Author: Ximeng Mao
Publisher:
ISBN:
Category :
Languages : en
Pages :
Get Book Here
Book Description
"High dose rate (HDR) brachytherapy (BT) involves temporarily insertion of a sealed highly radioactive source inside or in close proximity of the target volume, by using catheters and/or applicators. Treatment planning in HDR BT is performed on a 3D set of computerized tomography or magnetic resonance images. The purpose of a treatment plan is to determine where (dwell position) and how long (dwell time) the radiation source should pause to expose its radiation. Each implanted catheter provides a set of possible dwell positions. Combinations of the possible dwell positions and dwell times, as well as utilizing contours of the target volume and organs at risk (OAR), contributes to optimization of treatment plans. The optimal plan has the best possible dose distribution with respect to the target volume and the OAR. Two key questions for treatment planning are how to evaluate a certain plan and how to search for the optimal plan. The traditional solutions to the two questions often lack the capability of fully utilizing previous experience, which result in inefficiency due to long computation times when solving the problems. In this thesis machine learning (ML) algorithms were investigated for evaluation and search for an optimal BT treatment plan. ML-based algorithms are chosen due to their ability to specialize in exploiting previous experience for better future performance. Evaluation of a certain treatment plan in the first problem requires calculation of the radiation dose. Clinical standards for BT dose calculation have traditionally been based on AAPM TG-43 report. In the TG-43 based dose calculation process, the affected malignant tissue, the surrounding radiation sensitive healthy organs, BT seeds, needles and applicators are considered to be water with unit mass density for simplification. This simplification overlooks the alteration of photon fluence and absorption of dose by different tissues, BT seeds, needles or applicators. Model based dose calculation algorithms (MBDCAs) provide a detailed and more accurate method for calculation of absorbed dose in heterogeneous systems such as the human body, with the Monte Carlo (MC) method being the gold standard. Recently, these algorithms have evolved from serving as a research tool into clinical practice in BT. To obtain accurate dose distributions, a correct geometrical description, density and tissue composition of the patient, a model of the BT seed and the implanted applicators with appropriate density and material composition are needed as inputs to these MBDCAs. AAPM TG-186 provides guidance for the use of MBDCAs. Although MC method is the most accurate technique for dose calculations, its use incurs an excessive computational cost and time. To provide a solution for the accuracy-time trade-off, a deep convolutional neural network (CNN) algorithm to predict dose distributions calculated with the MC method has been proposed in this thesis. The developed deep CNN based dose calculation algorithm was shown to be a promising method for accurate patient specific dosimetry in BT, at accuracy arbitrarily close to those of the source MC algorithm but with much faster computation times. Treatment plan optimization is traditionally solved as constrained optimization. Extended from core setup of plan optimization, a related plan analysis problem is formulated to focus on understanding the impacts of individual dwell position to overall plan performance. Derived from linear programming formulation of the optimization problem, reinforcement learning (RL) was applied to solve the plan analysis problem. Relying on the dose distribution at each dwell position, the RL solution showed flexibility in problem formulation as there is no need to enforce linearity. Moreover, when used in a simplified proof-of-concept setup derived from the real clinical case, the fully-trained RL agent showed the capability to reach optimal treatment plan within one step from any random start point"--
Author: Issam El Naqa
Publisher: Springer
ISBN: 3319183052
Category : Medical
Languages : en
Pages : 336
Get Book Here
Book Description
This book provides a complete overview of the role of machine learning in radiation oncology and medical physics, covering basic theory, methods, and a variety of applications in medical physics and radiotherapy. An introductory section explains machine learning, reviews supervised and unsupervised learning methods, discusses performance evaluation, and summarizes potential applications in radiation oncology. Detailed individual sections are then devoted to the use of machine learning in quality assurance; computer-aided detection, including treatment planning and contouring; image-guided radiotherapy; respiratory motion management; and treatment response modeling and outcome prediction. The book will be invaluable for students and residents in medical physics and radiation oncology and will also appeal to more experienced practitioners and researchers and members of applied machine learning communities.
Author:
Publisher:
ISBN:
Category :
Languages : en
Pages : 0
Get Book Here
Book Description
Radiation oncology is uniquely positioned to harness the power of big data as vast amounts of data are generated at an unprecedented pace for individual patients in imaging studies and radiation treatments worldwide. The big data encountered in the radiotherapy clinic may include patient demographics stored in the electronic medical record (EMR) systems, plan settings and dose volumetric information of the tumors and normal tissues generated by treatment planning systems (TPS), anatomical and functional information from diagnostic and therapeutic imaging modalities (e.g., CT, PET, MRI and kVCBCT) stored in picture archiving and communication systems (PACS), as well as the genomics, proteomics and metabolomics information derived from blood and tissue specimens. Yet, the great potential of big data in radiation oncology has not been fully exploited for the benefits of cancer patients due to a variety of technical hurdles and hardware limitations. With recent development in computer technology, there have been increasing and promising applications of machine learning algorithms involving the big data in radiation oncology. This research topic is intended to present novel technological breakthroughs and state-of-the-art developments in machine learning and data mining in radiation oncology in recent years.
Author: Jun Deng
Publisher: Frontiers Media SA
ISBN: 2889457303
Category :
Languages : en
Pages : 146
Get Book Here
Book Description
Author: Issam El Naqa
Publisher: Springer Nature
ISBN: 3030830470
Category : Science
Languages : en
Pages : 514
Get Book Here
Book Description
This book, now in an extensively revised and updated second edition, provides a comprehensive overview of both machine learning and deep learning and their role in oncology, medical physics, and radiology. Readers will find thorough coverage of basic theory, methods, and demonstrative applications in these fields. An introductory section explains machine and deep learning, reviews learning methods, discusses performance evaluation, and examines software tools and data protection. Detailed individual sections are then devoted to the use of machine and deep learning for medical image analysis, treatment planning and delivery, and outcomes modeling and decision support. Resources for varying applications are provided in each chapter, and software code is embedded as appropriate for illustrative purposes. The book will be invaluable for students and residents in medical physics, radiology, and oncology and will also appeal to more experienced practitioners and researchers and members of applied machine learning communities.
Author: Björn Morén
Publisher: Linköping University Electronic Press
ISBN: 9179297382
Category : Electronic books
Languages : sv
Pages : 53
Get Book Here
Book Description
Cancer is a widespread class of diseases that each year affects millions of people. It is mostly treated with chemotherapy, surgery, radiation therapy, or combinations thereof. High doserate (HDR) brachytherapy (BT) is one modality of radiation therapy, which is used to treat for example prostate cancer and gynecologic cancer. In BT, catheters (i.e., hollow needles) or applicators are used to place a single, small, but highly radioactive source of ionizing radiation close to or within a tumour, at dwell positions. An emerging technique for HDR BT treatment is intensity modulated brachytherapy (IMBT), in which static or dynamic shields are used to further shape the dose distribution, by hindering the radiation in certain directions. The topic of this thesis is the application of mathematical optimization to model and solve the treatment planning problem. The treatment planning includes decisions on catheter placement, that is, how many catheters to use and where to place them, as well as decisions for dwell times. Our focus is on the latter decisions. The primary treatment goals are to give the tumour a sufficiently high radiation dose while limiting the dose to the surrounding healthy organs, to avoid severe side effects. Because these aims are typically in conflict, optimization models of the treatment planning problem are inherently multiobjective. Compared to manual treatment planning, there are several advantages of using mathematical optimization for treatment planning. First, the optimization of treatment plans requires less time, compared to the time-consuming manual planning. Secondly, treatment plan quality can be improved by using optimization models and algorithms. Finally, with the use of sophisticated optimization models and algorithms the requirements of experience and skill level for the planners are lower. The use of optimization for treatment planning of IMBT is especially important because the degrees of freedom are too many for manual planning. The contributions of this thesis include the study of properties of treatment planning models, suggestions for extensions and improvements of proposed models, and the development of new optimization models that take clinically relevant, but uncustomary aspects, into account in the treatment planning. A common theme is the modelling of constraints on dosimetric indices, each of which is a restriction on the portion of a volume that receives at least a specified dose, or on the lowest dose that is received by a portion of a volume. Modelling dosimetric indices explicitly yields mixed-integer programs which are computationally demanding to solve. We have therefore investigated approximations of dosimetric indices, for example using smooth non-linear functions or convex functions. Contributions of this thesis are also a literature review of proposed treatment planning models for HDR BT, including mathematical analyses and comparisons of models, and a study of treatment planning for IMBT, which shows how robust optimization can be used to mitigate the risks from rotational errors in the shield placement. Cancer är en grupp av sjukdomar som varje år drabbar miljontals människor. De vanligaste behandlingsformerna är cellgifter, kirurgi, strålbehandling eller en kombination av dessa. I denna avhandling studeras högdosrat brachyterapi (HDR BT), vilket är en form av strålbehandling som till exempel används vid behandling av prostatacancer och gynekologisk cancer. Vid brachyterapibehandling används ihåliga nålar eller applikatorer för att placera en millimeterstor strålkälla antingen inuti eller intill en tumör. I varje nål finns det ett antal så kallade dröjpositioner där strålkällan kan stanna en viss tid för att bestråla den omkringliggande vävnaden, i alla riktningar. Genom att välja lämpliga tider för dröjpositionerna kan dosfördelningen formas efter patientens anatomi. Utöver HDR BT studeras också den nya tekniken intensitetsmodulerad brachyterapi (IMBT) vilket är en variation på HDR BT där skärmning används för att minska strålningen i vissa riktningar vilket gör det möjligt att forma dosfördelningen bättre. Planeringen av en behandling med HDR BT omfattar hur många nålar som ska användas, var de ska placeras samt hur länge strålkällan ska stanna i de olika dröjpositionerna. För HDR BT kan dessa vara flera hundra stycken medan det för IMBT snarare handlar om tusentals möjliga kombinationer av dröjpositioner och inställningar av skärmarna. Planeringen resulterar i en dosplan som beskriver hur hög stråldos som tumören och intilliggande frisk vävnad och riskorgan utsätts för. Dosplaneringen kan formuleras som ett matematiskt optimeringsproblem vilket är ämnet för avhandlingen. De övergripande målsättningarna för behandlingen är att ge en tillräckligt hög stråldos till tumören, för att döda alla cancerceller, samt att undvika att bestråla riskorgan eftersom det kan ge allvarliga biverkningar. Då alla målsättningarna inte samtidigt kan uppnås fullt ut så fås optimeringsproblem där flera målsättningar behöver prioriteras mot varandra. Utöver att dosplanen uppfyller kliniska behandlingsriktlinjer så är också tidsaspekten av planeringen viktig eftersom det är vanligt att den görs medan patienten är bedövad eller sövd. Vid utvärdering av en dosplan används dos-volymmått. För en tumör anger ett dosvolymmått hur stor andel av tumören som får en stråldos som är högre än en specificerad nivå. Dos-volymmått utgör en viktig del av målen för dosplaner som tas upp i kliniska behandlingsriktlinjer och ett exempel på ett sådant mål vid behandling av prostatacancer är att 95% av prostatans volym ska få en stråldos som är minst den föreskrivna dosen. Dos-volymmått utläses ur de kliniskt betydelsefulla dos-volym histogrammen som för varje stråldosnivå anger motsvarande volym som erhåller den dosen. En fördel med att använda matematisk optimering för dosplanering är att det kan spara tid jämfört med manuell planering. Med väl utvecklade modeller så finns det också möjlighet att skapa bättre dosplaner, till exempel genom att riskorganen nås av en lägre dos men med bibehållen dos till tumören. Vidare så finns det även fördelar med en process som inte är lika personberoende och som inte kräver erfarenhet i lika stor utsträckning som manuell dosplanering i dagsläget gör. Vid IMBT är det dessutom så många frihetsgrader att manuell planering i stort sett blir omöjligt. I avhandlingen ligger fokus på hur dos-volymmått kan användas och modelleras explicit i optimeringsmodeller, så kallade dos-volymmodeller. Detta omfattar såväl analys av egenskaper hos befintliga modeller, utvidgningar av tidigare använda modeller samt utveckling av nya optimeringsmodeller. Eftersom dos-volymmodeller modelleras som heltalsproblem, vilka är beräkningskrävande att lösa, så är det också viktigt att utveckla algoritmer som kan lösa dem tillräckligt snabbt för klinisk användning. Ett annat mål för modellutvecklingen är att kunna ta hänsyn till fler kriterier som är kliniskt relevanta men som inte ingår i dos-volymmodeller. En sådan kategori av mått är hur dosen är fördelad rumsligt, exempelvis att volymen av sammanhängande områden som får en alldeles för hög dos ska vara liten. Sådana områden går dock inte att undvika helt eftersom det är typiskt för dosplaner för brachyterapi att stråldosen fördelar sig ojämnt, med väldigt höga doser till små volymer precis intill strålkällorna. Vidare studeras hur små fel i inställningarna av skärmningen i IMBT påverkar dosplanens kvalitet och de olika utvärderingsmått som används kliniskt. Robust optimering har använts för att säkerställa att en dosplan tas fram som är robust sett till dessa möjliga fel i hur skärmningen är placerad. Slutligen ges en omfattande översikt över optimeringsmodeller för dosplanering av HDR BT och speciellt hur optimeringsmodellerna hanterar de motstridiga målsättningarna.
Author: Steven Minton
Publisher: Morgan Kaufmann
ISBN: 1483221172
Category : Social Science
Languages : en
Pages : 555
Get Book Here
Book Description
Machine Learning Methods for Planning provides information pertinent to learning methods for planning and scheduling. This book covers a wide variety of learning methods and learning architectures, including analogical, case-based, decision-tree, explanation-based, and reinforcement learning. Organized into 15 chapters, this book begins with an overview of planning and scheduling and describes some representative learning systems that have been developed for these tasks. This text then describes a learning apprentice for calendar management. Other chapters consider the problem of temporal credit assignment and describe tractable classes of problems for which optimal plans can be derived. This book discusses as well how reactive, integrated systems give rise to new requirements and opportunities for machine learning. The final chapter deals with a method for learning problem decompositions, which is based on an idealized model of efficiency for problem-reduction search. This book is a valuable resource for production managers, planners, scientists, and research workers.
Author: Jiahan Zhang
Publisher: Frontiers Media SA
ISBN: 2832523315
Category : Medical
Languages : en
Pages : 124
Get Book Here
Book Description
Author: Björn Morén
Publisher: Linköping University Electronic Press
ISBN: 9176851311
Category :
Languages : en
Pages : 63
Get Book Here
Book Description
Cancer is a widespread type of diseases that each year affects millions of people. It is mainly treated by chemotherapy, surgery or radiation therapy, or a combination of them. One modality of radiation therapy is high dose-rate brachytherapy, used in treatment of for example prostate cancer and gynecologic cancer. Brachytherapy is an invasive treatment in which catheters (hollow needles) or applicators are used to place the highly active radiation source close to or within a tumour. The treatment planning problem, which can be modelled as a mathematical optimization problem, is the topic of this thesis. The treatment planning includes decisions on how many catheters to use and where to place them as well as the dwell times for the radiation source. There are multiple aims with the treatment and these are primarily to give the tumour a radiation dose that is sufficiently high and to give the surrounding healthy tissue and organs (organs at risk) a dose that is sufficiently low. Because these aims are in conflict, modelling the treatment planning gives optimization problems which essentially are multiobjective. To evaluate treatment plans, a concept called dosimetric indices is commonly used and they constitute an essential part of the clinical treatment guidelines. For the tumour, the portion of the volume that receives at least a specified dose is of interest while for an organ at risk it is rather the portion of the volume that receives at most a specified dose. The dosimetric indices are derived from the dose-volume histogram, which for each dose level shows the corresponding dosimetric index. Dose-volume histograms are commonly used to visualise the three-dimensional dose distribution. The research focus of this thesis is mathematical modelling of the treatment planning and properties of optimization models explicitly including dosimetric indices, which the clinical treatment guidelines are based on. Modelling dosimetric indices explicitly yields mixedinteger programs which are computationally demanding to solve. The computing time of the treatment planning is of clinical relevance as the planning is typically conducted while the patient is under anaesthesia. Research topics in this thesis include both studying properties of models, extending and improving models, and developing new optimization models to be able to take more aspects into account in the treatment planning. There are several advantages of using mathematical optimization for treatment planning in comparison to manual planning. First, the treatment planning phase can be shortened compared to the time consuming manual planning. Secondly, also the quality of treatment plans can be improved by using optimization models and algorithms, for example by considering more of the clinically relevant aspects. Finally, with the use of optimization algorithms the requirements of experience and skill level for the planners are lower. This thesis summary contains a literature review over optimization models for treatment planning, including the catheter placement problem. How optimization models consider the multiobjective nature of the treatment planning problem is also discussed.
Author: X. Allen Li
Publisher: CRC Press
ISBN: 1439816352
Category : Medical
Languages : en
Pages : 404
Get Book Here
Book Description
Modern medical imaging and radiation therapy technologies are so complex and computer driven that it is difficult for physicians and technologists to know exactly what is happening at the point-of-care. Medical physicists responsible for filling this gap in knowledge must stay abreast of the latest advances at the intersection of medical imaging an
