Distinction between phyllodes tumor and fibroadenoma in breast ultrasound using deep learning image analysis.
- Stoffel E Institute for Diagnostic and Interventional Radiology, University Hospital of Zurich, Switzerland.
- Becker AS Institute for Diagnostic and Interventional Radiology, University Hospital of Zurich, Switzerland.
- Wurnig MC Institute for Diagnostic and Interventional Radiology, University Hospital of Zurich, Switzerland.
- Marcon M Institute for Diagnostic and Interventional Radiology, University Hospital of Zurich, Switzerland.
- Ghafoor S Institute for Diagnostic and Interventional Radiology, University Hospital of Zurich, Switzerland.
- Berger N Institute for Diagnostic and Interventional Radiology, University Hospital of Zurich, Switzerland.
- Boss A Institute for Diagnostic and Interventional Radiology, University Hospital of Zurich, Switzerland.
- 2018-09-28
Published in:
- European journal of radiology open. - 2018
English
Purpose
To evaluate the accuracy of a deep learning software (DLS) in the discrimination between phyllodes tumors (PT) and fibroadenomas (FA).
Methods
In this IRB-approved, retrospective, single-center study, we collected all ultrasound images of histologically secured PT (n = 11, 36 images) and a random control group with FA (n = 15, 50 images). The images were analyzed with a DLS designed for industrial grade image analysis, with 33 images withheld from training for validation purposes. The lesions were also interpreted by four radiologists. Diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC). Sensitivity, specificity, negative and positive predictive values were calculated at the optimal cut-off (Youden Index).
Results
The DLS was able to differentiate between PT and FA with good diagnostic accuracy (AUC = 0.73) and high negative predictive value (NPV = 100%). Radiologists showed comparable accuracy (AUC 0.60-0.77) at lower NPV (64-80%). When performing the readout together with the DLS recommendation, the radiologist's accuracy showed a non-significant tendency to improve (AUC 0.75-0.87, p = 0.07).
Conclusion
Deep learning based image analysis may be able to exclude PT with a high negative predictive value. Integration into the clinical workflow may enable radiologists to more confidently exclude PT, thereby reducing the number of unnecessary biopsies.
To evaluate the accuracy of a deep learning software (DLS) in the discrimination between phyllodes tumors (PT) and fibroadenomas (FA).
Methods
In this IRB-approved, retrospective, single-center study, we collected all ultrasound images of histologically secured PT (n = 11, 36 images) and a random control group with FA (n = 15, 50 images). The images were analyzed with a DLS designed for industrial grade image analysis, with 33 images withheld from training for validation purposes. The lesions were also interpreted by four radiologists. Diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC). Sensitivity, specificity, negative and positive predictive values were calculated at the optimal cut-off (Youden Index).
Results
The DLS was able to differentiate between PT and FA with good diagnostic accuracy (AUC = 0.73) and high negative predictive value (NPV = 100%). Radiologists showed comparable accuracy (AUC 0.60-0.77) at lower NPV (64-80%). When performing the readout together with the DLS recommendation, the radiologist's accuracy showed a non-significant tendency to improve (AUC 0.75-0.87, p = 0.07).
Conclusion
Deep learning based image analysis may be able to exclude PT with a high negative predictive value. Integration into the clinical workflow may enable radiologists to more confidently exclude PT, thereby reducing the number of unnecessary biopsies.
- Language
-
- English
- Open access status
- gold
- Identifiers
-
- DOI 10.1016/j.ejro.2018.09.002
- PMID 30258856
- Persistent URL
- https://folia.unifr.ch/global/documents/26096
Statistics
Document views: 12
File downloads:
- fulltext.pdf: 0