Enhancing Anomaly Detection in Medical Imaging: Blood UNet with Interpretable Insights

Wang Hao, Cao Kexin
Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing, PMLR 245:206-214, 2024.

Abstract

Researching anomaly detection in medical imaging, particularly in blood samples, is crucial for enhancing diagnostic accuracy. This article is to devise a robust method using Blood UNet, a modified U Net architecture integrated with Lesion Enhancing Network (LEN) and Shape Model (SHAP), to improve anomaly detection precision. Specifically, the research involves preprocessing the BloodMNIST, training the Blood UNET model, and interpreting its predictions using LEN and SHAP. Experimental results on BloodMNIST showcase the efficacy of identifying anomalies within blood samples. This study highlights the importance of leveraging advanced techniques like LEN and SHAP in medical diagnostics, contributing to better patient care and healthcare efficiency.

Cite this Paper

BibTeX
@InProceedings{pmlr-v245-hao24a, title = {Enhancing Anomaly Detection in Medical Imaging: Blood UNet with Interpretable Insights}, author = {Hao, Wang and Kexin, Cao}, booktitle = {Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing}, pages = {206--214}, year = {2024}, editor = {Nianyin, Zeng and Pachori, Ram Bilas}, volume = {245}, series = {Proceedings of Machine Learning Research}, month = {26--28 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v245/main/assets/hao24a/hao24a.pdf}, url = {https://proceedings.mlr.press/v245/hao24a.html}, abstract = {Researching anomaly detection in medical imaging, particularly in blood samples, is crucial for enhancing diagnostic accuracy. This article is to devise a robust method using Blood UNet, a modified U Net architecture integrated with Lesion Enhancing Network (LEN) and Shape Model (SHAP), to improve anomaly detection precision. Specifically, the research involves preprocessing the BloodMNIST, training the Blood UNET model, and interpreting its predictions using LEN and SHAP. Experimental results on BloodMNIST showcase the efficacy of identifying anomalies within blood samples. This study highlights the importance of leveraging advanced techniques like LEN and SHAP in medical diagnostics, contributing to better patient care and healthcare efficiency. } }
Endnote
%0 Conference Paper %T Enhancing Anomaly Detection in Medical Imaging: Blood UNet with Interpretable Insights %A Wang Hao %A Cao Kexin %B Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing %C Proceedings of Machine Learning Research %D 2024 %E Zeng Nianyin %E Ram Bilas Pachori %F pmlr-v245-hao24a %I PMLR %P 206--214 %U https://proceedings.mlr.press/v245/hao24a.html %V 245 %X Researching anomaly detection in medical imaging, particularly in blood samples, is crucial for enhancing diagnostic accuracy. This article is to devise a robust method using Blood UNet, a modified U Net architecture integrated with Lesion Enhancing Network (LEN) and Shape Model (SHAP), to improve anomaly detection precision. Specifically, the research involves preprocessing the BloodMNIST, training the Blood UNET model, and interpreting its predictions using LEN and SHAP. Experimental results on BloodMNIST showcase the efficacy of identifying anomalies within blood samples. This study highlights the importance of leveraging advanced techniques like LEN and SHAP in medical diagnostics, contributing to better patient care and healthcare efficiency.
APA
Hao, W. & Kexin, C.. (2024). Enhancing Anomaly Detection in Medical Imaging: Blood UNet with Interpretable Insights. Proceedings of 2024 International Conference on Machine Learning and Intelligent Computing, in Proceedings of Machine Learning Research 245:206-214 Available from https://proceedings.mlr.press/v245/hao24a.html.

Related Material