Neural Networks for Nodal Staging of Non–Small Cell Lung Cancer with FDG PET and CT: Importance of Combining Uptake Values and Sizes of Nodes and Primary Tumor

Abstract

To evaluate the effect of adding lymph node size to three previously explored artificial neural network (ANN) input parameters (primary tumor maximum standardized uptake value or tumor uptake, tumor size, and nodal uptake at N1, N2, and N3 stations) in the structure of the ANN.The goal was to allow the resulting ANN structure to relate lymph node uptake for size to primary tumor uptake for size in the determination of the status of nodes as human readers do. Materials and Methods:This prospective study was approved by the institutional review board, and informed consent was obtained from all participants. The authors developed a back-propagation ANN with one hidden layer and eight processing units. The data set used to train the network included node and tumor size and uptake from 133 patients with non-small cell lung cancer with surgically proved N status. Statistical analysis was performed with the paired t test. Results:The ANN correctly predicted the N stage in 99.2% of cases, compared with 72.4% for the expert reader (P , .001). In categorization of N0 and N1 versus N2 and N3 disease, the ANN performed with 99.2% accuracy versus 92.2% for the expert reader (P , .001). Conclusion:The ANN is 99.2% accurate in predicting surgical-pathologic nodal status with use of four fluorine 18 fluorodeoxyglucose (FDG) positron emission tomography (PET)/computed tomography (CT)-derived parameters. Malignant and benign inflammatory lymph nodes have overlapping appearances at FDG PET/CT but can be differentiated by ANNs when the crucial input of node size is used.q RSNA, 2013

Vascular endothelial growth factor C complements the ability of positron emission tomography to predict nodal disease in lung cancer

“…Practice guidelines recommend using several radiographic predictors of nodal disease to select patients for invasive staging—including FDG uptake within hilar and/or mediastinal nodes, lymphadenopathy, centrally located tumors, and tumors ≥3 cm. 1,2 Combining these factors with VEGF-C and other reported radiographic predictors of nodal disease—such as histologic information (eg, adenocarcinoma) from a transthoracic or transbronchial biopsy of the primary tumor, the SUV of the primary tumor, and patterns of FDG uptake across nodal stations 29–31 —may result in a highly accurate prediction model. The relative contribution of each predictor remains uncertain and a larger study will need to be performed assess the value of VEGF-C, although our post-hoc analyses suggest that it is a dominant predictor of nodal disease.…”

Прогнозування Гормонально-Метаболічних Порушень У Молодих Жінок Із Надлишковою Масою Тіла Та Ожирінням: Ефективність Застосування Штучних Нейронних Мереж

“…В галузі медичної науки та охорони здоров'я у світі накопичено вже досить багато прикладів ефективного застосування нейронних мереж [31][32][33][34]. Переважна більшість із них належить закордонним дослідникам і стосується можливостей використання ШНС для вирішення діагностичних завдань, у тому числі й у хворих з ендокринною патологією [35].…”

Improving PET Imaging Acquisition and Analysis With Machine Learning: A Narrative Review With Focus on Alzheimer's Disease and Oncology

“…74,75 Kirienko et al developed an algorithm composed of 2 networks, one as the feature “extractor” and another as a “classifier,” and provided evidence that their method could correctly classify patients with lung cancer based on TNM classification (tumor extent, lymph node involvement, and presence of metastases). 72,76 In addition to supervised ML algorithms, unsupervised learning has been applied to textural features. One study examined [ 18 F]FDG textural features that would reflect different histological architectures in patients with different cervical cancer subtypes.…”