Deep learning for segmentation of brain tumors: Impact of cross‐institutional training and testing

By Ehab Albadawy, Ashirbani Saha, Maciej A. Mazurowski. 2018

230 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Genetics, Neurology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Genetics

In Neurology

Citations in the corpus

An overview of deep learning in medical imaging focusing on MRI (2018, background): “[281] Deep learning for segmentation of brain tumors and impact of cross-institutional training and testing”
In Search of Lost Domain Generalization (2020, neutral): “As another example, systems trained on medical data collected in one hospital do not generalize to other health centers [Castro et al., 2019, AlBadawy et al., 2018, Perone et al., 2019, Heaven, 2020].”
WILDS: A Benchmark of in-the-Wild Distribution Shifts (2020, neutral): “The challenge is that variation in data collection and processing across different hospitals can degrade model accuracy on data from hospitals not included in the training set (e.g., Zech et al. (2018); AlBadawy et al. (2018)).”
In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness (2020, methodology): “When models are tested on distributions that are different from the training distribution, they typically suffer large drops in performance [44, 2, 22, 17, 3].”
Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution (2022, unknown): “, 2020), and medical diagnosis (AlBadawy et al., 2018), require models that also generalize to circumstances not seen in the training distribution.”
Design Characteristics of Studies Reporting the Performance of Artificial Intelligence Algorithms for Diagnostic Analysis of Medical Images: Results from Recently Published Papers (2019, methodology): “Since the performance of an AI algorithm is strongly dependent upon its training data, there is a genuine risk that AI algorithms may not perform well in real-world practice and that an algorithm trained at one institution provides inaccurate outputs when applied to data at another institution (9, 1”
Domain Adaptation for Medical Image Analysis: A Survey (2021, background): “Howev r, many conventional mac ine l arning methods ignore this problem, which would lead to performance degradation [26], [30].”
ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries (2019, background): “…a domain, there may be differences in the performance of models trained with different datasets due to variations in demographics, class prevalence, data collection instrument, and data acquisition settings (Zech et al. , 2018; Tomašev et al. , 2019; AlBadawy et al. , 2018; Ting et al. , 2017).”
Unsupervised domain adaptation for medical imaging segmentation with self-ensembling (2018, background): “The work (AlBadawy et al., 2018) discusses the impact of deep learning models across different institutions, showing a statistically signi ﬁ cant performance decrease in cross-institutional train-and-test protocols.”
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift (2022, methodology): “For example, models trained on medical data from a few hospitals work poorly when deployed broadly [Zech et al., 2018, AlBadawy et al., 2018].”
A Review on a Deep Learning Perspective in Brain Cancer Classification (2019, methodology): “A CNN-based brain tumor segmentation method was proposed in [102].”