Characterization of Lung Nodule Malignancy Using Hybrid Shape and Appearance Features

Abstract

Abstract. Computed tomography imaging is a standard modality for detecting and assessing lung cancer. In order to evaluate the malignancy of lung nodules, clinical practice often involves expert qualitative ratings on several criteria describing a nodule's appearance and shape. Translating these features for computer-aided diagnostics is challenging due to their subjective nature and the difficulties in gaining a complete description. In this paper, we propose a computerized approach to quantitatively evaluate both appearance distinctions and 3D surface variations. Nodule shape was modeled and parameterized using spherical harmonics, and appearance features were extracted using deep convolutional neural networks. Both sets of features were combined to estimate the nodule malignancy using a random forest classifier. The proposed algorithm was tested on the publicly available Lung Image Database Consortium dataset, achieving high accuracy. By providing lung nodule characterization, this method can provide a robust alternative reference opinion for lung cancer diagnosis.

Radiomics analysis of pulmonary nodules in low‐dose CT for early detection of lung cancer

“…Both Buty et al and Kumar et al applied deep learning techniques to predict malignancy of PNs. 32,33 Buty et al extracted 4096 appearance features using the pretrained deep neural network (AlexNet 48 ) and 400 shape features from spherical harmonics. They fed these features into a random forest classifier, which achieved an accuracy of 82.4%.…”

“…31 Buty et al developed a random forest classifier using 4096 appearance features extracted with a pretrained deep neural network and 400 shape features extracted with spherical harmonics. 32 Kumar et al developed a deep neural network model using 5000 features. 33 Liu et al proposed a linear classifier based on 24 image traits visually scored by physicians.…”

TumorNet: Lung nodule characterization using multi-view Convolutional Neural Network with Gaussian Process

“…In contrast to the previous studies that used pre-trained network [8,9], in this work, we proposed an end-to-end training of deep multi-view Convolutional Neural Network for nodule malignancy determination termed TumorNet. In order to cater to the need to have a large amount of labeled data for CNN, we performed data augmentation using scale, rotation and different categories of noise.…”

“…This has also attracted the attention of researchers working in lung nodule detection and classification with limited success since the feature learning and classification were considered as separate modules. In those frameworks a pre-trained CNN was only used for feature extraction whereas classification was based on an off-the-shelf classifier such as RF [8,9]. In sharp contrast to these methods, we perform an end-to-end training of CNN for nodule characterization while combining multi-view features to obtain improved characterization performance.…”

Quantitative imaging of cancer in the postgenomic era: Radio(geno)mics, deep learning, and habitats

“…Indeed, although only recently applied in radiomics, DL has proven valuable in both differential diagnosis [89][90][91][92][93][94][95][96][97][98][99][100][101][102][103] and prognosis prediction. 116 If enough computational power and training cases are available, full 3D CNNs can be used to provide better results. Although the solution to computing power is simply time and/or money, the solution to the limited availability of well-annotated training data sets is not so simple.…”