| 1. |
- Elhakim, Mohammad Talal, et al.
(author)
-
Breast cancer detection accuracy of AI in an entire screening population : a retrospective, multicentre study
- 2023
-
In: Cancer Imaging. - 1470-7330. ; 23:1
-
Journal article (peer-reviewed)abstract
- Background: Artificial intelligence (AI) systems are proposed as a replacement of the first reader in double reading within mammography screening. We aimed to assess cancer detection accuracy of an AI system in a Danish screening population. Methods: We retrieved a consecutive screening cohort from the Region of Southern Denmark including all participating women between Aug 4, 2014, and August 15, 2018. Screening mammograms were processed by a commercial AI system and detection accuracy was evaluated in two scenarios, Standalone AI and AI-integrated screening replacing first reader, with first reader and double reading with arbitration (combined reading) as comparators, respectively. Two AI-score cut-off points were applied by matching at mean first reader sensitivity (AIsens) and specificity (AIspec). Reference standard was histopathology-proven breast cancer or cancer-free follow-up within 24 months. Coprimary endpoints were sensitivity and specificity, and secondary endpoints were positive predictive value (PPV), negative predictive value (NPV), recall rate, and arbitration rate. Accuracy estimates were calculated using McNemar’s test or exact binomial test. Results: Out of 272,008 screening mammograms from 158,732 women, 257,671 (94.7%) with adequate image data were included in the final analyses. Sensitivity and specificity were 63.7% (95% CI 61.6%-65.8%) and 97.8% (97.7-97.8%) for first reader, and 73.9% (72.0-75.8%) and 97.9% (97.9-98.0%) for combined reading, respectively. Standalone AIsens showed a lower specificity (-1.3%) and PPV (-6.1%), and a higher recall rate (+ 1.3%) compared to first reader (p < 0.0001 for all), while Standalone AIspec had a lower sensitivity (-5.1%; p < 0.0001), PPV (-1.3%; p = 0.01) and NPV (-0.04%; p = 0.0002). Compared to combined reading, Integrated AIsens achieved higher sensitivity (+ 2.3%; p = 0.0004), but lower specificity (-0.6%) and PPV (-3.9%) as well as higher recall rate (+ 0.6%) and arbitration rate (+ 2.2%; p < 0.0001 for all). Integrated AIspec showed no significant difference in any outcome measures apart from a slightly higher arbitration rate (p < 0.0001). Subgroup analyses showed higher detection of interval cancers by Standalone AI and Integrated AI at both thresholds (p < 0.0001 for all) with a varying composition of detected cancers across multiple subgroups of tumour characteristics. Conclusions: Replacing first reader in double reading with an AI could be feasible but choosing an appropriate AI threshold is crucial to maintaining cancer detection accuracy and workload.
|
|
| 2. |
- Mortensen, Mike A., et al.
(author)
-
Artificial intelligence-based versus manual assessment of prostate cancer in the prostate gland: a method comparison study
- 2019
-
In: Clinical Physiology and Functional Imaging. - : Wiley. - 1475-0961 .- 1475-097X. ; 39:6, s. 399-406
-
Journal article (peer-reviewed)abstract
- Aim : To test the feasibility of a fully automated artificial intelligence-based method providing PET measures of prostate cancer (PCa). Methods : A convolutional neural network (CNN) was trained for automated measurements in 18F-choline (FCH) PET/CT scans obtained prior to radical prostatectomy (RP) in 45 patients with newly diagnosed PCa. Automated values were obtained for prostate volume, maximal standardized uptake value (SUVmax), mean standardized uptake value of voxels considered abnormal (SUVmean) and volume of abnormal voxels (Volabn). The product SUVmean × Volabn was calculated to reflect total lesion uptake (TLU). Corresponding manual measurements were performed. CNN-estimated data were compared with the weighted surgically removed tissue specimens and manually derived data and related to clinical parameters assuming that 1 g ≈ 1 ml of tissue. Results : The mean (range) weight of the prostate specimens was 44 g (20–109), while CNN-estimated volume was 62 ml (31–108) with a mean difference of 13·5 g or ml (95% CI: 9·78–17·32). The two measures were significantly correlated (r = 0·77, P<0·001). Mean differences (95% CI) between CNN-based and manually derived PET measures of SUVmax, SUVmean, Volabn (ml) and TLU were 0·37 (−0·01 to 0·75), −0·08 (−0·30 to 0·14), 1·40 (−2·26 to 5·06) and 9·61 (−3·95 to 23·17), respectively. PET findings Volabn and TLU correlated with PSA (P<0·05), but not with Gleason score or stage. Conclusion : Automated CNN segmentation provided in seconds volume and simple PET measures similar to manually derived ones. Further studies on automated CNN segmentation with newer tracers such as radiolabelled prostate-specific membrane antigen are warranted.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
- Piri, Reza, et al.
(author)
-
Aortic wall segmentation in F-18-sodium fluoride PET/CT scans: Head-to-head comparison of artificial intelligence-based versus manual segmentation
- 2022
-
In: Journal of Nuclear Cardiology. - : Springer Science and Business Media LLC. - 1532-6551 .- 1071-3581. ; 29:4, s. 2001-2010
-
Journal article (peer-reviewed)abstract
- Background We aimed to establish and test an automated AI-based method for rapid segmentation of the aortic wall in positron emission tomography/computed tomography (PET/CT) scans. Methods For segmentation of the wall in three sections: the arch, thoracic, and abdominal aorta, we developed a tool based on a convolutional neural network (CNN), available on the Research Consortium for Medical Image Analysis (RECOMIA) platform, capable of segmenting 100 different labels in CT images. It was tested on F-18-sodium fluoride PET/CT scans of 49 subjects (29 healthy controls and 20 angina pectoris patients) and compared to data obtained by manual segmentation. The following derived parameters were compared using Bland-Altman Limits of Agreement: segmented volume, and maximal, mean, and total standardized uptake values (SUVmax, SUVmean, SUVtotal). The repeatability of the manual method was examined in 25 randomly selected scans. Results CNN-derived values for volume, SUVmax, and SUVtotal were all slightly, i.e., 13-17%, lower than the corresponding manually obtained ones, whereas SUVmean values for the three aortic sections were virtually identical for the two methods. Manual segmentation lasted typically 1-2 hours per scan compared to about one minute with the CNN-based approach. The maximal deviation at repeat manual segmentation was 6%. Conclusions The automated CNN-based approach was much faster and provided parameters that were about 15% lower than the manually obtained values, except for SUVmean values, which were comparable. AI-based segmentation of the aorta already now appears as a trustworthy and fast alternative to slow and cumbersome manual segmentation.
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Saboury, Babak, et al.
(author)
-
Alavi–carlsen calcification score (Accs): A simple measure of global cardiac atherosclerosis burden
- 2021
-
In: Diagnostics. - : MDPI AG. - 2075-4418. ; 11:8
-
Journal article (peer-reviewed)abstract
- Multislice cardiac CT characterizes late stage macrocalcification in epicardial arteries as op-posed to PET/CT, which mirrors early phase arterial wall changes in epicardial and transmural coronary arteries. With regard to tracer, there has been a shift from using mainly18 F-fluorodeoxyglucose (FDG), indicating inflammation, to applying predominantly18 F-sodium fluoride (NaF) due to its high affinity for arterial wall microcalcification and more consistent association with cardiovascular risk factors. To make NaF-PET/CT an indispensable adjunct to clinical assessment of cardiac atherosclerosis, the Alavi–Carlsen Calcification Score (ACCS) has been proposed. It constitutes a global assessment of cardiac atherosclerosis burden in the individual patient, supported by an artificial intelligence (AI)-based approach for fast observer-independent segmentation. Common measures for characterizing epicardial coronary atherosclerosis by NaF-PET/CT as the maximum standardized uptake value (SUV) or target-to-background ratio are more versatile, error prone, and less reproducible than the ACCS, which equals the average cardiac SUV. The AI-based approach ensures a quick and easy delineation of the entire heart in 3D to obtain the ACCS expressing ongoing global cardiac atherosclerosis, even before it gives rise to CT-detectable coronary calcification. The quantification of global cardiac atherosclerotic burden by the ACCS is suited for management triage and monitoring of disease progression with and without intervention.
|
|
| 10. |
|
|
