A comparison of the fusion model of deep learning neural networks with human observation for lung nodule detection and classification

Abstract

Objectives: To compare the diagnostic performance of a newly developed artificial intelligence (AI) algorithm derived from the fusion of convolution neural networks (CNN) versus human observers in the estimation of malignancy risk in pulmonary nodules. Methods: The study population consists of 158 nodules from 158 patients. All nodules (81 benign and 77 malignant) were determined to be malignant or benign by a radiologist based on pathologic assessment and/or follow-up imaging. Two radiologists and an AI platform analyzed the nodules based on the Lung-RADS classification. The two observers also noted the size, location, and morphologic features of the nodules. An intraclass correlation coefficient was calculated for both observers and the AI; ROC curve analysis was performed to determine diagnostic performances. Results: Nodule size, presence of spiculation, and presence of fat were significantly different between the malignant and benign nodules (p < 0.001, for all three). Eighteen (11.3%) nodules were not detected and analyzed by the AI. Observer 1, observer 2, and the AI had an AUC of 0.917 ± 0.023, 0.870 ± 0.033, and 0.790 ± 0.037 in the ROC analysis of malignity probability, respectively. The observers were in almost perfect agreement for localization, nodule size, and lung-RADS classification [κ (95% CI)=0.984 (0.961–1.000), 0.978 (0.970–0.984), and 0.924 (0.878–0.970), respectively]. Conclusion: The performance of the fusion AI algorithm in estimating the risk of malignancy was slightly lower than the performance of the observers. Fusion AI algorithms might be applied in an assisting role, especially for inexperienced radiologists. Advances in knowledge: In this study we proposed a fusion model using four state-of-art object detectors for lung nodule detection and discrimination. The use of fusion of deep learning neural networks might be used in a supportive role for radiologists when interpreting lung nodule discrimination

A CT-Based Radiomic Signature for the Differentiation of Pulmonary Hamartomas from Carcinoid Tumors

“…There has been a recent increase in the volume of research on the applications of thoracic tumors. [ 14 ]. It is possible to extract multiple quantitative features from medical images, including CT and MRI, through the application of high-throughput computing [ 15 ].…”

“…It is possible to extract multiple quantitative features from medical images, including CT and MRI, through the application of high-throughput computing [ 15 ]. These features include the use of intensity, shape, texture, wavelet, and LOG features to build predictive or prognostic non-invasive biomarkers for imaging modalities [ 8 , 9 , 10 , 11 , 12 , 13 , 14 , 15 , 16 ].…”

“…Radiomics can quantify the high-dimensional mineable features and identify underlying differences, offering a virtually unbounded stock of imaging biomarkers that have the potential to enhance diagnostic performance [ 21 , 22 , 23 , 24 ]. In particular, there has been a widespread application of tissue-based features in the differential diagnosis of SPN [ 8 , 14 , 23 , 24 ].…”

Development and Validation of a Deep Learning Model for Histopathological Slide Analysis in Lung Cancer Diagnosis

“…Many successful models were created to distinguish between healthy and tumor lung cells using the CNN approach; for instance, Gürsoy et al [11] developed an AI-based model employing a CNN for comparative diagnostic evaluation against human pathologists. The dataset comprised 158 nodules extracted from lung cancer patients, with a distribution of 77 malignant and 81 benign cases, assessed independently by two radiologists and pathologists.…”

The Convergence of Radiology and Genomics: Advancing Breast Cancer Diagnosis with Radiogenomics

“…Medical imaging analysis is now being developed using Artificial Intelligence (AI) and initial results are promising. In terms of cancer diagnosis and prognosis, it is thought that AI can possibly match or even enhance work conducted by skilled pathologists [ 68 ]. AI-powered radiogenomics will be able to identify patterns in an image and associate those traits with particular phenotypes [ 69 ].…”