Detection Systems in Lung Cancer and Imaging, Volume 1 Detection Systems in Lung Cancer and Imaging, Volume 1 Edited by Ayman El-Baz University of Louisville, Louisville, Kentucky, USA and University of Louisville at AlAlamein International University (UofL-AIU), New Alamein City, Egypt Jasjit S Suri AtheroPoint LLC, Roseville, CA, USA IOP Publishing, Bristol, UK ªIOPPublishingLtd2021 Allrightsreserved.Nopartofthispublicationmaybereproduced,storedinaretrievalsystem ortransmittedinanyformorbyanymeans,electronic,mechanical,photocopying,recording orotherwise,withoutthepriorpermissionofthepublisher,orasexpresslypermittedbylawor undertermsagreedwiththeappropriaterightsorganization.Multiplecopyingispermittedin accordancewiththetermsoflicencesissuedbytheCopyrightLicensingAgency,theCopyright ClearanceCentreandotherreproductionrightsorganizations. PermissiontomakeuseofIOPPublishingcontentotherthanassetoutabovemaybesought [email protected]. AymanEl-BazandJasjitSSurihaveassertedtheirrighttobeidentifiedastheeditorsofthiswork inaccordancewithsections77and78oftheCopyright,DesignsandPatentsAct1988. ISBN 978-0-7503-3355-9(ebook) ISBN 978-0-7503-3353-5(print) ISBN 978-0-7503-3356-6(myPrint) ISBN 978-0-7503-3354-2(mobi) DOI 10.1088/978-0-7503-3355-9 Version:20220101 IOPebooks BritishLibraryCataloguing-in-PublicationData:Acataloguerecordforthisbookisavailable fromtheBritishLibrary. PublishedbyIOPPublishing,whollyownedbyTheInstituteofPhysics,London IOPPublishing,TempleCircus,TempleWay,Bristol,BS16HG,UK USOffice:IOPPublishing,Inc.,190NorthIndependenceMallWest,Suite601,Philadelphia, PA19106,USA With love and affection to my mother and father, whose loving spirit sustains me still —Ayman El-Baz To my late loving parents, immediate family, and children —Jasjit S Suri Contents Preface xiii Acknowledgement xiv Editor biographies xv List of contributors xvi 1 Lung cancer classification using wavelet recurrent 1-1 neural network Devi Nurtiyasari, Dedi Rosadi and Abdurakhman 1.1 Introduction 1-1 1.2 Lung cancer and lung image 1-2 1.2.1 Lung cancer 1-2 1.2.2 Lung image 1-2 1.2.3 Image processing 1-6 1.3 Classification process 1-7 1.3.1 Classification 1-7 1.3.2 Features extraction 1-8 1.3.3 Wavelet 1-11 1.3.4 Machine learning 1-16 1.3.5 Neural network 1-16 1.3.6 Recurrent neural network 1-22 1.3.7 Mean square error 1-22 1.3.8 Sensitivity, specificity, and accuracy 1-22 1.4 Dataset 1-23 1.5 Modeling wavelet recurrent neural network for lung cancer nodule 1-25 classification 1.5.1 Image denoising using wavelet 1-25 1.5.2 Wavelet recurrent neural network for lung cancer classification 1-26 1.6 Results and discussion 1-28 1.7 Conclusion 1-30 References 1-30 2 Diagnosis of diffusion-weighted magnetic resonance imaging 2-1 (DWI) for lung cancer Katsuo Usuda and Hidetaka Uramoto 2.1 Introduction 2-1 vii DetectionSystemsinLungCancerandImaging,Volume1 2.2 Diagnosis of lung cancer and the pulmonary nodules and 2-1 masses (figures 2.1–2.6, table 2.1) 2.3 Diagnostic capability of nodal involvement in lung cancer 2-4 (figures 2.7–2.9) 2.4 Recurrence or metastasis from lung cancer (figure 2.11) 2-7 2.5 Diagnosis of lung cancer by whole-body DWI 2-8 2.6 Response evaluation to chemotherapy and/or radiotherapy 2-8 (figure 2.11, table 2.2) 2.7 ADC and pathology 2-8 2.8 Medical cost of examinations 2-9 2.9 Advantage and disadvantage of MRI 2-10 2.10 Future plans 2-10 2.11 Conclusion 2-10 References 2-10 3 Computer assisted detection of low/high grade nodule from 3-1 lung CT scan slices using handcrafted features Seifedine Kadry and Venkatesan Rajinikanth 3.1 Introduction 3-1 3.2 Computer assisted detection system 3-4 3.2.1 Image collection 3-6 3.2.2 3D to 2D conversion 3-6 3.2.3 Threshold filter implementation 3-6 3.2.4 Nodule segmentation 3-8 3.2.5 Feature extraction 3-8 3.2.6 Feature selection 3-9 3.2.7 Classifier implementation 3-12 3.2.8 Validation of the CAD system 3-13 3.3 Results and discussions 3-14 3.4 Conclusion 3-17 References 3-17 4 Computer-aided lung cancer screening in computed 4-1 tomography: state-of the-art and future perspectives Joa˜o Pedrosa, Guilherme Aresta and Carlos Ferreira 4.1 Introduction 4-1 4.1.1 Computer-aided lung cancer screening 4-5 viii DetectionSystemsinLungCancerandImaging,Volume1 4.2 Computer-aided lung nodule detection 4-7 4.3 Computer-aided lung nodule segmentation 4-13 4.4 Computer-aided lung nodule characterization 4-16 4.4.1 Malignancy characterization 4-16 4.4.2 Other nodule features 4-19 4.5 Computer-aided lung cancer patient diagnosis/management 4-21 4.5.1 Lung cancer patient diagnosis 4-21 4.5.2 Patient follow-up recommendation 4-23 4.6 Available datasets 4-24 4.6.1 ANODE09 dataset 4-24 4.6.2 Lung image database consortium image collection dataset 4-25 4.6.3 Luna16 dataset 4-25 4.6.4 National lung screening trial dataset 4-26 4.6.5 Kaggle data Science Bowl 2017 dataset 4-26 4.6.6 LNDB dataset 4-26 4.7 Conclusion and future perspectives 4-26 References 4-30 5 Radiation therapy in lung cancer treatment 5-1 Mary McGunigal, Jonathan W Lischalk, Pamela Randolph-Jackson and Puja Gaur Khaitan References 5-9 6 Application of visual sensing technology in lung cancer 6-1 screening Rongpeng Li, Yonghong Xu and Nana Xu 6.1 Introduction 6-1 6.2 Section 1: detection of lung cancer-related markers in exhaled breath 6-4 through the visual sensing technology 6.2.1 Definition of VOCs in exhaled breath 6-4 6.2.2 Production mechanism of lung cancer-related VOCs in 6-6 exhaled breath 6.2.3 Preparation method of sensor chip 6-7 6.2.4 Collection of lung cancer-related VOCs in exhaled breath 6-8 6.2.5 Analysis of VOC patterns 6-8 6.2.6 Computational formulas of the relative standard deviation 6-10 (RSD or %RSD) and concentrations of saturated vapor (C) s ix