Evaluation of novice reader diagnostic performance in coronary CT angiography using an advanced cardiac software package

Automated Identification of Coronary Arteries in Assisting Inexperienced Readers: Comparison between Two Commercial Vendors

Background: to assess the performance and speed of two commercially available advanced cardiac software packages in the automated identification of coronary vessels as an aiding tool for inexperienced readers. Methods: Hundred and sixty patients undergoing coronary CT angiography (CCTA) were prospectively enrolled from February until September 2021 and randomized in two groups, each one composed by 80 patients. Patients in group 1 were scanned on Revolution EVO CT Scanner (GE Healthcare), while patients in group 2 had the CCTA performed on Brilliance iCT (Philips Healthcare); each examination was evaluated on the respective vendor proprietary advanced cardiac software (software 1 and 2, respectively). Two inexperienced readers in cardiac imaging verified the software performance in the automated identification of the three major coronary vessels: (RCA, LCx, and LAD) and in the number of identified coronary segments. Time of analysis was also recorded. Results: software 1 correctly and automatically nominated 202/240 (84.2%) of the three main coronary vessels, while software 2 correctly identified 191/240 (79.6%) (p = 0.191). Software 1 achieved greater performances in recognizing the LCx (81.2% versus 67.5%; p = 0.048), while no differences have been reported in detecting the RCA (p = 0.679), and the LAD (p = 0.618). On a per-segment analysis, software 1 outperformed software 2, automatically detecting 942/1062 (88.7%) coronary segments, while software 2 detected 797/1078 (73.9%) (p < 0.001). Average reconstruction and detection time was of 13.8 s for software 1 and 21.9 s for software 2 (p < 0.001). Conclusions: automated cardiac software packages are a reliable and time-saving tool for inexperienced reader. Software 1 outperforms software 2 and might therefore better assist inexperienced CCTA readers in automated identification of the three main vessels and coronaries segments, with a consistent time saving of the reading session.

Evaluation of a Novel Content-Based Image Retrieval System for the Differentiation of Interstitial Lung Diseases in CT Examinations

To evaluate the reader's diagnostic performance against the ground truth with and without the help of a novel content-based image retrieval system (CBIR) that retrieves images with similar CT patterns from a database of 79 different interstitial lung diseases. We evaluated three novice readers' and three resident physicians' (with at least three years of experience) diagnostic performance evaluating 50 different CTs featuring 10 different patterns (e.g., honeycombing, tree-in bud, ground glass, bronchiectasis, etc.) and 24 different diseases (sarcoidosis, UIP, NSIP, Aspergillosis, COVID-19 pneumonia etc.). The participants read the cases first without assistance (and without feedback regarding correctness), and with a 2-month interval in a random order with the assistance of the novel CBIR. To invoke the CBIR, a ROI is placed into the pathologic pattern by the reader and the system retrieves diseases with similar patterns. To further narrow the differential diagnosis, the readers can consult an integrated textbook and have the possibility of selecting high-level semantic features representing clinical information (chronic, infectious, smoking status, etc.). We analyzed readers' accuracy without and with CBIR assistance and further tested the hypothesis that the CBIR would help to improve diagnostic performance utilizing Wilcoxon signed rank test. The novice readers demonstrated an unassisted accuracy of 18/28/44%, and an assisted accuracy of 84/82/90%, respectively. The resident physicians demonstrated an unassisted accuracy of 56/56/70%, and an assisted accuracy of 94/90/96%, respectively. For each reader, as well as overall, Sign test demonstrated statistically significant (p < 0.01) difference between the unassisted and the assisted reads. For students and physicians, Chi²-test and Mann-Whitney-U test demonstrated statistically significant (p < 0.01) difference for unassisted reads and statistically insignificant (p > 0.01) difference for assisted reads. The evaluated CBIR relying on pattern analysis and featuring the option to filter the results of the CBIR by predominant characteristics of the diseases via selecting high-level semantic features helped to drastically improve novices' and resident physicians' accuracy in diagnosing interstitial lung diseases in CT.

Accuracy evaluation of patient-specific 3D-printed aortic anatomy

INTRODUCTION

3D printing has a wide range of applications in medicine. In surgery, this technique can be used for preoperative planning of complex procedures, production of patient specific implants, as well as training. However, accuracy evaluations of 3D vascular models are rare.

OBJECTIVES

Aim of this study was to investigate the accuracy of patient-specific 3D-printed aortic anatomies.

METHODS

Patients suffering from aorto-iliac aneurysms and with indication for treatment were selected on the basis of different anatomy and localization of the aneurysm in the period from January 1st 2014 to May 27th 2016. Six patients with aorto-iliac aneurysms were selected out of the database for 3D-printing. Subsequently, computed tomography (CT) images of the printed 3D-models were compared with the original CT data sets.

RESULTS

The mean deviation of the six 3D-vascular models ranged between -0.73 mm and 0.14 mm compared to the original CT-data. The relative deviation of the measured values showed no significant difference between the 3D-vascular and the original patient CT-data.

CONCLUSION

Our results showed that 3D printing has the potential to produce patient-specific 3D vascular models with reliable accuracy. This enables the use of such models for the development of new endovascular procedures and devices.

Computer-aided CT coronary artery stenosis detection: comparison with human reading and quantitative coronary angiography

To evaluate computer-aided stenosis detection for computed tomography coronary angiography (CTA) in comparison with human reading and conventional coronary angiography (CCA) as the reference standard. 50 patients underwent CTA and CCA and out of these 44 were evaluable for computer-aided stenosis detection. The diagnostic performance of the software and of human reading were compared and quantitative coronary angiography (QCA) served as the reference standard for the detection of significant stenosis (>50 %). Overall, three readers with high (reader 1), intermediate (reader 2) and low (reader 3) experience in cardiac CT imaging performed the manual CTA evaluation on a commercially available workstation, whereas the automated software processed the datasets without any human interaction. The prevalence of coronary artery disease was 41 % (18/44) and QCA indicated significant stenosis (>50 %) in 33 coronary vessels. The automated software accurately diagnosed 18 individuals with significant coronary artery disease (CAD), and correctly ruled out CAD in 10 patients. In summary the sensitivity of computer-aided detection was 100 %/94 % (per-patient/per-vessel) and the specificity was 38 %/70 %, the positive predictive value (PPV) was 53 %/42 % and the negative predictive value (NPV) was 100 %/98 %. In comparison, reader 1-3 showed per-patient sensitivities of 100/94/89 %, specificities of 73/69/50 %, PPVs of 72/68/55 % and NPVs of 100/95/87 %. Computer-aided detection yields a high NPV that is comparable to more experienced human readers. However, PPV is rather low and in the range of an unexperienced reader.