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 patients with histologically proven primary liver cancers, including six early, 58 well-differentiated, 109 moderately differentiated, 29 poorly differentiated hepatocellular carcinomas (HCCs), and 13 non-HCC malignant lesions containing cholangiocellular components. We performed TL using various pretrained CNNs and preoperative three-phasic DCE-CT images. Three-phasic DCE-CT images were manually registered to correct respiratory motion. The registered DCE-CT images were then assigned to the three color channels of an input image for TL: pre-contrast, early phase, and delayed phase images for the blue, red, and green channels, respectively. To evaluate the effects of image registration, the registered input image was intentionally misaligned in the three color channels by pixel shifts, rotations, and skews with various degrees. The diagnostic performances (DP) of the pretrained CNNs after TL in the test set were compared by three general radiologists (GRs) and two experienced abdominal radiologists (ARs). The effects of misalignment in the input image and the type of pretrained CNN on the DP were statistically evaluated. RESULTS:The mean DPs for histological subtype classification and differentiation in primary malignant liver tumors on DCE-CT for GR and AR were 39.1%, and 47.9%, respectively. The highest mean DPs for CNNs after TL with pixel shifts, rotations, and skew misalignments were 44.1%, 44.2%, and 43.7%, respectively. Two-way analysis of variance revealed that the DP is significantly affected by the type of pretrained CNN (P = 0.0001), but not by misalignments in input images other than skew deformations. CONCLUSION:TL using pretrained CNNs is robust against misregistration of multiphasic images and comparable to experienced ARs in classifying primary liver cancers using three-phasic DCE-CT.

authors

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

doi

10.1007/s11548-019-01987-1

subject

Has Abstract

pub_date

2019-08-01 00:00:00

pages

1295-1301

issue

8

eissn

1861-6410

issn

1861-6429

pii

10.1007/s11548-019-01987-1

journal_volume

14

pub_type

杂志文章
  • A low-cost tracked C-arm (TC-arm) upgrade system for versatile quantitative intraoperative imaging.

    abstract:PURPOSE:C-arm fluoroscopy is frequently used in clinical applications as a low-cost and mobile real-time qualitative assessment tool. C-arms, however, are not widely accepted for applications involving quantitative assessments, mainly due to the lack of reliable and low-cost position tracking methods, as well as adequa...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-013-0957-9

    authors: Amiri S,Wilson DR,Masri BA,Anglin C

    更新日期:2014-07-01 00:00:00

  • Comparison of different grid of tags detection methods in tagged cardiac MR imaging.

    abstract:PURPOSE:Non-invasive imaging assessment of cardiac function is important in cardiovascular disease diagnosis, especially for evaluation of local cardiac motion. Tagged cardiac MRI has been developed for this purpose, but evaluation of the results requires quantification and automation. METHODS:Two methods utilizing ac...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-010-0495-7

    authors: Histace A,Portefaix C,Matuszewski B

    更新日期:2011-03-01 00:00:00

  • PyDBS: an automated image processing workflow for deep brain stimulation surgery.

    abstract:PURPOSE:Deep brain stimulation (DBS) is a surgical procedure for treating motor-related neurological disorders. DBS clinical efficacy hinges on precise surgical planning and accurate electrode placement, which in turn call upon several image processing and visualization tasks, such as image registration, image segmenta...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-014-1007-y

    authors: D'Albis T,Haegelen C,Essert C,Fernández-Vidal S,Lalys F,Jannin P

    更新日期:2015-02-01 00:00:00

  • Planning nonlinear access paths for temporal bone surgery.

    abstract:PURPOSE:Interventions at the otobasis operate in the narrow region of the temporal bone where several highly sensitive organs define obstacles with minimal clearance for surgical instruments. Nonlinear trajectories for potential minimally invasive interventions can provide larger distances to risk structures and optimi...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1712-z

    authors: Fauser J,Sakas G,Mukhopadhyay A

    更新日期:2018-05-01 00:00:00

  • A Survey of auditory display in image-guided interventions.

    abstract:PURPOSE:This article investigates the current state of the art of the use of auditory display in image-guided medical interventions. Auditory display is a means of conveying information using sound, and we review the use of this approach to support navigated interventions. We discuss the benefits and drawbacks of publi...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章,评审

    doi:10.1007/s11548-017-1547-z

    authors: Black D,Hansen C,Nabavi A,Kikinis R,Hahn H

    更新日期:2017-10-01 00:00:00

  • Analyzing shoulder translation with navigation technology.

    abstract:PURPOSE:Asymmetric stress imposed on the shoulder can lead to anterior shoulder instability in young athletes who perform repetitive overhead motions. A common treatment, surgical anterior capsule tightening, assumes that the instability is caused by abnormal anterior laxity. This study investigated the possibility tha...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-012-0782-6

    authors: Zakani S,Venne G,Smith EJ,Bicknell R,Ellis RE

    更新日期:2012-11-01 00:00:00

  • Incorporating prior shape knowledge via data-driven loss model to improve 3D liver segmentation in deep CNNs.

    abstract:PURPOSE:Convolutional neural networks (CNNs) have obtained enormous success in liver segmentation. However, there are several challenges, including low-contrast images, and large variations in the shape, and appearance of the liver. Incorporating prior knowledge in deep CNN models improves their performance and general...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-019-02085-y

    authors: Mohagheghi S,Foruzan AH

    更新日期:2020-02-01 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

  • Unravelling the effect of data augmentation transformations in polyp segmentation.

    abstract:PURPOSE:Data augmentation is a common technique to overcome the lack of large annotated databases, a usual situation when applying deep learning to medical imaging problems. Nevertheless, there is no consensus on which transformations to apply for a particular field. This work aims at identifying the effect of differen...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02262-4

    authors: Sánchez-Peralta LF,Picón A,Sánchez-Margallo FM,Pagador JB

    更新日期:2020-12-01 00:00:00

  • Automatic needle tracking using Mask R-CNN for MRI-guided percutaneous interventions.

    abstract:PURPOSE:Accurate needle tracking provides essential information for MRI-guided percutaneous interventions. Passive needle tracking using MR images is challenged by variations of the needle-induced signal void feature in different situations. This work aimed to develop an automatic needle tracking algorithm for MRI-guid...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02226-8

    authors: Li X,Young AS,Raman SS,Lu DS,Lee YH,Tsao TC,Wu HH

    更新日期:2020-10-01 00:00:00

  • Path generator control system and virtual compliance calculator for maxillofacial massage robots.

    abstract:PURPOSE:Oral disorders such as temporomandibular joint disorders (TMD) and dry mouth are common and often require treatment. Maxillofacial massage is used as a complementary and alternative therapy for these disorders. We developed an oral rehabilitation robot that massages the maxillofacial tissues for this purpose. I...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-009-0383-1

    authors: Ishii H,Koga H,Obokawa Y,Solis J,Takanishi A,Katsumata A

    更新日期:2010-01-01 00:00:00

  • Vertebra identification using template matching modelmp and K-means clustering.

    abstract:PURPOSE:Accurate vertebra detection and segmentation are essential steps for automating the diagnosis of spinal disorders. This study is dedicated to vertebra alignment measurement, the first step in a computer-aided diagnosis tool for cervical spine trauma. Automated vertebral segment alignment determination is a chal...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章,评审

    doi:10.1007/s11548-013-0927-2

    authors: Larhmam MA,Benjelloun M,Mahmoudi S

    更新日期:2014-03-01 00:00:00

  • Four-dimensional computed tomography angiography analysis of internal carotid arteries opacification at the skull base to detect delayed cerebral ischemia: a feasibility study.

    abstract:PURPOSE:Delayed cerebral ischemia represents a significant cause of poor functional outcome for patients with vasospasm after subarachnoid hemorrhage. We investigated whether delayed cerebral ischemia could be detected by the arterial opacification of internal carotid artery at the level of the skull base. METHODS:In ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02268-y

    authors: Ognard J,Cheddad El Aouni M,Dissaux B,Jomaah R,Rousseau PY,Burdin V,Ben Salem D,Gentric JC

    更新日期:2020-12-01 00:00:00

  • Endoscopic scene labelling and augmentation using intraoperative pulsatile motion and colour appearance cues with preoperative anatomical priors.

    abstract:PURPOSE:Despite great advances in medical image segmentation, the accurate and automatic segmentation of endoscopic scenes remains a challenging problem. Two important aspects have to be considered in segmenting an endoscopic scene: (1) noise and clutter due to light reflection and smoke from cutting tissue, and (2) st...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-015-1331-x

    authors: Nosrati MS,Amir-Khalili A,Peyrat JM,Abinahed J,Al-Alao O,Al-Ansari A,Abugharbieh R,Hamarneh G

    更新日期:2016-08-01 00:00:00

  • Automatic airway tree segmentation based on multi-scale context information.

    abstract:PURPOSE:Airway tree segmentation plays a pivotal role in chest computed tomography (CT) analysis tasks such as lesion localization, surgical planning, and intra-operative guidance. The remaining challenge is to identify small bronchi correctly, which facilitates further segmentation of the pulmonary anatomies. METHODS...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02293-x

    authors: Zhou K,Chen N,Xu X,Wang Z,Guo J,Liu L,Yi Z

    更新日期:2021-01-19 00:00:00

  • Automatic detection of perforator vessels using infrared thermography in reconstructive surgery.

    abstract:PURPOSE:Knowing the location of the blood vessels supplying the skin and subcutaneous tissue is a requirement during the planning of tissue transfer in reconstructive surgery. Commonly used imaging techniques such as computed tomography angiography and indocyanine green angiography expose the patient to radiation or a ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1892-6

    authors: Unger M,Markfort M,Halama D,Chalopin C

    更新日期:2019-03-01 00:00:00

  • Multistage segmentation model and SVM-ensemble for precise lung nodule detection.

    abstract:PURPOSE:Lung cancer detection at its initial stages increases the survival chances of patients. Automatic detection of lung nodules facilitates radiologists during the diagnosis. However, there is a challenge of false positives in automated systems which may lead to wrong findings. Precise segmentation facilitates to a...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1715-9

    authors: Naqi SM,Sharif M,Yasmin M

    更新日期:2018-07-01 00:00:00

  • Robust motion tracking in liver from 2D ultrasound images using supporters.

    abstract:PURPOSE:Effectiveness of image-guided radiation therapy with precise dose delivery depends highly on accurate target localization, which may involve motion during treatment due to, e.g., breathing and drift. Therefore, it is important to track the motion and adjust the radiation delivery accordingly. Tracking generally...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-017-1559-8

    authors: Ozkan E,Tanner C,Kastelic M,Mattausch O,Makhinya M,Goksel O

    更新日期:2017-06-01 00:00:00

  • Hand-eye calibration for surgical cameras: a Procrustean Perspective-n-Point solution.

    abstract:PURPOSE:Surgical cameras are prevalent in modern operating theatres often used as surrogates for direct vision. A surgical navigational system is a useful adjunct, but requires an accurate "hand-eye" calibration to determine the geometrical relationship between the surgical camera and tracking markers. METHODS:Using a...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-017-1590-9

    authors: Morgan I,Jayarathne U,Rankin A,Peters TM,Chen ECS

    更新日期:2017-07-01 00:00:00

  • Automated aorta segmentation in low-dose chest CT images.

    abstract:PURPOSE:Abnormalities of aortic surface and aortic diameter can be related to cardiovascular disease and aortic aneurysm. Computer-based aortic segmentation and measurement may aid physicians in related disease diagnosis. This paper presents a fully automated algorithm for aorta segmentation in low-dose non-contrast CT...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-013-0924-5

    authors: Xie Y,Padgett J,Biancardi AM,Reeves AP

    更新日期:2014-03-01 00:00:00

  • A vision-based system for fast and accurate laser scanning in robot-assisted phonomicrosurgery.

    abstract:PURPOSE:Surgical quality in phonomicrosurgery can be improved by open-loop laser control (e.g., high-speed scanning capabilities) with a robust and accurate closed-loop visual servoing systems. A new vision-based system for laser scanning control during robot-assisted phonomicrosurgery was developed and tested. METHOD...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-014-1078-9

    authors: Dagnino G,Mattos LS,Caldwell DG

    更新日期:2015-02-01 00:00:00

  • Feature detection in biological tissues using multi-band and narrow-band imaging.

    abstract:PURPOSE:In the past decade, augmented reality systems have been expected to support surgical operations by making it possible to view invisible objects that are inside or occluded by the skull, hands, or organs. However, the properties of biological tissues that are non-rigid and featureless require a large number of d...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-016-1458-4

    authors: Tamura Y,Mashita T,Kuroda Y,Kiyokawa K,Takemura H

    更新日期:2016-12-01 00:00:00

  • Precise 3D/2D calibration between a RGB-D sensor and a C-arm fluoroscope.

    abstract:PURPOSE:Calibration and registration are the first steps for augmented reality and mixed reality applications. In the medical field, the calibration between an RGB-D camera and a C-arm fluoroscope is a new topic which introduces challenges. METHOD:A convenient and efficient calibration phantom is designed by combining...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-015-1347-2

    authors: Wang X,Habert S,Ma M,Huang CH,Fallavollita P,Navab N

    更新日期:2016-08-01 00:00:00

  • Development and evaluation of a prototype detector for an intraoperative laparoscopic coincidence imaging system with PET tracers.

    abstract:PURPOSE:Conventional positron emission tomography can be used only preoperatively to identify lymph node metastases, and hence, these growths are difficult to locate intraoperatively. Previously, an intraoperative laparoscopic coincidence imaging system, with an external fixed detector array and a detector probe that c...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-020-02282-0

    authors: Liyanaarachchi MR,Shimazoe K,Takahashi H,Nakagawa K,Kobayashi E,Sakuma I

    更新日期:2021-01-01 00:00:00

  • Meaningful Assessment of Robotic Surgical Style using the Wisdom of Crowds.

    abstract:OBJECTIVE:Quantitative assessment of surgical skills is an important aspect of surgical training; however, the proposed metrics are sometimes difficult to interpret and may not capture the stylistic characteristics that define expertise. This study proposes a methodology for evaluating the surgical skill, based on metr...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-018-1738-2

    authors: Ershad M,Rege R,Fey AM

    更新日期:2018-07-01 00:00:00

  • Scaled, patient-specific 3D vertebral model reconstruction based on 2D lateral fluoroscopy.

    abstract:BACKGROUNDS:Accurate three-dimensional (3D) models of lumbar vertebrae are required for image-based 3D kinematics analysis. MRI or CT datasets are frequently used to derive 3D models but have the disadvantages that they are expensive, time-consuming or involving ionizing radiation (e.g., CT acquisition). An alternative...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-010-0515-7

    authors: Zheng G,Nolte LP,Ferguson SJ

    更新日期:2011-05-01 00:00:00

  • Suspension laryngoscopy using a curved-frame trans-oral robotic system.

    abstract:PURPOSE:Suspension laryngoscopy has been employed for laryngeal diseases such as treatment for a polyp, cystoma, or granuloma. After securing a straight path with a laryngoscope, the surgeon inserts rigid instruments and examines the target lesion by using a microscope. However, many patients suffer from secondary comp...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-013-0944-1

    authors: Kwon YS,Tae K,Yi BJ

    更新日期:2014-07-01 00:00:00

  • The effect of CyberDome, a novel 3-dimensional dome-shaped display system, on laparoscopic procedures.

    abstract:BACKGROUND:Laparoscopic surgeons require extended experience of cases to overcome the lack of depth perception on a two-dimensional (2D) display. Although a three-dimensional (3D) display was reported to be useful over two decades ago, 3D systems have not been widely used. Recently, we developed a novel 3D dome-shaped ...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-009-0282-5

    authors: Ohuchida K,Kenmotsu H,Yamamoto A,Sawada K,Hayami T,Morooka K,Hoshino H,Uemura M,Konishi K,Yoshida D,Maeda T,Ieiri S,Tanoue K,Tanaka M,Hashizume M

    更新日期:2009-03-01 00:00:00

  • Orbital volume analysis: validation of a semi-automatic software segmentation method.

    abstract:PURPOSE:The purpose of this study was to validate a quick, accurate and reproducible (semi-) automatic software segmentation method to measure orbital volume in the unaffected bony orbit. Precise volume measurement of the orbital cavity is a useful addition to pre-operative planning and intraoperative navigation in orb...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-015-1254-6

    authors: Jansen J,Schreurs R,Dubois L,Maal TJ,Gooris PJ,Becking AG

    更新日期:2016-01-01 00:00:00

  • Breast masses detection using phase portrait analysis and fuzzy inference systems.

    abstract:PURPOSE:Breast masses exhibit variability in margins, shapes, and dimensions, so their detection is a difficult task in mammographic computer-aided diagnosis. Mass detection is usually a two-step procedure: mass identification and false-positive reduction. A new method to automatically detect mass lesions in mammograph...

    journal_title:International journal of computer assisted radiology and surgery

    pub_type: 杂志文章

    doi:10.1007/s11548-011-0659-0

    authors: Mencattini A,Salmeri M

    更新日期:2012-07-01 00:00:00