Calibrated Diverse Ensemble Entropy Minimization for Robust Test-Time Adaptation in Prostate Cancer Detection
Na minha lista:
| Publicado no: | arXiv.org (Jul 17, 2024), p. n/a |
|---|---|
| Autor principal: | |
| Outros Autores: | , , , , , , , |
| Publicado em: |
Cornell University Library, arXiv.org
|
| Assuntos: | |
| Acesso em linha: | Citation/Abstract Full text outside of ProQuest |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3082383637 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2331-8422 | ||
| 035 | |a 3082383637 | ||
| 045 | 0 | |b d20240717 | |
| 100 | 1 | |a Gilany, Mahdi | |
| 245 | 1 | |a Calibrated Diverse Ensemble Entropy Minimization for Robust Test-Time Adaptation in Prostate Cancer Detection | |
| 260 | |b Cornell University Library, arXiv.org |c Jul 17, 2024 | ||
| 513 | |a Working Paper | ||
| 520 | 3 | |a High resolution micro-ultrasound has demonstrated promise in real-time prostate cancer detection, with deep learning becoming a prominent tool for learning complex tissue properties reflected on ultrasound. However, a significant roadblock to real-world deployment remains, which prior works often overlook: model performance suffers when applied to data from different clinical centers due to variations in data distribution. This distribution shift significantly impacts the model's robustness, posing major challenge to clinical deployment. Domain adaptation and specifically its test-time adaption (TTA) variant offer a promising solution to address this challenge. In a setting designed to reflect real-world conditions, we compare existing methods to state-of-the-art TTA approaches adopted for cancer detection, demonstrating the lack of robustness to distribution shifts in the former. We then propose Diverse Ensemble Entropy Minimization (DEnEM), questioning the effectiveness of current TTA methods on ultrasound data. We show that these methods, although outperforming baselines, are suboptimal due to relying on neural networks output probabilities, which could be uncalibrated, or relying on data augmentation, which is not straightforward to define on ultrasound data. Our results show a significant improvement of \(5\%\) to \(7\%\) in AUROC over the existing methods and \(3\%\) to \(5\%\) over TTA methods, demonstrating the advantage of DEnEM in addressing distribution shift. \keywords{Ultrasound Imaging \and Prostate Cancer \and Computer-aided Diagnosis \and Distribution Shift Robustness \and Test-time Adaptation.} | |
| 653 | |a Data augmentation | ||
| 653 | |a Entropy | ||
| 653 | |a Testing time | ||
| 653 | |a Neural networks | ||
| 653 | |a Prostate cancer | ||
| 653 | |a Ultrasonic testing | ||
| 653 | |a Optimization | ||
| 653 | |a Computer aided testing | ||
| 653 | |a Robustness (mathematics) | ||
| 653 | |a Deep learning | ||
| 653 | |a Machine learning | ||
| 653 | |a Adaptation | ||
| 653 | |a Real time | ||
| 653 | |a Ultrasonic imaging | ||
| 700 | 1 | |a Harmanani, Mohamed | |
| 700 | 1 | |a Wilson, Paul | |
| 700 | 1 | |a Minh Nguyen Nhat To | |
| 700 | 1 | |a Jamzad, Amoon | |
| 700 | 1 | |a Fooladgar, Fahimeh | |
| 700 | 1 | |a Wodlinger, Brian | |
| 700 | 1 | |a Abolmaesumi, Purang | |
| 700 | 1 | |a Mousavi, Parvin | |
| 773 | 0 | |t arXiv.org |g (Jul 17, 2024), p. n/a | |
| 786 | 0 | |d ProQuest |t Engineering Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3082383637/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch |
| 856 | 4 | 0 | |3 Full text outside of ProQuest |u http://arxiv.org/abs/2407.12697 |