Computational Intelligence and Healthcare Informatics. Группа авторов

unannotated images, in: Medical Image Computing and Comput.-Assisted Intervention, pp. 408–416, Springer, 2017.

      16. Sun, W., Tseng, T.B., Zhang, J., Qian, W., Computerized breast cancer analysis system using-three stage semi-supervised learning method. Comput. Methods Programs Biomed., 135, 77–88, 2016.

      17. Xia, Y., Liu, F., Yang, D., Cai, J., Yu, L., Zhu, Z., Xu, D., Yuille, A., Roth, H., 3d semi-supervised learning with uncertainty-aware multiview co-training, in: IEEE Winter Conf. Appl. Comput. Vis., 2020.

      18. Zhao, Y., Zeng, D., Socinski, M.A., Kosorok, M.R., Reinforcement learning strategies for clinical trials in nonsmall cell lung cancer. Biometrics, 67, 4, 1422–33, 2011 Dec.

      19. Pineau, J., Guez, A., Vincent, R., Panuccio, G., Avoli, M., Treating epilepsy via adaptive neurostimulation: a reinforcement learning approach. Int. J. Neural Syst., 19, 4, 227–40, 2009.

      20. Liu, Y., Logan, B., Liu, N., Xu, Z., Tang, J., Wang, Y., Deep reinforcement learning for dynamic treatment regimes on medical registry data. 2017 IEEE International Conference on Healthcare Informatics (ICHI), 2017 Aug., pp. 380–5.

      21. Raghu, A., Komorowski, M., Ahmed, I., Celi, L.A., Szolovits, P., Ghassemi, M., Deep reinforcement learning for sepsis treatment. CoRR, 2017, abs/1711.09602.

      22. https://news.stanford.edu/2017/01/25/artificial-intelligence-used-identify-skin-cancer (dated: 13-09-2020)

      23. Gulshan, V., Peng, L., Coram, M. et al., Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. JAMA, 316, 22, 2402–2410, 2016.

      24. Dash, S.S., Big data in healthcare: management, analysis and future prospects. J. Big Data, 6, 54, 2019.

      25. Johnston, L.R. and P.L., Suboptimal response to clopidogrel and the effect of prasugrel in acute coronary syndromes. Int. J. Cardiol., 995–999, 2013.

      26. Sean Chia, J.H., SAR by kinetics for drug discovery in protein misfolding diseases. PNAS, 2018.

      1 *Corresponding author: [email protected]

Part II MEDICAL DATA PROCESSING AND ANALYSIS

      2

      Thoracic Image Analysis Using Deep Learning

       Rakhi Wajgi1*, Jitendra V. Tembhurne2 and Dipak Wajgi2

       1Department of Computer Technology, Yeshwantrao Chavan College of Engineering, Nagpur, India

       2Department of Computer Science & Engineering, Indian Institute of Information Technology, Nagpur, India

       Abstract

      Thoracic diseases are caused due to ill condition of heart, lungs, mediastinum, diaphragm, and great vessels. Basically, it is a disorder of organs in thoracic region (rib cage). Thoracic diseases create severe burden on the overall health of a person and ignorance to them may lead to the sudden death of patients. Lung tuberculosis is one of the thoracic diseases which is accepted as worldwide pandemic. Prevalence of thoracic diseases is rising day by day due to various environmental factors and COVID-19 has trigged it at higher level. Chest radiography is the only omnipresent solution utilized to capture the abnormalities in the chest. It requires periodic visits by patient and timely tracking of findings and observations from the chest radiographic reports. These thoracic disorders are classified under various classes such as Atelectasis, Pneumonia, Hernia, Edema, Emphysema, Cardiomegaly, Fibrosis, Pneumothorax, Consolidation, Pleural Thickening, Effusion, Infiltration, Nodules, and Mass. Precise and reliable detection of these disorders required experienced radiologist. The major area of research in this domain is accurate localization and classification of affected region. In order to make accurate prognosis of chest diseases, research community has developed various automated models using deep learning. Deep learning has created a massive impact in terms of analysis in the domain of medical imaging where unprecedented amount of data is generated daily. There are various challenges faced by the community prior to model building. These challenges include orientation, data augmentation, colour space augmentation, and feature space augmentation of image but are pragmatically handle by various parameters and functions in deep learning models by maintaining their accuracies.

      This chapter aims to analyse critically the deep learning techniques utilized for thoracic image analysis with respective accuracy achieved by them. The various deep learning techniques are described along with dataset, activation function and model used, number and types of layers used, learning rate, training time, epoch, performance metric, hardware used, and type of abnormality detected. Moreover, a comparative analysis of existing deep learning models based on accuracy, precision, and recall is also presented with emphasize on the future direction of research.

      Keywords: Accuracy, classification, deep learning, localization, precision, recall, radiography, thoracic disorder

2.1 Introduction

      Identification of pathologies from chest x-ray (CXR) images plays a crucial role in planning of threptic strategies for diagnosis of thoracic diseases because thoracic diseases create severe burden on the overall health of a person and ignorance to them may lead to the sudden death of patients. Tuberculosis (TB) continues to remain major health threat worldwide and people continue to fall sick due to TB every year. According to WHO report of 2019 [24], 1.4 million people died due to TB in 2019. When a person suffers with TB, it takes time for symptoms to express prominently. Till then, the infection transfers from person to person results in increase in prevalence of infection and mortality rate. Moreover, Pneumonia is also creating major burden in many countries. Since December 2019, people all over the world were suddenly suffered with Pneumonia with unknown etiology which results in COVID-19 Pandemic. TB, Pneumonia and other disorders are located in the thoracic region are known as thoracic disorders and location of Thoracic pathology is captured through x-ray of thoracic region. There are 14 different classes of thoracic pathologies such as Atelectasis, Pneumonia, Hernia, Edema, Emphysema, Cardiomegaly, Fibrosis, Pneumothorax, Consolidation, Pleural Thickening, Effusion, Infiltration, Nodules, and Mass. CXR is the most preferable screening tool used by radiologist for prediction of abnormalities in thorax region. To understand the exact location and type of pathology, expert radiologists are needed who have enough experience in the field of detecting pathologies from the chest radiology x-ray and are seldom available.

      Furthermore, economically less developed countries lack with experienced radiologist and growing air pollution is badly impacting human lungs for which x-ray is the only reasonable tool to detect abnormalities in them. Recent pandemic of COVID-19 motivates researchers to design deep learning models which can predict the impact of SARS CoV-2 virus on human lungs at early stages as well as to identify post COVID effect on lungs. Patients suffering with thoracic abnormalities are associated with major change in their mental, social, and health-related quality of life. For some of them, early chest radiography can save their life and prevent them from undergoing unnecessary exposure to x-rays radiations. Thus, this motivates to explore new findings from it. Therefore, to make accurate prognosis of chest pathologies, researchers have automated the process of localization using Deep Leaning (DL) techniques. These models will act as an assistant to less experienced radiologist with the help of which prediction can be tallied. Due to significant contribution of deep learning in medical field in terms of object detection and classification, researchers have developed many models of DL for classification and localization of thoracic pathologies and compared their efficacy with other models on the basis of various