Distribution-free risk control adds organ-specific recall guarantees to frozen segmentation. We calibrate per-organ thresholds for an AMOS-trained nnU-Net, audit transfer to RAOS, and estimate local re-certification cost using case-level voxel false-negative rate (FNR). The AMOS control passes, but $7/12$ organs exceed $\alpha{=}0.10$ after transfer; smaller calibration sets can mask exceedances with conservative or vacuous thresholds. Risk-Controlling Prediction Sets (RCPS) give high-probability control of population-mean risk, whereas Conformal Risk Control (CRC) gives weaker expectation control. Both require exchangeability; fixed and global thresholds give no per-organ guarantee. The Waudby--Smith--Ramdas (WSR) betting bound re-certifies six Tier-1 organs with 25 local cases, versus 30--40 for Hoeffding--Bentkus (HB). CRC needs 10--15 but has a heavier individual-case tail. No Tier-2 organ meets our illustrative precision criterion with 25 cases.
Results indicate that clinically meaningful failure detection can be derived from unlabeled data, and propose a label-free framework for calibrating OOD score thresholds.
M. Nielsen, A. Castelo, M. Altaie et al.· medRxiv· 0 citations
Ten architectures spanning convolutional, attention-based, transformer, and state–space (Mamba) families on the AMOS CT dataset under one identical nnU-Net-style pipeline are benchmarked, with per-organ Dice, 95-percentile Hausdorff Distance (HD95), and Normalised Surface Dice, with pairwise significance tested on an i...
Alexandros Barmperis, Olga Menegaki, Anna Panagiotakopoulou et al.· Journal of Imaging· 0 citations
SWIFT, a SWin pretrained model wtih parameter-eFficient and tumor-aware fine-tuning for rectal cancer segmentation, is introduced, supporting robustness across pretrained initializations rather than external clinical generalizability.
A. Rangnekar, J. T. Gomez, J. Deasy et al.· 0 citations
A targeted source-inclusion sensitivity analysis indicates model- and cohort-dependent sensitivity to training-pool composition, rather than a universal benefit from adding data or a universally preferred configuration, in breast ultrasound segmentation.
Lin Ma· Medical Engineering and Phys...· 0 citations
The SAM-Med3D model was initialized from public pretrained weights and fine-tuned on the training cohort without architectural modification, then assessed with simulated/oracle-guided prompts at 1, 3, 5, 7, 9, and 11 clicks using Dice, HD95, 3-mm surface Dice, and volume consistency.
Bo-Ying Li, Ting Fan, Jia-Yan Chen et al.· Radiological Physics and Tec...· 0 citations
A Dynamic Uncertainty-aware Network (DynU-Net) is proposed, a multi-task framework that adaptively balances segmentation and classification through learnable per-task uncertainty parameters that consistently outperforms both single-task and existing multi-task baselines.
Ngoc Ly Tran, Thi Thu Thuy Nguyen, Ba-Hung Ngo et al.· Journal of Computational Des...· 0 citations
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
Exploring how generative AI could make machine vision more accessible to businesses. The post GenEye in a Box: Making Machine Vision Something You Can Just Ask For appeared first on GPT-Lab.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
