The Effects of Perinodular Features on Solid Lung Nodule Classification

Calheiros, José Lucas Leite; Amorim, Lucas; Lima, Lucas; Filho, Ailton Felix de Lima; Júnior, José Raniery Ferreira; Oliveira, Marcelo Costa

doi:10.1007/s10278-021-00453-2

Cited by 26 publications

(15 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A nodule ROI always includes the intranodule region (inside nodule region), but depending on the nodule shape, the perinodular region (around nodule region) is included in greater or lesser extent. Since, in [22,23], it is reported that the importance of using perinodular region in the classification of benign and malignant nodules, the size of ROIs was enlarged 15% of its original size. The volume ROI extracted using the coordinates of the annotated bounding box is the input to the whole workflow.…”

Section: Nodule Extractionmentioning

confidence: 99%

An Intelligent Radiomic Approach for Lung Cancer Screening

et al. 2022

View full text Add to dashboard Cite

The efficiency of lung cancer screening for reducing mortality is hindered by the high rate of false positives. Artificial intelligence applied to radiomics could help to early discard benign cases from the analysis of CT scans. The available amount of data and the fact that benign cases are a minority, constitutes a main challenge for the successful use of state of the art methods (like deep learning), which can be biased, over-fitted and lack of clinical reproducibility. We present an hybrid approach combining the potential of radiomic features to characterize nodules in CT scans and the generalization of the feed forward networks. In order to obtain maximal reproducibility with minimal training data, we propose an embedding of nodules based on the statistical significance of radiomic features for malignancy detection. This representation space of lesions is the input to a feed forward network, which architecture and hyperparameters are optimized using own-defined metrics of the diagnostic power of the whole system. Results of the best model on an independent set of patients achieve 100% of sensitivity and 83% of specificity (AUC = 0.94) for malignancy detection.

show abstract

Section: Nodule Extractionmentioning

confidence: 99%

An Intelligent Radiomic Approach for Lung Cancer Screening

et al. 2022

View full text Add to dashboard Cite

show abstract

“…To do that, the authors used a standard decision tree to perform the multivariate classification [Ferreira Junior et al 2018]. Calheiros et al investigated further margin sharpness features by including perinodular zone characterization [Calheiros et al 2021]. The developed method increased the performance when integrating parenchyma-originated features of the histogram skewness (Equation 1.10), and the GLCM prominence, shade, correlation, energy, and entropy (Equations 1.13, 1.14, 1.16, 1.20, and 1.29, respectively).…”

Section: Lung Neoplasms In Computed Tomographymentioning

confidence: 99%

Biomarcadores Radiômicos de Precisão: uma breve introdução, alguns desenvolvimentos técnicos e várias aplicações clínicas

Ferreira¹

2021

Minicursos Do SBCAS 2021

View full text Add to dashboard Cite

Computer tools have been part of the clinical routine on a daily basis for radiological image interpretation. However, they are limited to quantifying basic information about the lesions that a medical examination may present, like a nodule size or mass volume.Radiomic biomarkers emerged in this context to address this problem by quantifying the images massively and characterizing them comprehensively to allow the precision phenotyping needed in the current personalized medicine era. Thus, this book chapter introduces some robust radiomic biomarkers identified in the past few years for different pathological imaging patterns of diseases from two critical human systems, i.e., respiratory and musculoskeletal. The text initiates with the primary motivation for radiomic biomarker development, discovery, and validation. The following sections present a quick background with the basic theory for the remainder of the manuscript. Finally, the chapter approaches the state-of-the-art radiomic precision biomarkers for three different diseases and modalities of medical images: covid-19 in chest radiography, lung neoplasms in computed tomography, and spondyloarthritis in magnetic resonance imaging.

show abstract

“…Al-Shabi et al [ 31 ] established deep local global networks to classify lung nodules. Lei et al [ 32 ] focused on the boundary of lung nodules to realize the classification of lung nodules under the condition of low-dose CT. Calheiros et al [ 33 ] classified the signs of lung nodules from the surrounding conditions of lung nodules. Halder et al [ 34 ] constructed an adaptive morphology-aided 2-path progressive neural network to segment lung nodules.…”

Section: Introductionmentioning

confidence: 99%

Lung Nodule Segmentation and Recognition Algorithm Based on Multiposition U-Net

Zhang¹,

Lin²,

Hui³

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Lung nodules are the main lesions of the lung, and conditions of the lung can be directly displayed through CT images. Due to the limited pixel number of lung nodules in the lung, doctors have the risk of missed detection and false detection in the detection process. In order to reduce doctors’ work intensity and assist doctors to make accurate diagnosis, a lung nodule segmentation and recognition algorithm is proposed by simulating doctors’ diagnosis process with computer intelligent methods. Firstly, the attention mechanism model is established to focus on the region of lung parenchyma. Then, a pyramid network of bidirectional enhancement features is established from multiple body positions to extract lung nodules. Finally, the morphological and imaging features of lung nodules are calculated, and then, the signs of lung nodules can be identified. The experiments show that the algorithm conforms to the doctor’s diagnosis process, focuses the region of interest step by step, and achieves good results in lung nodule segmentation and recognition.

show abstract

The Effects of Perinodular Features on Solid Lung Nodule Classification

Cited by 26 publications

References 41 publications

An Intelligent Radiomic Approach for Lung Cancer Screening

An Intelligent Radiomic Approach for Lung Cancer Screening

Biomarcadores Radiômicos de Precisão: uma breve introdução, alguns desenvolvimentos técnicos e várias aplicações clínicas

Lung Nodule Segmentation and Recognition Algorithm Based on Multiposition U-Net

Contact Info

Product

Resources

About