Towards Out-of-Distribution Detection for breast cancer classification in Point-of-Care Ultrasound Imaging (2402.18960v1)
Abstract: Deep learning has shown to have great potential in medical applications. In critical domains as such, it is of high interest to have trustworthy algorithms which are able to tell when reliable assessments cannot be guaranteed. Detecting out-of-distribution (OOD) samples is a crucial step towards building a safe classifier. Following a previous study, showing that it is possible to classify breast cancer in point-of-care ultrasound images, this study investigates OOD detection using three different methods: softmax, energy score and deep ensembles. All methods are tested on three different OOD data sets. The results show that the energy score method outperforms the softmax method, performing well on two of the data sets. The ensemble method is the most robust, performing the best at detecting OOD samples for all three OOD data sets.
- “A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises,” Proceedings of the IEEE, vol. 109, no. 5, pp. 820–838, 2021.
- “Generalized out-of-distribution detection: A survey,” CoRR, vol. abs/2110.11334, 2021.
- “Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial,” Mechanical Systems and Signal Processing, vol. 205, pp. 110796, 2023.
- “Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries,” CA: a cancer journal for clinicians, vol. 71, no. 3, pp. 209–249, 2021.
- “Breast cancer in low-middle income countries: abnormality in splicing and lack of targeted treatment options,” American journal of cancer research, vol. 10, no. 5, pp. 1568, 2020.
- WHO, “The global breast cancer initiative,” 2022, https://www.who.int/publications/m/item/the-global-breast-cancer-initiative-gbci Accessed: 2023-11-22.
- “Classification of point-of-care ultrasound in breast imaging using deep learning,” in Medical Imaging 2023: Computer-Aided Diagnosis. International Society for Optics and Photonics, 2023, vol. 12465, p. 124650Y, SPIE.
- “A baseline for detecting misclassified and out-of-distribution examples in neural networks,” arXiv preprint arXiv:1610.02136, 2016.
- “Energy-based out-of-distribution detection,” Advances in Neural Information Processing Systems, 2020.
- “Mood: Multi-level out-of-distribution detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021.
- “Neural network ensembles,” IEEE transactions on pattern analysis and machine intelligence, vol. 12, no. 10, pp. 993–1001, 1990.
- “Simple and scalable predictive uncertainty estimation using deep ensembles,” Advances in neural information processing systems, vol. 30, 2017.
- GE Healthcare, “Vscan air,” https://vscan.rocks/product/vscanair Accessed: 2023-11-22.
- Li Deng, “The mnist database of handwritten digit images for machine learning research,” IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 141–142, 2012.
- “Ultrasound image database,” http://splab.cz/en/download/databaze/ultrasound Accessed: 2023-11-08.
- Alexander LeNail, “Nn-svg: Publication-ready neural network architecture schematics,” Journal of Open Source Software, vol. 4, no. 33, pp. 747, 2019.
- “Deep neural networks are easily fooled: High confidence predictions for unrecognizable images,” CoRR, vol. abs/1412.1897, 2014.