Intracranial aneurysms at MR angiography: effect of computer-aided diagnosis on radiologists' detection performance

Usefulness of copper filters in digital chest radiography based on the relationship between effective detective quantum efficiency and deep learning-based segmentation accuracy of the tumor area

This study aimed to determine the optimal radiographic conditions for detecting lesions on digital chest radiographs using an indirect conversion flat-panel detector with a copper (Cu) filter. First, we calculated the effective detective quantum efficiency (DQE) by considering clinical conditions to evaluate the image quality. We then measured the segmentation accuracy using a U-net convolutional network to verify the effectiveness of the Cu filter. We obtained images of simulated lung tumors using 10-mm acrylic spheres positioned at the right lung apex and left middle lung of an adult chest phantom. The Dice coefficient was calculated as the similarity between the output and learning images to evaluate the accuracy of tumor area segmentation using U-net. Our results showed that effective DQE was higher in the following order up to the spatial frequency of 2 cycles/mm: 120 kV + no Cu, 120 kV + Cu 0.1 mm, and 120 kV + Cu 0.2 mm. The segmented region was similar to the true region for mass-area extraction in the left middle lobe. The lesion segmentation in the upper right lobe with 120 kV + no Cu and 120 kV + Cu 0.1 mm was less successful. However, adding a Cu filter yielded reproducible images with high Dice coefficients, regardless of the tumor location. We confirmed that adding a Cu filter decreases the X-ray absorption efficiency while improving the signal-to-noise ratio (SNR). Furthermore, artificial intelligence accurately segments low-contrast lesions.

Detection of cerebral aneurysms using artificial intelligence: a systematic review and meta-analysis

BACKGROUND

Subarachnoid hemorrhage from cerebral aneurysm rupture is a major cause of morbidity and mortality. Early aneurysm identification, aided by automated systems, may improve patient outcomes. Therefore, a systematic review and meta-analysis of the diagnostic accuracy of artificial intelligence (AI) algorithms in detecting cerebral aneurysms using CT, MRI or DSA was performed.

METHODS

MEDLINE, Embase, Cochrane Library and Web of Science were searched until August 2021. Eligibility criteria included studies using fully automated algorithms to detect cerebral aneurysms using MRI, CT or DSA. Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis: Diagnostic Test Accuracy (PRISMA-DTA), articles were assessed using Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2). Meta-analysis included a bivariate random-effect model to determine pooled sensitivity, specificity, and area under the receiver operator characteristic curve (ROC-AUC).

PROSPERO

CRD42021278454.

RESULTS

43 studies were included, and 41/43 (95%) were retrospective. 34/43 (79%) used AI as a standalone tool, while 9/43 (21%) used AI assisting a reader. 23/43 (53%) used deep learning. Most studies had high bias risk and applicability concerns, limiting conclusions. Six studies in the standalone AI meta-analysis gave (pooled) 91.2% (95% CI 82.2% to 95.8%) sensitivity; 16.5% (95% CI 9.4% to 27.1%) false-positive rate (1-specificity); 0.936 ROC-AUC. Five reader-assistive AI studies gave (pooled) 90.3% (95% CI 88.0% - 92.2%) sensitivity; 7.9% (95% CI 3.5% to 16.8%) false-positive rate; 0.910 ROC-AUC.

CONCLUSION

AI has the potential to support clinicians in detecting cerebral aneurysms. Interpretation is limited due to high risk of bias and poor generalizability. Multicenter, prospective studies are required to assess AI in clinical practice.

Automated Detection of Cerebral Aneurysms on TOF-MRA Using a Deep Learning Approach: An External Validation Study

BACKGROUND AND PURPOSE

Cerebral aneurysms yield the risk of rupture, severe disability and death. Thus, early detection of cerebral aneurysms is crucial to ensure timely treatment, if necessary. AI-based software tools are expected to enhance radiologists' performance in detecting pathologies like cerebral aneurysms in the future. Our aim was to evaluate the diagnostic performance of an artificial intelligence-based software designed to detect intracranial aneurysms on TOF-MRA.

MATERIALS AND METHODS

One hundred ninety-one MR imaging data sets were analyzed using the software mdbrain for the presence of intracranial aneurysms on TOF-MRA obtained using two 3T MR imaging scanners or a 1.5T MR imaging scanner according to our clinical standard protocol. The results were compared with the reading of an experienced radiologist as a criterion standard to measure the sensitivity, specificity, positive and negative predictive values, and accuracy of the software. Additionally, detection rates depending on size, morphology, and location of the aneurysms were evaluated.

RESULTS

Fifty-four aneurysms were detected by the expert reader. The overall sensitivity of the software for the detection of cerebral aneurysms was 72.6%, the specificity was 87.2%, and the accuracy was 82.6%. The positive predictive value was 67.9%, and the negative predictive value was 88.5%. We observed a sensitivity of 100% for saccular aneurysms of >5 mm without signs of thrombosis and low detection rates for fusiform or thrombosed aneurysms of 33.3% and 16.7%, respectively. Of 8 aneurysms that were not included in the initial written reports but were detected by the expert reader, retrospectively, 4 were detected by the software.

CONCLUSIONS

Our data suggest that the software can assist radiologists in reporting TOF-MRA. The software was highly reliable in detecting saccular aneurysms, while for fusiform or thrombosed aneurysms, further improvements are needed. Further studies are necessary to investigate the impact of the software on detection rates, interrater reliability, and reading times.

The Usefulness of Computer-Aided Detection of Brain Metastases on Contrast-Enhanced Computed Tomography Using Single-Shot Multibox Detector: Observer Performance Study

OBJECTIVE

This study aimed to test the usefulness of computer-aided detection (CAD) for the detection of brain metastasis (BM) on contrast-enhanced computed tomography.

METHODS

The test data set included whole-brain axial contrast-enhanced computed tomography images of 25 cases with 62 BMs and 5 cases without BM. Six radiologists from 3 institutions with 2 to 4 years of experience independently reviewed the cases, both in conditions with and without CAD assistance. Sensitivity, positive predictive value, number of false positives, and reading time were compared between the conditions using paired t tests. Subanalysis was also performed for groups of lesions divided according to size. A P value <0.05 was considered statistically significant.

RESULTS

With CAD, sensitivity significantly increased from 80.4% to 83.9% (P = 0.04), whereas positive predictive value significantly decreased from 88.7% to 84.8% (P = 0.03). Reading time with and without CAD was 112 and 107 seconds, respectively (P = 0.38), and the number of false positives was 10.5 with CAD and 7.0 without CAD (P = 0.053). Sensitivity significantly improved for 6- to 12-mm lesions, from 71.2% without CAD to 80.3% with CAD (P = 0.02). The sensitivity of the CAD (95.2%) was significantly higher than that of any reader (with CAD: P = 0.01; without CAD: P = 0.005).

CONCLUSIONS

Computer-aided detection significantly improved BM detection sensitivity without prolonging reading time while marginally increased the false positives.

Detection of acute rib fractures on CT images with convolutional neural networks: effect of location and type of fracture and reader's experience

PURPOSE

The evaluation of all ribs on thin-slice CT images is time consuming and it can be difficult to accurately assess the location and type of rib fracture in an emergency. The aim of our study was to develop and validate a convolutional neural network (CNN) algorithm for the detection of acute rib fractures on thoracic CT images and to investigate the effect of the CNN algorithm on radiologists' performance.

METHODS

The dataset for development of a CNN consisted of 539 thoracic CT scans with 4906 acute rib fractures. A three-dimensional faster region-based CNN was trained and evaluated by using tenfold cross-validation. For an observer performance study to investigate the effect of CNN outputs on radiologists' performance, 30 thoracic CT scans (28 scans with 90 acute rib fractures and 2 without rib fractures) which were not included in the development dataset were used. Observer performance study involved eight radiologists who evaluated CT images first without and second with CNN outputs. The diagnostic performance was assessed by using figure of merit (FOM) values obtained from the jackknife free-response receiver operating characteristic (JAFROC) analysis.

RESULTS

When radiologists used the CNN output for detection of rib fractures, the mean FOM value significantly increased for all readers (0.759 to 0.819, P = 0.0004) and for displaced (0.925 to 0.995, P = 0.0028) and non-displaced fractures (0.678 to 0.732, P = 0.0116). At all rib levels except for the 1st and 12th ribs, the radiologists' true-positive fraction of the detection became significantly increased by using the CNN outputs.

CONCLUSION

The CNN specialized for the detection of acute rib fractures on CT images can improve the radiologists' diagnostic performance regardless of the type of fractures and reader's experience. Further studies are needed to clarify the usefulness of the CNN for the detection of acute rib fractures on CT images in actual clinical practice.

Deep neural network-based detection and segmentation of intracranial aneurysms on 3D rotational DSA

OBJECTIVE

Accurate diagnosis and measurement of intracranial aneurysms are challenging. This study aimed to develop a 3D convolutional neural network (CNN) model to detect and segment intracranial aneurysms (IA) on 3D rotational DSA (3D-RA) images.

METHODS

3D-RA images were collected and annotated by 5 neuroradiologists. The annotated images were then divided into three datasets: training, validation, and test. A 3D Dense-UNet-like CNN (3D-Dense-UNet) segmentation algorithm was constructed and trained using the training dataset. Diagnostic performance to detect aneurysms and segmentation accuracy was assessed for the final model on the test dataset using the free-response receiver operating characteristic (FROC). Finally, the CNN-inferred maximum diameter was compared against expert measurements by Pearson's correlation and Bland-Altman limits of agreement (LOA).

RESULTS

A total of 451 patients with 3D-RA images were split into n = 347/41/63 training/validation/test datasets, respectively. For aneurysm detection, observed FROC analysis showed that the model managed to attain a sensitivity of 0.710 at 0.159 false positives (FP)/case, and 0.986 at 1.49 FP/case. The proposed method had good agreement with reference manual aneurysmal maximum diameter measurements (8.3 ± 4.3 mm vs. 7.8 ± 4.8 mm), with a correlation coefficient r = 0.77, small bias of 0.24 mm, and LOA of -6.2 to 5.71 mm. 37.0% and 77% of diameter measurements were within ±1 mm and ±2.5 mm of expert measurements.

CONCLUSIONS

A 3D-Dense-UNet model can detect and segment aneurysms with relatively high accuracy using 3D-RA images. The automatically measured maximum diameter has potential clinical application value.

Deep Learning-Based Software Improves Clinicians' Detection Sensitivity of Aneurysms on Brain TOF-MRA

BACKGROUND AND PURPOSE

The detection of cerebral aneurysms on MRA is a challenging task. Recent studies have used deep learning-based software for automated detection of aneurysms on MRA and have reported high performance. The purpose of this study was to evaluate the incremental value of using deep learning-based software for the detection of aneurysms on MRA by 2 radiologists, a neurosurgeon, and a neurologist.

MATERIALS AND METHODS

TOF-MRA examinations of intracranial aneurysms were retrospectively extracted. Four physicians interpreted the MRA blindly. After a washout period, they interpreted MRA again using the software. Sensitivity and specificity per patient, sensitivity per lesion, and the number of false-positives per case were measured. Diagnostic performances, including subgroup analysis of lesions, were compared. Logistic regression with a generalized estimating equation was used.

RESULTS

A total of 332 patients were evaluated; 135 patients had positive findings with 169 lesions. With software assistance, patient-based sensitivity was statistically improved after the washout period (73.5% versus 86.5%, P < .001). The neurosurgeon and neurologist showed a significant increase in patient-based sensitivity with software assistance (74.8% versus 85.2%, P = .03, and 56.3% versus 84.4%, P < .001, respectively), while the number of false-positive cases did not increase significantly (23 versus 30, P = .20, and 22 versus 24, P = .75, respectively).

CONCLUSIONS

Software-aided reading showed significant incremental value in the sensitivity of clinicians in the detection of aneurysms on MRA without a significant increase in false-positive findings, especially for the neurosurgeon and neurologist. Software-aided reading showed equivocal value for the radiologist.

Computer-aided detection of cerebral aneurysms with magnetic resonance angiography: usefulness of volume rendering to display lesion candidates

PURPOSE

The clinical usefulness of computer-aided detection of cerebral aneurysms has been investigated using different methods to present lesion candidates, but suboptimal methods may have limited its usefulness. We compared three presentation methods to determine which can benefit radiologists the most by enabling them to detect more aneurysms.

MATERIALS AND METHODS

We conducted a multireader multicase observer performance study involving six radiologists and using 470 lesion candidates output by a computer-aided detection program, and compared the following three different presentation methods using the receiver operating characteristic analysis: (1) a lesion candidate is encircled on axial slices, (2) a lesion candidate is overlaid on a volume-rendered image, and (3) combination of (1) and (2). The response time was also compared.

RESULTS

As compared with axial slices, radiologists showed significantly better detection performance when presented with volume-rendered images. There was no significant difference in response time between the two methods. The combined method was associated with a significantly longer response time, but had no added merit in terms of diagnostic accuracy.

CONCLUSION

Even with the aid of computer-aided detection, radiologists overlook many aneurysms if the presentation method is not optimal. Overlaying colored lesion candidates on volume-rendered images can help them detect more aneurysms.

Artificial Intelligence in the Management of Intracranial Aneurysms: Current Status and Future Perspectives

Intracranial aneurysms with subarachnoid hemorrhage lead to high morbidity and mortality. It is of critical importance to detect aneurysms, identify risk factors of rupture, and predict treatment response of aneurysms to guide clinical interventions. Artificial intelligence has received worldwide attention for its impressive performance in image-based tasks. Artificial intelligence serves as an adjunct to physicians in a series of clinical settings, which substantially improves diagnostic accuracy while reducing physicians' workload. Computer-assisted diagnosis systems of aneurysms based on MRA and CTA using deep learning have been evaluated, and excellent performances have been reported. Artificial intelligence has also been used in automated morphologic calculation, rupture risk stratification, and outcomes prediction with the implementation of machine learning methods, which have exhibited incremental value. This review summarizes current advances of artificial intelligence in the management of aneurysms, including detection and prediction. The challenges and future directions of clinical implementations of artificial intelligence are briefly discussed.

Diagnostic value of alternative techniques to gadolinium-based contrast agents in MR neuroimaging-a comprehensive overview

Gadolinium-based contrast agents (GBCAs) increase lesion detection and improve disease characterization for many cerebral pathologies investigated with MRI. These agents, introduced in the late 1980s, are in wide use today. However, some non-ionic linear GBCAs have been associated with the development of nephrogenic systemic fibrosis in patients with kidney failure. Gadolinium deposition has also been found in deep brain structures, although it is of unclear clinical relevance. Hence, new guidelines from the International Society for Magnetic Resonance in Medicine advocate cautious use of GBCA in clinical and research practice. Some linear GBCAs were restricted from use by the European Medicines Agency (EMA) in 2017.

This review focuses on non-contrast-enhanced MRI techniques that can serve as alternatives for the use of GBCAs. Clinical studies on the diagnostic performance of non-contrast-enhanced as well as contrast-enhanced MRI methods, both well established and newly proposed, were included. Advantages and disadvantages together with the diagnostic performance of each method are detailed. Non-contrast-enhanced MRIs discussed in this review are arterial spin labeling (ASL), time of flight (TOF), phase contrast (PC), diffusion-weighted imaging (DWI), magnetic resonance spectroscopy (MRS), susceptibility weighted imaging (SWI), and amide proton transfer (APT) imaging.

Ten common diseases were identified for which studies reported comparisons of non-contrast-enhanced and contrast-enhanced MRI. These specific diseases include primary brain tumors, metastases, abscess, multiple sclerosis, and vascular conditions such as aneurysm, arteriovenous malformation, arteriovenous fistula, intracranial carotid artery occlusive disease, hemorrhagic, and ischemic stroke.

In general, non-contrast-enhanced techniques showed comparable diagnostic performance to contrast-enhanced MRI for specific diagnostic questions. However, some diagnoses still require contrast-enhanced imaging for a complete examination.

Accuracy of detecting enlargement of aneurysms using different MRI modalities and measurement protocols

OBJECTIVE

Aneurysm growth is considered predictive of future rupture of intracranial aneurysms. However, how accurately neuroradiologists can reliably detect incremental aneurysm growth using clinical MRI is still unknown. The purpose of this study was to assess the agreement rate of detecting aneurysm enlargement employing generally used MRI modalities.

METHODS

Three silicone flow phantom models, each with 8 aneurysms of various sizes at different sites, were used in this study. The aneurysm models were identical except for an incremental increase in the sizes of the 8 aneurysms, which ranged from 0.4 mm to 2 mm. The phantoms were imaged on 1.5-T and 3-T MRI units with both time-of-flight (TOF) and contrast-enhanced MR angiography. Three independent expert neuroradiologists measured the aneurysms in a blinded manner using different measurement approaches. The individual and agreement detection rates of aneurysm enlargement among the 3 experts were calculated.

RESULTS

The mean detection rate of any increase in any aneurysmal dimension was 95.7%. The detection rates of the 3 observers (observers A, B, and C) were 98.0%, 96.6%, and 92.7%, respectively (p = 0.22). The detection rates of each MRI modality were 91.3% using 1.5-T TOF, 97.2% using 1.5-T with Gd, 95.8% using 3.0-T TOF, and 97.2% using 3.0-T with Gd (p = 0.31). On the other hand, the mean detection rate for aneurysm enlargement was 54.8%. Specifically, the detection rates of observers A, B, and C were 49.0%, 46.1%, and 66.7%, respectively (p = 0.009). As the incremental enlargement value increased, the detection rate for aneurysm enlargement increased. The use of 1.5-T Gd improved the detection rate for small incremental enlargement (e.g., 0.4–1 mm) of the aneurysm (p = 0.04). The location of the aneurysm also affected the detection rate for aneurysm enlargement (p < 0.0001).

CONCLUSIONS

The detection rate and interobserver agreement were very high for aneurysm enlargement of 0.4–2 mm. The detection rate for at least 1 increase in any aneurysm dimension did not depend on the choice of MRI modality or measurement protocol. Use of Gd improved the accuracy of measurement. Aneurysm location may influence the accuracy of detecting enlargement.

Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms

Purpose To develop and evaluate a supportive algorithm using deep learning for detecting cerebral aneurysms at time-of-flight MR angiography to provide a second assessment of images already interpreted by radiologists. Materials and Methods MR images reported by radiologists to contain aneurysms were extracted from four institutions for the period from November 2006 through October 2017. The images were divided into three data sets: training data set, internal test data set, and external test data set. The algorithm was constructed by deep learning with the training data set, and its sensitivity to detect aneurysms in the test data sets was evaluated. To find aneurysms that had been overlooked in the initial reports, two radiologists independently performed a blinded interpretation of aneurysm candidates detected by the algorithm. When there was disagreement, the final diagnosis was made in consensus. The number of newly detected aneurysms was also evaluated. Results The training data set, which provided training and validation data, included 748 aneurysms (mean size, 3.1 mm ± 2.0 [standard deviation]) from 683 examinations; 318 of these examinations were on male patients (mean age, 63 years ± 13) and 365 were on female patients (mean age, 64 years ± 13). Test data were provided by the internal test data set (649 aneurysms [mean size, 4.1 mm ± 3.2] in 521 examinations, including 177 male patients and 344 female patients with mean age of 66 years ± 12 and 67 years ± 13, respectively) and the external test data set (80 aneurysms [mean size, 4.1 mm ± 2.1] in 67 examinations, including 19 male patients and 48 female patients with mean age of 63 years ± 12 and 68 years ± 12, respectively). The sensitivity was 91% (592 of 649) and 93% (74 of 80) for the internal and external test data sets, respectively. The algorithm improved aneurysm detection in the internal and external test data sets by 4.8% (31 of 649) and 13% (10 of 80), respectively, compared with the initial reports. Conclusion A deep learning algorithm detected cerebral aneurysms in radiologic reports with high sensitivity and improved aneurysm detection compared with the initial reports. © RSNA, 2018 See also the editorial by Flanders in this issue.

Computer-Assisted Detection of Cerebral Aneurysms in MR Angiography in a Routine Image-Reading Environment: Effects on Diagnosis by Radiologists

BACKGROUND AND PURPOSE

Experiences with computer-assisted detection of cerebral aneurysms in diagnosis by radiologists in real-life clinical environments have not been reported. The purpose of this study was to evaluate the usefulness of computer-assisted detection in a routine reading environment.

MATERIALS AND METHODS

During 39 months in a routine clinical practice environment, 2701 MR angiograms were each read by 2 radiologists by using a computer-assisted detection system. Initial interpretation was independently made without using the detection system, followed by a possible alteration of diagnosis after referring to the lesion candidate output from the system. We used the final consensus of the 2 radiologists as the reference standard. The sensitivity and specificity of radiologists before and after seeing the lesion candidates were evaluated by aneurysm- and patient-based analyses.

RESULTS

The use of the computer-assisted detection system increased the number of detected aneurysms by 9.3% (from 258 to 282). Aneurysm-based analysis revealed that the apparent sensitivity of the radiologists' diagnoses made without and with the detection system was 64% and 69%, respectively. The detection system presented 82% of the aneurysms. The detection system more frequently benefited radiologists than being detrimental.

CONCLUSIONS

Routine integration of computer-assisted detection with MR angiography for cerebral aneurysms is feasible, and radiologists can detect a number of additional cerebral aneurysms by using the detection system without a substantial decrease in their specificity. The low confidence of radiologists in the system may limit its usefulness.

Comparing the performance of visual estimation and standard uptake value of F-18 fluorodeoxyglucose positron emission tomography/computed tomography for detecting malignancy in pancreatic tumors other than invasive ductal carcinoma

INTRODUCTION

The utility of FDG PET/CT for the detection and evaluation of invasive ductal carcinoma has been widely reported, but a few studies have assessed the utility of FDG PET/CT to detect malignancy in a variety of pancreatic lesions other than invasive ductal carcinoma.

PURPOSE

To compare the diagnostic performance of visual estimation with the semi-quantitative scores of FDG PET/CT for detecting malignancy in a variety of pancreatic lesions other than invasive ductal carcinoma.

MATERIAL AND METHODS

Images of pathologically proven pancreatic lesions from 32 patients were retrospectively evaluated: 14 benign lesions, 7 borderline (low malignant) lesions, and 11 malignant lesions. The average scores from visual estimation by the two observers were compared to two semi-quantitative analyses of FDG uptake in the lesions, namely the maximum standardized uptake value (SUVmax) and mean standardized uptake value (SUVmean).

RESULTS

Visual analysis value, SUVmax and SUVmean were 0.33 ± 0.21, 1.8 ± 0.7 and 1.5 ± 0.7 for the benign lesions, 0.70 ± 0.28, 5.0 ± 2.6 and 3.1±1.7 for the borderline lesions, and 0.73 ± 0.18, 4.7 ± 2.5 and 3.2 ± 1.6 for the malignant lesions, respectively. Receiver operating characteristic analysis revealed the areas under the curves for detecting non-benign (malignant or borderline) lesions through visual analysis, SUVmax, and SUVmean were 0.914, 0.954, and 0.875, respectively.

CONCLUSION

For a variety of pancreatic lesions other than invasive ductal carcinoma, visual analysis and semi-quantitative analyses all showed strong diagnostic performance. However, semi-quantitative analysis with SUVmax proved to be the most effective method for detecting non-benign pancreatic lesions.

Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting

BACKGROUND AND PURPOSE

MRA is widely accepted as a noninvasive diagnostic tool for the detection of intracranial aneurysms, but detection is still a challenging task with rather low detection rates. Our aim was to examine the performance of a computer-aided diagnosis algorithm for detecting intracranial aneurysms on MRA in a clinical setting.

MATERIALS AND METHODS

Aneurysm detectability was evaluated retrospectively in 48 subjects with and without computer-aided diagnosis by 6 readers using a clinical 3D viewing system. Aneurysms ranged from 1.1 to 6.0 mm (mean = 3.12 mm, median = 2.50 mm). We conducted a multireader, multicase, double-crossover design, free-response, observer-performance study on sets of images from different MRA scanners by using DSA as the reference standard. Jackknife alternative free-response operating characteristic curve analysis with the figure of merit was used.

RESULTS

For all readers combined, the mean figure of merit improved from 0.655 to 0.759, indicating a change in the figure of merit attributable to computer-aided diagnosis of 0.10 (95% CI, 0.03-0.18), which was statistically significant (F(1,47) = 7.00, P = .011). Five of the 6 radiologists had improved performance with computer-aided diagnosis, primarily due to increased sensitivity.

CONCLUSIONS

In conditions similar to clinical practice, using computer-aided diagnosis significantly improved radiologists' detection of intracranial DSA-confirmed aneurysms of ≤6 mm.

An engineering view on megatrends in radiology: digitization to quantitative tools of medicine

Within six months of the discovery of X-ray in 1895, the technology was used to scan the interior of the human body, paving the way for many innovations in the field of medicine, including an ultrasound device in 1950, a CT scanner in 1972, and MRI in 1980. More recent decades have witnessed developments such as digital imaging using a picture archiving and communication system, computer-aided detection/diagnosis, organ-specific workstations, and molecular, functional, and quantitative imaging. One of the latest technical breakthrough in the field of radiology has been imaging genomics and robotic interventions for biopsy and theragnosis. This review provides an engineering perspective on these developments and several other megatrends in radiology.

Computer-aided diagnosis for detection of lacunar infarcts on MR images: ROC analysis of radiologists' performance

The purpose of this study was to retrospectively evaluate radiologist performance in detection of lacunar infarcts on T1- and T2-weighted images, without and with the use of a computer-aided diagnosis (CAD) scheme. Thirty T1-weighted and 30 T2-weighted MR images obtained from 30 patients were used for assessing observer performance. These images were acquired using the fast spin-echo sequence with a 1.5-T MR imaging scanner. The group included 15 patients (age range, 48-83 years; mean age, 67.2 years; 10 men and five women) with a lacunar infarct and 15 patients (age range, 39-76 years; mean age, 64.0 years; eight men and seven women) without lacunar infarcts. Nine radiologists participated in the study. The radiologists initially interpreted the T1- and T2-weighted images without and then with the use of CAD, which indicated their confidence levels regarding the presence (or absence) of lacunar infarcts and the most likely position of a lesion on each MR scan. The observers' performance without and with the computer output was evaluated by performing receiver operating characteristic analysis. For the nine radiologists, the mean area under the best-fit binormal receiver operating characteristic curve plotted for unit square values of radiologists who interpreted the images without and with the scheme were 0.891 and 0.937, respectively. The performance of the radiologists improved significantly when they used the computer output (p=0.032). The CAD scheme has potential to improve the accuracy of radiologists' performance in detection of lacunar infarcts.

Magnetic Resonance Image Analysis for Brain CAD Systems with Machine Learning

This chapter describes the image analysis for brain Computer-Aided Diagnosis (CAD) systems with machine learning techniques, which could assist radiologists in the detection of such brain diseases as asymptomatic unruptured aneurysms, Alzheimer’s Disease (AD), vascular dementia, and Multiple Sclerosis (MS) by magnetic resonance imaging. Image analysis in CAD systems consists of image enhancement, initial detection, and image feature extraction, including segmentation. In addition, the authors review the classification of true and false positives using machine learning techniques, as well as the evaluation methods and development cycle for CAD systems.

Multicentre multiobserver study of diffusion-weighted and fluid-attenuated inversion recovery MRI for the diagnosis of sporadic Creutzfeldt-Jakob disease: a reliability and agreement study

Objectives To assess the utility of the display standardisation of diffusion-weighted MRI (DWI) and to compare the effectiveness of DWI and fluid-attenuated inversion recovery (FLAIR) MRI for the diagnosis of sporadic Creutzfeldt-Jakob disease (sCJD). Design A reliability and agreement study. Setting Thirteen MRI observers comprising eight neurologists and five radiologists at two universities in Japan. Participants Data of 1.5-Tesla DWI and FLAIR were obtained from 29 patients with sCJD and 13 controls. Outcome measures Standardisation of DWI display was performed utilising b0 imaging. The observers participated in standardised DWI, variable DWI (the display adjustment was observer dependent) and FLAIR sessions. The observers independently assessed each MRI for CJD-related lesions, that is, hyperintensity in the cerebral cortex or striatum, using a continuous rating scale. Performance was evaluated by the area under the receiver operating characteristics curve (AUC). Results The mean AUC values were 0.84 (95% CI 0.81 to 0.87) for standardised DWI, 0.85 (95% CI 0.82 to 0.88) for variable DWI and 0.68 (95% CI 0.63 to 0.72) for FLAIR, demonstrating the superiority of DWI (p<0.05). There was a trend for higher intraclass correlations of standardised DWI (0.74, 95% CI 0.66 to 0.83) and variable DWI (0.72, 95% CI 0.62 to 0.81) than that of FLAIR (0.63, 95% CI 0.53 to 0.74), although the differences were not statistically significant. Conclusions Standardised DWI is as reliable as variable DWI, and the two DWI displays are superior to FLAIR for the diagnosis of sCJD. The authors propose that hyperintensity in the cerebral cortex or striatum on 1.5-Tesla DWI but not FLAIR can be a reliable diagnostic marker for sCJD.

Predicting readers' diagnostic accuracy with a new CAD algorithm

RATIONALE AND OBJECTIVES

Before computer-aided detection (CAD) algorithms can be used in clinical practice, they must be shown to improve readers' diagnostic accuracy over their unaided performance. This is usually accomplished through a large multireader, multicase (MRMC) clinical trial. It is burdensome, however, for an MRMC study to be performed with each new release of a CAD algorithm. The aim of this report is to present an approach for building models to predict readers' accuracy with a new CAD algorithm.

MATERIALS AND METHODS

A modeling approach for predicting readers' results with a new CAD algorithm is described. Multiple-variable logistic regression was used to build models for readers' sensitivity and false-positive rate, given the results of an MRMC study with an older CAD algorithm and the stand-alone performance results of a new CAD algorithm. Data from a large lung MRMC CAD trial are used to illustrate the modeling approach and test the ability of the models to predict readers' accuracy with the new CAD algorithm.

RESULTS

The model overestimated the readers' actual sensitivity with the new CAD algorithm, but this did not reach statistical significance (0.621 vs 0.603, P = .147). The observed and predicted false-positive rates also did not differ significantly (0.275 vs 0.285, P = .250).

CONCLUSIONS

Using one clinical study as a test case, it is shown that the modeling approach is feasible. More testing of the approach is needed to determine if and under what circumstances it can be used as an alternative to a full-scale MRMC study. Meanwhile, the approach can be used to determine if a new CAD algorithm is likely to improve readers' accuracy before embarking on a full-scale MRMC study.

Fast inversion recovery magnetic resonance angiography of the intracranial arteries

Inversion-prepared pulse sequences can be used for noncontrast MR angiography (MRA) but suffer from long scan times when acquired using conventional nonaccelerated techniques. This work proposes a subtraction-based spin-labeling, three-dimensional fast inversion recovery MRA (FIR-MRA) method for imaging the intracranial arteries. FIR-MRA uses alternating cycles of nonselective and slab-selective inversions, leading to dark-blood and bright-blood images, respectively. The signal difference between these images eliminates static background tissue and generates the angiogram. To reduce scan time, segmented fast gradient recalled echo readout and parallel imaging are applied. The inversion recovery with embedded self-calibration method used allows for parallel acceleration at factors of 2 and above. An off-resonance selective inversion provides effective venous suppression, with no detriment to the depiction of arteries. FIR-MRA was compared against conventional three-dimensional time-of-flight angiography at 3 T in eight normal subjects. Results showed that FIR-MRA had superior vessel conspicuity in the distal vessels (P < 0.05), and equal or better vessel continuity and venous suppression. However, FIR-MRA had inferior vessel sharpness (P < 0.05) in four of nine vessel groups. The clinical utility of FIR-MRA was demonstrated in three MRA patients.

Computer-aided detection of intracranial aneurysms in MR angiography

Intracranial aneurysms represent a significant cause of morbidity and mortality. While the risk factors for aneurysm formation are known, the detection of aneurysms remains challenging. Magnetic resonance angiography (MRA) has recently emerged as a useful non-invasive method for aneurysm detection. However, even for experienced neuroradiologists, the sensitivity to small (<5 mm) aneurysms in MRA images is poor, on the order of 30~60% in recent, large series. We describe a fully automated computer-aided detection (CAD) scheme for detecting aneurysms on 3D time-of-flight (TOF) MRA images. The scheme locates points of interest (POIs) on individual MRA datasets by combining two complementary techniques. The first technique segments the intracranial arteries automatically and finds POIs from the segmented vessels. The second technique identifies POIs directly from the raw, unsegmented image dataset. This latter technique is useful in cases of incomplete segmentation. Following a series of feature calculations, a small fraction of POIs are retained as candidate aneurysms from the collected POIs according to predetermined rules. The CAD scheme was evaluated on 287 datasets containing 147 aneurysms that were verified with digital subtraction angiography, the accepted standard of reference for aneurysm detection. For two different operating points, the CAD scheme achieved a sensitivity of 80% (71% for aneurysms less than 5 mm) with three mean false positives per case, and 95% (91% for aneurysms less than 5 mm) with nine mean false positives per case. In conclusion, the CAD scheme showed good accuracy and may have application in improving the sensitivity of aneurysm detection on MR images.

Diffusion-weighted imaging in ischemic stroke: effect of display method on observers' diagnostic performance

RATIONALE AND OBJECTIVES

When evaluating ischemic stroke on diffusion-weighted magnetic resonance imaging (DWI), the display method has not been investigated. The purpose of this study was to determine whether standardization of the display method for DWI affects observers' diagnostic performance in detecting ischemic stroke on DWI.

MATERIALS AND METHODS

Twenty-six observers evaluated 40 DWI studies in 20 patients with acute (< 6 hours) middle cerebral arterial strokes and 20 controls for the presence of hyperintense lesions in 10 areas using the Alberta Stroke Programme Early CT Score (ASPECTS) system and one area in the corona radiata using a modified version of the ASPECTS system (ASPECTS-DWI). The images were reviewed using a standardized display method (SDM) and a conventional display method (CDM). The reading time was recorded for each session. The observers' performance was evaluated with receiver-operating characteristic analysis.

RESULTS

In all observers with ASPECTS-DWI scores of < or = 8 points, the value of the mean average area under the receiver-operating characteristic curve was slightly higher for the SDM than the CDM, but the difference was not statistically significant. In the insular ribbon, diagnostic accuracy was significantly higher with the SDM than the CDM (P = .036). In the other locations, there were no significant differences. With the SDM, the mean reading time was reduced by 7.5 seconds (P = .024).

CONCLUSION

The SDM improved diagnostic accuracy for the insular ribbon and shortened the reading time, although it did not improve observers' performance with the ASPECTS-DWI system.

Usefulness of computer-aided diagnosis schemes for vertebral fractures and lung nodules on chest radiographs

OBJECTIVE

We retrospectively evaluated the usefulness of computer-aided diagnosis (CAD) schemes to radiologist performance in the simultaneous detection of vertebral fractures and lung nodules on chest radiographs.

MATERIALS AND METHODS

We evaluated posteroanterior and lateral chest images of 21 patients with vertebral fractures, 31 patients with lung nodules, and 10 persons acting as controls. The total number of subjects was 60 because both lesions were present in four patients. Eighteen radiologists were asked to detect vertebral fractures and nodules simultaneously on posteroanterior and lateral images. The radiologists indicated their confidence level ratings regarding the presence or absence of lesions and the most likely location of each lesion on either posteroanterior or lateral images, first without and then with CAD output. The observers' performance was evaluated with use of receiver operating characteristic (ROC) and jackknife free-response ROC curves.

RESULTS

With the CAD scheme, the average area under the ROC curve for detection of vertebral fractures improved from 0.906 to 0.951 (p = 0.002). That for lung nodules also improved, but the improvement was not statistically significant (0.804-0.816, p = 0.297). The figure-of-merit values obtained with the jackknife free-response ROC program improved from 0.585 to 0.680 (p < 0.001) for vertebral fractures and from 0.622 to 0.650 (p = 0.017) for nodules, both results having statistical significance. Average sensitivity in the detection of lesions improved from 59.8% to 69.3% for vertebral fractures and from 64.9% to 67.6% for nodules.

CONCLUSION

In the detection of vertebral fractures and lung nodules on chest images, diagnostic accuracy among radiologists improves with the use of CAD.

Computer-aided diagnosis scheme for detection of lacunar infarcts on MR images

RATIONALE AND OBJECTIVES

The detection and management of asymptomatic lacunar infarcts on magnetic resonance (MR) images are important tasks for radiologists to ensure the prevention of severe cerebral infarctions. However, accurate identification of the lacunar infarcts on MR images is a difficult task for the radiologists. Therefore the purpose of this study was to develop a computer-aided diagnosis scheme for the detection of lacunar infarcts to assist radiologists' interpretation as a "second opinion."

MATERIALS AND METHODS

Our database comprised 1,143 T1- and 1,143 T2-weighted images obtained from 132 patients. The locations of the lacunar infarcts were determined by experienced neuroradiologists. We first segmented the cerebral region in a T1-weighted image by using a region growing technique for restricting the search area of lacunar infarcts. For identifying the initial lacunar infarcts candidates, a top-hat transform and multiple-phase binarization were then applied to the T2-weighted image within the segmented cerebral region. For eliminating the false positives (FPs), we determined 12 features--the locations x and y, signal intensity differences in the T1- and T2-weighted images, nodular components from a scale of 1 to 4, and nodular and linear components from a scale of 1 to 4. The nodular components and the linear components were obtained using a filter bank technique. The rule-based schemes and a support vector machine with 12 features were applied to the regions of the initial candidates for distinguishing between lacunar infarcts and FPs.

RESULTS

Our computerized scheme was evaluated by using a holdout method. The sensitivity of the detection of lacunar infarcts was 96.8% (90/93) with 0.76 FP per image.

CONCLUSIONS

Our computerized scheme would be useful in assisting radiologists for identifying lacunar infarcts in MR images.

Computer-aided diagnosis in medical imaging: historical review, current status and future potential

Computer-aided diagnosis (CAD) has become one of the major research subjects in medical imaging and diagnostic radiology. In this article, the motivation and philosophy for early development of CAD schemes are presented together with the current status and future potential of CAD in a PACS environment. With CAD, radiologists use the computer output as a "second opinion" and make the final decisions. CAD is a concept established by taking into account equally the roles of physicians and computers, whereas automated computer diagnosis is a concept based on computer algorithms only. With CAD, the performance by computers does not have to be comparable to or better than that by physicians, but needs to be complementary to that by physicians. In fact, a large number of CAD systems have been employed for assisting physicians in the early detection of breast cancers on mammograms. A CAD scheme that makes use of lateral chest images has the potential to improve the overall performance in the detection of lung nodules when combined with another CAD scheme for PA chest images. Because vertebral fractures can be detected reliably by computer on lateral chest radiographs, radiologists' accuracy in the detection of vertebral fractures would be improved by the use of CAD, and thus early diagnosis of osteoporosis would become possible. In MRA, a CAD system has been developed for assisting radiologists in the detection of intracranial aneurysms. On successive bone scan images, a CAD scheme for detection of interval changes has been developed by use of temporal subtraction images. In the future, many CAD schemes could be assembled as packages and implemented as a part of PACS. For example, the package for chest CAD may include the computerized detection of lung nodules, interstitial opacities, cardiomegaly, vertebral fractures, and interval changes in chest radiographs as well as the computerized classification of benign and malignant nodules and the differential diagnosis of interstitial lung diseases. In order to assist in the differential diagnosis, it would be possible to search for and retrieve images (or lesions) with known pathology, which would be very similar to a new unknown case, from PACS when a reliable and useful method has been developed for quantifying the similarity of a pair of images for visual comparison by radiologists.

Diagnostic imaging over the last 50 years: research and development in medical imaging science and technology

Over the last 50 years, diagnostic imaging has grown from a state of infancy to a high level of maturity. Many new imaging modalities have been developed. However, modern medical imaging includes not only image production but also image processing, computer-aided diagnosis (CAD), image recording and storage, and image transmission, most of which are included in a picture archiving and communication system (PACS). The content of this paper includes a short review of research and development in medical imaging science and technology, which covers (a) diagnostic imaging in the 1950s, (b) the importance of image quality and diagnostic performance, (c) MTF, Wiener spectrum, NEQ and DQE, (d) ROC analysis, (e) analogue imaging systems, (f) digital imaging systems, (g) image processing, (h) computer-aided diagnosis, (i) PACS, (j) 3D imaging and (k) future directions. Although some of the modalities are already very sophisticated, further improvements will be made in image quality for MRI, ultrasound and molecular imaging. The infrastructure of PACS is likely to be improved further in terms of its reliability, speed and capacity. However, CAD is currently still in its infancy, and is likely to be a subject of research for a long time.

Computerized detection of intracranial aneurysms for three-dimensional MR angiography: feature extraction of small protrusions based on a shape-based difference image technique

We have improved a computerized scheme for the detection of intracranial aneurysms for three-dimensional (3-D) magnetic resonance angiography (MRA) by the use of image features of small protrusions extracted based on a shape-based difference image (SBDI) technique. Initial candidates were identified by use of a multiple gray-level thresholding technique in dot enhanced images, and by finding short branches in skeleton images. Image features related to aneurysms were determined based on candidate regions segmented by use of a region growing technique. For extracting additional features on small protrusions or small aneurysms, we have developed an SBDI technique, which was based on the shape-based difference between an original segmented vessel and a vessel with suppressed local change in thickness. The SBDI technique was useful for obtaining local changes in vessel thickness, i.e., SBD regions, which could be small aneurysms in the case of true positives, but thin or very small regions in the case of false positives. Many false positives were removed by means of rule-based schemes and linear discriminant analysis on various 3-D localized image features, including SBDI features. We tested the computerized scheme on 53 cases with 61 aneurysms and 62 nonaneurysm cases based on a leave-one-out-by-patient test method. As a result, false positives per patient decreased from 5.8 to 3.8, while a high sensitivity of 97% was maintained by use of the SBDI technique, in which SBDI features were effective for removing some false positives. The computer-aided diagnostic (CAD) scheme may be robust and useful in assisting radiologists in the detection of intracranial aneurysms for MRA.