With an estimated 160,000 deaths in 2018, lung cancer is the most common cause of cancer death in the United States1. Lung cancer screening using low-dose computed tomography has been shown to reduce mortality by 20–43% and is now included in US screening guidelines1–6. Existing challenges include inter-grader variability and high false-positive and false-negative rates7–10. We propose a deep learning algorithm that uses a patient’s current and prior computed tomography volumes to predict the risk of lung cancer. Our model achieves a state-of-the-art performance (94.4% area under the curve) on 6,716 National Lung Cancer Screening Trial cases, and performs similarly on an independent clinical validation set of 1,139 cases. We conducted two reader studies. When prior computed tomography imaging was not available, our model outperformed all six radiologists with absolute reductions of 11% in false positives and 5% in false negatives. Where prior computed tomography imaging was available, the model performance was on-par with the same radiologists. This creates an opportunity to optimize the screening process via computer assistance and automation. While the vast majority of patients remain unscreened, we show the potential for deep learning models to increase the accuracy, consistency and adoption of lung cancer screening worldwide. A convolutional neural network performs automated prediction of malignancy risk of pulmonary nodules in chest CT scan volumes and improves accuracy of lung cancer screening.

End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography

MultiResUNet : Rethinking the U-Net architecture for multimodal biomedical image segmentation.

Accelerating Magnetic Resonance Imaging (MRI) by taking fewer measurements has the potential to reduce medical costs, minimize stress to patients and make MRI possible in applications where it is currently prohibitively slow or expensive. We introduce the fastMRI dataset, a large-scale collection of both raw MR measurements and clinical MR images, that can be used for training and evaluation of machine-learning approaches to MR image reconstruction. By introducing standardized evaluation criteria and a freely-accessible dataset, our goal is to help the community make rapid advances in the state of the art for MR image reconstruction. We also provide a self-contained introduction to MRI for machine learning researchers with no medical imaging background.

fastMRI: An Open Dataset and Benchmarks for Accelerated MRI.

Automatic diagnosing lung cancer from computed tomography scans involves two steps: detect all suspicious lesions (pulmonary nodules) and evaluate the whole-lung/pulmonary malignancy. Currently, there are many studies about the first step, but few about the second step. Since the existence of nodule does not definitely indicate cancer, and the morphology of nodule has a complicated relationship with cancer, the diagnosis of lung cancer demands careful investigations on every suspicious nodule and integration of information of all nodules. We propose a 3-D deep neural network to solve this problem. The model consists of two modules. The first one is a 3-D region proposal network for nodule detection, which outputs all suspicious nodules for a subject. The second one selects the top five nodules based on the detection confidence, evaluates their cancer probabilities, and combines them with a leaky noisy-OR gate to obtain the probability of lung cancer for the subject. The two modules share the same backbone network, a modified U-net. The overfitting caused by the shortage of the training data is alleviated by training the two modules alternately. The proposed model won the first place in the Data Science Bowl 2017 competition.

Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network

Extracting, harvesting, and building large-scale annotated radiological image datasets is a greatly important yet challenging problem. Meanwhile, vast amounts of clinical annotations have been collected and stored in hospitals’ picture archiving and communication systems (PACS). These types of annotations, also known as bookmarks in PACS, are usually marked by radiologists during their daily workflow to highlight significant image findings that may serve as reference for later studies. We propose to mine and harvest these abundant retrospective medical data to build a large-scale lesion image dataset. Our process is scalable and requires minimum manual annotation effort. We mine bookmarks in our institute to develop DeepLesion, a dataset with 32,735 lesions in 32,120 CT slices from 10,594 studies of 4,427 unique patients. There are a variety of lesion types in this dataset, such as lung nodules, liver tumors, enlarged lymph nodes, and so on. It has the potential to be used in various medical image applications. Using DeepLesion, we train a universal lesion detector that can find all types of lesions with one unified framework. In this challenging task, the proposed lesion detector achieves a sensitivity of 81.1% with five false positives per image.

/pdf/deeplesion-automated-mining-of-large-scale-lesion-299wat6ycw.pdf

DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning

Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge.

Due to the high incidence of the lung cancer all over the world, computer-aided detection (CAD) systems play an important role in screening. Classification in CAD systems have to deal with highly imbalanced datasets composed by actual nodules and non-nodules structures. The application of data balancing techniques helps the training process of the classifiers making the generation of the classification rules more effective. The purpose of this paper is to compare the performance of different data balancing techniques applied to the classification of lung nodules. According to the reviewed literature, this is the first time that different data balancing methods are evaluated on the problem of lung nodule detection using a large data set. A web-based framework was used to evaluate the different methods applied to a classical CAD system (ETROCAD) presented in the LUNA16 Challenge. In the experiments, data balance using SMOTE and SMOTE-TL lead to the best results, with a score of 0.760 and 0.759 respectively, in comparison to 0.748 when not balancing the data. At the time of writing this paper, the SMOTE-based ETROCAD system have the best score among all the classical systems using handcrafted features in LUNA16 web sit.

/pdf/evaluation-of-data-balancing-techniques-application-to-cad-ow0rnxh0m0.pdf

Alexander Sóñora-Mengana

Papers

Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: The LUNA16 challenge.

Evaluation of data balancing techniques. Application to CAD of lung nodules using the LUNA16 framework