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\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_1$$\end{document}1) is devoted to the identification of the lung parenchyma; the second one (U-net\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$_2$$\end{document}2) 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.

Supplementary Information

The online version supplementary material available at 10.1007/s11548-021-02501-2.

Strategies to develop radiomics and machine learning models for lung cancer stage and histology prediction using small data samples

Predictive models based on radiomics and machine-learning (ML) need large and annotated datasets for training, often difficult to collect. We designed an operative pipeline for model training to exploit data already available to the scientific community. The aim of this work was to explore the capability of radiomic features in predicting tumor histology and stage in patients with non-small cell lung cancer (NSCLC). We analyzed the radiotherapy planning thoracic CT scans of a proprietary sample of 47 subjects (L-RT) and integrated this dataset with a publicly available set of 130 patients from the MAASTRO NSCLC collection (Lung1). We implemented intra- and inter-sample cross-validation strategies (CV) for evaluating the ML predictive model performances with not so large datasets. We carried out two classification tasks: histology classification (3 classes) and overall stage classification (two classes: stage I and II). In the first task, the best performance was obtained by a Random Forest classifier, once the analysis has been restricted to stage I and II tumors of the Lung1 and L-RT merged dataset (AUC = 0.72 ± 0.11). For the overall stage classification, the best results were obtained when training on Lung1 and testing of L-RT dataset (AUC = 0.72 ± 0.04 for Random Forest and AUC = 0.84 ± 0.03 for linear-kernel Support Vector Machine). According to the classification task to be accomplished and to the heterogeneity of the available dataset(s), different CV strategies have to be explored and compared to make a robust assessment of the potential of a predictive model based on radiomics and ML.

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, DgN_DBT, for mean glandular dose (MGD) estimates in digital breast tomosynthesis (DBT). The DgN_DBT coefficients are proposed as unique conversion coefficients for MGD estimates, in place of dose conversion coefficients in mammography (DgN_DM or c, g, s triad as proposed in worldwide quality assurance protocols) used together with the T correction factor. DgN_DBT 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 DgN_DBT 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 DgN_DBT 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 (CTDI_vol 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 f_50%/f_10% 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.

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.

Evaluation of the intra- and inter-method agreement of brain MRI segmentation software packages: A comparison between SPM12 and FreeSurfer v6.0

PURPOSE

The lack of inter-method agreement can produce inconsistent results in neuroimaging studies. We evaluated the intra-method repeatability and the inter-method reproducibility of two widely-used automatic segmentation methods for brain MRI: the FreeSurfer (FS) and the Statistical Parametric Mapping (SPM) software packages.

METHODS

We segmented the gray matter (GM), the white matter (WM) and subcortical structures in test-retest MRI data of healthy volunteers from Kirby-21 and OASIS datasets. We used Pearson's correlation (r), Bland-Altman plot and Dice index to study intra-method repeatability and inter-method reproducibility. In order to test whether different processing methods affect the results of a neuroimaging-based group study, we carried out a statistical comparison between male and female volume measures.

RESULTS

A high correlation was found between test-retest volume measures for both SPM (r in the 0.98-0.99 range) and FS (r in the 0.95-0.99 range). A non-null bias between test-retest FS volumes was detected for GM and WM in the OASIS dataset. The inter-method reproducibility analysis measured volume correlation values in the 0.72-0.98 range and the overlap between the segmented structures assessed by the Dice index was in the 0.76-0.83 range. SPM systematically provided significantly greater GM volumes and lower WM and subcortical volumes with respect to FS. In the male vs. female brain volume comparisons, inconsistencies arose for the OASIS dataset, where the gender-related differences appear subtler with respect to the Kirby dataset.

CONCLUSIONS

The inter-method reproducibility should be evaluated before interpreting the results of neuroimaging studies.

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 The Authors Hippocampus Published by Wiley Periodicals, Inc.

Large scale validation of the M5L lung CAD on heterogeneous CT datasets

PURPOSE

M5L, a fully automated computer-aided detection (CAD) system for the detection and segmentation of lung nodules in thoracic computed tomography (CT), is presented and validated on several image datasets.

METHODS

M5L is the combination of two independent subsystems, based on the Channeler Ant Model as a segmentation tool [lung channeler ant model (lungCAM)] and on the voxel-based neural approach. The lungCAM was upgraded with a scan equalization module and a new procedure to recover the nodules connected to other lung structures; its classification module, which makes use of a feed-forward neural network, is based of a small number of features (13), so as to minimize the risk of lacking generalization, which could be possible given the large difference between the size of the training and testing datasets, which contain 94 and 1019 CTs, respectively. The lungCAM (standalone) and M5L (combined) performance was extensively tested on 1043 CT scans from three independent datasets, including a detailed analysis of the full Lung Image Database Consortium/Image Database Resource Initiative database, which is not yet found in literature.

RESULTS

The lungCAM and M5L performance is consistent across the databases, with a sensitivity of about 70% and 80%, respectively, at eight false positive findings per scan, despite the variable annotation criteria and acquisition and reconstruction conditions. A reduced sensitivity is found for subtle nodules and ground glass opacities (GGO) structures. A comparison with other CAD systems is also presented.

CONCLUSIONS

The M5L performance on a large and heterogeneous dataset is stable and satisfactory, although the development of a dedicated module for GGOs detection could further improve it, as well as an iterative optimization of the training procedure. The main aim of the present study was accomplished: M5L results do not deteriorate when increasing the dataset size, making it a candidate for supporting radiologists on large scale screenings and clinical programs.

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.

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.

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.

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.

A pixel detector-based single photon-counting system as fast spectrometer for diagnostic X-ray beams

Recent advances in semiconductor pixel detectors and read-out electronics allowed to build the first prototypes of single photon-counting imaging systems that represent the last frontier of digital radiography. Among the advantages with respect to commercially available digital imaging systems, there are direct conversion of photon energy into electrical charge and the effective rejection of electronic noise by means of a thresholding process. These features allow the photon-counting systems to achieve high imaging performances in terms of spatial and contrast resolution. Moreover, the now available deep integration techniques allow the reduction of the pixel size and the improvement of the functionality of the single cell and the read-out speed so as to cope with the high fluxes found in diagnostic radiology. In particular, the single photon-counting system presented in this paper is based on a 300-microm thick silicon pixel detector bump-bonded to the Medipix2 read-out chip to form an assembly of 256 x 256 square pixels at a pitch of 55 microm. Each cell comprises a low-noise preamplifier, two pulse height discriminators and a 14-bit counter. The maximum counting rate per pixel is 1 MHz. The chip can operate in two modalities: it records the events with energy above a threshold (single mode) or between two energy thresholds (window mode). Exploiting this latter feature, a possible application of such a system as a fast spectrometer is presented to study the energy spectrum of diagnostic beams produced by X-ray tubes.

Dental radiology dosimetric data as routinely collected in an Italian hospital

The work presented here was developed in the framework of the SENTINEL Project and is devoted to the analysis of dental radiology dosimetric data. The procedure of data processing allows the analysis of some important aspects related to the protection of the patient and the staff because of the position of the operators near the patient and their exposure to the radiation scattered by the patient. Dental radiology data was collected in an Italian hospital. Following the Italian quality assurance (QA) protocols and suggestions by the leaders of the SENTINEL Project, X-ray equipment performances have been analysed in terms of: kVp accuracy, exposure time accuracy and precision, tube output, dose reproducibility and linearity, beam collimation, artefacts and light tightness. Referring to these parameters the physical quality index (QI) was analysed. In a single numerical value between 0 and 1, QI summarises the results of quality tests for radiological devices. The actual impact of such a figure (as suggested by international QA protocols or as adopted by local QA routine) on the policy of machine maintenance and replacement is discussed.

Characterization of mammographic masses using a gradient-based segmentation algorithm and a neural classifier

Computerized methods have recently shown a great potential in providing radiologists with a second opinion about the visual diagnosis of the malignancy of mammographic masses. The computer-aided diagnosis (CAD) system we developed for the mass characterization is mainly based on a segmentation algorithm and on the neural classification of several features computed on the segmented mass. Mass-segmentation plays a key role in most computerized systems. Our technique is a gradient-based one, showing the main characteristic that no free parameters have been evaluated on the data set used in this analysis, thus it can directly be applied to data sets acquired in different conditions without any ad hoc modification. A data set of 226 masses (109 malignant and 117 benign) has been used in this study. The segmentation algorithm works with a comparable efficiency both on malignant and benign masses. Sixteen features based on shape, size and intensity of the segmented masses are extracted and analyzed by a multi-layered perceptron neural network trained with the error back-propagation algorithm. The capability of the system in discriminating malignant from benign masses has been evaluated in terms of the receiver-operating characteristic (ROC) analysis. A feature selection procedure has been carried out on the basis of the feature discriminating power and of the linear correlations interplaying among them. The comparison of the areas under the ROC curves obtained by varying the number of features to be classified has shown that 12 selected features out of the 16 computed ones are powerful enough to achieve the best classifier performances. The radiologist assigned the segmented masses to three different categories: correctly-, acceptably- and non-acceptably-segmented masses. We initially estimated the area under ROC curve only on the first category of segmented masses (the 88.5% of the data set), then extending the classification to the second subclass (reaching the 97.8% of the data set) and finally to the whole data set, obtaining A(z)=0.805+/-0.030, 0.787+/-0.024 and 0.780+/-0.023, respectively.

Comparison of two portable solid state detectors with an improved collimation and alignment device for mammographic x-ray spectroscopy

We describe a portable system for mammographic x-ray spectroscopy, based on a 2 X 2 X 1 mm3 cadmium telluride (CdTe) solid state detector, that is greatly improved over a similar system based on a 3 X 3 X 2 mm3 cadmium zinc telluride (CZT) solid state detector evaluated in an earlier work. The CdTe system utilized new pinhole collimators and an alignment device that facilitated measurement of mammographic x-ray spectra. Mammographic x-ray spectra acquired by each system were comparable. Half value layer measurements obtained using an ion chamber agreed closely with those derived from the x-ray spectra measured by either detector. The faster electronics and other features of the CdTe detector allowed its use with a larger pinhole collimator than could be used with the CZT detector. Additionally, the improved pinhole collimator and alignment features of the apparatus permitted much more rapid setup for acquisition of x-ray spectra than was possible on the system described in the earlier work. These improvements in detector technology, collimation and ease of alignment, as well as low cost, make this apparatus attractive as a tool for both laboratory research and advanced mammography quality control.

A completely automated CAD system for mass detection in a large mammographic database

Mass localization plays a crucial role in computer-aided detection (CAD) systems for the classification of suspicious regions in mammograms. In this article we present a completely automated classification system for the detection of masses in digitized mammographic images. The tool system we discuss consists in three processing levels: (a) Image segmentation for the localization of regions of interest (ROIs). This step relies on an iterative dynamical threshold algorithm able to select iso-intensity closed contours around gray level maxima of the mammogram. (b) ROI characterization by means of textural features computed from the gray tone spatial dependence matrix (GTSDM), containing second-order spatial statistics information on the pixel gray level intensity. As the images under study were recorded in different centers and with different machine settings, eight GTSDM features were selected so as to be invariant under monotonic transformation. In this way, the images do not need to be normalized, as the adopted features depend on the texture only, rather than on the gray tone levels, too. (c) ROI classification by means of a neural network, with supervision provided by the radiologist's diagnosis. The CAD system was evaluated on a large database of 3369 mammographic images [2307 negative, 1062 pathological (or positive), containing at least one confirmed mass, as diagnosed by an expert radiologist]. To assess the performance of the system, receiver operating characteristic (ROC) and free-response ROC analysis were employed. The area under the ROC curve was found to be Az = 0.783 +/- 0.008 for the ROI-based classification. When evaluating the accuracy of the CAD against the radiologist-drawn boundaries, 4.23 false positives per image are found at 80% of mass sensitivity.

A study on two different CAD systems for mammography as an aid to radiological diagnosis in the search of microcalcification clusters

OBJECTIVE

The aim of the present study was to evaluate the efficacy of two different computer aided detection (CAD) systems for mammography in improving radiological diagnosis in the search of microcalcification clusters. The CAD systems used are: the SecondLooktrade mark (CADx Medical Systems, Canada) commercial system and the CALMA (computer assisted library in MAmmography) research CAD system. Three radiologists were asked to read mammographic images with and without the support of the CAD systems.

MATERIAL AND METHODS

Three radiologists with respectively 3, 5 and 7 years of practice in mammogram reading in an Italian public hospital analysed a dataset composed of 120 digitized mammograms of healthy subjects with no lesion (proven by a radiological follow up of at least 3 years) and 70 images of patients with malignant cluster of microcalcification (proven by histopathological examination) both with no CAD support as well as with the help of the SecondLooktrade mark system. After 3 months they were asked to observe the same digitized mammograms with the assistance of the CALMA system. The radiologists worked independently and were unaware of the final diagnosis. The values of the area A(z) under the ROC curve, diagnostic sensitivity, specificity, positive and negative predictive values, and diagnostic accuracy were evaluated with and without the support of the CAD systems. The reading time and qualitative evaluations of each radiologist were also reported.

RESULTS

With the support of the two CAD systems an improvement in A(z) area was obtained ranging from 0.01 to 0.04. Sensitivity increased from +8.6 to +15.7% and specificity decreased from 0.8 to 4.2%.

CONCLUSION

In our study, not conditioned by the dataset, the CAD systems as second reader produced an increase in overall sensitivity of up to 15.7%, with a little decrease in specificity of up to 4.2%. Based on these results both CAD systems might be used in the current practise to improve the sensitivity values of conventional reading (radiologist alone). The results of this study show that no significant differences exist in term of A(z), sensitivity and specificity between CALMA and CADx.

GPCALMA: a Grid-based tool for mammographic screening

OBJECTIVES

The next generation of high energy physics (HEP) experiments requires a GRID approach to a distributed computing system: the key concept is the Virtual ORGANISATION (VO), a group of distributed users with a common goal and the will to share their resources.

METHODS

A similar approach, applied to a group of hospitals that joined the GPCALMA project (Grid Platform for Computer Assisted Library for MAmmography), will allow common screening programs for early diagnosis of breast and, in the future, lung cancer. The application code makes use of neural networks for the image analysis and is useful in improving the radiologists' diagnostic performance. GRID services allow remote image analysis and interactive online diagnosis, with a potential for a relevant reduction of the delays presently associated with screening programs.

RESULTS AND CONCLUSIONS

A prototype of the system, based on AliEn GRID Services [1], is already available, with a central server running common services [2] and several clients connecting to it. Mammograms can be acquired in any location; the related information required to select and access them at any time is stored in a common service called Data Catalogue, which can be queried by any client. Thanks to the PROOF facility [3], the result of a query can be used as input for analysis algorithms, which are executed on the nodes where the input images are stored,. The selected approach avoids data transfers for all the images with a negative diagnosis and allows an almost real time diagnosis for the set of images with high cancer probability.