Surgical tool detection and tracking in retinal microsurgery

Alsheakhali, Mohamed; Yiğitsoy, Mehmet; Eslami, Abouzar; Navab, Nassir

doi:10.1117/12.2082335

Cited by 10 publications

(13 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed algorithm is evaluated by estimating the pose of one of the instruments present in the laparoscopic surgery since the other instrument has a fixed pose. The performance of the algorithm was evaluated using three different metrics: (1) accuracy threshold score defined by Sznitman et al [10] to measure the pixel-wise detection accuracy for each instrument joint, (2) the strict Percentage of Correct Parts (strict PCP) [17] for gripper parts detection accuracy, and (3) the angular threshold score defined in [5] to measure the accuracy of estimating the shaft's orientation. The algorithm runs at 15-fps for public and laparoscopic datasets and 18-fps for Zeiss dataset on a normal personal computer.…”

Section: Experiments and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

CRF-Based Model for Instrument Detection and Pose Estimation in Retinal Microsurgery

Alsheakhali

Eslami

Roodaki

et al. 2016

Computational and Mathematical Methods in Medicine

Self Cite

View full text Add to dashboard Cite

Detection of instrument tip in retinal microsurgery videos is extremely challenging due to rapid motion, illumination changes, the cluttered background, and the deformable shape of the instrument. For the same reason, frequent failures in tracking add the overhead of reinitialization of the tracking. In this work, a new method is proposed to localize not only the instrument center point but also its tips and orientation without the need of manual reinitialization. Our approach models the instrument as a Conditional Random Field (CRF) where each part of the instrument is detected separately. The relations between these parts are modeled to capture the translation, rotation, and the scale changes of the instrument. The tracking is done via separate detection of instrument parts and evaluation of confidence via the modeled dependence functions. In case of low confidence feedback an automatic recovery process is performed. The algorithm is evaluated on in vivo ophthalmic surgery datasets and its performance is comparable to the state-of-the-art methods with the advantage that no manual reinitialization is needed.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

“…Much research has been done to address the problem of detecting and tracking medical instruments including color-based [4, 5] and geometry-based [6–8] approaches. A recent work of Roodaki et al [1] proposed to estimate the instrument tip depth to retina surface by building their method on top of instrument tracking algorithms.…”

Section: Previous Workmentioning

confidence: 99%

CRF-Based Model for Instrument Detection and Pose Estimation in Retinal Microsurgery

Alsheakhali

Eslami

Roodaki

et al. 2016

Computational and Mathematical Methods in Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…To finish, we describe general optimization strategies which can be employed to constrain the detection search space as to obtain faster and/or more accurate detection results. (Allan et al, 2014) G (Allan et al, 2015) G (Alsheakhali et al, 2015) A (Bouget et al, 2015) D (Burschka et al, 2005) A D (Cano et al, 2008) A (Doignon et al, 2005) A (Doignon et al, 2007) G (Haase et al, 2013) A (Kumar et al, 2013b) D (Li et al, 2014) D (McKenna et al, 2005) G (Pezzementi et al, 2009) G (Reiter & Allen, 2010) G (Reiter et al, 2012c) G (Reiter et al, 2012a) D (Richa et al, 2011a) D (Rieke et al, 2015) D (Speidel et al, 2006) G (Speidel et al, 2008) A (Speidel et al, 2014) A (Sznitman et al, 2012) D (Sznitman et al, 2013) G D (Sznitman et al, 2014) A (Voros et al, 2007) A (Wolf et al, 2011) G (Zhou & Payandeh, 2014) A…”

Section: Tool Detection Methodsmentioning

confidence: 99%

“…Data (Allan et al, 2014) M E S 1920 × 1080 400 1 (Allan et al, 2015) M E S 720 × 576 1000 1 (Alsheakhali et al, 2015) R M M 1920 × 1080 400 1 (Bouget et al, 2015) N M M 612 × 460 2476 14 (Burschka et al, 2005) E -S -< 500 1 M -- (Cano et al, 2008) M E M -550 2 (Doignon et al, 2005) M E M 640 × 480 52 1 (Doignon et al, 2007) (Speidel et al, 2008…”

Section: Study Conditionsmentioning

confidence: 99%

“…By decoupling luminosity from other components, more robustness is provided towards lighting changes. The CIE L*A*B* space which is closely modelled on human visual perception has also been used (Alsheakhali et al, 2015). This space allows a wider range of possible colors than RGB, but come with the tradeoff that more than 8 bits are needed to each channel, increasing processing time.…”

Section: Colormentioning

confidence: 99%

See 1 more Smart Citation

Vision-based and marker-less surgical tool detection and tracking: a review of the literature

Bouget

Allan

Stoyanov

et al. 2017

Medical Image Analysis

230

144

View full text Add to dashboard Cite

In recent years, tremendous progress has been made in surgical practice for example with Minimally Invasive Surgery (MIS). To overcome challenges coming from deported eye-to-hand manipulation, robotic and computer-assisted systems have been developed. Having real-time knowledge of the pose of surgical tools with respect to the surgical camera and underlying anatomy is a key ingredient for such systems. In this paper, we present a review of the literature dealing with vision-based and marker-less surgical tool detection. This paper includes three primary contributions: (1) identification and analysis of data-sets used for developing and testing detection algorithms, (2) in-depth comparison of surgical tool detection methods from the feature extraction process to the model learning strategy and highlight existing shortcomings, and (3) analysis of validation techniques employed to obtain detection performance results and establish comparison between surgical tool detectors. The papers included in the review were selected through PubMed and Google Scholar searches using the keywords: "surgical tool detection", "surgical tool tracking", "surgical instrument detection" and "surgical instrument tracking" limiting results to the year range 2000 2015. Our study shows that despite significant progress over the years, the lack of established surgical tool data-sets, and reference format for performance assessment and method ranking is preventing faster improvement.

show abstract