Shot boundary detection in endoscopic surgery videos using a variational Bayesian framework.

Abstract:

PURPOSE:Over the last decade, the demand for content management of video recordings of surgical procedures has greatly increased. Although a few research methods have been published toward this direction, the related literature is still in its infancy. In this paper, we address the problem of shot detection in endoscopic surgery videos, a fundamental step in content-based video analysis. METHODS:The video is first decomposed into short clips that are processed sequentially. After feature extraction, we employ spatiotemporal Gaussian mixture models (GMM) for each clip and apply a variational Bayesian (VB) algorithm to approximate the posterior distribution of the model parameters. The proper number of components is handled automatically by the VBGMM algorithm. The estimated components are matched along the video sequence via their Kullback-Leibler divergence. Shot borders are defined when component tracking fails, signifying a different visual appearance of the surgical scene. RESULTS:Experimental evaluation was performed on laparoscopic videos containing a variable number of shots. Performance was measured via precision, recall, coverage and overflow metrics. The proposed method was compared with GMM and a shot detection method based on spatiotemporal motion differences (MotionDiff). The results demonstrate that VBGMM has higher performance than all other methods for most assessment metrics: precision and recall >80 %, coverage: 84 %. Overflow for VBGMM was worse than MotionDiff (37 vs. 27 %). CONCLUSIONS:The proposed method generated promising results for shot border detection. Spatiotemporal modeling via VBGMMs provides a means to explore additional applications such as component tracking.

authors

Loukas C,Nikiteas N,Schizas D,Georgiou E

doi

10.1007/s11548-016-1431-2

subject

Has Abstract

pub_date

2016-11-01 00:00:00

pages

1937-1949

issue

11

eissn

1861-6410

issn

1861-6429

pii

10.1007/s11548-016-1431-2

journal_volume

11

pub_type

杂志文章
  • Ultrasound thermal monitoring with an external ultrasound source for customized bipolar RF ablation shapes.

    abstract:PURPOSE:Thermotherapy is a clinical procedure which delivers thermal energy to a target, and it has been applied for various medical treatments. Temperature monitoring during thermotherapy is important to achieve precise and reproducible results. Medical ultrasound can be used for thermal monitoring and is an attractiv...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1744-4

    authors: Kim Y,Audigier C,Ziegle J,Friebe M,Boctor EM

    更新日期:2018-06-01 00:00:00

  • Image-based laparoscopic bowel measurement.

    abstract:PURPOSE:Minimally invasive interventions offer benefits for patients, while also entailing drawbacks for surgeons, such as the loss of depth perception. Thus estimating distances, which is of particular importance in gastric bypasses, becomes difficult. In this paper, we propose an approach based on stereo endoscopy th...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-015-1291-1

    authors: Bodenstedt S,Wagner M,Mayer B,Stemmer K,Kenngott H,Müller-Stich B,Dillmann R,Speidel S

    更新日期:2016-03-01 00:00:00

  • Dynamic infrared thermography (DIRT) for assessment of skin blood perfusion in cranioplasty: a proof of concept for qualitative comparison with the standard indocyanine green video angiography (ICGA).

    abstract:PURPOSE:Complications in wound healing after neurosurgical operations occur often due to scarred dehiscence with skin blood perfusion disturbance. The standard imaging method for intraoperative skin perfusion assessment is the invasive indocyanine green video angiography (ICGA). The noninvasive dynamic infrared thermog...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-017-1683-5

    authors: Rathmann P,Chalopin C,Halama D,Giri P,Meixensberger J,Lindner D

    更新日期:2018-03-01 00:00:00

  • Preliminary study on magnetic tracking-based planar shape sensing and navigation for flexible surgical robots in transoral surgery: methods and phantom experiments.

    abstract:PURPOSE:Flexible surgical robot can work in confined and complex environments, which makes it a good option for minimally invasive surgery. In order to utilize flexible manipulators in complicated and constrained surgical environments, it is of great significance to monitor the position and shape of the curvilinear man...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-017-1672-8

    authors: Song S,Zhang C,Liu L,Meng MQ

    更新日期:2018-02-01 00:00:00

  • Gain determination of feedback force for an ultrasound scanning robot using genetic algorithm.

    abstract:PURPOSE:The remote medical diagnosis system (RMDS) is for providing medical diagnosis to the patients located in remote sites. To apply to RMDS and medical automation, many master-slave type ultrasound scanning robots are being developed and researched. One of the important research issue of the master-slave type ultra...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-019-01915-3

    authors: Kim YJ,Park CK,Kim KG

    更新日期:2019-05-01 00:00:00

  • Evaluation of a marker-less, intra-operative, augmented reality guidance system for robot-assisted laparoscopic radical prostatectomy.

    abstract:PURPOSE:Robot-assisted laparoscopic radical prostatectomy (RALRP) using the da Vinci surgical robot is a common treatment for organ-confined prostate cancer. Augmented reality (AR) can help during RALRP by showing the surgeon the location of anatomical structures and tumors from preoperative imaging. Previously, we pro...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02181-4

    authors: Kalia M,Mathur P,Tsang K,Black P,Navab N,Salcudean S

    更新日期:2020-07-01 00:00:00

  • A practical marker-less image registration method for augmented reality oral and maxillofacial surgery.

    abstract:BACKGROUND:Image registration lies in the core of augmented reality (AR), which aligns the virtual scene with the reality. In AR surgical navigation, the performance of image registration is vital to the surgical outcome. METHODS:This paper presents a practical marker-less image registration method for AR-guided oral ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-019-01921-5

    authors: Wang J,Shen Y,Yang S

    更新日期:2019-05-01 00:00:00

  • Patient-specific estimation of detailed cochlear shape from clinical CT images.

    abstract:PURPOSE:A personalized estimation of the cochlear shape can be used to create computational anatomical models to aid cochlear implant (CI) surgery and CI audio processor programming ultimately resulting in improved hearing restoration. The purpose of this work is to develop and test a method for estimation of the detai...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-017-1701-7

    authors: Kjer HM,Fagertun J,Wimmer W,Gerber N,Vera S,Barazzetti L,Mangado N,Ceresa M,Piella G,Stark T,Stauber M,Reyes M,Weber S,Caversaccio M,González Ballester MÁ,Paulsen RR

    更新日期:2018-03-01 00:00:00

  • Model-based segmentation in orbital volume measurement with cone beam computed tomography and evaluation against current concepts.

    abstract:PURPOSE:Objective determination of the orbital volume is important in the diagnostic process and in evaluating the efficacy of medical and/or surgical treatment of orbital diseases. Tools designed to measure orbital volume with computed tomography (CT) often cannot be used with cone beam CT (CBCT) because of inferior t...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-015-1228-8

    authors: Wagner ME,Gellrich NC,Friese KI,Becker M,Wolter FE,Lichtenstein JT,Stoetzer M,Rana M,Essig H

    更新日期:2016-01-01 00:00:00

  • Planning of mandibular reconstructions based on statistical shape models.

    abstract:PURPOSE:The reconstruction of large continuity defects of the mandible is a challenging task, especially when the shape of the missing part is not known prior to operation. Today, the surgical planning is based mainly on visual judgment and the individual skills and experience of the surgeons. The objective of the curr...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-016-1451-y

    authors: Raith S,Wolff S,Steiner T,Modabber A,Weber M,Hölzle F,Fischer H

    更新日期:2017-01-01 00:00:00

  • Detection and modelling of contacts in explicit finite-element simulation of soft tissue biomechanics.

    abstract:PURPOSE:Realistic modelling of soft tissue biomechanics and mechanical interactions between tissues is an important part of biomechanically-informed surgical image-guidance and surgical simulation. This submission details a contact-modelling pipeline suitable for implementation in explicit matrix-free FEM solvers. Whil...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-014-1142-5

    authors: Johnsen SF,Taylor ZA,Han L,Hu Y,Clarkson MJ,Hawkes DJ,Ourselin S

    更新日期:2015-11-01 00:00:00

  • Automated identification and reduction of artifacts in cine four-dimensional computed tomography (4DCT) images using respiratory motion model.

    abstract:PURPOSE:Four-dimensional computed tomography (4DCT) images are often marred by artifacts that substantially degrade image quality and confound image interpretation. Human observation remains the standard method of 4DCT artifact evaluation, which is time-consuming and subjective. We develop a method to automatically ide...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-017-1538-0

    authors: Li M,Castillo SJ,Castillo R,Castillo E,Guerrero T,Xiao L,Zheng X

    更新日期:2017-09-01 00:00:00

  • Fast and flexible distance measures for treatment planning.

    abstract:PURPOSE:Distance measures are required for diagnoses, therapy decision and documentation. With today's high-resolution CT and MR imaging techniques, high- quality images have become possible. Yet, manual measurement can be tedious. We present a method for automatically determining different distance-based measures on s...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-010-0519-3

    authors: Rössling I,Cyrus C,Dornheim L,Boehm A,Preim B

    更新日期:2010-11-01 00:00:00

  • Development of preoperative planning software for transforaminal endoscopic surgery and the guidance for clinical applications.

    abstract:PURPOSE:Preoperative planning is of great importance for transforaminal endoscopic techniques applied in percutaneous endoscopic lumbar discectomy. In this study, a modular preoperative planning software for transforaminal endoscopic surgery was developed and demonstrated. METHODS:The path searching method is based on...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-015-1282-2

    authors: Chen X,Cheng J,Gu X,Sun Y,Politis C

    更新日期:2016-04-01 00:00:00

  • Automatic segmentation of stereoelectroencephalography (SEEG) electrodes post-implantation considering bending.

    abstract:PURPOSE:The accurate and automatic localisation of SEEG electrodes is crucial for determining the location of epileptic seizure onset. We propose an algorithm for the automatic segmentation of electrode bolts and contacts that accounts for electrode bending in relation to regional brain anatomy. METHODS:Co-registered ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1740-8

    authors: Granados A,Vakharia V,Rodionov R,Schweiger M,Vos SB,O'Keeffe AG,Li K,Wu C,Miserocchi A,McEvoy AW,Clarkson MJ,Duncan JS,Sparks R,Ourselin S

    更新日期:2018-06-01 00:00:00

  • Temporal enhancement of 2D color Doppler echocardiography sequences by fragment-based frame reordering and refinement.

    abstract:PURPOSE:The goal of this study was to develop an algorithm that enhances the temporal resolution of two-dimensional color Doppler echocardiography (2D CDE) by reordering all the acquired frames and filtering out the frames corrupted by out-of-plane motion and arrhythmia. METHODS:The algorithm splits original frame seq...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-019-01926-0

    authors: Terentjev AB,Perrin DP,Settlemier SH,Zurakowski D,Smirnov PO,Del Nido PJ,Shturts IV,Vasilyev NV

    更新日期:2019-04-01 00:00:00

  • Interactive determination of robust safety margins for oncologic liver surgery.

    abstract:OBJECTIVE:Complex oncologic interventions in the liver require an extensive and careful preoperative analysis. Particularly the achievement of an optimal safety margin around tumors remains a difficult task for surgeons. METHODS:We present new methods for evaluating different safety margins and their effect on the ass...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-009-0359-1

    authors: Hansen C,Zidowitz S,Hindennach M,Schenk A,Hahn H,Peitgen HO

    更新日期:2009-09-01 00:00:00

  • Image-based 3D modeling and validation of radiofrequency interstitial tumor ablation using a tissue-mimicking breast phantom.

    abstract:PURPOSE:Minimally invasive treatment of solid cancers, especially in the breast and liver, remains clinically challenging, despite a variety of treatment modalities, including radiofrequency ablation (RFA), microwave ablation or high-intensity focused ultrasound. Each treatment modality has advantages and disadvantages...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-012-0769-3

    authors: Wang Z,Aarya I,Gueorguieva M,Liu D,Luo H,Manfredi L,Wang L,McLean D,Coleman S,Brown S,Cuschieri A

    更新日期:2012-11-01 00:00:00

  • Interactive bone drilling using a 2D pointing device to support Microendoscopic Discectomy planning.

    abstract:PURPOSE:To support preoperative planning of bone drilling for Microendoscopic Discectomy, we present a set of interactive bone-drilling methods using a general 2D pointing device. METHODS:Unlike the existing methods, our framework has the following features: (1) the user can directly cut away arbitrary 3D regions on t...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-010-0413-z

    authors: Imanishi K,Nakao M,Kioka M,Mori M,Yoshida M,Takahashi T,Minato K

    更新日期:2010-09-01 00:00:00

  • Segmentation of the placenta and its vascular tree in Doppler ultrasound for fetal surgery planning.

    abstract:PURPOSE:Twin-to-twin transfusion syndrome (TTTS) is a serious condition that occurs in about 10-15% of monochorionic twin pregnancies. In most instances, the blood flow is unevenly distributed throughout the placenta anastomoses leading to the death of both fetuses if no surgical procedure is performed. Fetoscopic lase...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02256-2

    authors: Perera-Bel E,Ceresa M,Torrents-Barrena J,Masoller N,Valenzuela-Alcaraz B,Gratacós E,Eixarch E,González Ballester MA

    更新日期:2020-11-01 00:00:00

  • Video-based computer navigation in knee arthroscopy for patient-specific ACL reconstruction.

    abstract:PURPOSE:The anterior cruciate ligament tear is a common medical condition that is treated using arthroscopy by pulling a tissue graft through a tunnel opened with a drill. The correct anatomical position and orientation of this tunnel are crucial for knee stability, and drilling an adequate bone tunnel is the most tech...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-019-02021-0

    authors: Raposo C,Barreto JP,Sousa C,Ribeiro L,Melo R,Oliveira JP,Marques P,Fonseca F,Barrett D

    更新日期:2019-09-01 00:00:00

  • Multi-input deep learning architecture for predicting breast tumor response to chemotherapy using quantitative MR images.

    abstract:PURPOSE:Neoadjuvant chemotherapy (NAC) aims to minimize the tumor size before surgery. Predicting response to NAC could reduce toxicity and delays to effective intervention. Computational analysis of dynamic contrast-enhanced magnetic resonance images (DCE-MRI) through deep convolution neural network (CNN) has shown a ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02209-9

    authors: El Adoui M,Drisis S,Benjelloun M

    更新日期:2020-09-01 00:00:00

  • Temporal bone borehole accuracy for cochlear implantation influenced by drilling strategy: an in vitro study.

    abstract:PURPOSE:Minimally invasive cochlear implantation is a surgical technique which requires drilling a canal from the mastoid surface toward the basal turn of the cochlea. The choice of an appropriate drilling strategy is hypothesized to have significant influence on the achievable targeting accuracy. Therefore, a method i...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-014-0997-9

    authors: Kobler JP,Schoppe M,Lexow GJ,Rau TS,Majdani O,Kahrs LA,Ortmaier T

    更新日期:2014-11-01 00:00:00

  • Accurate two-dimensional cardiac strain calculation using adaptive windowed Fourier transform and Gabor wavelet transform.

    abstract:PURPOSE:Cardiac strain calculated from tagged magnetic resonance (MR) images provides clinicians information about abnormalities of heart-wall motion in patients. It is important to develop an accurate method to determine the cardiac strain efficiently. An adaptive windowed harmonic phase (AWHARP) method is proposed fo...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-012-0689-2

    authors: Fu YB,Chui CK,Teo CL

    更新日期:2013-01-01 00:00:00

  • Use the force: deformation correction in robotic 3D ultrasound.

    abstract:PURPOSE:Ultrasound acquisitions are typically affected by deformations due to the pressure applied onto the contact surface. While a certain amount of pressure is necessary to ensure good acoustic coupling and visibility of the anatomy under examination, the caused deformations hinder accurate localization and geometri...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1716-8

    authors: Virga S,Göbl R,Baust M,Navab N,Hennersperger C

    更新日期:2018-05-01 00:00:00

  • Development of a shoulder-mounted robot for MRI-guided needle placement: phantom study.

    abstract:PURPOSE:This paper presents new quantitative data on a signal-to-noise ratio (SNR) study, distortion study, and targeting accuracy phantom study for our patient-mounted robot (called Arthrobot). Arthrobot was developed as an MRI-guided needle placement device for diagnostic and interventional procedures such as arthrog...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1839-y

    authors: Monfaredi R,Iordachita I,Wilson E,Sze R,Sharma K,Krieger A,Fricke S,Cleary K

    更新日期:2018-11-01 00:00:00

  • A preregistered STAMP method for image-guided temporal bone surgery.

    abstract:OBJECTIVES:Image-guided otological surgeries require minimal invasiveness and high accuracy, and these two factors usually compete with each other. Our recently developed registration method, called the STAMP method, showed minimal invasiveness with accuracy comparable to that of the current more invasive registration ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-013-0916-5

    authors: Oka M,Cho B,Matsumoto N,Hong J,Jinnouchi M,Ouchida R,Komune S,Hashizume M

    更新日期:2014-01-01 00:00:00

  • Estimating needle tip deflection in biological tissue from a single transverse ultrasound image: application to brachytherapy.

    abstract:PURPOSE:This paper proposes a method to predict the deflection of a flexible needle inserted into soft tissue based on the observation of deflection at a single point along the needle shaft. METHODS:We model the needle-tissue as a discretized structure composed of several virtual, weightless, rigid links connected by ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-015-1329-4

    authors: Rossa C,Sloboda R,Usmani N,Tavakoli M

    更新日期:2016-07-01 00:00:00

  • Designing and validating a PVA liver phantom with respiratory motion for needle-based interventions.

    abstract:PURPOSE:The purpose is to design and validate an anthropomorphic polyvinyl alcohol (PVA) liver phantom with respiratory motion to simulate needle-based interventions. Such a system can, for example, be used as a validation tool for novel needles. METHODS:Image segmentations of CT scans of four patients during inspirat...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-019-02029-6

    authors: de Jong TL,Moelker A,Dankelman J,van den Dobbelsteen JJ

    更新日期:2019-12-01 00:00:00

  • Dynamic contrast-enhanced computed tomography diagnosis of primary liver cancers using transfer learning of pretrained convolutional neural networks: Is registration of multiphasic images necessary?

    abstract:PURPOSE:To evaluate the effect of image registration on the diagnostic performance of transfer learning (TL) using pretrained convolutional neural networks (CNNs) and three-phasic dynamic contrast-enhanced computed tomography (DCE-CT) for primary liver cancers. METHODS:We retrospectively evaluated 215 consecutive pati...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-019-01987-1

    authors: Yamada A,Oyama K,Fujita S,Yoshizawa E,Ichinohe F,Komatsu D,Fujinaga Y

    更新日期:2019-08-01 00:00:00