Pith. sign in

REVIEW 5 cited by

Metrics Matter in Surgical Phase Recognition

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.13961 v1 pith:SS4ZDLBC submitted 2023-05-23 cs.CV

Metrics Matter in Surgical Phase Recognition

classification cs.CV
keywords evaluationphaserecognitionsurgicaldetailsresultscholec80differences
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Surgical phase recognition is a basic component for different context-aware applications in computer- and robot-assisted surgery. In recent years, several methods for automatic surgical phase recognition have been proposed, showing promising results. However, a meaningful comparison of these methods is difficult due to differences in the evaluation process and incomplete reporting of evaluation details. In particular, the details of metric computation can vary widely between different studies. To raise awareness of potential inconsistencies, this paper summarizes common deviations in the evaluation of phase recognition algorithms on the Cholec80 benchmark. In addition, a structured overview of previously reported evaluation results on Cholec80 is provided, taking known differences in evaluation protocols into account. Greater attention to evaluation details could help achieve more consistent and comparable results on the surgical phase recognition task, leading to more reliable conclusions about advancements in the field and, finally, translation into clinical practice.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition

    cs.CV 2026-05 conditional novelty 7.0

    SurgicalMamba adapts Mamba2 with dual-path SSD, intensity-modulated stepping, and state regramming to reach state-of-the-art online accuracy on seven surgical phase recognition benchmarks while keeping per-frame cost ...

  2. SurgicalMamba: Dual-Path SSD with State Regramming for Online Surgical Phase Recognition

    cs.CV 2026-05 unverdicted novelty 7.0

    SurgicalMamba achieves SOTA online accuracy on surgical phase recognition benchmarks by adding dual-path SSD, intensity-modulated stepping, and state regramming to Mamba2 while keeping per-frame cost O(d).

  3. Current validation practice undermines surgical AI development

    q-bio.OT 2025-11 accept novelty 7.0

    A consensus-based catalog of 18 validation pitfalls, with evidence that common practices understate uncertainty, hide failures, and flip algorithm rankings in surgical video AI.

  4. HTT-Net: Hierarchical Text-guided Transition Modeling for Surgical Video Phase Recognition

    cs.CV 2026-07 conditional novelty 6.0

    A hierarchical text-guided network that constructs and calibrates phase segments improves surgical phase recognition, setting a high Jaccard on Cholec80 and reporting large gains on a private LCRS-100 benchmark.

  5. Current validation practice undermines surgical AI development

    q-bio.OT 2025-11 conditional novelty 6.0

    A multi-stage Delphi consensus with 92 experts catalogs widespread validation pitfalls in surgical AI video analysis across data, metrics, and reporting, supported by a systematic review and empirical experiments.