Investigation of a potential upstream harmonization based on image appearance matching to improve radiomics features robustness: a phantom study.

Objective. Radiomics is a promising valuable analysis tool consisting in extracting quantitative information from medical images. However, the extracted radiomics features are too sensitive to variations in used image acquisition and reconstruction parameters. This limited robustness hinders the generalizable validity of radiomics-assisted models. Our aim is to investigate a possible harmonization strategy based on matching image quality to improve feature robustness.Approach.We acquired CT scans of a phantom with two scanners across different dose levels and percentages of Iterative Reconstruction algorithms. The detectability index was used as a comprehensive task-based image quality metric. A statistical analysis based on the Intraclass Correlation Coefficient was performed to determine if matching image quality/appearance could enhance the robustness of radiomics features extracted from the phantom images. Additionally, an Artificial Neural Network was trained on these features to automatically classify the scanner used for image acquisition.Main results.We found that the ICC of the features across protocols providing a similar detectability index improves with respect to the ICC of the features across protocols providing a different detectability index. This improvement was particularly noticeable in features relevant for distinguishing between scanners.Significance.This preliminary study demonstrates that a harmonization based on image quality/appearance matching could improve radiomics features robustness and heterogeneous protocols can be used to obtain a similar image appearance in terms of the detectability index. Thus protocols with a lower dose level could be selected to reduce the amount of radiation dose delivered to the patient and simultaneously obtain a more robust quantitative analysis.

Quantification of pulmonary involvement in COVID-19 pneumonia: an upgrade of the LungQuant software for lung CT segmentation.

Computed tomography (CT) scans are used to evaluate the severity of lung involvement in patients affected by COVID-19 pneumonia. Here, we present an improved version of the LungQuant automatic segmentation software (LungQuant v2), which implements a cascade of three deep neural networks (DNNs) to segment the lungs and the lung lesions associated with COVID-19 pneumonia. The first network (BB-net) defines a bounding box enclosing the lungs, the second one (U-net 1 ) outputs the mask of the lungs, and the final one (U-net 2 ) generates the mask of the COVID-19 lesions. With respect to the previous version (LungQuant v1), three main improvements are introduced: the BB-net, a new term in the loss function in the U-net for lesion segmentation and a post-processing procedure to separate the right and left lungs. The three DNNs were optimized, trained and tested on publicly available CT scans. We evaluated the system segmentation capability on an independent test set consisting of ten fully annotated CT scans, the COVID-19-CT-Seg benchmark dataset. The test performances are reported by means of the volumetric dice similarity coefficient (vDSC) and the surface dice similarity coefficient (sDSC) between the reference and the segmented objects. LungQuant v2 achieves a vDSC (sDSC) equal to 0.96 ± 0.01 (0.97 ± 0.01) and 0.69 ± 0.08 (0.83 ± 0.07) for the lung and lesion segmentations, respectively. The output of the segmentation software was then used to assess the percentage of infected lungs, obtaining a Mean Absolute Error (MAE) equal to 2%.

A multicenter evaluation of a deep learning software (LungQuant) for lung parenchyma characterization in COVID-19 pneumonia.

BACKGROUND: The role of computed tomography (CT) in the diagnosis and characterization of coronavirus disease 2019 (COVID-19) pneumonia has been widely recognized. We evaluated the performance of a software for quantitative analysis of chest CT, the LungQuant system, by comparing its results with independent visual evaluations by a group of 14 clinical experts. The aim of this work is to evaluate the ability of the automated tool to extract quantitative information from lung CT, relevant for the design of a diagnosis support model. METHODS: LungQuant segments both the lungs and lesions associated with COVID-19 pneumonia (ground-glass opacities and consolidations) and computes derived quantities corresponding to qualitative characteristics used to clinically assess COVID-19 lesions. The comparison was carried out on 120 publicly available CT scans of patients affected by COVID-19 pneumonia. Scans were scored for four qualitative metrics: percentage of lung involvement, type of lesion, and two disease distribution scores. We evaluated the agreement between the LungQuant output and the visual assessments through receiver operating characteristics area under the curve (AUC) analysis and by fitting a nonlinear regression model. RESULTS: Despite the rather large heterogeneity in the qualitative labels assigned by the clinical experts for each metric, we found good agreement on the metrics compared to the LungQuant output. The AUC values obtained for the four qualitative metrics were 0.98, 0.85, 0.90, and 0.81. CONCLUSIONS: Visual clinical evaluation could be complemented and supported by computer-aided quantification, whose values match the average evaluation of several independent clinical experts. KEY POINTS: We conducted a multicenter evaluation of the deep learning-based LungQuant automated software. We translated qualitative assessments into quantifiable metrics to characterize coronavirus disease 2019 (COVID-19) pneumonia lesions. Comparing the software output to the clinical evaluations, results were satisfactory despite heterogeneity of the clinical evaluations. An automatic quantification tool may contribute to improve the clinical workflow of COVID-19 pneumonia.

In-vivo range verification analysis with in-beam PET data for patients treated with proton therapy at CNAO.

Morphological changes that may arise through a treatment course are probably one of the most significant sources of range uncertainty in proton therapy. Non-invasive in-vivo treatment monitoring is useful to increase treatment quality. The INSIDE in-beam Positron Emission Tomography (PET) scanner performs in-vivo range monitoring in proton and carbon therapy treatments at the National Center of Oncological Hadrontherapy (CNAO). It is currently in a clinical trial (ID: NCT03662373) and has acquired in-beam PET data during the treatment of various patients. In this work we analyze the in-beam PET (IB-PET) data of eight patients treated with proton therapy at CNAO. The goal of the analysis is twofold. First, we assess the level of experimental fluctuations in inter-fractional range differences (sensitivity) of the INSIDE PET system by studying patients without morphological changes. Second, we use the obtained results to see whether we can observe anomalously large range variations in patients where morphological changes have occurred. The sensitivity of the INSIDE IB-PET scanner was quantified as the standard deviation of the range difference distributions observed for six patients that did not show morphological changes. Inter-fractional range variations with respect to a reference distribution were estimated using the Most-Likely-Shift (MLS) method. To establish the efficacy of this method, we made a comparison with the Beam's Eye View (BEV) method. For patients showing no morphological changes in the control CT the average range variation standard deviation was found to be 2.5 mm with the MLS method and 2.3 mm with the BEV method. On the other hand, for patients where some small anatomical changes occurred, we found larger standard deviation values. In these patients we evaluated where anomalous range differences were found and compared them with the CT. We found that the identified regions were mostly in agreement with the morphological changes seen in the CT scan.

Quantification of pulmonary involvement in COVID-19 pneumonia by means of a cascade of two U-nets: training and assessment on multiple datasets using different annotation criteria.

PURPOSE: This study aims at exploiting artificial intelligence (AI) for the identification, segmentation and quantification of COVID-19 pulmonary lesions. The limited data availability and the annotation quality are relevant factors in training AI-methods. We investigated the effects of using multiple datasets, heterogeneously populated and annotated according to different criteria. METHODS: We developed an automated analysis pipeline, the LungQuant system, based on a cascade of two U-nets. The first one (U-net[Formula: see text]) is devoted to the identification of the lung parenchyma; the second one (U-net[Formula: see text]) acts on a bounding box enclosing the segmented lungs to identify the areas affected by COVID-19 lesions. Different public datasets were used to train the U-nets and to evaluate their segmentation performances, which have been quantified in terms of the Dice Similarity Coefficients. The accuracy in predicting the CT-Severity Score (CT-SS) of the LungQuant system has been also evaluated. RESULTS: Both the volumetric DSC (vDSC) and the accuracy showed a dependency on the annotation quality of the released data samples. On an independent dataset (COVID-19-CT-Seg), both the vDSC and the surface DSC (sDSC) were measured between the masks predicted by LungQuant system and the reference ones. The vDSC (sDSC) values of 0.95±0.01 and 0.66±0.13 (0.95±0.02 and 0.76±0.18, with 5 mm tolerance) were obtained for the segmentation of lungs and COVID-19 lesions, respectively. The system achieved an accuracy of 90% in CT-SS identification on this benchmark dataset. CONCLUSION: We analysed the impact of using data samples with different annotation criteria in training an AI-based quantification system for pulmonary involvement in COVID-19 pneumonia. In terms of vDSC measures, the U-net segmentation strongly depends on the quality of the lesion annotations. Nevertheless, the CT-SS can be accurately predicted on independent test sets, demonstrating the satisfactory generalization ability of the LungQuant.

Normalized glandular dose coefficients for digital breast tomosynthesis systems with a homogeneous breast model.

This work aims at calculating and releasing tabulated values of dose conversion coefficients, DgNDBT, for mean glandular dose (MGD) estimates in digital breast tomosynthesis (DBT). The DgNDBT coefficients are proposed as unique conversion coefficients for MGD estimates, in place of dose conversion coefficients in mammography (DgNDM or c, g, s triad as proposed in worldwide quality assurance protocols) used together with the T correction factor. DgNDBT is the MGD per unit incident air kerma measured at the breast surface for a 0° projection and the entire tube load used for the scan. The dataset of polyenergetic DgNDBT coefficients was derived via a Monte Carlo software based on the Geant4 toolkit. Dose coefficients were calculated for a grid of values of breast characteristics (breast thickness in the range 20-90 mm and glandular fraction by mass of 1%, 25%, 50%, 75%, 100%) and the simulated geometries, scan protocols, irradiation geometries and typical spectral qualities replicated those of six commercial DBT systems (GE SenoClaire, Hologic Selenia Dimensions, GE Senographe Pristina, Fujifilm Amulet Innovality, Siemens Mammomat Inspiration and IMS Giotto Class). For given breast characteristics, target/filter combination, tube voltage and half value layer (HVL), two spectra with two HVL values have been simulated in order to permit MGD estimates from experimental HVL values via mathematical interpolation from tabulated values. The adopted breast model assumes homogenous composition of glandular and adipose tissues; it includes a 1.45 mm thick skin envelope in place of the 4-5 mm envelope commonly adopted in dosimetry protocols. The simulation code was validated versus AAPM Task group 195 Monte Carlo reference data sets (absolute differences not higher than 1.1%) and by comparison to relative dosimetry measurements with radiochromic film in a PMMA test object (differences within the maximum experimental uncertainty of 11%). The calculated coefficients show maximum relative deviations of -17.6% and +6.1% from those provided by the DBT dose coefficients adopted in the EUREF protocol and of 1.5%, on average, from data in the AAPM TG223 report. A spreadsheet is provided for interpolating the tabulated DgNDBT coefficients for arbitrary values of HVL, compressed breast thickness and glandular fraction, in the corresponding investigated ranges, for each DBT unit modeled in this work.

A comprehensive assessment of physical image quality of five different scanners for head CT imaging as clinically used at a single hospital centre-A phantom study.

Nowadays, given the technological advance in CT imaging and increasing heterogeneity in characteristics of CT scanners, a number of CT scanners with different manufacturers/technologies are often installed in a hospital centre and used by various departments. In this phantom study, a comprehensive assessment of image quality of 5 scanners (from 3 manufacturers and with different models) for head CT imaging, as clinically used at a single hospital centre, was hence carried out. Helical and/or sequential acquisitions of the Catphan-504 phantom were performed, using the scanning protocols (CTDIvol range: 54.7-57.5 mGy) employed by the staff of various Radiology/Neuroradiology departments of our institution for routine head examinations. CT image quality for each scanner/acquisition protocol was assessed through noise level, noise power spectrum (NPS), contrast-to-noise ratio (CNR), modulation transfer function (MTF), low contrast detectability (LCD) and non-uniformity index analyses. Noise values ranged from 3.5 HU to 5.7 HU across scanners/acquisition protocols. NPS curves differed in terms of peak position (range: 0.21-0.30 mm-1). A substantial variation of CNR values with scanner/acquisition protocol was observed for different contrast inserts. The coefficient of variation (standard deviation divided by mean value) of CNR values across scanners/acquisition protocols was 18.3%, 31.4%, 34.2%, 30.4% and 30% for teflon, delrin, LDPE, polystyrene and acrylic insert, respectively. An appreciable difference in MTF curves across scanners/acquisition protocols was revealed, with a coefficient of variation of f50%/f10% of MTF curves across scanners/acquisition protocols of 10.1%/7.4%. A relevant difference in LCD performance of different scanners/acquisition protocols was found. The range of contrast threshold for a typical object size of 3 mm was 3.7-5.8 HU. Moreover, appreciable differences in terms of NUI values (range: 4.1%-8.3%) were found. The analysis of several quality indices showed a non-negligible variability in head CT imaging capabilities across different scanners/acquisition protocols. This highlights the importance of a physical in-depth characterization of image quality for each CT scanner as clinically used, in order to optimize CT imaging procedures.

Technical evaluation of image quality in synthetic mammograms obtained from 15° and 40° digital breast tomosynthesis in a commercial system: a quantitative comparison.

Digital breast tomosynthesis (DBT) has recently gained interest both for breast cancer screening and diagnosis. Its employment has increased also in conjunction with digital mammography (DM), to improve cancer detection and reduce false positive recall rate. Synthetic mammograms (SMs) reconstructed from DBT data have been introduced to replace DM in the DBT + DM approach, for preserving the benefits of the dual-acquisition modality whilst reducing radiation dose and compression time. Therefore, different DBT models have been commercialized and the effective potential of each system has been investigated. In particular, wide-angle DBT was shown to provide better depth resolution than narrow-angle DBT, while narrow-angle DBT allows better identification of microcalcifications compared to wide-angle DBT. Given the increasing employment of SMs as supplement to DBT, a comparison of image quality between SMs obtained in narrow-angle and wide-angle DBT is of practical interest. Therefore, the aim of this phantom study was to evaluate and compare the image quality of SMs reconstructed from 15° (SM15) and 40° (SM40) DBT in a commercial system. Spatial resolution, noise and contrast properties were evaluated through the modulation transfer function (MTF), noise power spectrum, maps of signal-to-noise ratio (SNR), image contrast, contrast-to-noise ratio (CNR) and contrast-detail (CD) thresholds. SM40 expressed higher MTF than SM15, but also lower SNR and CNR levels. SM15 and SM40 were characterized by slight different texture, and a different behavior in terms of contrast was found. SM15 provided better CD performances than SM40. These results suggest that the employment of wide/narrow-angle DBT + SM images should be optimized based on the specific image task.

Dealing with confounders and outliers in classification medical studies: The Autism Spectrum Disorders case study.

Machine learning (ML) approaches have been widely applied to medical data in order to find reliable classifiers to improve diagnosis and detect candidate biomarkers of a disease. However, as a powerful, multivariate, data-driven approach, ML can be misled by biases and outliers in the training set, finding sample-dependent classification patterns. This phenomenon often occurs in biomedical applications in which, due to the scarcity of the data, combined with their heterogeneous nature and complex acquisition process, outliers and biases are very common. In this work we present a new workflow for biomedical research based on ML approaches, that maximizes the generalizability of the classification. This workflow is based on the adoption of two data selection tools: an autoencoder to identify the outliers and the Confounding Index, to understand which characteristics of the sample can mislead classification. As a study-case we adopt the controversial research about extracting brain structural biomarkers of Autism Spectrum Disorders (ASD) from magnetic resonance images. A classifier trained on a dataset composed by 86 subjects, selected using this framework, obtained an area under the receiver operating characteristic curve of 0.79. The feature pattern identified by this classifier is still able to capture the mean differences between the ASD and Typically Developing Control classes on 1460 new subjects in the same age range of the training set, thus providing new insights on the brain characteristics of ASD. In this work, we show that the proposed workflow allows to find generalizable patterns even if the dataset is limited, while skipping the two mentioned steps and using a larger but not well designed training set would have produced a sample-dependent classifier.

Comprehensive assessment of image quality in synthetic and digital mammography: a quantitative comparison.

Recent advances in digital breast tomosynthesis (DBT) technology were focused on the reconstruction of 2D "Synthesized Mammograms" (SMs) from DBT dataset. The introduction of SMs could avoid an additional digital mammography (DM) which is often required in complement to DBT examinations. Therefore, breast absorbed dose and compression time can be significantly reduced in DBT+SM procedures with respect to DBT+DM modality. However, to date, a limited number of studies have objectively characterised the image quality of SMs with respect to DM images. Therefore, the aim of this phantom study was to comprehensively compare SMs and DM images in terms of several image quality parameters. A Selenia Dimensions system (Hologic, Bedford, Mass, USA) was employed in this work. Five different phantoms were adopted to study noise, contrast and spatial resolution properties of the images. Specifically, noise power spectrum (NPS), maps of signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), modulation transfer function (MTF) and contrast-detail (CD) thresholds were evaluated both for SM and DM modalities. SMs were characterised by different texture, noise and SNR spatial distribution properties with respect to DM images. Additionally, while in some conditions SM provides higher CNR than DM, lower overall performances in terms spatial resolution and CD curves were found in comparison to DM images. Therefore, given the great benefits of SMs in terms of dose and compression time saving, further clinical investigations on SMs image quality properties could be of practical interest to integrate our findings.

A cloud-based computer-aided detection system improves identification of lung nodules on computed tomography scans of patients with extra-thoracic malignancies.

OBJECTIVES: To compare unassisted and CAD-assisted detection and time efficiency of radiologists in reporting lung nodules on CT scans taken from patients with extra-thoracic malignancies using a Cloud-based system. MATERIALS AND METHODS: Three radiologists searched for pulmonary nodules in patients with extra-thoracic malignancy who underwent CT (slice thickness/spacing 2 mm/1.7 mm) between September 2015 and March 2016. All nodules detected by unassisted reading were measured and coordinates were uploaded on a cloud-based system. CAD marks were then reviewed by the same readers using the cloud-based interface. To establish the reference standard all nodules ≥ 3 mm detected by at least one radiologist were validated by two additional experienced radiologists in consensus. Reader detection rate and reporting time with and without CAD were compared. The study was approved by the local ethics committee. All patients signed written informed consent. RESULTS: The series included 225 patients (age range 21-90 years, mean 62 years), including 75 patients having at least one nodule, for a total of 215 nodules. Stand-alone CAD sensitivity for lesions ≥ 3 mm was 85% (183/215, 95% CI: 82-91); mean false-positive rate per scan was 3.8. Sensitivity across readers in detecting lesions ≥ 3 mm was statistically higher using CAD: 65% (95% CI: 61-69) versus 88% (95% CI: 86-91, p<0.01). Reading time increased by 11% using CAD (296 s vs. 329 s; p<0.05). CONCLUSION: In patients with extra-thoracic malignancies, CAD-assisted reading improves detection of ≥ 3-mm lung nodules on CT, slightly increasing reading time. KEY POINTS: • CAD-assisted reading improves the detection of lung nodules compared with unassisted reading on CT scans of patients with primary extra-thoracic tumour, slightly increasing reading time. • Cloud-based CAD systems may represent a cost-effective solution since CAD results can be reviewed while a separated cloud back-end is taking care of computations. • Early identification of lung nodules by CAD-assisted interpretation of CT scans in patients with extra-thoracic primary tumours is of paramount importance as it could anticipate surgery and extend patient life expectancy.

Computed tomography imaging with the Adaptive Statistical Iterative Reconstruction (ASIR) algorithm: dependence of image quality on the blending level of reconstruction.

Computed tomography (CT) is a useful and widely employed imaging technique, which represents the largest source of population exposure to ionizing radiation in industrialized countries. Adaptive Statistical Iterative Reconstruction (ASIR) is an iterative reconstruction algorithm with the potential to allow reduction of radiation exposure while preserving diagnostic information. The aim of this phantom study was to assess the performance of ASIR, in terms of a number of image quality indices, when different reconstruction blending levels are employed. CT images of the Catphan-504 phantom were reconstructed using conventional filtered back-projection (FBP) and ASIR with reconstruction blending levels of 20, 40, 60, 80, and 100%. Noise, noise power spectrum (NPS), contrast-to-noise ratio (CNR) and modulation transfer function (MTF) were estimated for different scanning parameters and contrast objects. Noise decreased and CNR increased non-linearly up to 50 and 100%, respectively, with increasing blending level of reconstruction. Also, ASIR has proven to modify the NPS curve shape. The MTF of ASIR reconstructed images depended on tube load/contrast and decreased with increasing blending level of reconstruction. In particular, for low radiation exposure and low contrast acquisitions, ASIR showed lower performance than FBP, in terms of spatial resolution for all blending levels of reconstruction. CT image quality varies substantially with the blending level of reconstruction. ASIR has the potential to reduce noise whilst maintaining diagnostic information in low radiation exposure CT imaging. Given the opposite variation of CNR and spatial resolution with the blending level of reconstruction, it is recommended to use an optimal value of this parameter for each specific clinical application.

Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge.

Automatic detection of pulmonary nodules in thoracic computed tomography (CT) scans has been an active area of research for the last two decades. However, there have only been few studies that provide a comparative performance evaluation of different systems on a common database. We have therefore set up the LUNA16 challenge, an objective evaluation framework for automatic nodule detection algorithms using the largest publicly available reference database of chest CT scans, the LIDC-IDRI data set. In LUNA16, participants develop their algorithm and upload their predictions on 888 CT scans in one of the two tracks: 1) the complete nodule detection track where a complete CAD system should be developed, or 2) the false positive reduction track where a provided set of nodule candidates should be classified. This paper describes the setup of LUNA16 and presents the results of the challenge so far. Moreover, the impact of combining individual systems on the detection performance was also investigated. It was observed that the leading solutions employed convolutional networks and used the provided set of nodule candidates. The combination of these solutions achieved an excellent sensitivity of over 95% at fewer than 1.0 false positives per scan. This highlights the potential of combining algorithms to improve the detection performance. Our observer study with four expert readers has shown that the best system detects nodules that were missed by expert readers who originally annotated the LIDC-IDRI data. We released this set of additional nodules for further development of CAD systems.

ARIANNA: A research environment for neuroimaging studies in autism spectrum disorders.

The complexity and heterogeneity of Autism Spectrum Disorders (ASD) require the implementation of dedicated analysis techniques to obtain the maximum from the interrelationship among many variables that describe affected individuals, spanning from clinical phenotypic characterization and genetic profile to structural and functional brain images. The ARIANNA project has developed a collaborative interdisciplinary research environment that is easily accessible to the community of researchers working on ASD (https://arianna.pi.infn.it). The main goals of the project are: to analyze neuroimaging data acquired in multiple sites with multivariate approaches based on machine learning; to detect structural and functional brain characteristics that allow the distinguishing of individuals with ASD from control subjects; to identify neuroimaging-based criteria to stratify the population with ASD to support the future development of personalized treatments. Secure data handling and storage are guaranteed within the project, as well as the access to fast grid/cloud-based computational resources. This paper outlines the web-based architecture, the computing infrastructure and the collaborative analysis workflows at the basis of the ARIANNA interdisciplinary working environment. It also demonstrates the full functionality of the research platform. The availability of this innovative working environment for analyzing clinical and neuroimaging information of individuals with ASD is expected to support researchers in disentangling complex data thus facilitating their interpretation.

Hippocampal subfields at ultra high field MRI: An overview of segmentation and measurement methods.

The hippocampus is one of the most interesting and studied brain regions because of its involvement in memory functions and its vulnerability in pathological conditions, such as neurodegenerative processes. In the recent years, the increasing availability of Magnetic Resonance Imaging (MRI) scanners that operate at ultra-high field (UHF), that is, with static magnetic field strength ≥7T, has opened new research perspectives. Compared to conventional high-field scanners, these systems can provide new contrasts, increased signal-to-noise ratio and higher spatial resolution, thus they may improve the visualization of very small structures of the brain, such as the hippocampal subfields. Studying the morphometry of the hippocampus is crucial in neuroimaging research because changes in volume and thickness of hippocampal subregions may be relevant in the early assessment of pathological cognitive decline and Alzheimer's Disease (AD). The present review provides an overview of the manual, semi-automated and fully automated methods that allow the assessment of hippocampal subfield morphometry at UHF MRI, focusing on the different hippocampal segmentation produced. © 2017 Wiley Periodicals, Inc.

Predictive Models Based on Support Vector Machines: Whole-Brain versus Regional Analysis of Structural MRI in the Alzheimer's Disease.

Decision-making systems trained on structural magnetic resonance imaging data of subjects affected by the Alzheimer's disease (AD) and healthy controls (CTRL) are becoming widespread prognostic tools for subjects with mild cognitive impairment (MCI). This study compares the performances of three classification methods based on support vector machines (SVMs), using as initial sets of brain voxels (ie, features): (1) the segmented grey matter (GM); (2) regions of interest (ROIs) by voxel-wise t-test filtering; (3) parceled ROIs, according to prior knowledge. The recursive feature elimination (RFE) is applied in all cases to investigate whether feature reduction improves the classification accuracy. We analyzed more than 600 AD Neuroimaging Initiative (ADNI) subjects, training the SVMs on the AD/CTRL dataset, and evaluating them on a trial MCI dataset. The classification performance, evaluated as the area under the receiver operating characteristic curve (AUC), reaches AUC = (88.9 ± .5)% in 20-fold cross-validation on the AD/CTRL dataset, when the GM is classified as a whole. The highest discrimination accuracy between MCI converters and nonconverters is achieved when the SVM-RFE is applied to the whole GM: with AUC reaching (70.7 ± .9)%, it outperforms both ROI-based approaches in predicting the AD conversion.

Combination of computer-aided detection algorithms for automatic lung nodule identification.

PURPOSE: The aim of this work is to evaluate the potential of combining different computer-aided detection (CADe) methods to increase the actual support for radiologists of automated systems in the identification of pulmonary nodules in CT scans. METHODS: The outputs of three different CADe systems developed by researchers of the Italian MAGIC-5 collaboration were combined. The systems are: the CAMCADe (based on a Channeler-Ant-Model which segments vessel tree and nodule candidates and a neural classifier), the RGVPCADe (a Region-Growing- Volume-Plateau algorithm detects nodule candidates and a neural network reduces false positives); the VBNACADe (two dedicated procedures, based respectively on a 3D dot-enhancement algorithm and on intersections of pleura surface normals, identifies internal and juxtapleural nodules, and a Voxel-Based-Neural-Approach reduces false positives. A dedicated OsiriX plugin implemented with the Cocoa environments of MacOSX allows annotating nodules and visualizing singles and combined CADe findings. RESULTS: The combined CADe has been tested on thin slice (lower than 2 mm) CTs of the LIDC public research database and the results have been compared with those obtained by the single systems. The FROC (Free Receiver Operating Characteristic) curves show better results than the best of the single approaches. CONCLUSIONS: Has been demonstrated that the combination of different approaches offers better results than each single CADe system. A clinical validation of the combined CADe as second reader is being addressed by means of the dedicated OsiriX plugin.

Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: The ANODE09 study.

Numerous publications and commercial systems are available that deal with automatic detection of pulmonary nodules in thoracic computed tomography scans, but a comparative study where many systems are applied to the same data set has not yet been performed. This paper introduces ANODE09 ( http://anode09.isi.uu.nl), a database of 55 scans from a lung cancer screening program and a web-based framework for objective evaluation of nodule detection algorithms. Any team can upload results to facilitate benchmarking. The performance of six algorithms for which results are available are compared; five from academic groups and one commercially available system. A method to combine the output of multiple systems is proposed. Results show a substantial performance difference between algorithms, and demonstrate that combining the output of algorithms leads to marked performance improvements.

A novel multithreshold method for nodule detection in lung CT.

Multislice computed tomography (MSCT) is a valuable tool for lung cancer detection, thanks to its ability to identify noncalcified nodules of small size (from about 3 mm). Due to the large number of images generated by MSCT, there is much interest in developing computer-aided detection (CAD) systems that could assist radiologists in the lung nodule detection task. A complete multistage CAD system, including lung boundary segmentation, regions of interest (ROIs) selection, feature extraction, and false positive reduction is presented. The selection of ROIs is based on a multithreshold surface-triangulation approach. Surface triangulation is performed at different threshold values, varying from a minimum to a maximum value in a wide range. At a given threshold value, a ROI is defined as the volume inside a connected component of the triangulated isosurface. The evolution of a ROI as a function of the threshold can be represented by a treelike structure. A multithreshold ROI is defined as a path on this tree, which starts from a terminal ROI and ends on the root ROI. For each ROI, the volume, surface area, roundness, density, and moments of inertia are computed as functions of the threshold and used as input to a classification system based on artificial neural networks. The method is suitable to detect different types of nodules, including juxta-pleural nodules and nodules connected to blood vessels. A training set of 109 low-dose MSCT scans made available by the Pisa center of the Italung-CT trial and annotated by expert radiologists was used for the algorithm design and optimization. The system performance was tested on an independent set of 23 low-dose MSCT scans coming from the Pisa Italung-CT center and on 83 scans made available by the Lung Image Database Consortium (LIDC) annotated by four expert radiologists. On the Italung-CT test set, for nodules having a diameter greater than or equal to 3 mm, the system achieved 84% and 71% sensitivity at false positive/scan rates of 10 and 4, respectively. For nodules having a diameter greater than or equal to 4 mm, the sensitivities were 97% and 80% at false positive/scan rates of 10 and 4, respectively. On the LIDC data set, the system achieved a 79% sensitivity at a false positive/scan rate of 4 in the detection of nodules with a diameter greater than or equal to 3 mm that have been annotated by all four radiologists.

Automatic analysis of medial temporal lobe atrophy from structural MRIs for the early assessment of Alzheimer disease.

The purpose of this study is to develop a software for the extraction of the hippocampus and surrounding medial temporal lobe (MTL) regions from T1-weighted magnetic resonance (MR) images with no interactive input from the user, to introduce a novel statistical indicator, computed on the intensities in the automatically extracted MTL regions, which measures atrophy, and to evaluate the accuracy of the newly developed intensity-based measure of MTL atrophy to (a) distinguish between patients with Alzheimer disease (AD), patients with amnestic mild cognitive impairment (aMCI), and elderly controls by using established criteria for patients with AD and aMCI as the reference standard and (b) infer about the clinical outcome of aMCI patients. For the development of the software, the study included 61 patients with mild AD (17 men, 44 women; mean age +/- standard deviation (SD), 75.8 years +/- 7.8; Mini Mental State Examination (MMSE) score, 24.1 +/- 3.1), 42 patients with aMCI (11 men, 31 women; mean age +/- SD, 75.2 years +/- 4.9; MMSE score, 27.9 +/- 1.9), and 30 elderly healthy controls (10 men, 20 women; mean age +/- SD, 74.7 years +/- 5.2; MMSE score, 29.1 +/- 0.8). For the evaluation of the statistical indicator, 150 patients with mild AD (62 men, 88 women; mean age +/- SD, 76.3 years +/- 5.8; MMSE score, 23.2 +/- 4.1), 247 patients with aMCI (143 men, 104 women; mean age +/- SD, 75.3 years +/- 6.7; MMSE score, 27.0 +/- 1.8), and 135 elderly healthy controls (61 men, 74 women; mean age +/- SD, 76.4 years +/- 6.1). Fifty aMCI patients were evaluated every 6 months over a 3 year period to assess conversion to AD. For each participant, two subimages of the MTL regions were automatically extracted from T1-weighted MR images with high spatial resolution. An intensity-based MTL atrophy measure was found to separate control, MCI, and AD cohorts. Group differences were assessed by using two-sample t test. Individual classification was analyzed by using receiver operating characteristic (ROC) curves. Compared to controls, significant differences in the intensity-based MTL atrophy measure were detected in both groups of patients (AD vs controls, 0.28 +/- 0.03 vs 0.34 +/- 0.03, P < 0.001; aMCI vs controls, 0.31 +/- 0.03 vs 0.34 +/- 0.03, P < 0.001). Moreover, the subgroup of aMCI converters was significantly different from controls (0.27 +/- 0.034 vs 0.34 +/- 0.03, P < 0.001). Regarding the ROC curve for intergroup discrimination, the area under the curve was 0.863 for AD patients vs controls, 0.746 for all aMCI patients vs controls, and 0.880 for aMCI converters vs controls. With specificity set at 85%, the sensitivity was 74% for AD vs controls, 45% for aMCI vs controls, and 83% for aMCI converters vs controls. The automated analysis of MTL atrophy in the segmented volume is applied to the early assessment of AD, leading to the discrimination of aMCI converters with an average 3 year follow-up. This procedure can provide additional useful information in the early diagnosis of AD.