Work

What Can Conformal Risk Control Certify for PET/CT Tumour Segmentation?

Year: 2026
Type: conference-paper
Abstract: A conformal guarantee for segmentation is useful only when the controlled loss reflects the clinical decision. In PET/CT tumour imaging, missing a whole lesion can matter more than small boundary errors. We apply connected-component risk-controlling prediction sets (RCPS) to fixed, pretrained LesionTracer probability maps for 900 autoPET cases, asking whether one global threshold can certify a binary missed-lesion loss and a continuous voxel-level missed-tumour loss. At α = δ = 0.1, the binary loss cannot be certified: on lesion-positive calibration cases its empirical risk is 0.177 even at the smallest threshold we evaluated. The voxel loss behaves differently: an empirical-Bernstein bound certifies λ^=0.78, giving P(Rvox(λ^) ≤ 0.1) ≥ 0.9, once lesion-free cases contribute zero loss. This binary infeasibility holds for coverage requirements γ from 0.5 to 0.9. We read the contrast as a statement about the prediction family: a global threshold cannot recover lesions the network never supported.
Language: English
Open Access status: green
OpenAlex ID: W7217905032
FWCI: 1.24
Cites: 9
Cited by: 1
Related to: 10