An artificial intelligence-driven scoring system to measure histological disease activity in ulcerative colitis.

BACKGROUND AND AIMS: Assessment and scoring of histological images in Ulcerative colitis (UC) is prone to inter- and intra-observer variability. This study aimed to investigate whether an artificial intelligence (AI) system developed using image processing and machine learning algorithms could measure histological disease activity based on the Nancy index. METHODS: A total of 200 histological images of patients with UC were used in this study. A novel AI algorithm was developed using state-of-the-art image processing and machine learning algorithms based on deep learning and feature extraction. The cell regions of each image, followed by the Nancy index, were manually annotated and measured independently by four histopathologists. Manual and AI-automated measurements of the Nancy index score were conducted and assessed using the intraclass correlation coefficient (ICC). RESULTS: The 200-image dataset was divided into two groups (80% was used for training and 20% for testing). Intraclass correlation coefficient statistical analyses were performed to evaluate the AI tool and used as a reference to calculate the accuracy. The average ICC among the histopathologists was 89.3 and the average ICC between histopathologists and the AI tool was 87.2. The AI tool was found to be highly correlated with histopathologists. CONCLUSIONS: The high correlation of performance of the AI method suggests promising potential for inflammatory bowel disease clinical applications. A standardized automated histological AI-driven scoring system can potentially be used in daily inflammatory bowel disease practice to reduce training needs and resource use, eliminate the subjectivity of the pathologists, and assess disease severity for treatment decisions.

MRI Digital Artery Volume Index (DAVIX) as a surrogate outcome measure of digital ulcer disease in patients with systemic sclerosis: a prospective cohort study.

BACKGROUND: Vascular fibrosis is a key manifestation of systemic sclerosis that leads to the narrowing of small and medium arteries, causing vascular clinical manifestations including digital ulcers and pulmonary arterial hypertension. We investigated the potential of the MRI-based Digital Artery Volume Index (DAVIX) as a surrogate outcome measure of vascular fibrosis by using it to quantify and predict the burden of digital ulcer disease in patients with systemic sclerosis. METHODS: Two independent cohorts of patients participating in the prospective observational study STRIKE were consecutively enrolled from the Scleroderma Clinic of the Leeds Teaching Hospitals Trust, Leeds, UK. Eligible patients were aged 18 years or older and fulfilled the very early diagnosis of systemic sclerosis (VEDOSS) or the 2013 American College of Rheumatology (ACR)-European Alliance of Associations for Rheumatology (EULAR) systemic sclerosis classification criteria. DAVIX was calculated as the percentage mean of the ratio of digital artery volume to finger volume in the four fingers of the dominant hand. Data were collected at baseline and 12-month follow-up, and the primary outcome was the presence of digital ulcers at 12-month follow-up. FINDINGS: Between Feb 7, 2018, and April 11, 2022, we included 85 patients in the exploratory cohort and 150 in the validation cohort. In the exploratory cohort, the mean age was 54·5 years (SD 11·6), 75 (88%) of 85 patients were women, ten (12%) were men, and 69 (82%) were White. In the validation cohort, the mean age was 53·5 years (SD 13·8), 136 (91%) of 150 patients were women, 14 (9%) were men, and 127 (85%) were White. In the exploratory cohort, DAVIX was significantly lower in patients with previous or active digital ulcers (0·34% [IQR 0·16-0·69]) than in those without digital ulcer disease (0·65% [0·42-0·88]; p=0·015); this finding was substantiated in the validation cohort (0·43% [0·20-0·73] vs 0·73% [0·53-0·97]; p<0·0001). Patients who developed new digital ulcers during 12-month follow-up had a lower DAVIX (0·23% [0·10-0·66]) than those who did not (0·65% [0·45-0·91]; p=0·0039). DAVIX was negatively correlated with disease duration (r=-0·415; p<0·0001), the ratio of forced vital capacity to the diffusing capacity of the lungs for carbon monoxide (r=-0·334; p=0·0091), nailfold capillaroscopy pattern (r=-0·447; p<0·0001), and baseline modified Rodnan skin score (r=-0·305; p=0·014) and was positively correlated with the diffusing capacity of carbon monoxide (r=0·368; p=0·0041). DAVIX was negatively correlated with change in score on the Scleroderma Health Assessment Questionnaire-Disability Index (r=-0·308; p=0·024), Visual Analogue Scale (VAS) Raynaud's (r=-0·271; p=0·044), and VAS digital ulcers (r=-0·291; p=0·044). INTERPRETATION: DAVIX is a promising surrogate outcome measure of digital ulcer disease in patients with systemic sclerosis. The ability of DAVIX to non-invasively predict future digital ulcers and worsening of patient-reported outcomes could aid patient enrichment and stratification in clinical trials. Clinically, DAVIX could offer insights into the assessment of vascular activity. The sensitivity of DAVIX to change over time and with treatment will establish its value as an imaging outcome measure of vascular disease. FUNDING: National Institute for Health Research Biomedical Research Centre and University of Leeds Industry Engagement Accelerator Fund.

Three-Dimensional Adaptive Image Compression Concept for Medical Imaging: Application to Computed Tomography Angiography for Peripheral Arteries.

Advances in computed tomography (CT) have resulted in a substantial increase in the size of datasets. We built a new concept of medical image compression that provides the best compromise between compression rate and image quality. The method is based on multiple contexts and regions-of-interest (ROI) defined according to the degree of clinical interest. High priority areas (primary ROIs) are assigned a lossless compression. Other areas (secondary ROIs and background) are compressed with moderate or heavy losses. The method is applied to a whole dataset of CT angiography (CTA) of the lower extremity vasculature. It is compared to standard lossy compression techniques in terms of quantitative and qualitative image quality. It is also compared to standard lossless compression techniques in terms of image size reduction and compression ratio. The proposed compression method met quantitative criteria for high-quality encoding. It obtained the highest qualitative image quality rating score, with a statistically significant difference compared to other methods. The average compressed image size was up to 61% lower compared to standard compression techniques, with a 9:1 compression ratio compared with original non-compressed images. Our new adaptive 3D compression method for CT images can save data storage space while preserving clinically relevant information.

Multimodal imaging of the distal interphalangeal-joint synovio-entheseal complex in psoriatic arthritis (MIDAS): a cross-sectional study on the diagnostic accuracy of different imaging modalities comparing psoriatic arthritis to psoriasis and osteoarthritis.

OBJECTIVE: Can ultrasound (US), MRI and X-ray applied to the distal interphalangeal (DIP)-joint and synovio-entheseal complex (SEC) discriminate between patients with psoriatic arthritis (PsA), skin psoriasis (PsO) and hand osteoarthritis (OA)? METHODS: In this prospective, cross-sectional study, patients with DIP-joint PsA and nail involvement (n=50), PsO with nail involvement (n=12); and OA (n=13); were consecutively recruited. Risk ratios (RR) were calculated for US, MRI and X-ray findings of the DIP-joint and SEC between diagnoses. RESULTS: New bone formation (NBF) in US and MRI was a hallmark of OA, reducing the risk of having PsA (RR 0.52 (95% CI 0.43 to 0.63) and 0.64 (95% CI 0.56 to 0.74). The OA group was different from PsA and PsO on all MRI and X-ray outcomes reflected in a lower RR of having PsA; RR ranging from 0.20 (95% CI 0.13 to 0.31) for MRI bone marrow oedema (BMO) to 0.85 (95% CI 0.80 to 0.90) in X-ray enthesitis. No outcome in US, MRI or X-ray was significantly associated with a higher risk of PsA versus PsO, although there was a trend to a higher degree of US erosions and NBF in PsA. 82% of PsA and 67% of PsO was treated with disease modifying antirheumatic drugs which commonly reflects the clinical setting. CONCLUSION: High grade of US, MRI and X-ray NBF reduce the RR of having PsA compared with OA. In PsA versus PsO patients, there was a trend for US to demonstrate more structural changes in PsA although this did not reach significance.

Current Landscape of Imaging and the Potential Role for Artificial Intelligence in the Management of COVID-19.

The clinical management of COVID-19 is challenging. Medical imaging plays a critical role in the early detection, clinical monitoring and outcomes assessment of this disease. Chest x-ray radiography and computed tomography) are the standard imaging modalities used for the structural assessment of the disease status, while functional imaging (namely, positron emission tomography) has had limited application. Artificial intelligence can enhance the predictive power and utilization of these imaging approaches and new approaches focusing on detection, stratification and prognostication are showing encouraging results. We review the current landscape of these imaging modalities and artificial intelligence approaches as applied in COVID-19 management.

Artificial Intelligence-Based Clinical Decision Support Systems Using Advanced Medical Imaging and Radiomics.

Artificial intelligence (AI) is poised to make a veritable impact in medicine. Clinical decision support (CDS) is an important area where AI can augment the clinician's capability to collect, understand and make inferences on an overwhelming volume of patient data to reach the optimal clinical decision. Advancements in medical image analysis, such as Radiomics, and data computation, such as machine learning, have expanded our understanding of disease processes and their management. In this article, we review the most relevant concepts of AI as applicable to advanced imaging-based clinical decision support systems.

The usability aspects of medication-related decision support systems in the inpatient setting: A systematic review.

Effort has been made to study the effect of medication-related clinical decision support systems in the inpatient setting; however, there is not much known about the usability of these systems. The goal of this study is to systematically review studies that focused on the usability aspects such as effectiveness, efficiency, and satisfaction of these systems. We systematically searched relevant articles in Scopus, Embase, and PubMed from 1 January 2000 to 1 January 2016, and found 22 articles. Based on Van Welie's usability model, we categorized usability aspects in terms of usage indicators and means. Our results showed that evidence was mainly found for effectiveness and efficiency. They showed positive results in the usage indicators errors and safety and performance speed. The means warnings and adaptability also had mostly positive results. To date, the effects satisfaction of clinical decision support system remains understudied. Aspects such as memorability, learnability, and consistency require more attention.

CT attenuation values of blood and myocardium: rationale for accurate coronary artery calcifications detection with multi-detector CT.

OBJECTIVES: To determine inter-session and intra/inter-individual variations of the attenuations of aortic blood/myocardium with MDCT in the context of calcium scoring. To evaluate whether these variations are dependent on patients' characteristics. METHODS: Fifty-four volunteers were evaluated with calcium scoring non-enhanced CT. We measured attenuations (inter-individual variation) and standard deviations (SD, intra-individual variation) of the blood in the ascending aorta and of the myocardium of left ventricle. Every volunteer was examined twice to study the inter-session variation. The fat pad thickness at the sternum and noise (SD of air) were measured too. These values were correlated with the measured aortic/ventricular attenuations and their SDs (Pearson). Historically fixed thresholds (90 and 130 HU) were tested against different models based on attenuations of blood/ventricle. RESULTS: The mean attenuation was 46 HU (range, 17-84 HU) with mean SD 23 HU for the blood, and 39 HU (10-82 HU) with mean SD 18 HU for the myocardium. The attenuation/SD of the blood were significantly higher than those of the myocardium (p < 0.01). The inter-session variation was not significant. There was a poor correlation between SD of aortic blood/ventricle with fat thickness/noise. Based on existing models, 90 HU threshold offers a confidence interval of approximately 95% and 130 HU more than 99%. CONCLUSIONS: Historical thresholds offer high confidence intervals for exclusion of aortic blood/myocardium and by the way for detecting calcifications. Nevertheless, considering the large variations of blood/myocardium CT values and the influence of patient's characteristics, a better approach might be an adaptive threshold.

Computer Aided Detection and measurement of peripheral artery disease.

Computer-Aided Tomography Angiography (CTA) images are the standard for assessing Peripheral artery disease (PAD). This paper presents a Computer Aided Detection (CAD) and Computer Aided Measurement (CAM) system for PAD. The CAD stage detects the arterial network using a 3D region growing method and a fast 3D morphology operation. The CAM stage aims to accurately measure the artery diameters from the detected vessel centerline, compensating for the partial volume effect using Expectation Maximization (EM) and a Markov Random field (MRF). The system has been evaluated on phantom data and also applied to fifteen (15) CTA datasets, where the detection accuracy of stenosis was 88% and the measurement accuracy was with an 8% error.

Variability of ascending aorta diameter measurements as assessed with electrocardiography-gated multidetector computerized tomography and computer assisted diagnosis software.

Recently, morphometric measurements of the ascending aorta have been done with ECG-gated multidector computerized tomography (MDCT) to help the development of future novel transcatheter therapies (TCT); nevertheless, the variability of such measurements remains unknown. Thirty patients referred for ECG-gated CT thoracic angiography were evaluated. Continuous reformations of the ascending aorta, perpendicular to the centerline, were obtained automatically with a commercially available computer aided diagnosis (CAD). Then measurements of the maximal diameter were done with the CAD and manually by two observers (separately). Measurements were repeated one month later. The Bland-Altman method, Spearman coefficients, and a Wilcoxon signed-rank test were used to evaluate the variability, the correlation, and the differences between observers. The interobserver variability for maximal diameter between the two observers was up to 1.2 mm with limits of agreement [-1.5, +0.9] mm; whereas the intraobserver limits were [-1.2, +1.0] mm for the first observer and [-0.8, +0.8] mm for the second observer. The intraobserver CAD variability was 0.8 mm. The correlation was good between observers and the CAD (0.980-0.986); however, significant differences do exist (P<0.001). The maximum variability observed was 1.2 mm and should be considered in reports of measurements of the ascending aorta. The CAD is as reproducible as an experienced reader.

Shape-based computer-aided detection of lung nodules in thoracic CT images.

In this paper, a new computer tomography (CT) lung nodule computer-aided detection (CAD) method is proposed for detecting both solid nodules and ground-glass opacity (GGO) nodules (part solid and nonsolid). This method consists of several steps. First, the lung region is segmented from the CT data using a fuzzy thresholding method. Then, the volumetric shape index map, which is based on local Gaussian and mean curvatures, and the "dot" map, which is based on the eigenvalues of a Hessian matrix, are calculated for each voxel within the lungs to enhance objects of a specific shape with high spherical elements (such as nodule objects). The combination of the shape index (local shape information) and "dot" features (local intensity dispersion information) provides a good structure descriptor for the initial nodule candidates generation. Antigeometric diffusion, which diffuses across the image edges, is used as a preprocessing step. The smoothness of image edges enables the accurate calculation of voxel-based geometric features. Adaptive thresholding and modified expectation-maximization methods are employed to segment potential nodule objects. Rule-based filtering is first used to remove easily dismissible nonnodule objects. This is followed by a weighted support vector machine (SVM) classification to further reduce the number of false positive (FP) objects. The proposed method has been trained and validated on a clinical dataset of 108 thoracic CT scans using a wide range of tube dose levels that contain 220 nodules (185 solid nodules and 35 GGO nodules) determined by a ground truth reading process. The data were randomly split into training and testing datasets. The experimental results using the independent dataset indicate an average detection rate of 90.2%, with approximately 8.2 FP/scan. Some challenging nodules such as nonspherical nodules and low-contrast part-solid and nonsolid nodules were identified, while most tissues such as blood vessels were excluded. The method's high detection rate, fast computation, and applicability to different imaging conditions and nodule types shows much promise for clinical applications.

Efficient computer-aided detection of ground-glass opacity nodules in thoracic CT images.

In this paper, an efficient compute-aided detection method is proposed for detecting Ground-Glass Opacity (GGO) nodules in thoracic CT images. GGOs represent a clinically important type of lung nodule which are ignored by many existing CAD systems. Anti-geometric diffusion is used as preprocessing to remove image noise. Geometric shape features (such as shape index and dot enhancement), are calculated for each voxel within the lung area to extract potential nodule concentrations. Rule based filtering is then applied to remove False Positive regions. The proposed method has been validated on a clinical dataset of 50 thoracic CT scans that contains 52 GGO nodules. A total of 48 nodules were correctly detected and resulted in an average detection rate of 92.3%, with the number of false positives at approximately 12.7/scan (0.07/slice). The high detection performance of the method suggested promising potential for clinical applications.

Automated detection of lung nodules in CT images using shape-based genetic algorithm.

A shape-based genetic algorithm template-matching (GATM) method is proposed for the detection of nodules with spherical elements. A spherical-oriented convolution-based filtering scheme is used as a pre-processing step for enhancement. To define the fitness function for GATM, a 3D geometric shape feature is calculated at each voxel and then combined into a global nodule intensity distribution. Lung nodule phantom images are used as reference images for template matching. The proposed method has been validated on a clinical dataset of 70 thoracic CT scans (involving 16,800 CT slices) that contains 178 nodules as a gold standard. A total of 160 nodules were correctly detected by the proposed method and resulted in a detection rate of about 90%, with the number of false positives at approximately 14.6/scan (0.06/slice). The high-detection performance of the method suggested promising potential for clinical applications.

Volumetric quantification of atherosclerotic plaque in CT considering partial volume effect.

Coronary artery calcification (CAC) is quantified based on a computed tomography (CT) scan image. A calcified region is identified. Modified expectation maximization (MEM) of a statistical model for the calcified and background material is used to estimate the partial calcium content of the voxels. The algorithm limits the region over which MEM is performed. By using MEM, the statistical properties of the model are iteratively updated based on the calculated resultant calcium distribution from the previous iteration. The estimated statistical properties are used to generate a map of the partial calcium content in the calcified region. The volume of calcium in the calcified region is determined based on the map. The experimental results on a cardiac phantom, scanned 90 times using 15 different protocols, demonstrate that the proposed method is less sensitive to partial volume effect and noise, with average error of 9.5% (standard deviation (SD) of 5-7mm(3)) compared with 67% (SD of 3-20mm(3)) for conventional techniques. The high reproducibility of the proposed method for 35 patients, scanned twice using the same protocol at a minimum interval of 10 min, shows that the method provides 2-3 times lower interscan variation than conventional techniques.

Computer assisted detection software for CT colonography: effect of sphericity filter on performance characteristics for patients with and without fecal tagging.

The aim of this study is to investigate the effect of changing sphericity filter values on performance of a computer assisted detection (CAD) system for CT colonography for data with and without fecal tagging. Colonography data from 138 patients with 317 validated polyps were divided into those with (86) and without (52) fecal tagging. Polyp coordinates were established by three observers and datasets analysed subsequently by a proprietary CAD system used at four discrete sphericity filter settings. Prompts were compared with the known coordinates in order to determine sensitivity and specificity. Sensitivity was highest at low sphericity; of 164 polyps 6 mm or more, 144 (87.8%) were detected at sphericity 0.3, and 132 (80.1%) at sphericity 0.9. Of 42 polyps measuring 10 mm or more, 40 (95.2%) were detected at sphericity 0.3, and 36 (85.7%) at sphericity 0.9. There was no significant difference in sensitivity for tagged and un-tagged data but specificity was reduced in tagged data at low sphericity and significantly reduced in untagged data at high sphericity. CAD had a sensitivity of 95.2% for polyps measuring 1 cm or more and 87.8% for polyps 6 mm or more when used at a sphericity setting of 0.3. Higher sphericity settings increased specificity while reducing sensitivity. The bowel preparation used significantly impacts on specificity.

Computed tomographic colonography: assessment of radiologist performance with and without computer-aided detection.

BACKGROUND & AIMS: In isolation, computer-aided detection (CAD) for computed tomographic (CT) colonography is as effective as optical colonoscopy for detection of significant adenomas. However, the unavoidable interaction between CAD and the reader has not been addressed. METHODS: Ten readers trained in CT but without special expertise in colonography interpreted CT colonography images of 107 patients (60 with 142 polyps), first without CAD and then with CAD after temporal separation of 2 months. Per-patient and per-polyp detection were determined by comparing responses with known patient status. RESULTS: With CAD, 41 (68%; 95% confidence interval [CI], 55%-80%) of the 60 patients with polyps were identified more frequently by readers. Per-patient sensitivity increased significantly in 70% of readers, while specificity dropped significantly in only one. Polyp detection increased significantly with CAD; on average, 12 more polyps were detected by each reader (9.1%, 95% CI, 5.2%-12.8%). Small- (< or =5 mm) and medium-sized (6-9 mm) polyps were significantly more likely to be detected when prompted correctly by CAD. However, overall performance was relatively poor; even with CAD, on average readers detected only 10 polyps (51.0%) > or =10 mm and 24 (38.2%) > or =6 mm. Interpretation time was shortened significantly with CAD: by 1.9 minutes (95% CI, 1.4-2.4 minutes) for patients with polyps and by 2.9 minutes (95% CI, 2.5-3.3 minutes) for patients without. Overall, 9 readers (90%) benefited significantly from CAD, either by increased sensitivity and/or by reduced interpretation time. CONCLUSIONS: CAD for CT colonography significantly increases per-patient and per-polyp detection and significantly reduces interpretation times but cannot substitute for adequate training.

Polyp detection with CT colonography: primary 3D endoluminal analysis versus primary 2D transverse analysis with computer-assisted reader software.

PURPOSE: To retrospectively compare primary three-dimensional (3D) endoluminal analysis with primary two-dimensional (2D) transverse analysis supplemented by computer-assisted reader (CAR) software for computed tomographic (CT) polyp detection and reader reporting times. MATERIALS AND METHODS: Ethical permission and patient consent were obtained from all donor institutions for use of CT colonography data sets. Twenty CT colonography data sets from 14 men (median age, 61 years; age range, 52-78 years) with 48 endoscopically proved polyps were selected. Polyp coordinates were documented in consensus by three unblinded radiologists to create a reference standard. Two radiologists read the data sets, which were randomized between primary 3D endoluminal views with 2D problem solving and 2D views supplemented by CAR software. Reading times and diagnostic confidence were documented. The CAR software highlighted possible polyps by superimposing circles on the 2D transverse images. Data sets were reread after 1 month by using the opposing analysis method. Detection rates were compared by using the McNemar test. Reporting times and diagnostic confidence were compared by using the paired t test and Mann-Whitney U test, respectively. RESULTS: Mean sensitivity values for polyps measuring 1-5, 6-9, and 10 mm or larger were 14%, 53%, and 83%, respectively, for 2D CAR analysis and 16%, 53%, and 67%, respectively, for primary 3D analysis. Overall sensitivity values were 41% for 2D CAR analysis and 39% for primary 3D analysis (P=.77). Reader 1 detected more polyps than reader 2, particularly when using the 3D fly-through method (P=.002). Mean reading times were significantly longer with the 3D method (P=.001). Mean false-positive findings were 1.5 for 2D analysis and 5.5 for 3D analysis. Reader confidence was not significantly different between analysis methods (P=.42). CONCLUSION: Two-dimensional CAR analysis is quicker and at least matches the sensitivity of primary 3D endoluminal analysis, with fewer false-positive findings.

Computer-assisted reader software versus expert reviewers for polyp detection on CT colonography.

OBJECTIVE: The purpose of our study was to assess the sensitivity of computer-assisted reader (CAR) software for polyp detection compared with the performance of expert reviewers. MATERIALS AND METHODS: A library of colonoscopically validated CT colonography cases were collated and separated into training and test sets according to the time of accrual. Training data sets were annotated in consensus by three expert radiologists who were aware of the colonoscopy report. A subset of 45 training cases containing 100 polyps underwent batch analysis using ColonCAR version 1.2 software to determine the optimum polyp enhancement filter settings for polyp detection. Twenty-five consecutive positive test data sets were subsequently interpreted individually by each expert, who was unaware of the endoscopy report, and before generation of the annotated reference via an unblinded consensus interpretation. ColonCAR version 1.2 software was applied to the test cases, at optimized polyp enhancement filter settings, to determine diagnostic performance. False-positive findings were classified according to importance. RESULTS: The 25 test cases contained 32 nondiminutive polyps ranging from 6 to 35 mm in diameter. The ColonCAR version 1.2 software identified 26 (81%) of 32 polyps compared with an average sensitivity of 70% for the expert reviewers. Eleven (92%) of 12 polyps > or = 10 mm were detected by ColonCAR version 1.2. All polyps missed by experts 1 (n = 4) and 2 (n = 3) and 12 (86%) of 14 polyps missed by expert 3 were detected by ColonCAR version 1.2. The median number of false-positive highlights per case was 13, of which 91% were easily dismissed. CONCLUSION: ColonCAR version 1.2 is sensitive for polyp detection, with a clinically acceptable false-positive rate. ColonCAR version 1.2 has a synergistic effect to the reviewer alone, and its standalone performance may exceed even that of experts.