Question 1: What is the main challenge in building robust deep learning CNN (DL-CNN) models for detection and characterization of breast cancer? |
Reference: | Chan H- P, Samala RK, Hadjiiski LM. CAD and AI for breast cancer—recent development and challenges. Br J Radiol 2020; 93: 20190580. |
Choice A: | Lack of freely available DL-CNN software packages |
Choice B: | Lack of sufficiently large memory to hold the DL-CNN structure |
Choice C: | Lack of a large enough well-annotated data set to have independent training, validation, and test partitions |
Choice D: | To reach high accuracy on the training data set |
Question 2: The transfer learning technique for the deep learning networks is characterized best by: |
Reference: | Yosinski J., Clune J., Bengio Y., Lipson H., How transferable are features in deep neural networks?, Advances in Neural Information Processing Systems 27, pp. 3320-3328, Dec. 2014. |
Choice A: | Fast training of the entire deep learning CNN structure. |
Choice B: | Freezing the parameters/weights of part of a deep learning CNN already trained with a large data set and retraining/fine-tuning the rest of the structure with a new data set relevant to the specific application of interest. |
Choice C: | Backpropagation |
Choice D: | Large learning rate |
Question 3: Deep learning based feature extraction is often achieved by: |
Reference: | Wang J, Yang X, Cai H, Tan W, Jin C, Li L. Discrimination of breast cancer with microcalcifications on mammography by deep learning. Scientific Report 2016; 6: 27327. doi: https:// doi. org/ 10. 1038/ srep27327. |
Choice A: | Using the domain knowledge and expertise of human developers, who translate the perceived image characteristics to descriptors by applying relevant mathematical functions to the image data |
Choice B: | Random forest classifier |
Choice C: | Principle component analysis |
Choice D: | Autoencoder |
Question 4: Current commercial AI algorithms can provide: |
Reference: | Rodríguez-Ruiz A, Krupinski E, Mordang J-J, et al. Detection of Breast Cancer with Mammography: Effect of an Artificial Intelligence Support System. Radiology. 2018;290(2):305–314.
Rodriguez-Ruiz A, Lång K, Gubern-Merida A, et al. Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. European Radiology. 2019;29(9):4825–4832. |
Choice A: | A per-case probability of malignancy present score |
Choice B: | A probability of malignancy score for a lesion upon clicking on it |
Choice C: | Markers for all lesions detected in a case |
Choice D: | All of the above |
Question 5: Possible applications for AI algorithms in breast imaging that have been studied do NOT include: |
Reference: | Rodríguez-Ruiz A, Krupinski E, Mordang J-J, et al. Detection of Breast Cancer with Mammography: Effect of an Artificial Intelligence Support System. Radiology. 2018;290(2):305–314.
Rodriguez-Ruiz A, Lång K, Gubern-Merida A, et al. Can we reduce the workload of mammographic screening by automatic identification of normal exams with artificial intelligence? A feasibility study. European Radiology. 2019;29(9):4825–4832.
Conant EF, Toledano AY, Periaswamy S, et al. Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis. Radiology: Artificial Intelligence. 2019;1(4):e180096. |
Choice A: | Decision support |
Choice B: | Pre-selection of normal cases |
Choice C: | Pre-selection of difficult cases |
Choice D: | Faster navigation |
Question 6: The main benefit of using AI algorithms during interpretation of digital breast tomosynthesis images is: |
Reference: | Conant EF, Toledano AY, Periaswamy S, et al. Improving Accuracy and Efficiency with Concurrent Use of Artificial Intelligence for Digital Breast Tomosynthesis. Radiology: Artificial Intelligence. 2019;1(4):e180096. |
Choice A: | Reduced reading time |
Choice B: | Improved sensitivity |
Choice C: | Improved specificity |
Choice D: | Improved accuracy |