Application of deep learning (3-dimensional convolutional neural network) for the prediction of pathological invasiveness in lung adenocarcinoma

Abstract

To compare results for radiological prediction of pathological invasiveness in lung adenocarcinoma between radiologists and a deep learning (DL) system. Ninety patients (50 men, 40 women; mean age, 66 years; range, 40–88 years) who underwent pre-operative chest computed tomography (CT) with 0.625-mm slice thickness were included in this retrospective study. Twenty-four cases of adenocarcinoma in situ (AIS), 20 cases of minimally invasive adenocarcinoma (MIA), and 46 cases of invasive adenocarcinoma (IVA) were pathologically diagnosed. Three radiologists of different levels of experience diagnosed each nodule by using previously documented CT findings to predict pathological invasiveness. DL was structured using a 3-dimensional (3D) convolutional neural network (3D-CNN) constructed with 2 successive pairs of convolution and max-pooling layers, and 2 fully connected layers. The output layer comprises 3 nodes to recognize the 3 conditions of adenocarcinoma (AIS, MIA, and IVA) or 2 nodes for 2 conditions (AIS and MIA/IVA). Results from DL and the 3 radiologists were statistically compared. No significant differences in pathological diagnostic accuracy rates were seen between DL and the 3 radiologists ( P >.11). Receiver operating characteristic analysis demonstrated that area under the curve for DL (0.712) was almost the same as that for the radiologist with extensive experience (0.714; P = .98). Compared with the consensus results from radiologists, DL offered significantly inferior sensitivity ( P = .0005), but significantly superior specificity ( P = .02). Despite the small training data set, diagnostic performance of DL was almost the same as the radiologist with extensive experience. In particular, DL provided higher specificity than radiologists.

Artificial Intelligence in Medical Imaging of the Breast

“…The output is then passed into the fully connected layer to classify the overall outcome, and the output layer directly outputs data analysis results. A multilayer perceptron is constructed by making and arranging layers with perceptrons in which all nodes in the model are fully connected together, thus solving more complex problems (19). The learning paradigm of CNNs also involves supervised learning and unsupervised learning; supervised learning refers to the training procedure in which the observed training data and the associated ground truth labels for that data (or sometimes referred to as "targets") are both required for training the model.…”

Deep Learning for the Preoperative Diagnosis of Metastatic Cervical Lymph Nodes on Contrast-Enhanced Computed ToMography in Patients with Oral Squamous Cell Carcinoma

“…With the continued development of artificial intelligence, deep learning (DL) has been applied to medical imaging for tissue characterization, outcome prediction, and automated detection [ 11 , 12 , 13 , 14 , 15 ]. DL enables the parameters to increase and handle complex tasks by increasing the layers of the neural networks that imitate models of brain structures connecting a large number of neurons.…”

A deep learning system that generates quantitative CT reports for diagnosing pulmonary Tuberculosis

“…Relevant studies have been conducted on the diagnosis of pulmonary nodules, the classification of benign and malignant tumors worldwide. [6][7][8][9][10][11][12]. This approach has been used to improve the diagnosis of pulmonary nodules and lung cancer worldwide [13][14][15][16].…”