Gonçalo Almeida | Universidade do Porto (original) (raw)
Uploads
Papers by Gonçalo Almeida
Journal of Medical Systems
Medical image segmentation has seen positive developments in recent years but remains challenging... more Medical image segmentation has seen positive developments in recent years but remains challenging with many practical obstacles to overcome. The applications of this task are wide-ranging in many fields of medicine, and used in several imaging modalities which usually require tailored solutions. Deep learning models have gained much attention and have been lately recognized as the most successful for automated segmentation. In this work we show the versatility of this technique by means of a single deep learning architecture capable of successfully performing segmentation on two very different types of imaging: computed tomography and magnetic resonance. The developed model is fully convolutional with an encoder-decoder structure and high-resolution pathways which can process whole three-dimensional volumes at once, and learn directly from the data to find which voxels belong to the regions of interest and localize those against the background. The model was applied to two publicly available datasets achieving equivalent results for both imaging modalities, as well as performing segmentation of different organs in different anatomic regions with comparable success.
Multimedia Tools and Applications
Three-dimensional (3D) image reconstruction is emerging as a leading challenge for 3D media on th... more Three-dimensional (3D) image reconstruction is emerging as a leading challenge for 3D media on the Internet and virtual reality. In this regard, compression performance in 3D technology is one of the most important issues. Various codecs such as HEVC and AV1 have been suggested to improve compression performance in 3D technology. In this study, a hybrid method based on AV1 codec combined with mathematical methods is proposed for improving the quality of this codec. In the proposed method, two AV1 compression
Computers in Biology and Medicine, 2022
Computed Tomography (CT) imaging is used in Radiation Therapy planning, where the treatment is ca... more Computed Tomography (CT) imaging is used in Radiation Therapy planning, where the treatment is carefully tailored to each patient in order to maximize radiation dose to the target while decreasing adverse effects to nearby healthy tissues. A crucial step in this process is manual organ contouring, which if performed automatically could considerably decrease the time to starting treatment and improve outcomes. Computerized segmentation of male pelvic organs has been studied for decades and deep learning models have brought considerable advances to the field, but improvements are still demanded. A two-step framework for automatic segmentation of the prostate, bladder and rectum is presented: a convolutional neural network enhanced with attention gates performs an initial segmentation, followed by a region-based active contour model to fine-tune the segmentations to each patient's specific anatomy. The framework was evaluated on a large collection of planning CTs of patients who had Radiation Therapy for prostate cancer. The Surface Dice Coefficient improved from 79.41 to 81.00% on segmentation of the prostate, 94.03 to 95.36% on the bladder and 82.17 to 83.68% on the rectum, comparing the proposed framework with the baseline convolutional neural network. This study shows that traditional image segmentation algorithms can help improve the immense gains that deep learning models have brought to the medical imaging segmentation field.
Journal of Medical Systems
Acta medica portuguesa, 2016
Experiences of clinical and nonclinical learning environments, as well as assessment and study en... more Experiences of clinical and nonclinical learning environments, as well as assessment and study environments influence student satisfaction with their medical schools. Student-tutor ratios may impact on their perception of clinical learning environments. The aim of this study was to analyze medical students' satisfaction and student-tutor ratios in relation to medical schools' number of admissions. A questionnaire was created, regarding learning, assessment and study environments in eight medical schools. 2037 students participated in this cross-sectional study. Cronbach' alpha (internal consistency) was calculated and principal component analysis was conducted. Pearson correlations and multiple comparisons were analyzed. Assessment environments showed the highest satisfaction scores and clinical learning environments the lowest scores. The national student-tutor ratio in clinical rotations is 7.53; there are significant differences among schools. Institutions with higher...
Acta Médica Portuguesa, 2016
Introduction: Experiences of clinical and nonclinical learning environments, as well as assessmen... more Introduction: Experiences of clinical and nonclinical learning environments, as well as assessment and study environments influence student satisfaction with their medical schools. Student-tutor ratios may impact on their perception of clinical learning environments. The aim of this study was to analyze medical students’ satisfaction and student-tutor ratios in relation to medical schools’ number of admissions. Materials and Methods: A questionnaire was created, regarding learning, assessment and study environments in eight medical schools. 2037 students participated in this cross-sectional study. Cronbach’s alpha (internal consistency) was calculated and principal component analysis was conducted. Pearson correlations and multiple comparisons were analyzed. Results: Assessment environments showed the highest satisfaction scores and clinical learning environments the lowest scores. The national student-tutor ratio in clinical rotations is 7.53; there are significant differences amon...
Journal of Medical Systems
Medical image segmentation has seen positive developments in recent years but remains challenging... more Medical image segmentation has seen positive developments in recent years but remains challenging with many practical obstacles to overcome. The applications of this task are wide-ranging in many fields of medicine, and used in several imaging modalities which usually require tailored solutions. Deep learning models have gained much attention and have been lately recognized as the most successful for automated segmentation. In this work we show the versatility of this technique by means of a single deep learning architecture capable of successfully performing segmentation on two very different types of imaging: computed tomography and magnetic resonance. The developed model is fully convolutional with an encoder-decoder structure and high-resolution pathways which can process whole three-dimensional volumes at once, and learn directly from the data to find which voxels belong to the regions of interest and localize those against the background. The model was applied to two publicly available datasets achieving equivalent results for both imaging modalities, as well as performing segmentation of different organs in different anatomic regions with comparable success.
Multimedia Tools and Applications
Three-dimensional (3D) image reconstruction is emerging as a leading challenge for 3D media on th... more Three-dimensional (3D) image reconstruction is emerging as a leading challenge for 3D media on the Internet and virtual reality. In this regard, compression performance in 3D technology is one of the most important issues. Various codecs such as HEVC and AV1 have been suggested to improve compression performance in 3D technology. In this study, a hybrid method based on AV1 codec combined with mathematical methods is proposed for improving the quality of this codec. In the proposed method, two AV1 compression
Computers in Biology and Medicine, 2022
Computed Tomography (CT) imaging is used in Radiation Therapy planning, where the treatment is ca... more Computed Tomography (CT) imaging is used in Radiation Therapy planning, where the treatment is carefully tailored to each patient in order to maximize radiation dose to the target while decreasing adverse effects to nearby healthy tissues. A crucial step in this process is manual organ contouring, which if performed automatically could considerably decrease the time to starting treatment and improve outcomes. Computerized segmentation of male pelvic organs has been studied for decades and deep learning models have brought considerable advances to the field, but improvements are still demanded. A two-step framework for automatic segmentation of the prostate, bladder and rectum is presented: a convolutional neural network enhanced with attention gates performs an initial segmentation, followed by a region-based active contour model to fine-tune the segmentations to each patient's specific anatomy. The framework was evaluated on a large collection of planning CTs of patients who had Radiation Therapy for prostate cancer. The Surface Dice Coefficient improved from 79.41 to 81.00% on segmentation of the prostate, 94.03 to 95.36% on the bladder and 82.17 to 83.68% on the rectum, comparing the proposed framework with the baseline convolutional neural network. This study shows that traditional image segmentation algorithms can help improve the immense gains that deep learning models have brought to the medical imaging segmentation field.
Journal of Medical Systems
Acta medica portuguesa, 2016
Experiences of clinical and nonclinical learning environments, as well as assessment and study en... more Experiences of clinical and nonclinical learning environments, as well as assessment and study environments influence student satisfaction with their medical schools. Student-tutor ratios may impact on their perception of clinical learning environments. The aim of this study was to analyze medical students' satisfaction and student-tutor ratios in relation to medical schools' number of admissions. A questionnaire was created, regarding learning, assessment and study environments in eight medical schools. 2037 students participated in this cross-sectional study. Cronbach' alpha (internal consistency) was calculated and principal component analysis was conducted. Pearson correlations and multiple comparisons were analyzed. Assessment environments showed the highest satisfaction scores and clinical learning environments the lowest scores. The national student-tutor ratio in clinical rotations is 7.53; there are significant differences among schools. Institutions with higher...
Acta Médica Portuguesa, 2016
Introduction: Experiences of clinical and nonclinical learning environments, as well as assessmen... more Introduction: Experiences of clinical and nonclinical learning environments, as well as assessment and study environments influence student satisfaction with their medical schools. Student-tutor ratios may impact on their perception of clinical learning environments. The aim of this study was to analyze medical students’ satisfaction and student-tutor ratios in relation to medical schools’ number of admissions. Materials and Methods: A questionnaire was created, regarding learning, assessment and study environments in eight medical schools. 2037 students participated in this cross-sectional study. Cronbach’s alpha (internal consistency) was calculated and principal component analysis was conducted. Pearson correlations and multiple comparisons were analyzed. Results: Assessment environments showed the highest satisfaction scores and clinical learning environments the lowest scores. The national student-tutor ratio in clinical rotations is 7.53; there are significant differences amon...