Multi-site Benchmarking of Deep Learning Models for Intraparenchymal Hemorrhage Segmentation on NCCT

Kaue Tartarotti Nepomuceno Duarte, Abhijot Singh Sidhu, Murilo Costa de Barros, Taha Aslan, Donghao Zhang, Jianhai Zhang, Devansh Bhatt, Brij Karmur, Mohamed AlShamrani, Wu Qiu, Aravind Ganesh, Bijoy Menon

Keywords: stroke, intraparenchymal, hemorrhage, artificial intelligence, medicine, computed tomography

Abstract: Intraparenchymal hemorrhage (IPH) is a critical and often fatal subtype of hemorrhagic stroke, requiring rapid and accurate diagnosis on non-contrast computed tomography (NCCT) scans for effective treatment. While deep learning (DL) models, more specifically using convolutional neural networks (CNNs), offer potential for automating IPH segmentation, their real-world clinical utility is often limited by the lack of explicit data integration across diverse hospital sites with varying imaging protocols. This study conducted a multi-site benchmarking of four prominent CNN architectures: baseline U-Net, Attention U-Net, Feature Pyramid Network (FPN), and Trans U-Net, for IPH segmentation on a heterogeneous dataset from 17 clinical sites. Models were rigorously evaluated using F-measure (\textit{a.k.a.}, Dice), Intersection over Union (IoU), and 95\% Hausdorff Distance ($d_{H95}$). The advanced CNN variants (Attention U-Net, FPN, Trans U-Net) significantly outperformed the baseline U-Net in F-measure and IoU (\textit{e.g.}, FPN F-measure: $0.868$ vs. U-Net: $0.819$, $p<0.001$), with no significant difference among them. For boundary error, Attention U-Net and FPN demonstrated a substantial reduction in $d_{H95}$ (42–50\%) compared to the baseline, whereas Trans U-Net showed improvement, but it was not significant. These models exhibited robust cross-site generalization across hemorrhage volumes, with minimal site-specific effects on performance. This study demonstrates that advanced CNN variants can be adopted for IPH segmentation to standardize and potentially accelerate IPH diagnosis.

Primary Subject Area: Segmentation

Secondary Subject Area: Detection and Diagnosis

Registration Requirement: Yes

Visa & Travel: Yes

Read CFP & Author Instructions: Yes

Originality Policy: Yes

Single-blind & Not Under Review Elsewhere: Yes

LLM Policy: Yes

Submission Number: 40