# Advancing Brain Metastases Detection in T1-Weighted Contrast-Enhanced 3D MRI using Noisy Student-based Training

arXiv: https://arxiv.org/abs/2111.05959 · HTML: https://mlsanity.com/paper/2111.05959/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 44 references that are in the map.
- First posted on arXiv 10 Nov 2021.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [AbdomenCT-1K: Is Abdominal Organ Segmentation A Solved Problem?](https://mlsanity.com/paper/2010.14808/) (2020)
- [Deep Learning Enables Automatic Detection and Segmentation of Brain Metastases on Multi-Sequence MRI](https://mlsanity.com/paper/1903.07988/) (2019)
- [Development and Validation of Deep Learning Algorithms for Detection of Critical Findings in Head CT Scans](https://mlsanity.com/paper/1803.05854/) (2018)
- [DeepSEED: 3D Squeeze-and-Excitation Encoder-Decoder Convolutional Neural Networks for Pulmonary Nodule Detection](https://mlsanity.com/paper/1904.03501/) (2019)
- [Integrating AI into Radiology workflow: Levels of research, production, and feedback maturity](https://mlsanity.com/paper/1910.06424/) (2019)
- [Automated Brain Metastases Detection Framework for T1-Weighted Contrast-Enhanced 3D MRI](https://mlsanity.com/paper/1908.04701/) (2019)
- [Semi-supervised learning for generalizable intracranial hemorrhage detection and segmentation](https://mlsanity.com/paper/2105.00582/) (2021)
- [PatchFCN for Intracranial Hemorrhage Detection](https://mlsanity.com/paper/1806.03265/) (2018)
- [Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer](https://mlsanity.com/paper/2103.07062/) (2021)
- [An Orchestration Platform that Puts Radiologists in the Driver's Seat of AI Innovation: A Methodological Approach](https://mlsanity.com/paper/2107.04409/) (2021)
- [A new semi-supervised self-training method for lung cancer prediction](https://mlsanity.com/paper/2012.09472/) (2020)

## Built on by (most cited first, 1 of 1)

- [Deep learning with noisy labels in medical prediction problems: a scoping review](https://mlsanity.com/paper/2403.13111/) (2024)

## Abstract (arXiv)

The detection of brain metastases (BM) in their early stages could have a positive impact on the outcome of cancer patients. We previously developed a framework for detecting small BM (with diameters of less than 15mm) in T1-weighted Contrast-Enhanced 3D Magnetic Resonance images (T1c) to assist medical experts in this time-sensitive and high-stakes task. The framework utilizes a dedicated convolutional neural network (CNN) trained using labeled T1c data, where the ground truth BM segmentations were provided by a radiologist. This study aims to advance the framework with a noisy student-based self-training strategy to make use of a large corpus of unlabeled T1c data (i.e., data without BM segmentations or detections). Accordingly, the work (1) describes the student and teacher CNN architectures, (2) presents data and model noising mechanisms, and (3) introduces a novel pseudo-labeling strategy factoring in the learned BM detection sensitivity of the framework. Finally, it describes a semi-supervised learning strategy utilizing these components. We performed the validation using 217 labeled and 1247 unlabeled T1c exams via 2-fold cross-validation. The framework utilizing only the labeled exams produced 9.23 false positives for 90% BM detection sensitivity; whereas, the framework using the introduced learning strategy led to ~9% reduction in false detections (i.e., 8.44) for the same sensitivity level. Furthermore, while experiments utilizing 75% and 50% of the labeled datasets resulted in algorithm performance degradation (12.19 and 13.89 false positives respectively), the impact was less pronounced with the noisy student-based training strategy (10.79 and 12.37 false positives respectively).