Application of Deep Learning to Combine Clinical and Imaging Data to Localize, Characterize, and Prognosticate Lung Cancer Patients
Traditional methods of lung cancer diagnosis and prognosis research often relied on manual feature engineering to extract what the investigator thought were important imaging features to predict patient outcome. These were manually annotated and combined with categorial variables from clinical data to create a prediction model, often with a variation of generalized linear models or Cox proportional hazards models. Unfortunately, image analysis portion was inevitably limited by the subjectivity of data annotator and manual feature engineering task which always resulted in information loss.
Recent advancements in machine learning with artificial neural network, also known as deep learning, has brought about exciting improvement in computer vision. Starting in 2016, computer vision has consistently surpassing human experts in classifying objects on the ImageNet large scale visual recognition challenge (ILSVRC). Numerous cross-pollination projects between machine learning and radiology have begun, with the goal of improving radiologists' diagnostic accuracy and improve workflow efficiency. Unfortunately, a majority of these interdisciplinary projects remain in immature or experimental stage at this point, in part due to paucity of large-scale available medical data such as the NSLT data.
With this project, we plan to fully utilize the NLST data to create a convolutional neural network to automatically extract relevant features from imaging data and then combine this with a separate regression network that brings together clinical data. This will be followed by a top layer that accounts for all of these features to predict useful information for the patient, including characterization of lung nodule and prognostication for the patient. In the process, we also plan to optimize and utilize a previously developed lung nodule localizer. Ultimately, our algorithm will bring a fresh perspective and improvement to existing diagnosis and staging systems for lung cancer.
1. Develop artificial neural network models to combine high-dimensional imaging features from chest CT and relevant clinical variables to predict prognostic outcomes and other secondary outcomes of lung cancer
2. Develop combined and individual algorithms for localizing pulmonary nodules, characterizing a given nodule, and/or prognosticating patient outcome
3. Search for optimal hyper-parameters for 3D convolutional neural network architecture on chest CT studies
4. Search for optimal hyper-parameters for long short-term memory network on chest CT studies
5. Optimize a previously developed lung nodule localizer network.
N/A
-
High precision localization of pulmonary nodules on chest CT utilizing axial slice number labels.
Chillakuru YR, Kranen K, Doppalapudi V, Xiong Z, Fu L, Heydari A, Sheth A, Seo Y, Vu T, Sohn JH
BMC Med Imaging. 2021 Apr 9; Volume 21 (Issue 1): Pages 66 PUBMED