João Gustavo Atkinson Amorim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
João Gustavo Atkinson Amorim has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Aldo von Wangenheim
Federal University of Santa Catarina
4 shared publications - André Victória Matias
Department of Informatics and Statistics, Federal University of Santa Catarina, Florianópolis, Brazil
4 shared publications - Luiz Antonio Buschetto Macarini
Automation and Systems Department, Federal University of Santa Catarina, Florianópolis, Brazil
4 shared publications - Adriane Parraga
School of Computer Engineering, State University of Rio Grande do Sul (UERGS), Guaíba, Brazil
2 shared publications Allan Cerentini
Federal University of Santa Catarina, Brazil
2 shared publications- Allan Cerentini
Department of Informatics and Statistics, Federal University of Santa Catarina, Florianópolis, Brazil
2 shared publications
Latest Publications
- Open Access
Comparative analysis of deep learning approaches for AgNOR-stained cytology samples interpretation
Cervical cancer is a public health problem, where the treatment has a better chance of success if detected early. The analysis is a manual process which is subject to a human error, so this paper provides a way to analyze argyrophilic nucleolar organizer regions (AgNOR) stained slide using deep learning approaches. Also, this paper compares models for instance and semantic detection approaches. Our results show that the semantic segmentation using U-Net with ResNet-18 or ResNet-34 as the backbone have similar results, and the best model shows an IoU for nucleus, cluster, and satellites of 0.83, 0.92, and 0.99 respectively. For instance segmentation, the Mask R-CNN using ResNet-50 performs better in the visual inspection and has a 0.61 of the IoU metric. We conclude that the instance segmentation and semantic segmentation models can be used in combination to make a cascade model able to select a nucleus and subsequently segment the nucleus and its respective nucleolar organizer regions (NORs).
Open AccessComparative analysis of deep learning approaches for AgNOR-stained cytology samples interpretation
Cervical cancer is a public health problem, where the treatment has a better chance of success if detected early. The analysis is a manual process which is subject to a human error, so this paper provides a way to analyze argyrophilic nucleolar organizer regions (AgNOR) stained slide using deep learning approaches. Also, this paper compares models for instance and semantic detection approaches. Our results show that the semantic segmentation using U-Net with ResNet-18 or ResNet-34 as the backbone have similar results, and the best model shows an IoU for nucleus, cluster, and satellites of 0.83, 0.92, and 0.99 respectively. For instance segmentation, the Mask R-CNN using ResNet-50 performs better in the visual inspection and has a 0.61 of the IoU metric. We conclude that the instance segmentation and semantic segmentation models can be used in combination to make a cascade model able to select a nucleus and subsequently segment the nucleus and its respective nucleolar organizer regions (NORs).
- 3 July 2022
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 43 (13) , 4758-4773
Biomass estimation of spring wheat with machine learning methods using UAV-based multispectral imaging
Remote biomass estimation can benefit agricultural practices in several ways, especially larger areas since it does not require local measurements. The advances of the last few decades in machine learning techniques have created new possibilities for estimating aboveground biomass. A pipeline was established from image acquisition to modelling shoot biomass of two wheat cultivars used in Southern Brazil (TBIO Toruk and BRS Parrudo). A UAV was used to acquire multispectral images with high spatial resolution to calculate vegetation indices (VIs). These VIs along with machine learning approaches are used to model the measured biomass of crops in different growth phases. To correlate the wheat images with measured shoot dry biomass, the following regression models were investigated: random forest, support vector regression, and artificial neural networks. An experiment was designed and conducted at the Agriculture Experimental Station of the Federal University of Rio Grande do Sul (EEA/UFRGS) to assess wheat growth. Variability in crop growth was created for all test areas by varying nitrogen availability. To determine shoot biomass, plants were sampled at three different crop growth stages: V6 (stage of six fully developed leaves), three nodes, and flowering. Our results indicate the importance of the radiometric calibration used. Also, the features extracted from images, such as the VIs combined with machine learning models can be used in precision agriculture for predicting the spatial variability of shoot biomass. The best model for Brazilian wheat cultivars was an artificial neural network with of 0.90, RMSE of 0.83t/ha, and nRMSE of 8.95%. We also found a strong correlation between ground NDVI with image-based NDVI, with an of 0.84.- 3 July 2022
- Published by Taylor & Francis in International Journal of Remote Sensing
- Vol. 43 (13) , 4758-4773
Biomass estimation of spring wheat with machine learning methods using UAV-based multispectral imaging
Remote biomass estimation can benefit agricultural practices in several ways, especially larger areas since it does not require local measurements. The advances of the last few decades in machine learning techniques have created new possibilities for estimating aboveground biomass. A pipeline was established from image acquisition to modelling shoot biomass of two wheat cultivars used in Southern Brazil (TBIO Toruk and BRS Parrudo). A UAV was used to acquire multispectral images with high spatial resolution to calculate vegetation indices (VIs). These VIs along with machine learning approaches are used to model the measured biomass of crops in different growth phases. To correlate the wheat images with measured shoot dry biomass, the following regression models were investigated: random forest, support vector regression, and artificial neural networks. An experiment was designed and conducted at the Agriculture Experimental Station of the Federal University of Rio Grande do Sul (EEA/UFRGS) to assess wheat growth. Variability in crop growth was created for all test areas by varying nitrogen availability. To determine shoot biomass, plants were sampled at three different crop growth stages: V6 (stage of six fully developed leaves), three nodes, and flowering. Our results indicate the importance of the radiometric calibration used. Also, the features extracted from images, such as the VIs combined with machine learning models can be used in precision agriculture for predicting the spatial variability of shoot biomass. The best model for Brazilian wheat cultivars was an artificial neural network with of 0.90, RMSE of 0.83t/ha, and nRMSE of 8.95%. We also found a strong correlation between ground NDVI with image-based NDVI, with an of 0.84.- 26 March 2022
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
Above-ground Biomass Wheat Estimation: Deep Learning with UAV-based RGB Images
Evaluation of biomass is essential in agriculture to delineate crop management practices, and this is usually done manually, which is time-consuming and destructive. This work proposes an artificial neural network and convolutional neural network to estimate the above-ground biomass (AGB) of wheat using visible spectrum images captured by an unmanned aerial vehicle. The utilized dataset has two Brazilian wheat types, called Parrudo and Toruk. Furthermore, the experimental area has variability in crop growth by varying the amount of nitrogen. To determine AGB, samples of plants were collected at three different crop growth stages, approximately a month apart, making our database spatial and temporal variability. We have shown the feasibility of developing a regression model using RGB images for biomass estimation for two wheat types. The best results for ANN were 489.5, 826.4, and 0.9056 for MAE, RMSE, and , respectively. In CNN, MAE = 699.2, RMSE = 940.5, and = 0.9065. These results show high accuracy in estimation of biomass, and the shows good estimation and generalization capacity. The results demonstrate that our methodology can be used in precision agriculture to predict the spatial and temporal variability of AGB.- 26 March 2022
- Published by Taylor & Francis in Applied Artificial Intelligence
- Vol. 36 (1)
Above-ground Biomass Wheat Estimation: Deep Learning with UAV-based RGB Images
Evaluation of biomass is essential in agriculture to delineate crop management practices, and this is usually done manually, which is time-consuming and destructive. This work proposes an artificial neural network and convolutional neural network to estimate the above-ground biomass (AGB) of wheat using visible spectrum images captured by an unmanned aerial vehicle. The utilized dataset has two Brazilian wheat types, called Parrudo and Toruk. Furthermore, the experimental area has variability in crop growth by varying the amount of nitrogen. To determine AGB, samples of plants were collected at three different crop growth stages, approximately a month apart, making our database spatial and temporal variability. We have shown the feasibility of developing a regression model using RGB images for biomass estimation for two wheat types. The best results for ANN were 489.5, 826.4, and 0.9056 for MAE, RMSE, and , respectively. In CNN, MAE = 699.2, RMSE = 940.5, and = 0.9065. These results show high accuracy in estimation of biomass, and the shows good estimation and generalization capacity. The results demonstrate that our methodology can be used in precision agriculture to predict the spatial and temporal variability of AGB.- Open Access
Comparison of Object Detection Approaches Applied to Field Images of Papanicolaou Stained Cytology Slides
Papanicolaou is an inexpensive and non-invasive method, generally applied to detect cervical cancer, that can also be useful to detect cancer on oral cavities. Although oral cancer is considered a global health issue with 350.000 people diagnosed over a year it can successfully be treated if diagnosed at early stages. The manual process of analyzing cells to detect abnormalities is time-consuming and subject to variations in perceptions from different professionals. To evaluate a possible solution to the automation of this process, in this paper we employ the object detection deep learning approach in the analysis of this type of image using 3 models: RetinaNet, Faster R-CNN, and Mask R-CNN. We trained and tested the models using images from 6 cytology slides (4 cancer cases and 2 healthy samples) and our results show that Mask R-CNN was the best model for localization and classification of nuclei with an IoU of 0.51 and recall of abnormal nuclei of 0.67.
Open AccessComparison of Object Detection Approaches Applied to Field Images of Papanicolaou Stained Cytology Slides
Papanicolaou is an inexpensive and non-invasive method, generally applied to detect cervical cancer, that can also be useful to detect cancer on oral cavities. Although oral cancer is considered a global health issue with 350.000 people diagnosed over a year it can successfully be treated if diagnosed at early stages. The manual process of analyzing cells to detect abnormalities is time-consuming and subject to variations in perceptions from different professionals. To evaluate a possible solution to the automation of this process, in this paper we employ the object detection deep learning approach in the analysis of this type of image using 3 models: RetinaNet, Faster R-CNN, and Mask R-CNN. We trained and tested the models using images from 6 cytology slides (4 cancer cases and 2 healthy samples) and our results show that Mask R-CNN was the best model for localization and classification of nuclei with an IoU of 0.51 and recall of abnormal nuclei of 0.67.
- 1 July 2021
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 91, 101934
What is the state of the art of computer vision-assisted cytology? A Systematic Literature Review
- 1 July 2021
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 91, 101934
What is the state of the art of computer vision-assisted cytology? A Systematic Literature Review
- 21 May 2021
- Published by Springer Nature in SN Computer Science
- Vol. 2 (4) , 1-15
Segmentation, Detection, and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou
- 21 May 2021
- Published by Springer Nature in SN Computer Science
- Vol. 2 (4) , 1-15
Segmentation, Detection, and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 53-58
Segmentation, Detection and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou
Although oral cancer is considered a global health issue with 350.000 people diagnosed over a year it can successfully be treated if diagnosed at early stages. Papanicolaou is an unexpensive and non-invasive method, generally applied to detect cervical cancer, but it can also be useful to detect cancer on oral cavities. The manual process of analyzing cells to detect abnormalities is a time-consuming cell analysis and is subject to variations in perceptions from different professionals. This paper compares models for three different deep learning approaches: segmentation, object detection and image classification. Our results show that the binary object detection with Faster R-CNN is the best approach for nuclei detection and localization (0.76 IoU). Since ResNet 34 had a good performance on abnormal nuclei classification (0.88 accuracy, 0.86 F_1 score) we concluded that these two models can be used in combination to make a localization and classification pipeline. This work reinforces that the automated analysis of oral cytology to make a pipeline for nuclei classification and localization using deep learning can help to minimize the subjectivity of the human analysis and also to detect cancer at early stages.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 53-58
Segmentation, Detection and Classification of Cell Nuclei on Oral Cytology Samples Stained with Papanicolaou
Although oral cancer is considered a global health issue with 350.000 people diagnosed over a year it can successfully be treated if diagnosed at early stages. Papanicolaou is an unexpensive and non-invasive method, generally applied to detect cervical cancer, but it can also be useful to detect cancer on oral cavities. The manual process of analyzing cells to detect abnormalities is a time-consuming cell analysis and is subject to variations in perceptions from different professionals. This paper compares models for three different deep learning approaches: segmentation, object detection and image classification. Our results show that the binary object detection with Faster R-CNN is the best approach for nuclei detection and localization (0.76 IoU). Since ResNet 34 had a good performance on abnormal nuclei classification (0.88 accuracy, 0.86 F_1 score) we concluded that these two models can be used in combination to make a localization and classification pipeline. This work reinforces that the automated analysis of oral cytology to make a pipeline for nuclei classification and localization using deep learning can help to minimize the subjectivity of the human analysis and also to detect cancer at early stages.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 552-557
A Novel Approach on Segmentation of AgNOR-Stained Cytology Images Using Deep Learning
Cervical cancer is the second most common cancer type in women. This is a deadly disease that could benefit from early detection methods. Cytology is a possible, noninvasive, alternative to biopsy for diagnosis of malignant lesions, where information about the cells can be obtained. This process consists of staining the slides being able to visualize the nuclei of the cells and then be properly diagnosed. In this work, silver-stained slides, a method known as Argyrophilic Nucleolar Organizer Regions (AgNOR), is employed. This method shows great potential for the diagnosis of the malignancy of lesions. However, it has not yet been much explored, mainly using computational methods. In this work, we propose the use of Convolutional Neural Networks on silver stained images to measure AgNOR quantitative image information. We will present the entire process, starting from pre-processing, passing through neural network training and results evaluation. The best results we obtained were 0.87 of Mean Intersection Over Union (mIoU) and 0.99 of Dice Similarity Coefficient (DSC) using an U-Net model with a ResNet18 as its backbone. The code and the dataset employed in this work are publicly available.
- 1 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 552-557
A Novel Approach on Segmentation of AgNOR-Stained Cytology Images Using Deep Learning
Cervical cancer is the second most common cancer type in women. This is a deadly disease that could benefit from early detection methods. Cytology is a possible, noninvasive, alternative to biopsy for diagnosis of malignant lesions, where information about the cells can be obtained. This process consists of staining the slides being able to visualize the nuclei of the cells and then be properly diagnosed. In this work, silver-stained slides, a method known as Argyrophilic Nucleolar Organizer Regions (AgNOR), is employed. This method shows great potential for the diagnosis of the malignancy of lesions. However, it has not yet been much explored, mainly using computational methods. In this work, we propose the use of Convolutional Neural Networks on silver stained images to measure AgNOR quantitative image information. We will present the entire process, starting from pre-processing, passing through neural network training and results evaluation. The best results we obtained were 0.87 of Mean Intersection Over Union (mIoU) and 0.99 of Dice Similarity Coefficient (DSC) using an U-Net model with a ResNet18 as its backbone. The code and the dataset employed in this work are publicly available.
- 9 November 2018
- Published by Springer Nature
- p. 388-399
Wheat Plots Segmentation for Experimental Agricultural Field from Visible and Multispectral UAV Imaging
- 9 November 2018
- Published by Springer Nature
- p. 388-399
Wheat Plots Segmentation for Experimental Agricultural Field from Visible and Multispectral UAV Imaging