TotalSegmentator-KonfAI

KonfAI-accelerated adaptation of TotalSegmentator — whole-body multi-organ CT / MRI segmentation, built with KonfAI.

🧩 Models

Task	Modality	Labels	Ensemble	Notes
total	CT	117	5	full accuracy
total-3mm	CT	117	1	fast (3 mm)
total_mr	MRI	50	2
total_mr-3mm	MRI	50	1	fast (3 mm)

3D residual UNet · patch [96, 128, 160] · resampled to 1.5 mm.

🚀 Usage

pip install totalsegmentator-konfai
totalsegmentator-konfai segment total -i input_ct.nii.gz -o output/

• Generic runner: konfai-apps infer VBoussot/TotalSegmentator-KonfAI:total -i input_ct.nii.gz -o output/
• Interactive: SlicerKonfAI — the ⚙ Advanced dialog overrides patch size and batch size.

⚡ Performance & VRAM

Same input, same weights (Datasets 291–295, 1.5 mm, 5-model total), same PyTorch build (cu13.0), single NVIDIA RTX PRO 5000 (24 GB). Peak RAM = process-tree resident set; peak VRAM = over baseline.

Case (voxels)	Tool	Time	Peak RAM	Peak VRAM
S — 240 × 220 × 200	KonfAI	12 s	6.0 GB	12.0 GB
	Original	35 s	21 GB	3.7 GB
M — 533 × 390 × 177	KonfAI	17 s	6.5 GB	12.9 GB
	Original	61 s	26.5 GB	5.1 GB
L — 512 × 512 × 531	KonfAI	314 s	19.3 GB	10.4 GB
	Original	459 s	51.8 GB	23.3 GB

1.5–3.5× faster, 2.7–4.1× less host RAM. KonfAI trades more VRAM on small/medium cases (larger patches, GPU accumulation) for the speed-up while staying inside 24 GB; on large cases streaming bounds VRAM (10.4 GB) where the original nears the card limit (23.3 GB) — then lighter on both RAM and VRAM. The batch size is auto-selected from your free VRAM; on cards below 24 GB use total-3mm (1 model, 3 mm). Override with --patch-size / --batch-size.

🔗 Links

• 🧠 Original TotalSegmentator: github.com/wasserth/TotalSegmentator
• 🧠 KonfAI: github.com/vboussot/KonfAI
• 📦 PyPI: totalsegmentator-konfai