PCA for Enhanced Cross-Dataset Generalizability in Breast Ultrasound Tumor Segmentation

In medical image segmentation, limited external validity remains a critical obstacle when models are deployed across unseen datasets, an issue particularly pronounced in the ultrasound image domain.Existing solutions-such as domain adaptation and GAN-based style transfer-while promising, often fall short in the medical domain where datasets are typically small and diverse.This paper presents a novel application of principal component analysis (PCA) to address this limitation.PCA preprocessing reduces noise and emphasizes essential features by retaining approximately 90% of the dataset variance.We evaluate our approach across six diverse breast tumor ultrasound datasets comprising 3,983 B-mode images and corresponding expert tumor segmentation masks.For each dataset, a corresponding dimensionality reduced PCA-dataset is created and U-Net-based segmentation models are trained on each of the twelve datasets.Each model trained on an original dataset was inferenced on the remaining five outof-domain original datasets (baseline results), while each model trained on a PCA dataset was inferenced on five out-of-domain PCA datasets.Our experimental results indicate that using PCA reconstructed datasets, instead of original images, improves the model's recall and Dice scores, particularly for model-dataset pairs where baseline performance was lowest, achieving statistically significant gains in recall (0.57 0.07 vs. 0.70 0.05, p = 0.0004) and Dice scores (0.50 0.06 vs. 0.58 0.06, p = 0.03).Our method reduced the decline in recall values due to external validation by 33%.These findings underscore the potential of PCA reconstruction as a safeguard to mitigate declines in segmentation performance, especially in challenging cases, with implications for enhancing external validity in real-world medical applications.Future studies are proposed to optimize PCA configurations for diverse imaging datasets and exploring integration with existing external validation methods.