Deep Multi-task Prediction of Lung Cancer and Cancer-free Progression from Censored Heterogenous Clinical Imaging

@article{Gao2020DeepMP,
  title={Deep Multi-task Prediction of Lung Cancer and Cancer-free Progression from Censored Heterogenous Clinical Imaging},
  author={Riqiang Gao and Ling-feng Li and Yucheng Tang and Sanja L. Antic and Alexis B. Paulson and Yuankai Huo and Kim L. Sandler and Pierre P. Massion and Bennett A. Landman},
  journal={Proceedings of SPIE--the International Society for Optical Engineering},
  year={2020},
  volume={11313}
}
  • Riqiang Gao, L. Li, +6 authors B. Landman
  • Published 2020
  • Medicine, Computer Science
  • Proceedings of SPIE--the International Society for Optical Engineering
Annual low dose computed tomography (CT) lung screening is currently advised for individuals at high risk of lung cancer (e.g., heavy smokers between 55 and 80 years old). The recommended screening practice significantly reduces all-cause mortality, but the vast majority of screening results are negative for cancer. If patients at very low risk could be identified based on individualized, image-based biomarkers, the health care resources could be more efficiently allocated to higher risk… Expand
Development and Characterization of a Chest CT Atlas
TLDR
A thoracic atlas built upon a large low dose CT (LDCT) database of lung cancer screening program is proposed and a significant improvement in terms of registration success rate based on manual QA is achieved. Expand
Technical Report: Quality Assessment Tool for Machine Learning with Clinical CT
  • Riqiang Gao, Mirza S. Khan, +6 authors B. Landman
  • Computer Science
  • ArXiv
  • 2021
TLDR
A pipeline specifically designed to identify and resolve issues encountered with large-scale data mining of clinically acquired CT data is created and illustrated and found to be useful and time-saving for research study of clinical data. Expand
Time-distanced gates in long short-term memory networks
TLDR
The DLSTM approach is shown to be compatible with families of linear, quadratic, exponential, and log-exponential temporal models, and can be readily extended with other temporal dependence interactions while hardly increasing overall model complexity. Expand
Deep multi-path network integrating incomplete biomarker and chest CT data for evaluating lung cancer risk
TLDR
The proposed M3Net framework provides an effective way to integrate image and non-image data in the context of missing information and suggests that integrating subjects with missing either CDEs/biomarker or CT imaging features can contribute to the discriminatory power of the model. Expand

References

SHOWING 1-10 OF 14 REFERENCES
Lung Cancer Detection using Co-learning from Chest CT Images and Clinical Demographics
TLDR
A 3D attention-based deep convolutional neural net (DCNN) is proposed to identify lung cancer from the chest CT scan without prior anatomical location of the suspicious nodule, and to improve upon the non-invasive discrimination between benign and malignant. Expand
MTMR-Net: Multi-task Deep Learning with Margin Ranking Loss for Lung Nodule Analysis
TLDR
A Multi-Task deep learning framework with a novel Margin Ranking loss (referred as MTMR-Net) for automated lung nodule analysis achieved competitive classification performance and more accurate attribute scoring over the state-of-the-arts. Expand
Pan-Renal Cell Carcinoma classification and survival prediction from histopathology images using deep learning
TLDR
This study demonstrates how deep learning framework can be used for an automatic classification of Renal Cell Carcinoma (RCC) subtypes, and for identification of features that predict survival outcome from digital histopathological images. Expand
Evaluate the Malignancy of Pulmonary Nodules Using the 3-D Deep Leaky Noisy-OR Network
TLDR
A 3-D deep neural network for automatic diagnosing lung cancer from computed tomography scans that 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. Expand
Selection criteria for lung-cancer screening.
TLDR
The use of the PLCO(M2012) model was more sensitive than the NLST criteria for lung-cancer detection and compared the accuracy of PLCo(M 2012) criteria withNLST criteria to detect lung cancer. Expand
Distanced LSTM: Time-Distanced Gates in Long Short-Term Memory Models for Lung Cancer Detection
TLDR
The DLSTM framework is evaluated in three datasets including simulated data, 1794 National Lung Screening Trial scans, and 1420 clinically acquired data with heterogeneous and irregular temporal accession to demonstrate that the method achieves competitive performance on both simulated and regularly sampled datasets. Expand
Cancer treatment and survivorship statistics, 2016
The number of cancer survivors continues to increase because of both advances in early detection and treatment and the aging and growth of the population. For the public health community to betterExpand
Cancer treatment and survivorship statistics, 2012
TLDR
Common cancer treatments, survival rates, and posttreatment concerns are summarized and the new National Cancer Survivorship Resource Center is introduced, which has engaged more than 100 volunteer survivorship experts nationwide to develop tools for cancer survivors, caregivers, health care professionals, advocates, and policy makers. Expand
Author Correction: End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography
An amendment to this paper has been published and can be accessed via a link at the top of the paper.
SphereFace: Deep Hypersphere Embedding for Face Recognition
TLDR
This paper proposes the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features in deep face recognition (FR) problem under open-set protocol. Expand
...
1
2
...