Enhancing Robustness of Deep Learning to Batch Effects from Multi-site Data for Segmentation of Clinically Significant Prostate Cancer on MRI.

Deep learning (DL) has shown promise in segmenting clinically significant prostate cancer (csPCa) on MRI. However, batch effects arising from multi-site variations impact their generalizability. This study investigates the impact of training data harmonization, diversity, and few-shot fine-tuning on DL in segmenting csPCa on multi-site MRI. 3 T prostate MRI from N = 1822 patients of four sites (public: D₁, N = 1500; D₂, N = 157; institutional: D₃, N = 47; D₄, N = 118) was leveraged. Bi-parametric MRI (T2-weighted, ADC) was harmonized with csPCa lesions delineated by expert radiologists. nnU-Net DL models for csPCa segmentation on MRI were trained separately (C₁ on D₁; C₂ on D₂) and jointly (C₃ on D₁-D₂). The jointly trained C₃ model was then fine-tuned on D₃ and D₄ using few-shot learning in increments of 50%, 75%, and 100% of train data. Models were primarily evaluated on holdout test sets using sensitivity primarily, in addition to AUC, DSC, precision, and Hausdorff distance (paired t-tests for evaluating significance). Batch effects persisted across datasets despite harmonization. For csPCa segmentation on D1/D2 test sets, C1 achieved sensitivities of 0.51 ± 0.34/0.11 ± 0.17, C2 achieved 0.23 ± 0.31/0.17 ± 0.22, while C3 improved to 0.48 ± 0.36/0.33 ± 0.26. On D3/D4 test sets, C3 achieved zero-shot sensitivities of 0.19 ± 0.22/0.37 ± 0.35. Few-shot fine-tuning on D3 and D4 improved sensitivity to 0.32 ± 0.26/0.54 ± 0.30 on D3/D4 test sets after using 100% of available fine-tuning samples. On subset analyses, lesions > 0.5 cm3 had consistently higher segmentation performance compared to smaller lesions < 0.5 cm3. Diverse multi-site training improves robustness of DL models for csPCa segmentation. Pre-trained models perform modestly on institutional MRI datasets under zero-shot inference, but few-shot fine-tuning on target sites enhances performance.