000308544 001__ 308544 000308544 005__ 20260129155728.0 000308544 0247_ $$2doi$$a10.1016/j.media.2026.103945 000308544 0247_ $$2pmid$$apmid:41564633 000308544 0247_ $$2ISSN$$a1361-8415 000308544 0247_ $$2ISSN$$a1361-8431 000308544 0247_ $$2ISSN$$a1361-8423 000308544 037__ $$aDKFZ-2026-00170 000308544 041__ $$aEnglish 000308544 082__ $$a610 000308544 1001_ $$aRueckert, Tobias$$b0 000308544 245__ $$aComparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge. 000308544 260__ $$aAmsterdam [u.a.]$$bElsevier Science$$c2026 000308544 3367_ $$2DRIVER$$aarticle 000308544 3367_ $$2DataCite$$aOutput Types/Journal article 000308544 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1769698602_582793 000308544 3367_ $$2BibTeX$$aARTICLE 000308544 3367_ $$2ORCID$$aJOURNAL_ARTICLE 000308544 3367_ $$00$$2EndNote$$aJournal Article 000308544 500__ $$a#NCTZFB26# 000308544 520__ $$aReliable recognition and localization of surgical instruments in endoscopic video recordings are foundational for a wide range of applications in computer- and robot-assisted minimally invasive surgery (RAMIS), including surgical training, skill assessment, and autonomous assistance. However, robust performance under real-world conditions remains a significant challenge. Incorporating surgical context - such as the current procedural phase - has emerged as a promising strategy to improve robustness and interpretability. To address these challenges, we organized the Surgical Procedure Phase, Keypoint, and Instrument Recognition (PhaKIR) sub-challenge as part of the Endoscopic Vision (EndoVis) challenge at MICCAI 2024. We introduced a novel, multi-center dataset comprising thirteen full-length laparoscopic cholecystectomy videos collected from three distinct medical institutions, with unified annotations for three interrelated tasks: surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation. Unlike existing datasets, ours enables joint investigation of instrument localization and procedural context within the same data while supporting the integration of temporal information across entire procedures. We report results and findings in accordance with the BIAS guidelines for biomedical image analysis challenges. The PhaKIR sub-challenge advances the field by providing a unique benchmark for developing temporally aware, context-driven methods in RAMIS and offers a high-quality resource to support future research in surgical scene understanding. 000308544 536__ $$0G:(DE-HGF)POF4-315$$a315 - Bildgebung und Radioonkologie (POF4-315)$$cPOF4-315$$fPOF IV$$x0 000308544 588__ $$aDataset connected to CrossRef, PubMed, , Journals: inrepo02.dkfz.de 000308544 650_7 $$2Other$$aInstrument instance segmentation 000308544 650_7 $$2Other$$aInstrument keypoint estimation 000308544 650_7 $$2Other$$aRobot-assisted surgery 000308544 650_7 $$2Other$$aSurgical phase recognition 000308544 7001_ $$aRauber, David$$b1 000308544 7001_ $$aMaerkl, Raphaela$$b2 000308544 7001_ $$aKlausmann, Leonard$$b3 000308544 7001_ $$aYildiran, Suemeyye R$$b4 000308544 7001_ $$aGutbrod, Max$$b5 000308544 7001_ $$aNunes, Danilo Weber$$b6 000308544 7001_ $$aMoreno, Alvaro Fernandez$$b7 000308544 7001_ $$aLuengo, Imanol$$b8 000308544 7001_ $$aStoyanov, Danail$$b9 000308544 7001_ $$aToussaint, Nicolas$$b10 000308544 7001_ $$aCho, Enki$$b11 000308544 7001_ $$aKim, Hyeon Bae$$b12 000308544 7001_ $$aChoo, Oh Sung$$b13 000308544 7001_ $$aKim, Ka Young$$b14 000308544 7001_ $$aKim, Seong Tae$$b15 000308544 7001_ $$aArantes, Gonçalo$$b16 000308544 7001_ $$aSong, Kehan$$b17 000308544 7001_ $$aZhu, Jianjun$$b18 000308544 7001_ $$aXiong, Junchen$$b19 000308544 7001_ $$aLin, Tingyi$$b20 000308544 7001_ $$aKikuchi, Shunsuke$$b21 000308544 7001_ $$aMatsuzaki, Hiroki$$b22 000308544 7001_ $$aKouno, Atsushi$$b23 000308544 7001_ $$aManesco, João Renato Ribeiro$$b24 000308544 7001_ $$aPapa, João Paulo$$b25 000308544 7001_ $$aChoi, Tae-Min$$b26 000308544 7001_ $$aJeong, Tae Kyeong$$b27 000308544 7001_ $$aPark, Juyoun$$b28 000308544 7001_ $$aAlabi, Oluwatosin$$b29 000308544 7001_ $$aWei, Meng$$b30 000308544 7001_ $$aVercauteren, Tom$$b31 000308544 7001_ $$aWu, Runzhi$$b32 000308544 7001_ $$aXu, Mengya$$b33 000308544 7001_ $$aWang, An$$b34 000308544 7001_ $$aBai, Long$$b35 000308544 7001_ $$aRen, Hongliang$$b36 000308544 7001_ $$0P:(DE-HGF)0$$aYamlahi, Amine$$b37 000308544 7001_ $$0P:(DE-He78)19525b4b76d116daa9394a3e4f6b7233$$aHennighausen, Jakob$$b38 000308544 7001_ $$0P:(DE-He78)26a1176cd8450660333a012075050072$$aMaier-Hein, Lena$$b39 000308544 7001_ $$aKondo, Satoshi$$b40 000308544 7001_ $$aKasai, Satoshi$$b41 000308544 7001_ $$aHirasawa, Kousuke$$b42 000308544 7001_ $$aYang, Shu$$b43 000308544 7001_ $$aWang, Yihui$$b44 000308544 7001_ $$aChen, Hao$$b45 000308544 7001_ $$aRodríguez, Santiago$$b46 000308544 7001_ $$aAparicio, Nicolás$$b47 000308544 7001_ $$aManrique, Leonardo$$b48 000308544 7001_ $$aLyons, Juan Camilo$$b49 000308544 7001_ $$aHosie, Olivia$$b50 000308544 7001_ $$aAyobi, Nicolás$$b51 000308544 7001_ $$aArbeláez, Pablo$$b52 000308544 7001_ $$aLi, Yiping$$b53 000308544 7001_ $$aAl Khalil, Yasmina$$b54 000308544 7001_ $$aNasirihaghighi, Sahar$$b55 000308544 7001_ $$0P:(DE-He78)191434cf815e27a18a86287bacc2d496$$aSpeidel, Stefanie$$b56 000308544 7001_ $$aRueckert, Daniel$$b57 000308544 7001_ $$aFeussner, Hubertus$$b58 000308544 7001_ $$aWilhelm, Dirk$$b59 000308544 7001_ $$aPalm, Christoph$$b60 000308544 773__ $$0PERI:(DE-600)1497450-2$$a10.1016/j.media.2026.103945$$gVol. 109, p. 103945 -$$p103945$$tMedical image analysis$$v109$$x1361-8415$$y2026 000308544 909CO $$ooai:inrepo02.dkfz.de:308544$$pVDB 000308544 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-HGF)0$$aDeutsches Krebsforschungszentrum$$b37$$kDKFZ 000308544 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)19525b4b76d116daa9394a3e4f6b7233$$aDeutsches Krebsforschungszentrum$$b38$$kDKFZ 000308544 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)26a1176cd8450660333a012075050072$$aDeutsches Krebsforschungszentrum$$b39$$kDKFZ 000308544 9101_ $$0I:(DE-588b)2036810-0$$6P:(DE-He78)191434cf815e27a18a86287bacc2d496$$aDeutsches Krebsforschungszentrum$$b56$$kDKFZ 000308544 9131_ $$0G:(DE-HGF)POF4-315$$1G:(DE-HGF)POF4-310$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lKrebsforschung$$vBildgebung und Radioonkologie$$x0 000308544 9141_ $$y2026 000308544 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bMED IMAGE ANAL : 2022$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)1160$$2StatID$$aDBCoverage$$bCurrent Contents - Engineering, Computing and Technology$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-02 000308544 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bMED IMAGE ANAL : 2022$$d2025-01-02 000308544 9201_ $$0I:(DE-He78)E130-20160331$$kE130$$lE130 Intelligente Medizinische Systeme$$x0 000308544 9201_ $$0I:(DE-He78)DD04-20160331$$kDD04$$lKoordinierungsstelle NCT Dresden$$x1 000308544 9201_ $$0I:(DE-He78)DD06-20160331$$kDD06$$lNCT DD Translationale Chirurgische Onkologie$$x2 000308544 980__ $$ajournal 000308544 980__ $$aVDB 000308544 980__ $$aI:(DE-He78)E130-20160331 000308544 980__ $$aI:(DE-He78)DD04-20160331 000308544 980__ $$aI:(DE-He78)DD06-20160331 000308544 980__ $$aUNRESTRICTED