# Surgical Phase and Instrument Recognition: How to identify appropriate Dataset Splits

arXiv: https://arxiv.org/abs/2306.16879 · HTML: https://mlsanity.com/paper/2306.16879/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 49 references that are in the map.
- First posted on arXiv 29 Jun 2023.

## Builds on (most cited first, 18 of 18)

- [EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos](https://mlsanity.com/paper/1602.03012/) (2016)
- [TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks](https://mlsanity.com/paper/2003.10751/) (2020)
- [Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos](https://mlsanity.com/paper/2109.03223/) (2021)
- [Surgical Data Science: Enabling Next-Generation Surgery](https://mlsanity.com/paper/1701.06482/) (2017)
- [Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer](https://mlsanity.com/paper/2103.09712/) (2021)
- [Multi-Task Recurrent Convolutional Network with Correlation Loss for Surgical Video Analysis](https://mlsanity.com/paper/1907.06099/) (2019)
- [OperA: Attention-Regularized Transformers for Surgical Phase Recognition](https://mlsanity.com/paper/2103.03873/) (2021)
- [Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark](https://mlsanity.com/paper/2109.14956/) (2021)
- [DeepPhase: Surgical Phase Recognition in CATARACTS Videos](https://mlsanity.com/paper/1807.10565/) (2018)
- [Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room](https://mlsanity.com/paper/2005.03501/) (2020)
- [Multi-Task Temporal Convolutional Networks for Joint Recognition of Surgical Phases and Steps in Gastric Bypass Procedures](https://mlsanity.com/paper/2102.12218/) (2021)
- [The TUM LapChole dataset for the M2CAI 2016 workflow challenge](https://mlsanity.com/paper/1610.09278/) (2016)
- [Rendezvous in Time: An Attention-based Temporal Fusion approach for Surgical Triplet Recognition](https://mlsanity.com/paper/2211.16963/) (2022)
- [CholecTriplet2022: Show me a tool and tell me the triplet -- an endoscopic vision challenge for surgical action triplet detection](https://mlsanity.com/paper/2302.06294/) (2023)
- [On the Pitfalls of Batch Normalization for End-to-End Video Learning: A Study on Surgical Workflow Analysis](https://mlsanity.com/paper/2203.07976/) (2022)
- [Metrics Matter in Surgical Phase Recognition](https://mlsanity.com/paper/2305.13961/) (2023)
- [Data Twinning](https://mlsanity.com/paper/2110.02927/) (2021)
- [ARST: Auto-Regressive Surgical Transformer for Phase Recognition from Laparoscopic Videos](https://mlsanity.com/paper/2209.01148/) (2022)

## Built on by (most cited first, 1 of 1)

- [Spatiotemporal Recognition of Abdominal Wall Layers During Optical Trocar Entry](https://mlsanity.com/paper/2610.14512/) (2026)

## Abstract (arXiv)

Purpose: Machine learning models can only be reliably evaluated if training, validation, and test data splits are representative and not affected by the absence of classes of interest. Surgical workflow and instrument recognition tasks are complicated in this manner, because of heavy data imbalances resulting from different lengths of phases and their erratic occurrences. Furthermore, the issue becomes difficult as sub-properties that help define phases, like instrument (co-)occurrence, are usually not considered when defining the split. We argue that such sub-properties must be equally considered. Methods: This work presents a publicly available data visualization tool that enables interactive exploration of dataset splits for surgical phase and instrument recognition. It focuses on the visualization of the occurrence of phases, phase transitions, instruments, and instrument combinations across sets. Particularly, it facilitates the assessment and identification of sub-optimal dataset splits. Results: We performed an analysis of common Cholec80 dataset splits using the proposed application and were able to uncover phase transitions and combinations of instruments that were not represented in one of the sets. Additionally, we outlined possible improvements to the splits. A user study with ten participants demonstrated the ability of participants to solve a selection of data exploration tasks using the proposed application. Conclusion: In highly unbalanced class distributions, special care should be taken with respect to the selection of an appropriate dataset split. Our interactive data visualization tool presents a promising approach for the assessment of dataset splits for surgical phase and instrument recognition. Evaluation results show that it can enhance the development of machine learning models. The application is available at https://cardio-ai.github.io/endovis-ml/ .