12
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Combining deep learning and coherent anti-Stokes Raman scattering imaging for automated differential diagnosis of lung cancer

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract.

          Lung cancer is the most prevalent type of cancer and the leading cause of cancer-related deaths worldwide. Coherent anti-Stokes Raman scattering (CARS) is capable of providing cellular-level images and resolving pathologically related features on human lung tissues. However, conventional means of analyzing CARS images requires extensive image processing, feature engineering, and human intervention. This study demonstrates the feasibility of applying a deep learning algorithm to automatically differentiate normal and cancerous lung tissue images acquired by CARS. We leverage the features learned by pretrained deep neural networks and retrain the model using CARS images as the input. We achieve 89.2% accuracy in classifying normal, small-cell carcinoma, adenocarcinoma, and squamous cell carcinoma lung images. This computational method is a step toward on-the-spot diagnosis of lung cancer and can be further strengthened by the efforts aimed at miniaturizing the CARS technique for fiber-based microendoscopic imaging.

          Related collections

          Most cited references43

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

          Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly representative, hierarchical image features from sufficient training data. However, obtaining datasets as comprehensively annotated as ImageNet in the medical imaging domain remains a challenge. There are currently three major techniques that successfully employ CNNs to medical image classification: training the CNN from scratch, using off-the-shelf pre-trained CNN features, and conducting unsupervised CNN pre-training with supervised fine-tuning. Another effective method is transfer learning, i.e., fine-tuning CNN models pre-trained from natural image dataset to medical image tasks. In this paper, we exploit three important, but previously understudied factors of employing deep convolutional neural networks to computer-aided detection problems. We first explore and evaluate different CNN architectures. The studied models contain 5 thousand to 160 million parameters, and vary in numbers of layers. We then evaluate the influence of dataset scale and spatial image context on performance. Finally, we examine when and why transfer learning from pre-trained ImageNet (via fine-tuning) can be useful. We study two specific computer-aided detection (CADe) problems, namely thoraco-abdominal lymph node (LN) detection and interstitial lung disease (ILD) classification. We achieve the state-of-the-art performance on the mediastinal LN detection, and report the first five-fold cross-validation classification results on predicting axial CT slices with ILD categories. Our extensive empirical evaluation, CNN model analysis and valuable insights can be extended to the design of high performance CAD systems for other medical imaging tasks.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Visualizing data using ti-SNE

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              The International Epidemiology of Lung Cancer: geographical distribution and secular trends.

              This review presents the latest available international data for lung cancer incidence, mortality and survival, emphasizing the established causal relationship between smoking and lung cancer. In 2002, it was estimated that 1.35 million people throughout the world were diagnosed with lung cancer, and 1.18 million died of lung cancer-more than for any other type of cancer. There are some key differences in the epidemiology of lung cancer between more developed and less developed countries. In more developed countries, incidence and mortality rates are generally declining among males and are starting to plateau for females, reflecting previous trends in smoking prevalence. In contrast, there are some populations in less developed countries where increasing lung cancer rates are predicted to continue, due to endemic use of tobacco. A higher proportion of lung cancer cases are attributable to nonsmoking causes within less developed countries, particularly among women. Worldwide, the majority of lung cancer patients are diagnosed after the disease has progressed to a more advanced stage. Despite advances in chemotherapy, prognosis for lung cancer patients remains poor, with 5-year relative survival less than 14% among males and less than 18% among females in most countries. Given the increasing incidence of lung cancer in less developed countries and the current lack of effective treatment for advanced lung cancers, these results highlight the need for ongoing global tobacco reform to reduce the international burden of lung cancer.
                Bookmark

                Author and article information

                Journal
                J Biomed Opt
                J Biomed Opt
                JBOPFO
                JBO
                Journal of Biomedical Optics
                Society of Photo-Optical Instrumentation Engineers
                1083-3668
                1560-2281
                30 October 2017
                October 2017
                : 22
                : 10
                : 106017
                Affiliations
                [a ]Translational Biophotonics Laboratory , Department of Systems Medicine and Bioengineering, Houston Methodist Research Institute, Weill Cornell Medicine, Houston, Texas, United States
                [b ]Rice University , Department of Electrical and Computer Engineering, Houston, Texas, United States
                Author notes
                [* ]Address all correspondence to: Stephen T. C. Wong, E-mail: STWong@ 123456houstonmethodist.org
                Article
                JBO-170444RR 170444RR
                10.1117/1.JBO.22.10.106017
                5661703
                29086544
                1000446c-7b8e-4965-99bd-647f211249d6
                © The Authors.

                Published by SPIE under a Creative Commons Attribution 3.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

                History
                : 7 July 2017
                : 4 October 2017
                Page count
                Figures: 7, Tables: 0, References: 76, Pages: 10
                Funding
                Funded by: National Institutes of Health (NIH) http://dx.doi.org/10.13039/100000002
                Award ID: UO1 188388
                Funded by: U.S. Department of Defense (DOD) http://dx.doi.org/10.13039/100000005
                Award ID: W81XWH-14-1-0537
                Funded by: John S. Dunn Research Foundation
                Funded by: Cancer Fighters of Houston Foundation
                Categories
                Research Papers: Imaging
                Paper
                Custom metadata
                Weng et al.: Combining deep learning and coherent anti-Stokes Raman scattering imaging…

                Biomedical engineering
                nonlinear microscopy,medical imaging,lung cancer,classification,artificial intelligence,deep learning

                Comments

                Comment on this article