| 1. |
- Rodriguez-Ruiz, Alejandro, et al.
(författare)
-
Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study
- 2019
-
Ingår i: European Radiology. - : Springer Science and Business Media LLC. - 0938-7994 .- 1432-1084. ; 29:9, s. 4825-4832
-
Tidskriftsartikel (refereegranskat)abstract
- Purpose: To study the feasibility of automatically identifying normal digital mammography (DM) exams with artificial intelligence (AI) to reduce the breast cancer screening reading workload. Methods and materials: A total of 2652 DM exams (653 cancer) and interpretations by 101 radiologists were gathered from nine previously performed multi-reader multi-case receiver operating characteristic (MRMC ROC) studies. An AI system was used to obtain a score between 1 and 10 for each exam, representing the likelihood of cancer present. Using all AI scores between 1 and 9 as possible thresholds, the exams were divided into groups of low- and high likelihood of cancer present. It was assumed that, under the pre-selection scenario, only the high-likelihood group would be read by radiologists, while all low-likelihood exams would be reported as normal. The area under the reader-averaged ROC curve (AUC) was calculated for the original evaluations and for the pre-selection scenarios and compared using a non-inferiority hypothesis. Results: Setting the low/high-likelihood threshold at an AI score of 5 (high likelihood > 5) results in a trade-off of approximately halving (− 47%) the workload to be read by radiologists while excluding 7% of true-positive exams. Using an AI score of 2 as threshold yields a workload reduction of 17% while only excluding 1% of true-positive exams. Pre-selection did not change the average AUC of radiologists (inferior 95% CI > − 0.05) for any threshold except at the extreme AI score of 9. Conclusion: It is possible to automatically pre-select exams using AI to significantly reduce the breast cancer screening reading workload. Key Points: • There is potential to use artificial intelligence to automatically reduce the breast cancer screening reading workload by excluding exams with a low likelihood of cancer. • The exclusion of exams with the lowest likelihood of cancer in screening might not change radiologists’ breast cancer detection performance. • When excluding exams with the lowest likelihood of cancer, the decrease in true-positive recalls would be balanced by a simultaneous reduction in false-positive recalls.
|
|
| 2. |
- Rodriguez-Ruiz, Alejandro, et al.
(författare)
-
Stand-Alone Artificial Intelligence for Breast Cancer Detection in Mammography : Comparison With 101 Radiologists
- 2019
-
Ingår i: Journal of the National Cancer Institute. - : Oxford University Press (OUP). - 1460-2105 .- 0027-8874. ; 111:9, s. 916-922
-
Tidskriftsartikel (refereegranskat)abstract
- BACKGROUND: Artificial intelligence (AI) systems performing at radiologist-like levels in the evaluation of digital mammography (DM) would improve breast cancer screening accuracy and efficiency. We aimed to compare the stand-alone performance of an AI system to that of radiologists in detecting breast cancer in DM.METHODS: Nine multi-reader, multi-case study datasets previously used for different research purposes in seven countries were collected. Each dataset consisted of DM exams acquired with systems from four different vendors, multiple radiologists' assessments per exam, and ground truth verified by histopathological analysis or follow-up, yielding a total of 2652 exams (653 malignant) and interpretations by 101 radiologists (28 296 independent interpretations). An AI system analyzed these exams yielding a level of suspicion of cancer present between 1 and 10. The detection performance between the radiologists and the AI system was compared using a noninferiority null hypothesis at a margin of 0.05.RESULTS: The performance of the AI system was statistically noninferior to that of the average of the 101 radiologists. The AI system had a 0.840 (95% confidence interval [CI] = 0.820 to 0.860) area under the ROC curve and the average of the radiologists was 0.814 (95% CI = 0.787 to 0.841) (difference 95% CI = -0.003 to 0.055). The AI system had an AUC higher than 61.4% of the radiologists.CONCLUSIONS: The evaluated AI system achieved a cancer detection accuracy comparable to an average breast radiologist in this retrospective setting. Although promising, the performance and impact of such a system in a screening setting needs further investigation.
|
|
| 3. |
- Fieselmann, Andreas, et al.
(författare)
-
Volumetric breast density measurement for personalized screening : Accuracy, reproducibility, and agreement with visual assessment
- 2018
-
Ingår i: 14th International Workshop on Breast Imaging (IWBI 2018). - : SPIE. - 9781510620070 ; 10718
-
Konferensbidrag (refereegranskat)abstract
- Assessment of breast density at the point of mammographic examination could lead to optimized breast cancer screening pathways. The onsite breast density information may offer guidance when to recommend supplemental imaging for women in a screening program. In this work, performance evaluation of a new software (Insight BD, Siemens Healthcare GmbH) for fast onsite quantification of volumetric breast density is presented. Accuracy of volumetric measurement is evaluated using breast tissue equivalent phantom experiments. Reproducibility of measurement results is analyzed using 8150 4-view mammography exams. Furthermore, agreement between breast density categories computed by the software with those determined visually by radiologists is examined. The results of the performance evaluation demonstrate that the software delivers accurate and reproducible measurements that agree well with the visual assessment of breast density by radiologists.
|
|
| 4. |
- Fieselmann, Andreas, et al.
(författare)
-
Volumetric breast density measurement for personalized screening : Accuracy, reproducibility, consistency, and agreement with visual assessment
- 2019
-
Ingår i: Journal of Medical Imaging. - 2329-4302. ; 6:3
-
Tidskriftsartikel (refereegranskat)abstract
- Assessment of breast density at the point of mammographic examination could lead to optimized breast cancer screening pathways. The onsite breast density information may offer guidance of when to recommend supplemental imaging for women in a screening program. A software application (Insight BD, Siemens Healthcare GmbH) for fast onsite quantification of volumetric breast density is evaluated. The accuracy of the method is assessed using breast tissue equivalent phantom experiments resulting in a mean absolute error of 3.84%. Reproducibility of measurement results is analyzed using 8427 exams in total, comparing for each exam (if available) the densities determined from left and right views, from cranio-caudal and medio-lateral oblique views, from full-field digital mammograms (FFDM) and digital breast tomosynthesis (DBT) data and from two subsequent exams of the same breast. Pearson correlation coefficients of 0.937, 0.926, 0.950, and 0.995 are obtained. Consistency of the results is demonstrated by evaluating the dependency of the breast density on women's age. Furthermore, the agreement between breast density categories computed by the software with those determined visually by 32 radiologists is shown by an overall percentage agreement of 69.5% for FFDM and by 64.6% for DBT data. These results demonstrate that the software delivers accurate, reproducible, and consistent measurements that agree well with the visual assessment of breast density by radiologists.
|
|
| 5. |
- Förnvik, Daniel, et al.
(författare)
-
A human observer study for evaluation and optimization of reconstruction methods in breast tomosynthesis using clinical cases
- 2011
-
Ingår i: Medical Imaging 2011: Physics of Medical Imaging. - : SPIE. - 0277-786X .- 1996-756X. ; 7961, s. 79615-79615
-
Konferensbidrag (refereegranskat)abstract
- In breast tomosynthesis1 (BT) a number of 2D projection images are acquired from different angles along a limited arc. The imaged breast volume is reconstructed from the projection images, providing 3D information. The purpose of the study was to investigate and optimize different reconstruction methods for BT in terms of image quality using human observers viewing clinical cases. Sixty-six cases with suspected masses and calcifications were collected from 55 patients. Four different reconstructions of each image set were evaluated by four observers (two experienced radiologists, two experienced medical physicists): filtered back projection (FBP), iterative adapted FBP (iFBP) and two ML-convex iterative algorithm (MLCI) reconstructions (8 and 10 iterations) that differed in noise level and contrast of clinical details. Representation of masses and microcalcifications was evaluated. The structures were rated according to the overall appearance in a rank-order study. The differently reconstructed images of the same structure were displayed side by side in random order. The observers were forced to rank the order of the different reconstructed images and their proportions at each rank were scored. The results suggest that even though the FBP contains most noise its reconstructions are considered best overall, followed by iFBP, which contains least noise. In both FBP and iFBP methods the sharp borders and mass speculations were better represented than in iterative reconstructions while out-of-plane artifacts were better suppressed in the latter. However, in clinical practice the differences between the reconstructions may be considered negligible.
|
|
