In this study, we characterize lung nodule malignancy subgroups using the malignancy likelihood ratings given by radiologists and improve the worst subgroup ...

In this study, we propose a curriculum group Distributionally Robust. Optimization (gDRO) approach to increase the performance of a worst malignant subgroup, ...

Our results indicate that our approach boosts the worst group subclass accuracy from the malignant category, by up to 6 percentage points compared to standard ...

Aug 6, 2024 · Request PDF | On Jun 1, 2023, Arun Sivakumar and others published Curriculum gDRO: Improving Lung Malignancy Classification through Robust ...

Therefore, we propose a novel curriculum gDRO training scheme that trains for an “easy” task (nodule malignancy is determinate or indeterminate for radiologists) ...

Curriculum gDRO: Improving Lung Malignancy Classification through Robust Curriculum Task Learning. Arun Sivakumar 1. ,. Yiyang Wang 1. ,. Roselyne Tchoua 1.

Bibliographic details on Curriculum gDRO: Improving Lung Malignancy Classification through Robust Curriculum Task Learning.

Curriculum gDRO: Improving Lung Malignancy Classification through Robust Curriculum Task Learning · Medicine, Computer Science. 2023 IEEE 36th International ...

Curriculum gDRO: Improving Lung Malignancy Classification through Robust Curriculum Task Learning. A Sivakumar, Y Wang, R Tchoua, T Ramaraj, J Furst, DS ...

Curriculum gDRO: Improving Lung Malignancy Classification through Robust Curriculum Task Learning · Medicine, Computer Science. 2023 IEEE 36th International ...