Automatic lung segmentation in CT images using mask R-CNN for mapping the feature extraction in supervised methods of machine learning using transfer learning

Souza, Luís Fabrício de F.; Holanda, Gabriel B.; Silva, Francisco Hércules dos S.; Alves, Shara S. A.; Filho, Pedro Pedrosa Rebouças

doi:10.3233/his-200287

Cited by 9 publications

(8 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Good pulmonary segmentation can optimize the method used to dispense with auxiliary fine-tuning techniques, for example [35], who used CNN to target lung regions. The same occurred with the study by Souza et al [36], which used the CNN Mask R-CNN network to segment lung images on CTs. The results were excellent with accuracy above 97%, raising the quality level of many studies using deep learning.…”

Section: Introductionmentioning

confidence: 64%

Internet of Medical Things: An Effective and Fully Automatic IoT Approach Using Deep Learning and Fine-Tuning to Lung CT Segmentation

Souza

Silva²,

Marques³

et al. 2020

Sensors

View full text Add to dashboard Cite

Several pathologies have a direct impact on society, causing public health problems. Pulmonary diseases such as Chronic obstructive pulmonary disease (COPD) are already the third leading cause of death in the world, leaving tuberculosis at ninth with 1.7 million deaths and over 10.4 million new occurrences. The detection of lung regions in images is a classic medical challenge. Studies show that computational methods contribute significantly to the medical diagnosis of lung pathologies by Computerized Tomography (CT), as well as through Internet of Things (IoT) methods based in the context on the health of things. The present work proposes a new model based on IoT for classification and segmentation of pulmonary CT images, applying the transfer learning technique in deep learning methods combined with Parzen’s probability density. The proposed model uses an Application Programming Interface (API) based on the Internet of Medical Things to classify lung images. The approach was very effective, with results above 98% accuracy for classification in pulmonary images. Then the model proceeds to the lung segmentation stage using the Mask R-CNN network to create a pulmonary map and use fine-tuning to find the pulmonary borders on the CT image. The experiment was a success, the proposed method performed better than other works in the literature, reaching high segmentation metrics values such as accuracy of 98.34%. Besides reaching 5.43 s in segmentation time and overcoming other transfer learning models, our methodology stands out among the others because it is fully automatic. The proposed approach has simplified the segmentation process using transfer learning. It has introduced a faster and more effective method for better-performing lung segmentation, making our model fully automatic and robust.

show abstract

Section: Introductionmentioning

confidence: 64%

Internet of Medical Things: An Effective and Fully Automatic IoT Approach Using Deep Learning and Fine-Tuning to Lung CT Segmentation

Souza

Silva²,

Marques³

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Each pixel needs to be compared with the surrounding similarity, that is, the detection point (middle point) needs to be compared with the points on the same tower and the adjacent upper and lower layers of the same tower. If the monitoring point is an extreme point, then it is the key point [10]. The contour lines of the surface corresponding to the Gaussian function used in the SIFT algorithm are concentric circles with a normal distribution centered on the key points.…”

Section: Pattern Recognitionmentioning

confidence: 99%

Paper Cuttings Pattern Feature Extraction Based on Machine Vision

Chen,

Wang,

Daud

2024

Advances in Transdisciplinary Engineering

View full text Add to dashboard Cite

According to the characteristics of exaggeration and deformation of paper cuttings patterns, this paper adopts machine vision to classify and recognize paper cuttings patterns and extract features. Based on the analysis of the characteristics acquired above, the nearest neighbor classifier is used for pattern recognition. Then, the normalized invariant moments are used to train the BP neural network, and a new neural network structure is obtained by combining hollow convolution and feature fusion modules to train the model to learn features. During the process of feature extraction, the improved SIFT algorithm is applied to improve the efficiency of the algorithm through dimensionality reduction, achieving the final feature matching. The experimental test uses a large number of paper cuttings pattern examples, and adopt Libsvm to process actual features. The results show that the improved algorithm can effectively remove noise interference in paper cuttings pattern matching, which greatly improves the accuracy, and the time complexity is better than traditional SIFT algorithm.

show abstract

“…However, it should be noted that the methodology was not able to effectively segment certain lung regions, which may be due to generalization of the model. Souza et al [38] used the Mask regions with convolutional neural networks (Mask R-CNN) model in combination with supervised and unsupervised approaches as fine-tuning strategies to segment lung regions on 39 CT images. As a result, the best method showed an accuracy of 95%.…”

Section: Literature Reviewmentioning

confidence: 99%

Deep Learning-Enabled Brain Stroke Classification on Computed Tomography營mages

Tursynova¹,

Omarov²,

Tukenova³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In the field of stroke imaging, deep learning (DL) has enormous untapped potential. When clinically significant symptoms of a cerebral stroke are detected, it is crucial to make an urgent diagnosis using available imaging techniques such as computed tomography (CT) scans. The purpose of this work is to classify brain CT images as normal, surviving ischemia or cerebral hemorrhage based on the convolutional neural network (CNN) model. In this study, we propose a computer-aided diagnostic system (CAD) for categorizing cerebral strokes using computed tomography images. Horizontal flip data magnification techniques were used to obtain more accurate categorization. Image Data Generator to magnify the image in real time and apply any random transformations to each training image. An early stopping method to avoid overtraining. As a result, the proposed methods improved several estimation parameters such as accuracy and recall, compared to other machine learning methods. A python web application was created to demonstrate the results of CNN model classification using cloud development techniques. In our case, the model correctly identified the drawing class as normal with 79% accuracy. Based on the collected results, it was determined that the presented automated diagnostic system could be used to assist medical professionals in detecting and classifying brain strokes.

show abstract

Automatic lung segmentation in CT images using mask R-CNN for mapping the feature extraction in supervised methods of machine learning using transfer learning

Cited by 9 publications

References 68 publications

Internet of Medical Things: An Effective and Fully Automatic IoT Approach Using Deep Learning and Fine-Tuning to Lung CT Segmentation

Internet of Medical Things: An Effective and Fully Automatic IoT Approach Using Deep Learning and Fine-Tuning to Lung CT Segmentation

Paper Cuttings Pattern Feature Extraction Based on Machine Vision

Deep Learning-Enabled Brain Stroke Classification on Computed Tomography營mages

Contact Info

Product

Resources

About