Artificial Intelligence in Cancer Diagnosis and Prognosis, Volume 1 Lung and kidney cancer Online at: https://doi.org/10.1088/978-0-7503-3595-9 IPEM–IOP Series in Physics and Engineering in Medicine and Biology Editorial Advisory Board Members Frank Verhaegen Kwan Hoong Ng Maastro Clinic, The Netherlands University of Malaya, Malaysia Carmel Caruana John Hossack University of Malta, Malta University of Virginia, USA Penelope Allisy-Roberts Tingting Zhu formerly of BIPM, Sèvres, France University of Oxford, UK Rory Cooper Dennis Schaart University of Pittsburgh, PA, USA TU Delft, The Netherlands Alicia El Haj Indra J Das University of Birmingham, UK NorthwesternUniversityFeinbergSchool of Medicine, USA About the Series TheseriesinPhysicsandEngineeringinMedicineandBiologywillallowtheInstitute of Physics and Engineering in Medicine (IPEM) to enhance its mission to ‘advance physics and engineering applied to medicine and biology for the public good’. It is focused on key areas including, but not limited to: (cid:129) clinical engineering (cid:129) diagnostic radiology (cid:129) informatics and computing (cid:129) magnetic resonance imaging (cid:129) nuclear medicine (cid:129) physiological measurement (cid:129) radiation protection (cid:129) radiotherapy (cid:129) rehabilitation engineering (cid:129) ultrasound and non-ionising radiation. A number of IPEM–IOP titles are being published as part of the EUTEMPE Network Series for Medical Physics Experts. A full list of titles published in this series can be found here: https://iopscience.iop. org/bookListInfo/physics-engineering-medicine-biology-series. Artificial Intelligence in Cancer Diagnosis and Prognosis, Volume 1 Lung and kidney cancer Edited by Ayman El-Baz University of Louisville, Louisville, KY, 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 ªIOPPublishingLtd2022 Allrightsreserved.Nopartofthispublicationmaybereproduced,storedinaretrievalsystem ortransmittedinanyformorbyanymeans,electronic,mechanical,photocopying,recording orotherwise,withoutthepriorpermissionofthepublisher,orasexpresslypermittedbylawor undertermsagreedwiththeappropriaterightsorganization.Multiplecopyingispermittedin accordancewiththetermsoflicencesissuedbytheCopyrightLicensingAgency,theCopyright ClearanceCentreandotherreproductionrightsorganizations. PermissiontomakeuseofIOPPublishingcontentotherthanassetoutabovemaybesought [email protected]. AymanEl-BazandJasjitSSurihaveassertedtheirrighttobeidentifiedastheeditorsofthiswork inaccordancewithsections77and78oftheCopyright,DesignsandPatentsAct1988. ISBN 978-0-7503-3595-9(ebook) ISBN 978-0-7503-3593-5(print) ISBN 978-0-7503-3596-6(myPrint) ISBN 978-0-7503-3594-2(mobi) DOI 10.1088/978-0-7503-3595-9 Version:20221001 IOPebooks BritishLibraryCataloguing-in-PublicationData:Acataloguerecordforthisbookisavailable fromtheBritishLibrary. PublishedbyIOPPublishing,whollyownedbyTheInstituteofPhysics,London IOPPublishing,No.2TheDistillery,Glassfields,AvonStreet,Bristol,BS20GR,UK USOffice:IOPPublishing,Inc.,190NorthIndependenceMallWest,Suite601,Philadelphia, PA19106,USA Withloveandaffectiontomymotherandfather,whoselovingspiritsustainsmestill. —Ayman El-Baz To my late loving parents, immediate family, and children. —Jasjit S Suri Contents Preface xiii Acknowledgements xiv Editor biographies xv List of contributors xvi 1 American Joint Committee on Cancer staging of lung and renal 1-1 cancers using a recurrent deep neural network model Dipanjan Moitra 1.1 Introduction 1-1 1.2 Background 1-2 1.2.1 Lung cancer 1-2 1.2.2 Renal cancer 1-3 1.2.3 Research scope 1-3 1.3 Methodology 1-4 1.3.1 AJCC staging 1-4 1.3.2 Database 1-5 1.3.3 The deep learning model 1-7 1.4 The experiment 1-9 1.5 Results and discussion 1-14 1.6 Conclusions 1-18 References 1-18 2 Neural-ensemble-based detection: a modern way to diagnose 2-1 lung cancer Sharayu Govardhane, Sahil Gandhi and Pravin Shende 2.1 Introduction 2-2 2.1.1 Lung cancer epidemiology 2-2 2.1.2 Signs and symptoms of lung cancer 2-2 2.1.3 Staging of lung cancer 2-3 2.1.4 Classification of lung cancer 2-3 2.2 Different methods of lung cancer detection 2-4 2.2.1 Invasive methods 2-5 2.2.2 Non-invasive methods 2-8 vii ArtificialIntelligenceinCancerDiagnosisandPrognosis,Volume1 2.3 Neural-ensemble-based detection 2-10 2.4 Conclusions 2-14 References and further reading 2-14 3 Computed tomography and magnetic resonance imaging 3-1 machine learning applications for renal cell carcinoma Elvira Guerriero, Arnaldo Stanzione, Lorenzo Ugga and Renato Cuocolo 3.1 Background 3-1 3.2 Applications 3-5 3.2.1 Malignant versus benign discrimination 3-5 3.2.2 Malignancy subtyping 3-8 3.2.3 Biologic aggressiveness 3-10 3.2.4 Correlation with overall and progression-free survival 3-12 under treatment 3.2.5 Prediction of perioperative complications 3-14 3.3 Conclusions 3-15 References 3-15 4 Pulmonary nodule-based feature learning for automated lung 4-1 tumor grading using convolutional neural networks Supriya Suresh and Subaji Mohan 4.1 Introduction 4-2 4.2 Literature review 4-3 4.2.1 Preprocessing 4-4 4.2.2 Candidate nodule segmentation 4-4 4.2.3 Feature extraction and classification 4-5 4.3 Methodology 4-7 4.3.1 Data acquisition 4-8 4.3.2 Preprocessing 4-8 4.3.3 NROI segmentation 4-10 4.3.4 GAN 4-10 4.3.5 Feature extraction 4-12 4.3.6 Classification 4-15 4.4 Results and discussion 4-16 4.5 Conclusions 4-30 References 4-30 viii ArtificialIntelligenceinCancerDiagnosisandPrognosis,Volume1 5 Detection of lung contours using closed principal curves and 5-1 machine learning Tao Peng, Yihuai Wang, Thomas Canhao Xu, Lianmin Shi, Jianwu Jiang and Shilang Zhu 5.1 Introduction 5-2 5.2 Materials and methods 5-3 5.2.1 Principal curve 5-4 5.2.2 Machine learning 5-5 5.2.3 Proposed algorithm 5-6 5.2.4 Quantitative evaluation 5-9 5.3 Results and discussion 5-9 5.3.1 Detecting contours in the private dataset using different 5-10 learning rates 5.3.2 Detecting contours in the private dataset using different 5-12 numbers of neurons in the hidden layer 5.3.3 Detecting contours in the private dataset using different 5-12 numbers of epochs 5.3.4 Detecting contours in the private dataset using different 5-16 algorithms 5.3.5 Detecting contours in the public LIDC–IDRI dataset using 5-18 different algorithms 5.4 Conclusions 5-19 Acknowledgments 5-20 References 5-20 6 Bytes, pixels, and bases: machine learning in imaging–omics 6-1 for renal cell carcinoma Ruchi Chauhan, C V Jawahar and P K Vinod 6.1 Introduction 6-1 6.1.1 The convergence of computers and cancer care 6-3 6.2 Imaging in renal cell carcinoma 6-5 6.2.1 Radiology 6-5 6.2.2 Pathology 6-6 6.3 Omics in renal cell carcinoma 6-7 6.3.1 Multiomics 6-9 6.4 Imaging–omics for kidney carcinoma 6-9 6.4.1 Radiomics 6-10 6.4.2 Pathomics 6-11 ix