Lung cancer has a high incidence and mortality rate. The five-year relative survival rate for all lung cancers is 18%. Due to the high mortality and incidence rate of lung cancer worldwide, early detection is essential. Low dose Computed Tomography (CT) is a commonly used technique for screening, diagnosis, and prognosis of non-small cell lung cancer (NSCLC). The National Lung Screening Trial (NLST) compared low-dose helical computed tomography (LDCT) and standard chest radiography (CXR) for three annual screens and reported a 20% relative reduction in lung cancer mortality for LDCT compared to CXR. As such, LDCT screening for lung cancer is an effective way of mitigating lung cancer mortality and is the only imaging option for those at high risk. Lung cancer screening for high-risk patients often detects a large number of indeterminate pulmonary nodules, of which only a subset will be identified as cancer. As such, reliable and reproducible biomarkers determining which indeterminate pulmonary nodules will be identified as cancer would have significant translational implications as a therapeutic method to enhance lung cancer screening for nodule detection. Radiomics is an approach to extract high-dimensional quantitative features from medical images, which can be used individually or merged with clinical data for predictive and diagnostic analysis. Quantitative radiomics features (size, shape, and texture) extracted from lung CT scans have been shown to predict cancer incidence and prognosis. Deep learning is an emerging machine learning approach, which has been applied to the classification and analysis of various cancers and tumors. To generate generic features (blobs, edges, etc.) from an image, different convolutional kernels are applied over the input image, and then those generic feature-based images are passed through some fully connected neural layers. This category of the neural network is called a convolutional neural network (CNN), which has achieved high accuracy on image data. With the advancement of deep learning and convolutional neural networks (CNNs), deep features can be utilized to analyze lung CTs for prognosis prediction and diagnosis. In this dissertation, deep learning-based approaches were presented for lung nodule malignancy prediction. A subset of cases from the NLST was chosen as a dataset in our study. We experimented with three different pre-trained CNNs for extracting deep features and used five different classifiers. Experiments were also conducted with deep features from different color channels of a pre-trained CNN. Selected deep features were combined with radiomics features. Three CNNs were designed and trained. Combinations of features from pre-trained, CNNs trained on NLST data, and classical radiomics were used to build classifiers. The best accuracy (76.79%) was obtained using feature combinations. An area under the receiver operating characteristic curve of 0.87 was obtained using a CNN trained on an augmented NLST data cohort. After that, each of the three CNNs was trained using seven different seeds to create the initial weights. These enabled variability in the CNN models, which were combined to generate a robust, more accurate ensemble model. Augmenting images using only rotation and flipping and training with images from T0 yielded the best accuracy to predict lung cancer incidence at T2 from a separate test cohort (Accuracy = 90.29%; AUC = 0.96) based on an ensemble 21 models. From this research, five conclusions were obtained, which will be utilized in future research. First, we proposed a simple and effective CNN architecture with a small number of parameters useful for smaller (medical) datasets. Second, we showed features obtained using transfer learning with all the channels of a pre-trained CNN performed better than features extracted using any single channel and we also constructed a new feature set by fusing quantitative features with deep features, which in turn enhanced classification performance. Third, ensemble learning with deep neural networks was a compelling approach that accurately predicted lung cancer incidence at the second screening after the baseline screen, mostly two years later. Fourth, we proposed a method for deep features to have a recognizable definition via semantic or quantitative features. Fifth, deep features were dependent on the scanner parameters, and the dependency was removed using pixel size based normalization.

Low-dose computed tomography (CT) screening has been widely used to detect and diagnose early stage lung cancer. Clinical trials have shown that low-dose CT reduced lung cancer mortality by 20% relative to plain chest radiography; however, challenges exist in current low-dose CT screening programs including high over-diagnosis rates, high cost and increased radiation exposure. This dissertation attempts to overcome these challenges by developing machine and deep learning models for automated lung cancer diagnosis and disease progression estimation. A novel lung segmentation approach was first developed using a bidirectional chain code method and machine learning framework. This method is designed to include the lung nodules attached to lung wall while minimizing over-segmentation error. Second, a hybrid ensemble convolutional neural network has been developed to classify lung nodule vs. non-nodule objects. The ensemble model combines the VGG, residual and densely connected module designs to improve the model classification robustness for external datasets collected with different acquisition parameters. Third, a hierarchical semantic convolutional neural network (HSCNN) has been described to classify lung nodule malignancy. Semantic characteristic features, predicted in parallel with the malignancy for each nodule, enable the interpretation of the model and improvement of malignancy prediction. Finally, a Bayesian framework combined with a continuous-time Markov model was developed to estimate the multi-state disease progression of lung cancer. The resulting model estimates individual lung cancer state transition information, providing the basis for personalized screening recommendations. Extensive experiments and results have proved the effectiveness of these methods paving the way to optimize and improve the effectiveness of existing low-dose CT screening programs.

Application of Artificial Intelligence in Early Detection of Lung Cancer presents the most up-to-date computer-aided diagnosis techniques used to effectively predict and diagnose lung cancer. The presence of pulmonary nodules on lung parenchyma is often considered an early sign of lung cancer, thus using machine and deep learning technologies to identify them is key to improve patients’ outcome and decrease the lethal rate of such disease. The book discusses topics such as basics of lung cancer imaging, pattern recognition techniques, deep learning, and nodule detection and localization. In addition, the book discusses risk prediction based on radiological analysis and 3D modeling. This is a valuable resource for cancer researchers, oncologists, graduate students, radiologists, and members of biomedical field who are interested in the potential of AI technologies in the diagnosis of lung cancer. Provides an overview of the latest developments of artificial intelligence technologies applied to the detection of pulmonary nodules Discusses the different technologies available and guides readers step-by-step to the most applicable one for the specific lung cancer type Describes the entire study design on prediction of lung cancer to help readers apply it to their research successfully

The adoption of Deep neural networks for lung cancer screening has been shown to improve detection of malignant nodules in sequential scans and to reduce the screening time1,2. However, DNNs fail to properly classify images when applied only to single low-dose computed tomography scans on indeterminate pulmonary nodules (4mm - 20mm in diameter). In addition, the limited size of most medical data sets utilized for deep learning leads to network overfitting and poor performance, making it difficult to translate to clinical settings3,4. The limited size of most medical dataset means that DNNs have difficulty identifying and evaluating features of interest and fail to generalize to novel data. However, guiding a neural network toward biological features that are known to be pathophysiologically relevant may improve both classification accuracy and generalizability5,6. For example, idiopathic pulmonary fibrosis and emphysema are both associated with increased lung inflammation and are considered pre-malignant conditions7-9. The aim of this work is to determine the contribution of biologically relevant features associated with increased risk of malignancy and embed them into deep learning methodologies to evaluate their contributions toward classification and model generalizability. Relevant biological features are identified through three methodologies: least absolute shrinkage and selection operator (LASSO), support vector machine (SVM), and random forest (RF). Using these quantitative features as the basis for classification, we increase the emphasis of specific tumor features through kernel manipulations using discrete wavelet decomposition and evaluate whether DNNs place emphasis on these select features for nodule classification. Results suggest that quantitative parenchymal features carry significant classification information across all machine learning methodologies applied. Using a combination of parenchymal features together with tumor specific features significantly improves classification performance of these methodologies compared to using only tumor specific features. Furthermore, DNNs extract abstract features that resemble these biological features when evaluating attention maps of the network. Features capturing nodule maximal diameter alongside textural and morphological features appear to drive nodule classification. The use of discrete wavelet decomposition to embed simplified features into CNNs improves classification accuracy of the model and reduces training time. This demonstrates that guiding a DNN toward select features can improve its performance while minimizing overfitting. The findings suggest that known pathophysiologically relevant features can be encoded into DNNs to improve network classification and generalizability to novel data. Furthermore, evaluating models based on misclassified nodules provides avenues to identify over-emphasized features in the network and correct them through image preprocessing. Overall, this body of work addresses several challenges present in the application of DNNs for early nodule detection. The performance of the generated models for single-shot classification of indeterminate pulmonary nodules shows promise for deployment as clinician co-pilots. Further studies on risk-benefits of these models in clinical settings are necessary to ensure proper performance prior to translation.

The seven-volume set LNCS 12261, 12262, 12263, 12264, 12265, 12266, and 12267 constitutes the refereed proceedings of the 23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020, held in Lima, Peru, in October 2020. The conference was held virtually due to the COVID-19 pandemic. The 542 revised full papers presented were carefully reviewed and selected from 1809 submissions in a double-blind review process. The papers are organized in the following topical sections: Part I: machine learning methodologies Part II: image reconstruction; prediction and diagnosis; cross-domain methods and reconstruction; domain adaptation; machine learning applications; generative adversarial networks Part III: CAI applications; image registration; instrumentation and surgical phase detection; navigation and visualization; ultrasound imaging; video image analysis Part IV: segmentation; shape models and landmark detection Part V: biological, optical, microscopic imaging; cell segmentation and stain normalization; histopathology image analysis; opthalmology Part VI: angiography and vessel analysis; breast imaging; colonoscopy; dermatology; fetal imaging; heart and lung imaging; musculoskeletal imaging Part VI: brain development and atlases; DWI and tractography; functional brain networks; neuroimaging; positron emission tomography

This book, now in an extensively revised and updated second edition, provides a comprehensive overview of both machine learning and deep learning and their role in oncology, medical physics, and radiology. Readers will find thorough coverage of basic theory, methods, and demonstrative applications in these fields. An introductory section explains machine and deep learning, reviews learning methods, discusses performance evaluation, and examines software tools and data protection. Detailed individual sections are then devoted to the use of machine and deep learning for medical image analysis, treatment planning and delivery, and outcomes modeling and decision support. Resources for varying applications are provided in each chapter, and software code is embedded as appropriate for illustrative purposes. The book will be invaluable for students and residents in medical physics, radiology, and oncology and will also appeal to more experienced practitioners and researchers and members of applied machine learning communities.

This book examines deep learning-based approaches in the field of cancer diagnostics, as well as pre-processing techniques, which are essential to cancer diagnostics. Topics include introduction to current applications of deep learning in cancer diagnostics, pre-processing of cancer data using deep learning, review of deep learning techniques in oncology, overview of advanced deep learning techniques in cancer diagnostics, prediction of cancer susceptibility using deep learning techniques, prediction of cancer reoccurrence using deep learning techniques, deep learning techniques to predict the grading of human cancer, different human cancer detection using deep learning techniques, prediction of cancer survival using deep learning techniques, complexity in the use of deep learning in cancer diagnostics, and challenges and future scopes of deep learning techniques in oncology.