2016 IEEE International Conference on Serious Games and Applications for Health (SeGAH), 2016
In this manuscript, we propose to adapt the B-Spline Explicit Active Surfaces (BEAS) framework fo... more In this manuscript, we propose to adapt the B-Spline Explicit Active Surfaces (BEAS) framework for semi-automatic kidney segmentation in computed tomography (CT) images. To study the best energy functional for kidney CT extraction, three different localized region-based energies were implemented within the BEAS framework, namely localized Chan-Vese, localized Yezzi, and signed localized Yezzi energies. Moreover, a novel gradient-based regularization term is proposed. The method was applied on 18 kidneys from 9 CT datasets, with different image properties. Several energy combinations were contrasted using surface-based comparison against ground truth meshes, assessing their accuracy and robustness against surface initialization. Overall, the hybrid energy functional combining the localized signed Yezzi energy with gradient-based regularization simultaneously showed the highest accuracy and the lowest sensitivity to the initialization. Volumetric analysis demonstrated the feasibility of the method from a clinical point of view, with similar reproducibility to manual observers.
Introdução ao problema da aquisição do relevo_____________________________ 7.3 Modelo para o sens... more Introdução ao problema da aquisição do relevo_____________________________ 7.3 Modelo para o sensor de ultrassons _______________________________________ 7.3.1 Modelo utilizado____________________________________________________________ 7.4 Determinação das dimensões do objecto ___________________________________ 7.5 Aquisição do relevo da superfície visível ___________________________________ 7.5.1 Fusão/Integração sensorial de dados provenientes de ultrassons _______________________ 7.6 Sumário _____________________________________________________________ 8. Resultados experimentais ______________________________________________124 8.1 Introdução ___________________________________________________________ 8.2 Testes realizados ______________________________________________________ 8.3 Apreciação dos resultados_______________________________________________ 9. Conclusões e sugestões para trabalho futuro _______________________________138 9.1 Conclusões ___________________________________________________________ 9.2 Sugestões para trabalho futuro __________________________________________
Pectus excavatum is the most common congenital deformity of the anterior chest wall, in which an ... more Pectus excavatum is the most common congenital deformity of the anterior chest wall, in which an abnormal formation of the rib cage gives the chest a caved-in or sunken appearance. Today, the surgical correction of this deformity is carried out in children and adults through Nuss technic, which consists in the placement of a prosthetic bar under the sternum and over the ribs. Although this technique has been shown to be safe and reliable, not all patients have achieved adequate cosmetic outcome. This often leads to psychological problems and social stress, before and after the surgical correction. This paper targets this particular problem by presenting a method to predict the patient surgical outcome based on pre-surgical imagiologic information and chest skin dynamic modulation. The proposed approach uses the patient pre-surgical thoracic CT scan and anatomical-surgical references to perform a 3D segmentation of the left ribs, right ribs, sternum and skin. The technique encompasses three steps: a) approximation of the cartilages, between the ribs and the sternum, trough b-spline interpolation; b) a volumetric mass spring model that connects two layers-inner skin layer based on the outer pleura contour and the outer surface skin; and c) displacement of the sternum according to the prosthetic bar position. A dynamic model of the skin around the chest wall region was generated, capable of simulating the effect of the movement of the prosthetic bar along the sternum. The results were compared and validated with patient postsurgical skin surface acquired with Polhemus FastSCAN system.
Pectus excavatum is the most common congenital deformity of the anterior thoracic wall. The surgi... more Pectus excavatum is the most common congenital deformity of the anterior thoracic wall. The surgical correction of such deformity, using Nuss procedure, consists in the placement of a personalized convex prosthesis into sub-sternal position to correct the deformity. The aim of this work is the CT-scan substitution by ultrasound imaging for the pre-operative diagnosis and pre-modeling of the prosthesis, in order to avoid patient radiation exposure. To accomplish this, ultrasound images are acquired along an axial plane, followed by a rigid registration method to obtain the spatial transformation between subsequent images. These images are overlapped to reconstruct an axial plane equivalent to a CT-slice. A phantom was used to conduct preliminary experiments and the achieved results were compared with the corresponding CT-data, showing that the proposed methodology can be capable to create a valid approximation of the anterior thoracic wall, which can be used to model/bend the prosthesis.
Background: Surgical repair of pectus excavatum (PE) has become more popular due to improvements ... more Background: Surgical repair of pectus excavatum (PE) has become more popular due to improvements in the minimally invasive Nuss procedure. The pre-surgical assessment of PE patients requires Computerized Tomography (CT), as the malformation characteristics vary from patient to patient. Objective: This work aims to characterize soft tissue thickness (STT) external to the ribs among PE patients. It also presents a comparative analysis between the anterior chest wall surface before and after surgical correction. Methods: Through surrounding tissue segmentation in CT data, STT values were calculated at different lines along the thoracic wall, with a reference point in the intersection of coronal and median planes. The comparative analysis between the two 3D anterior chest surfaces sets a surgical correction influence area (SCIA) and a volume of interest (VOI) based on image processing algorithms, 3D surface algorithms, and registration methods. Results: There are always variations between left and right side STTs (2.54 ± 2.05 mm and 2.95 ± 2.97 mm for female and male patients, respectively). STTs are dependent on age, sex, and body mass index of each patient. On female patients, breast tissue induces additional errors in bar manual ☆ Funding: This work was supported by "Fundação para a Ciência e a Tecnologia" (FCT), Portugal, through the R&D project referenced PTDC/SAU-BEB/
In the industry of foundry, the deburring of casting pieces is an important stage. Since the piec... more In the industry of foundry, the deburring of casting pieces is an important stage. Since the piece presents edges in the junction zone of the casting moulds, those usually are not desirable and should be eliminated. For solving this problem it was idealized a robotic system capable of deburring casting pieces with minimum human intervention. Consists of an ABB robot, a table of coordinates for fixation and movement of the casting pieces, an artificial vision system for identification and quality control of the casting pieces, a Bosch high frequency straight grinder and an force sensor that closes the feedback loop of the deburring process control.
This paper describes an empirical model of the time-of-flight of a sonar sensor, derived from dat... more This paper describes an empirical model of the time-of-flight of a sonar sensor, derived from data collected with a Polaroid ultrasonic range finder. The goal of this model is to enable the acquisition of the profile of surfaces with a minimum error. These surfaces can present ...
This paper presents complementary sensor fusion techniques for the acquisition of the profile of ... more This paper presents complementary sensor fusion techniques for the acquisition of the profile of surfaces with minimum error using low cost sensors ultrasonic sensors. These surfaces are composed by areas with different depths, corners and specular surfaces. To minimize the constraints of sonar sensors, it was developed dedicated software and hardware, as well as an empirical model was obtained from real data. This model is based in two proposed concepts: Points of Constant Depth (PCD) and Areas of Constant Depth (ACD). Having this sonar model in mind, four sensor fusion techniques are used separately to validate the PCDs and decide the ACDs: average and variance, fuzzy controller and heuristic method based in rules. In this work a PUMA 560 manipulator was equipped with a CCD video camera on the shoulder and four ultrasonic sensors on the wrist, to acquire data to model the geometry of the part's surface, exploiting the mobility of the robot. The CCD camera view defines the working area, while the ultrasonic sensors enable the acquisition of the surface profile. For the acquisition of the profile of surfaces with a minimum error different and complementary sensor fusion techniques are implemented and applied separately, namely the average and variance, kalman filter, fuzzy controller and heuristic method based in rules.
Deformational Plagiocephaly (DP) refers to an asymmetrical distortion of an infant’s skull result... more Deformational Plagiocephaly (DP) refers to an asymmetrical distortion of an infant’s skull resulting from external forces applied over time. The diagnosis of this condition is performed using asymmetry indexes that are estimated from specific anatomical landmarks, whose are manually defined on head models acquired using laser scans. However, this manual identification is susceptible to intra-/inter-observer variability, being also time-consuming. Therefore, automatic strategies for the identification of the landmarks and, consequently, extraction of asymmetry indexes, are claimed. A novel pipeline to automatically identify these landmarks on 3D head models and to estimate the relevant cranial asymmetry indexes is proposed. Thus, a template database is created and then aligned with the unlabelled patient through an iterative closest point (ICP) strategy. Here, an initial rigid alignment followed by an affine one are applied to remove global misalignments between each template and the...
In Computed Tomography (CT), bone segmentation is considered an important step to extract bone pa... more In Computed Tomography (CT), bone segmentation is considered an important step to extract bone parameters, which are frequently useful for computer-aided diagnosis, surgery and treatment of many diseases such as osteoporosis. Consequently, the development of accurate and reliable segmentation techniques is essential, since it often provides a great impact on quantitative image analysis and diagnosis outcome. This chapter presents an automated multistep approach for bone segmentation in volumetric CT datasets. It starts with a three-dimensional (3D) watershed operation on an image gradient magnitude. The outcome of the watershed algorithm is an over-partioning image of many 3D regions that can be merged, yielding a meaningful image partitioning. In order to reduce the number of regions, a merging procedure was performed that merges neighbouring regions presenting a mean intensity distribution difference of ±15%. Finally, once all bones have been distinguished in high contrast, the final 3D bone segmentation was achieved by selecting all regions with bone fragments, using the information retrieved by a threshold mask. The bones contours were accurately defined according to the watershed regions outlines instead of considering the thresholding segmentation result. This new method was tested to segment the rib cage on 185 CT images, acquired at the São João Hospital of Porto (Portugal) and evaluated using the dice similarity coefficient as a statistical validation metric, leading to a coefficient mean score of 0.89. This could represent a step forward towards accurate and automatic quantitative analysis in clinical environments and decreasing time-consumption, user dependence and subjectivity.
ISIE '97 Proceeding of the IEEE International Symposium on Industrial Electronics, 1997
The use of a multi-resolution control model for a robot painting system is reported in this paper... more The use of a multi-resolution control model for a robot painting system is reported in this paper. It gives a flexible and general framework for the control system design which eases software development and integration, as well as experimentation with different sensory behaviours.
1st Portuguese Meeting in Biomedical Engineering, ENBENG 2011, 2011
Abstract Liver cancer is one of the leading causes of death worldwide. Consequently, the developm... more Abstract Liver cancer is one of the leading causes of death worldwide. Consequently, the development of accurate and reliable segmentation techniques is indispensable for tumour volume measurement and staging analysis. An interactive algorithm for liver tumour ...
2016 IEEE International Conference on Serious Games and Applications for Health (SeGAH), 2016
In this manuscript, we propose to adapt the B-Spline Explicit Active Surfaces (BEAS) framework fo... more In this manuscript, we propose to adapt the B-Spline Explicit Active Surfaces (BEAS) framework for semi-automatic kidney segmentation in computed tomography (CT) images. To study the best energy functional for kidney CT extraction, three different localized region-based energies were implemented within the BEAS framework, namely localized Chan-Vese, localized Yezzi, and signed localized Yezzi energies. Moreover, a novel gradient-based regularization term is proposed. The method was applied on 18 kidneys from 9 CT datasets, with different image properties. Several energy combinations were contrasted using surface-based comparison against ground truth meshes, assessing their accuracy and robustness against surface initialization. Overall, the hybrid energy functional combining the localized signed Yezzi energy with gradient-based regularization simultaneously showed the highest accuracy and the lowest sensitivity to the initialization. Volumetric analysis demonstrated the feasibility of the method from a clinical point of view, with similar reproducibility to manual observers.
Introdução ao problema da aquisição do relevo_____________________________ 7.3 Modelo para o sens... more Introdução ao problema da aquisição do relevo_____________________________ 7.3 Modelo para o sensor de ultrassons _______________________________________ 7.3.1 Modelo utilizado____________________________________________________________ 7.4 Determinação das dimensões do objecto ___________________________________ 7.5 Aquisição do relevo da superfície visível ___________________________________ 7.5.1 Fusão/Integração sensorial de dados provenientes de ultrassons _______________________ 7.6 Sumário _____________________________________________________________ 8. Resultados experimentais ______________________________________________124 8.1 Introdução ___________________________________________________________ 8.2 Testes realizados ______________________________________________________ 8.3 Apreciação dos resultados_______________________________________________ 9. Conclusões e sugestões para trabalho futuro _______________________________138 9.1 Conclusões ___________________________________________________________ 9.2 Sugestões para trabalho futuro __________________________________________
Pectus excavatum is the most common congenital deformity of the anterior chest wall, in which an ... more Pectus excavatum is the most common congenital deformity of the anterior chest wall, in which an abnormal formation of the rib cage gives the chest a caved-in or sunken appearance. Today, the surgical correction of this deformity is carried out in children and adults through Nuss technic, which consists in the placement of a prosthetic bar under the sternum and over the ribs. Although this technique has been shown to be safe and reliable, not all patients have achieved adequate cosmetic outcome. This often leads to psychological problems and social stress, before and after the surgical correction. This paper targets this particular problem by presenting a method to predict the patient surgical outcome based on pre-surgical imagiologic information and chest skin dynamic modulation. The proposed approach uses the patient pre-surgical thoracic CT scan and anatomical-surgical references to perform a 3D segmentation of the left ribs, right ribs, sternum and skin. The technique encompasses three steps: a) approximation of the cartilages, between the ribs and the sternum, trough b-spline interpolation; b) a volumetric mass spring model that connects two layers-inner skin layer based on the outer pleura contour and the outer surface skin; and c) displacement of the sternum according to the prosthetic bar position. A dynamic model of the skin around the chest wall region was generated, capable of simulating the effect of the movement of the prosthetic bar along the sternum. The results were compared and validated with patient postsurgical skin surface acquired with Polhemus FastSCAN system.
Pectus excavatum is the most common congenital deformity of the anterior thoracic wall. The surgi... more Pectus excavatum is the most common congenital deformity of the anterior thoracic wall. The surgical correction of such deformity, using Nuss procedure, consists in the placement of a personalized convex prosthesis into sub-sternal position to correct the deformity. The aim of this work is the CT-scan substitution by ultrasound imaging for the pre-operative diagnosis and pre-modeling of the prosthesis, in order to avoid patient radiation exposure. To accomplish this, ultrasound images are acquired along an axial plane, followed by a rigid registration method to obtain the spatial transformation between subsequent images. These images are overlapped to reconstruct an axial plane equivalent to a CT-slice. A phantom was used to conduct preliminary experiments and the achieved results were compared with the corresponding CT-data, showing that the proposed methodology can be capable to create a valid approximation of the anterior thoracic wall, which can be used to model/bend the prosthesis.
Background: Surgical repair of pectus excavatum (PE) has become more popular due to improvements ... more Background: Surgical repair of pectus excavatum (PE) has become more popular due to improvements in the minimally invasive Nuss procedure. The pre-surgical assessment of PE patients requires Computerized Tomography (CT), as the malformation characteristics vary from patient to patient. Objective: This work aims to characterize soft tissue thickness (STT) external to the ribs among PE patients. It also presents a comparative analysis between the anterior chest wall surface before and after surgical correction. Methods: Through surrounding tissue segmentation in CT data, STT values were calculated at different lines along the thoracic wall, with a reference point in the intersection of coronal and median planes. The comparative analysis between the two 3D anterior chest surfaces sets a surgical correction influence area (SCIA) and a volume of interest (VOI) based on image processing algorithms, 3D surface algorithms, and registration methods. Results: There are always variations between left and right side STTs (2.54 ± 2.05 mm and 2.95 ± 2.97 mm for female and male patients, respectively). STTs are dependent on age, sex, and body mass index of each patient. On female patients, breast tissue induces additional errors in bar manual ☆ Funding: This work was supported by "Fundação para a Ciência e a Tecnologia" (FCT), Portugal, through the R&D project referenced PTDC/SAU-BEB/
In the industry of foundry, the deburring of casting pieces is an important stage. Since the piec... more In the industry of foundry, the deburring of casting pieces is an important stage. Since the piece presents edges in the junction zone of the casting moulds, those usually are not desirable and should be eliminated. For solving this problem it was idealized a robotic system capable of deburring casting pieces with minimum human intervention. Consists of an ABB robot, a table of coordinates for fixation and movement of the casting pieces, an artificial vision system for identification and quality control of the casting pieces, a Bosch high frequency straight grinder and an force sensor that closes the feedback loop of the deburring process control.
This paper describes an empirical model of the time-of-flight of a sonar sensor, derived from dat... more This paper describes an empirical model of the time-of-flight of a sonar sensor, derived from data collected with a Polaroid ultrasonic range finder. The goal of this model is to enable the acquisition of the profile of surfaces with a minimum error. These surfaces can present ...
This paper presents complementary sensor fusion techniques for the acquisition of the profile of ... more This paper presents complementary sensor fusion techniques for the acquisition of the profile of surfaces with minimum error using low cost sensors ultrasonic sensors. These surfaces are composed by areas with different depths, corners and specular surfaces. To minimize the constraints of sonar sensors, it was developed dedicated software and hardware, as well as an empirical model was obtained from real data. This model is based in two proposed concepts: Points of Constant Depth (PCD) and Areas of Constant Depth (ACD). Having this sonar model in mind, four sensor fusion techniques are used separately to validate the PCDs and decide the ACDs: average and variance, fuzzy controller and heuristic method based in rules. In this work a PUMA 560 manipulator was equipped with a CCD video camera on the shoulder and four ultrasonic sensors on the wrist, to acquire data to model the geometry of the part's surface, exploiting the mobility of the robot. The CCD camera view defines the working area, while the ultrasonic sensors enable the acquisition of the surface profile. For the acquisition of the profile of surfaces with a minimum error different and complementary sensor fusion techniques are implemented and applied separately, namely the average and variance, kalman filter, fuzzy controller and heuristic method based in rules.
Deformational Plagiocephaly (DP) refers to an asymmetrical distortion of an infant’s skull result... more Deformational Plagiocephaly (DP) refers to an asymmetrical distortion of an infant’s skull resulting from external forces applied over time. The diagnosis of this condition is performed using asymmetry indexes that are estimated from specific anatomical landmarks, whose are manually defined on head models acquired using laser scans. However, this manual identification is susceptible to intra-/inter-observer variability, being also time-consuming. Therefore, automatic strategies for the identification of the landmarks and, consequently, extraction of asymmetry indexes, are claimed. A novel pipeline to automatically identify these landmarks on 3D head models and to estimate the relevant cranial asymmetry indexes is proposed. Thus, a template database is created and then aligned with the unlabelled patient through an iterative closest point (ICP) strategy. Here, an initial rigid alignment followed by an affine one are applied to remove global misalignments between each template and the...
In Computed Tomography (CT), bone segmentation is considered an important step to extract bone pa... more In Computed Tomography (CT), bone segmentation is considered an important step to extract bone parameters, which are frequently useful for computer-aided diagnosis, surgery and treatment of many diseases such as osteoporosis. Consequently, the development of accurate and reliable segmentation techniques is essential, since it often provides a great impact on quantitative image analysis and diagnosis outcome. This chapter presents an automated multistep approach for bone segmentation in volumetric CT datasets. It starts with a three-dimensional (3D) watershed operation on an image gradient magnitude. The outcome of the watershed algorithm is an over-partioning image of many 3D regions that can be merged, yielding a meaningful image partitioning. In order to reduce the number of regions, a merging procedure was performed that merges neighbouring regions presenting a mean intensity distribution difference of ±15%. Finally, once all bones have been distinguished in high contrast, the final 3D bone segmentation was achieved by selecting all regions with bone fragments, using the information retrieved by a threshold mask. The bones contours were accurately defined according to the watershed regions outlines instead of considering the thresholding segmentation result. This new method was tested to segment the rib cage on 185 CT images, acquired at the São João Hospital of Porto (Portugal) and evaluated using the dice similarity coefficient as a statistical validation metric, leading to a coefficient mean score of 0.89. This could represent a step forward towards accurate and automatic quantitative analysis in clinical environments and decreasing time-consumption, user dependence and subjectivity.
ISIE '97 Proceeding of the IEEE International Symposium on Industrial Electronics, 1997
The use of a multi-resolution control model for a robot painting system is reported in this paper... more The use of a multi-resolution control model for a robot painting system is reported in this paper. It gives a flexible and general framework for the control system design which eases software development and integration, as well as experimentation with different sensory behaviours.
1st Portuguese Meeting in Biomedical Engineering, ENBENG 2011, 2011
Abstract Liver cancer is one of the leading causes of death worldwide. Consequently, the developm... more Abstract Liver cancer is one of the leading causes of death worldwide. Consequently, the development of accurate and reliable segmentation techniques is indispensable for tumour volume measurement and staging analysis. An interactive algorithm for liver tumour ...
Uploads
Papers by Jaime Fonseca