonstrate the applicability of the segmentation algorithm for the creation of patient-specific stented coronary artery for local hemodynamics analysis. METHODS: The proposed OCT segmentation algorithm comprises four steps: (1) image pre-processing, (2) lumen segmentation, (3) stent struts segmentation, (4) strut-based lumen correction. This segmentation process is then followed by an automatic OCT pullback image quality assessment. This method classifies the OCT pullback image quality as 'good' or 'poor' based on the number of regions detected by the stent segmentation. The segmentation algorithm was validated against manual segmentation of 1150 images obtained from 23 in vivo OCT pullbacks. RESULTS: When considering the entire set of OCT pullbacks, lumen segmentation showed results comparable with manual segmentation and with previous studies (sensitivity ~97%, specificity ~99%), while stent segmentation showed poorer results compared to manual segmentation (sensitivity ~63%, precision ~83%). The OCT pullback quality assessment algorithm classified 7 pullbacks as 'poor' quality cases. When considering only the 'good' classified cases, the performance indexes of the scaffold segmentation were higher (sensitivity >76%, precision >86%). CONCLUSIONS: This study proposes a segmentation algorithm for the detection of lumen contours and stent struts in low quality OCT images of patients treated with polymeric bioresorbable scaffolds. The segmentation results were successfully used for the reconstruction of one coronary artery model that included a bioresorbable scaffold geometry for computational fluid dynamics analysis.

Use of apparent diffusion coefficient images to predict response to induction chemotherapy in sinonasal cancer.

The purpose of this study is to identify a set of radiomic features extracted from apparent diffusion coefficient (ADC) maps, obtained using baseline diffusion weighted magnetic resonance imaging (DW-MRI), which are able to predict the outcome of induction chemotherapy (IC) in sinonasal cancers. Such prediction could help the clinician defining the better treatment for a particular patient. Eighty-eight radiomic features were extracted from the ADC maps of 15 patients that underwent IC. A preliminary filtering of the features was made by assessing their stability to geometrical transformations of the region of interest (ROI). Mann-Whitney tests corrected for control of false discoveries were performed to identify the features that could discriminate between responsive and nonresponsive patients (4 and 11 respectively). Twenty features were found to be able to discriminate the two groups and they can potentially be used for prediction of response to treatment.

Assessment of Stability and Discrimination Capacity of Radiomic Features on Apparent Diffusion Coefficient Images.

The objectives of the study are to develop a new way to assess stability and discrimination capacity of radiomic features without the need of test-retest or multiple delineations and to use information obtained to perform a preliminary feature selection. Apparent diffusion coefficient (ADC) maps were computed from diffusion-weighted magnetic resonance images (DW-MRI) of two groups of patients: 18 with soft tissue sarcomas (STS) and 18 with oropharyngeal cancers (OPC). Sixty-nine radiomic features were computed, using three different histogram discretizations (16, 32, and 64 bins). Geometrical transformations (translations) of increasing entity were applied to the regions of interest (ROIs), and the intra-class correlation coefficient (ICC) was used to compare the features computed on the original and modified ROIs. The distribution of ICC values for minimal and maximal entity translations (ICC10 and ICC100, respectively) was used to adjust thresholds of ICC (ICCmin and ICCmax) used to discriminate between good, unstable (ICC10 < ICCmin), and non-discriminative features (ICC100 > ICCmax). Fifty-four and 59 radiomic features passed the stability-based selection for all the three histogram discretizations for the OPC and STS datasets, respectively. The excluded features were similar across the different histogram discretizations (Jaccard's index 0.77 ± 0.13 and 0.9 ± 0.1 for OPC and STS, respectively) but different between datasets (Jaccard's index 0.19 ± 0.02). The results suggest that the observed radiomic features are mainly stable and discriminative, but the stability depends on the region of the body under observation. The method provides a way to assess stability without the need of test-retest or multiple delineations.

Radiomic analysis of soft tissues sarcomas can distinguish intermediate from high-grade lesions.

PURPOSE: To assess the feasibility of grading soft tissue sarcomas (STSs) using MRI features (radiomics). MATERIALS AND METHODS: MRI (echo planar SE, 1.5T) from 19 patients with STSs and a known histological grading, were retrospectively analyzed. The apparent diffusion coefficient (ADC) maps, obtained by diffusion-weighted imaging acquisitions, were analyzed through 65 radiomic features, intensity-based (first order statistics, FOS) and texture (gray level co-occurrence matrix, GLCM; and gray level run length matrix, GLRLM) features. Feature selection (sequential forward floating search) and classification (k-nearest neighbor classifier) were performed to distinguish intermediate- from high-grade STSs. Classification was performed using the three different sub-groups of features separately as well as all the features together. The entire dataset was divided in three subsets: the training, validation and test set, containing, respectively, 60, 30, and 10% of the data. RESULTS: Intermediate-grade lesions had a higher and less disperse ADC values compared with high-grade ones: most of FOS related to intensity are higher for the intermediate-grade STSs, while FOS related to signal variability were higher in the high grade (e.g., the feature variance is 2.6*105 ± 0.9*105 versus 3.3*105 ± 1.6*105 , P = 0.3). The GLCM features related to entropy and dissimilarity were higher in the high-grade. When performing classification, the best accuracy is obtained with a maximum of three features for each subgroup, FOS features being those leading to the best classification (validation set: FOS accuracy 0.90 ± 0.11, area under the curve [AUC] 0.85 ± 0.16; test set: FOS accuracy 0.88 ± 0.25, AUC 0.87 ± 0.34). CONCLUSION: Good accuracy and AUC could be obtained using only few Radiomic features, belonging to the FOS class. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2018;47:829-840.

Stability assessment of first order statistics features computed on ADC maps in soft-tissue sarcoma.

Radiomics extracts a large number of features from medical images to perform a quantitative characterization. Aim of this study was to assess radiomic features stability and relevance. Apparent diffusion coefficient (ADC) maps were computed from diffusion-weighted magnetic resonance images (DW-MRI) of 18 patients diagnosed with soft-tissue sarcomas (STSs). Thirty-seven intensity-based features were computed on the regions of interest (ROIs). First, ROIs of the images were subjected to translations and rotations in specific ranges. The 37 features computed on the original and transformed ROIs were compared in terms of percentage of variations. The intra-class correlation coefficient (ICC) was computed. To be accepted, a feature should satisfy the following conditions: the ICC after a minimum entity transformation is > 0.6 and the ICC after a maximum entity translation is <; 0.4. In total, 31 features out of 37 were accepted by the algorithm. This stability analysis can be used as a first step in the features selection process.

A framework for computational fluid dynamic analyses of patient-specific stented coronary arteries from optical coherence tomography images.

The clinical challenge of percutaneous coronary interventions (PCI) is highly dependent on the recognition of the coronary anatomy of each individual. The classic imaging modality used for PCI is angiography, but advanced imaging techniques that are routinely performed during PCI, like optical coherence tomography (OCT), may provide detailed knowledge of the pre-intervention vessel anatomy as well as the post-procedural assessment of the specific stent-to-vessel interactions. Computational fluid dynamics (CFD) is an emerging investigational tool in the setting of optimization of PCI results. In this study, an OCT-based reconstruction method was developed for the execution of CFD simulations of patient-specific coronary artery models which include the actual geometry of the implanted stent. The method was applied to a rigid phantom resembling a stented segment of the left anterior descending coronary artery. The segmentation algorithm was validated against manual segmentation. A strong correlation was found between automatic and manual segmentation of lumen in terms of area values. Similarity indices resulted >96% for the lumen segmentation and >77% for the stent strut segmentation. The 3D reconstruction achieved for the stented phantom was also assessed with the geometry provided by X-ray computed micro tomography scan, used as ground truth, and showed the incidence of distortion from catheter-based imaging techniques. The 3D reconstruction was successfully used to perform CFD analyses, demonstrating a great potential for patient-specific investigations. In conclusion, OCT may represent a reliable source for patient-specific CFD analyses which may be optimized using dedicated automatic segmentation algorithms.

Reconstruction of stented coronary arteries from optical coherence tomography images: Feasibility, validation, and repeatability of a segmentation method.

Optical coherence tomography (OCT) is an established catheter-based imaging modality for the assessment of coronary artery disease and the guidance of stent placement during percutaneous coronary intervention. Manual analysis of large OCT datasets for vessel contours or stent struts detection is time-consuming and unsuitable for real-time applications. In this study, a fully automatic method was developed for detection of both vessel contours and stent struts. The method was applied to in vitro OCT scans of eight stented silicone bifurcation phantoms for validation purposes. The proposed algorithm comprised four main steps, namely pre-processing, lumen border detection, stent strut detection, and three-dimensional point cloud creation. The algorithm was validated against manual segmentation performed by two independent image readers. Linear regression showed good agreement between automatic and manual segmentations in terms of lumen area (r>0.99). No statistically significant differences in the number of detected struts were found between the segmentations. Mean values of similarity indexes were >95% and >85% for the lumen and stent detection, respectively. Stent point clouds of two selected cases, obtained after OCT image processing, were compared to the centerline points of the corresponding stent reconstructions from micro computed tomography, used as ground-truth. Quantitative comparison between the corresponding stent points resulted in median values of ~150 µm and ~40 µm for the total and radial distances of both cases, respectively. The repeatability of the detection method was investigated by calculating the lumen volume and the mean number of detected struts per frame for seven repeated OCT scans of one selected case. Results showed low deviation of values from the median for both analyzed quantities. In conclusion, this study presents a robust automatic method for detection of lumen contours and stent struts from OCT as supported by focused validation against both manual segmentation and micro computed tomography and by good repeatability.

Combined approach for the biomechanical characterization of skin lesions.

Melanocytic nevi are common benign skin lesions, known as moles, due to proliferation of melanocytes, the pigmented skin cells. The uncontrolled growth of these cells leads instead to cutaneous malignant melanoma, an aggressive tumour whose rate of survival dramatically increases if early diagnosis is provided. Alteration on the mechanical properties of the skin in presence of lesions has been assessed. In this context, we aim at developing a combined approach consisting of an experimental and a computational study to biomechanically characterize the skin and both malign and benign skin lesions (i.e., nevi and malignant melanoma). In particular, the former study is performed to evaluate the biomechanical response of the different skin layers after the application of a displacement field and relies on a multi-scale strategy, ranging from the tissue level to the cellular level. Computational models will be tuned against experimental data (e.g., confocal laser scanning microscopy data) to estimate the mechanical properties of the different layers of the skin and the skin lesions. In particular, the confocal laser scanning microscopy is able to provide non-invasive histomorphological analysis of skin in vivo. The integration of the experimental and the computational results will allow the evaluation of possible alterations of the local mechanical properties occurring in case of pathological condition.

Quantitative characterization and identification of lymph nodes and nasopharingeal carcinoma by coregistered magnetic resonance images.

In this study we developed a technique to improve the identification of carcinoma and pathological lymph nodes in cases of Nasopharingeal Carcinoma (NPC), through a quantitative characterization of the tissues based on MR images: 3D VIBE (Volumetric Interpolated Breath-hold Examination) T1-CE (Contrast Enhanced), T1, T2 and Diffusion Weighted Imaging (DWI) for b-values 0,300,500,700,1000. The procedure included two phases: 1) coregistration of volumes and 2) tissue characterization. Concerning the first phase, the DICOM images were reassembled spatially and resampled with isotropic 0.5mm resolution. Coregistration was performed by two multiresolution rigid transformations, merging head and neck volumes, plus a final multiresolution non rigid transformation. The anatomical 3D CE-VIBE volume was taken as reference. The procedure for tissue characterization is semi automated and it required a radiologist to identify an example of tissue from the primary tumor and a metastatic lymph node. We generated a 8-dimensional membership function to perform a fuzzy-like identification of these tissues. The result of this procedure was the generation of two maps, which showed complementary characterization of lymph nodes and carcinoma. A few example will be shown to evidence the potentiality of this method in identification and characterization of NPC lesions.

A web-based tool for cooperating behaviors in eating and physical activity control.

The field of information technology and the Internet for health care has developed rapidly in the last few years. Furthermore, new services devoted to improve personalized healthcare are emerging from current web-orientated research. Control of eating and physical activity behaviors can be performed in a computer mediated way as a social networking application. To this purpose, we designed and implemented a web application based on the cooperation between two communities: Patients and Nutritionists. The patients are able to cooperate as within a self-help group, while nutritionists can guide patients struggling with incorrect lifestyle and its consequences.