← Back to all news
arXiv Computer Vision By Bowen Xiang, Michael I. Miga

When can multi-fragment 2D/3D registration be trusted? Calibrated certification and uncertainty-driven view planning for pelvic fracture fluoroscopy

Read the original on arXiv Computer Vision →

The paper presents a closed‑loop system for registering segmented CT fracture fragments to fluoroscopy, providing calibrated uncertainty bounds and flagging implausible or ambiguous fragments. After each shot, the system updates all fragment registrations, stops or plans the next view based on whether new views keep fragment positions within their bounds, and uses uncertainty‑driven planning to reduce the number of shots needed. Experiments on simulated fluoroscopy of 60 held‑out pelvic fractures show that 95% of the bounds cover 83% of unflagged fragments, with 91% of those within 5 mm, and that a simple rule requiring no fragment to move beyond its bound reduces false stops from 23% to 6% at a 2 mm threshold. "whyItMatters":"The study demonstrates that calibrated uncertainty and view‑planning can make multi‑fragment 2D/3D registration reliable enough to guide pelvic fracture surgery, potentially improving surgical accuracy and efficiency."

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Sep 4

Hold-Out Self-Validation Cannot Certify Photogrammetric Accuracy: Saturation and Blindness to Coherent Distortion

The paper argues that internal self-consistency checks cannot guarantee the accuracy of photogrammetric reconstructions, a limitation that is structural rather than a tuning issue. It introduces a track‑leakage‑free hold‑out protocol that withholds a deterministic subset of images and tests each against only 3D points supported by at least two retained images, ensuring no view is evaluated against the structure it helped create. Experiments on diverse datasets show that while the protocol is well‑posed, it saturates at a confidence score of 1.00 and fails to detect coherent distortion, missing large errors that can reach over 100 m. whyItMatters":"The study highlights that hold‑out self‑validation scores, increasingly used as quality evidence for metric deliverables, may be misleading and cannot replace external survey validation."

By Behnam Asadi
More like this →
arXiv Computer Vision
Oct 16

A Decision-Aware Evaluation Protocol for Uncertainty in Medical Image Segmentation

The paper introduces a decision‑aware evaluation protocol for medical image segmentation uncertainty that separates uncertainty estimation from deferral policy and assesses their joint performance under fixed review budgets. It reports metrics such as fixed‑budget error reduction, risk‑coverage behavior, region‑level review proxies, structural failure modes, and sensitivity to review assumptions. Experiments on retinal vessel, skin lesion, and polyp segmentation with various backbones and uncertainty estimators show that estimator rankings vary with review unit, uncertainty target, and cost model, and that boundary and thin‑structure failures are partly due to annotation ambiguity.

By Saket Maganti, Shreyank N Gowda
computer-vision
More like this →
Hugging Face Trending Papers
Jul 9

Metrics or Mirage? An Audit of Evaluation Inconsistencies in Colonoscopy Polyp Segmentation Benchmarks

Progress in colonoscopy polyp segmentation is routinely reported through leaderboard comparisons on a small set of public benchmarks. We argue that this apparent progress is difficult to verify: a systematic audit of \textbf{27 papers} published between 2015 and 2026 reveals three structural problems in how the community evaluates models.

computer-visionbenchmarks
More like this →