A test-bed for computer-assisted fusion of multi-modality medical images

1993 ◽  
pp. 664-668 ◽  
Author(s):  
K. Mikołajczyk ◽  
J. Owczarczyk ◽  
W. Rećko
Keyword(s):  
Medical Images ◽  
Computer Assisted ◽  
Test Bed

Computer-assisted frameworks for classification of liver, breast and blood neoplasias via neural networks: A survey based on medical images

2019 ◽  
Vol 335 ◽  
pp. 274-298 ◽  
Author(s):  
Antonio Brunetti ◽  
Leonarda Carnimeo ◽  
Gianpaolo Francesco Trotta ◽  
Vitoantonio Bevilacqua
Keyword(s):  
Neural Networks ◽  
Medical Images ◽  
Computer Assisted

scholarly journals Liver 3D modeling and hepatectomy simulation for the residents’ preoperative education

2015 ◽  
Author(s):  
Apollon Zygomalas ◽  
Vasileios Megalooikonomou ◽  
Dimitrios Koutsouris ◽  
Dimitrios Karavias ◽  
Ioannis Karagiannidis ◽  
...  
Keyword(s):  
Liver Resection ◽  
3D Modeling ◽  
Preoperative Planning ◽  
Medical Images ◽  
Patient Specific ◽  
Computer Assisted ◽  
Liver Imaging ◽  
Liver Segmentation ◽  
Preoperative Education ◽  
Liver Remnant

Background. Liver segmentation from medical images produces high quality patient specific 3D liver models which are used for preoperative planning and intraoperative guidance. These 3D models can be manipulated and visualized in various ways and can be useful for residents’ education. Objective. The aim of this study was to evaluate the implementation of a novel liver segmentation and hepatectomy simulation application as a tool for the residents’ preoperative education. Method. We developed in MATLAB® 2013a a liver segmentation and preoperative planning application. Ten liver imaging datasets of a prospectively selected random sample of patients undergoing elective hepatectomies at our institution were used for liver segmentation and 3D modeling. Residents were asked to identify anatomical and pathological structures and propose liver resection plans. Intraoperatively, they could consult the computer models in real time. Their surgical scenarios were evaluated and discussed with specialized liver surgeons. Learning objectives were defined and their accomplishment was evaluated using the Kirkpatrick’s four levels model. Results. The residents learned to 1) identify anatomical and pathological structures 2) calculate future liver remnant volume (FLR) from segmented liver images 3) propose liver resection plans based on FLR and liver vascular tree and tumor relations 4) consult liver medical images (CT and MRI) 5) understand the role of computer assisted surgery. They evaluated in-vivo their preoperative planning decisions and understood better the surgical operations. Conclusions. Our proposed liver segmentation and hepatectomy simulation application appears to be appropriate for the preoperative education of resident surgeons.

Influence of Input Image Configurations on Output of a Convolutional Neural Network to Detect Cerebral Aneurysms

2019 ◽  
Author(s):  
Kazuhiro Watanabe ◽  
Hitomi Anzai ◽  
Norman Juchler ◽  
Sven Hirsch ◽  
Philippe Bijlenga ◽  
...  
Keyword(s):  
Medical Imaging ◽  
Classification Accuracy ◽  
Input Data ◽  
Medical Images ◽  
Cerebral Aneurysms ◽  
Input Image ◽  
Computer Assisted ◽  
Imaging Data ◽  
Cad Systems ◽  
Unruptured Aneurysms

Abstract Rupture of cerebral aneurysms is the main cause of subarachnoid hemorrhage, which can have devastating effects on quality of life. The identification and assessment of unruptured aneurysms from medical images is therefore of significant clinical relevance. In recent years, the availability of clinical imaging data has rapidly increased, which calls for computer assisted detection (CAD) systems. Previous studies have shown that CAD systems based on convolutional neural networks (CNN) can help to detect cerebral aneurysms from magnetic resonance angiographies (MRAs). However, these CAD systems require large datasets of annotated medical images. Thus, more efficient tools for processing and categorizing medical imaging data are required. Previous studies of CNN-based classification for medical images used various patch configurations of input data. These studies showed that classification accuracy was affected by the patch size or image representation. Thus, we hypothesize that the accuracy of CADs to detect cerebral aneurysms can be improved by adjusting the configuration of the input patches. In the present study, we performed CNN-based medical imaging classification for varying input data configurations to examine the relationship between classification accuracy and data configuration.

scholarly journals Liver 3D modeling and hepatectomy simulation for the residents’ preoperative education

2015 ◽  
Author(s):  
Apollon Zygomalas ◽  
Vasileios Megalooikonomou ◽  
Dimitrios Koutsouris ◽  
Dimitrios Karavias ◽  
Ioannis Karagiannidis ◽  
...  
Keyword(s):  
Liver Resection ◽  
3D Modeling ◽  
Preoperative Planning ◽  
Medical Images ◽  
Patient Specific ◽  
Computer Assisted ◽  
Liver Imaging ◽  
Liver Segmentation ◽  
Preoperative Education ◽  
Liver Remnant

Background. Liver segmentation from medical images produces high quality patient specific 3D liver models which are used for preoperative planning and intraoperative guidance. These 3D models can be manipulated and visualized in various ways and can be useful for residents’ education. Objective. The aim of this study was to evaluate the implementation of a novel liver segmentation and hepatectomy simulation application as a tool for the residents’ preoperative education. Method. We developed in MATLAB® 2013a a liver segmentation and preoperative planning application. Ten liver imaging datasets of a prospectively selected random sample of patients undergoing elective hepatectomies at our institution were used for liver segmentation and 3D modeling. Residents were asked to identify anatomical and pathological structures and propose liver resection plans. Intraoperatively, they could consult the computer models in real time. Their surgical scenarios were evaluated and discussed with specialized liver surgeons. Learning objectives were defined and their accomplishment was evaluated using the Kirkpatrick’s four levels model. Results. The residents learned to 1) identify anatomical and pathological structures 2) calculate future liver remnant volume (FLR) from segmented liver images 3) propose liver resection plans based on FLR and liver vascular tree and tumor relations 4) consult liver medical images (CT and MRI) 5) understand the role of computer assisted surgery. They evaluated in-vivo their preoperative planning decisions and understood better the surgical operations. Conclusions. Our proposed liver segmentation and hepatectomy simulation application appears to be appropriate for the preoperative education of resident surgeons.

3-D organization of fibrinogen receptors using computer reconstruction and whole-mount microscopy

1988 ◽  
Vol 46 ◽  
pp. 30-31
Author(s):  
E. T. O'Toole ◽  
R. R. Hantgan ◽  
J. C. Lewis
Keyword(s):  
Whole Blood ◽  
Colloidal Gold ◽  
Blood Platelets ◽  
Cell Contact ◽  
Computer Assisted ◽  
Adherent Cells ◽  
Differential Centrifugation ◽  
Computer Reconstruction ◽  
Sds Page ◽  
Whole Mount

Thrombocytes (TC), the avian equivalent of blood platelets, support hemostasis by aggregating at sites of injury. Studies in our lab suggested that fibrinogen (fib) is a requisite cofactor for TC aggregation but operates by an undefined mechanism. To study the interaction of fib with TC and to identify fib receptors on cells, fib was purified from pigeon plasma, conjugated to colloidal gold and used both to facilitate aggregation and as a receptor probe. Described is the application of computer assisted reconstruction and stereo whole mount microscopy to visualize the 3-D organization of fib receptors at sites of cell contact in TC aggregates and on adherent cells.Pigeon TC were obtained from citrated whole blood by differential centrifugation, washed with Ca++ free Hank's balanced salts containing 0.3% EDTA (pH 6.5) and resuspended in Ca++ free Hank's. Pigeon fib was isolated by precipitation with PEG-1000 and the purity assessed by SDS-PAGE. Fib was conjugated to 25nm colloidal gold by vortexing and the conjugates used as the ligand to identify fib receptors.

Sign in / Sign up

Export Citation Format

Share Document