The electrochemical treatment (EChT) of tumours entails thattumour tissue is treated with a continuous direct currentthrough two or more electrodes placed in or near the tumour.Promising results have been reported from clinical trials inChina, where more than ten thousand patients have been treatedwith EChT during the past ten years. Before clinical trials canbe conducted outside of China, the underlying destructionmechanism behind EChT must be clarified and a reliabledose-planning strategy has to be developed. One approach inachieving this is through mathematical modelling. Mathematical models, describing the physicochemical reactionand transport processes of species dissolved in tissuesurrounding platinum anodes and cathodes, during EChT, aredeveloped and visualised in this thesis. The consideredelectrochemical reactions are oxygen and chlorine evolution, atthe anode, and hydrogen evolution at the cathode. Concentrationprofiles of substances dissolved in tissue, and the potentialprofile within the tissue itself, are simulated as functions oftime. In addition to the modelling work, the thesis includes anexperimental EChT study on healthy mammary tissue in rats. Theresults from the experimental study enable an investigation ofthe validity of the mathematical models, as well as of theirapplicability for dose planning. The studies presented in this thesis have given a strongindication of the destruction mechanism involved in EChT. It isshown by the modelling work, in combination with theexperiments, that the most probable cause of tissue destructionis acidification at the anode and alkalisation at the cathode.The pH profiles obtained from the theoretical models have showngood correlation with the experimentally measured destructionzones, assuming that a pH above and below certain values causetissue destruction. This implies that the models presented inthis thesis could be of use in predicting the tumourdestruction produced through EChT, and thereby provide a basisfor a systematic dose planning of clinical treatments.Moreover, the models can serve as valuable tools in optimisingthe operating conditions of EChT. Modelling work of theanode processes has explained the roleof chlorine in the underlying destruction mechanism behindEChT. It is found that the reactions of chlorine with tissueplay important roles as generators of hydrogen ions. Thecontribution of these reactions to the acidification of tissue,surrounding the anode, is strongly dependent on the appliedcurrent density and increases with decreasing currentdensity. <b>Keywords:</b>cancer, direct current, dose planning,electrochemical treatment (EChT), electrotherapy, mathematicalmodelling, tumour.

<p>The electrochemical treatment (EChT) of tumours entails thattumour tissue is treated with a continuous direct currentthrough two or more electrodes placed in or near the tumour.Promising results have been reported from clinical trials inChina, where more than ten thousand patients have been treatedwith EChT during the past ten years. Before clinical trials canbe conducted outside of China, the underlying destructionmechanism behind EChT must be clarified and a reliabledose-planning strategy has to be developed. One approach inachieving this is through mathematical modelling.</p><p>Mathematical models, describing the physicochemical reactionand transport processes of species dissolved in tissuesurrounding platinum anodes and cathodes, during EChT, aredeveloped and visualised in this thesis. The consideredelectrochemical reactions are oxygen and chlorine evolution, atthe anode, and hydrogen evolution at the cathode. Concentrationprofiles of substances dissolved in tissue, and the potentialprofile within the tissue itself, are simulated as functions oftime. In addition to the modelling work, the thesis includes anexperimental EChT study on healthy mammary tissue in rats. Theresults from the experimental study enable an investigation ofthe validity of the mathematical models, as well as of theirapplicability for dose planning.</p><p>The studies presented in this thesis have given a strongindication of the destruction mechanism involved in EChT. It isshown by the modelling work, in combination with theexperiments, that the most probable cause of tissue destructionis acidification at the anode and alkalisation at the cathode.The pH profiles obtained from the theoretical models have showngood correlation with the experimentally measured destructionzones, assuming that a pH above and below certain values causetissue destruction. This implies that the models presented inthis thesis could be of use in predicting the tumourdestruction produced through EChT, and thereby provide a basisfor a systematic dose planning of clinical treatments.Moreover, the models can serve as valuable tools in optimisingthe operating conditions of EChT.</p><p>Modelling work of theanode processes has explained the roleof chlorine in the underlying destruction mechanism behindEChT. It is found that the reactions of chlorine with tissueplay important roles as generators of hydrogen ions. Thecontribution of these reactions to the acidification of tissue,surrounding the anode, is strongly dependent on the appliedcurrent density and increases with decreasing currentdensity.</p><p><b>Keywords:</b>cancer, direct current, dose planning,electrochemical treatment (EChT), electrotherapy, mathematicalmodelling, tumour.</p>

In recent years, machine learning has become utilized in external radiation therapy treatment planning. This involves automatic generation of treatment plans based on CT-scans and other spatial information such as the location of tumors and organs. The utility lies in relieving clinical staff from the labor of manually or semi-manually creating such plans. Rather than predicting a deterministic plan, there is great value in modeling it stochastically, i.e. predicting a probability distribution of dose from CT-scans and delineated biological structures. The stochasticity inherent in the RT treatment problem stems from the fact that a range of different plans can be adequate for a patient. The particular distribution can be thought of as the prevalence in preferences among clinicians. Having more information about the range of possible plans represented in one model entails that there is more flexibility in forming a final plan. Additionally, the model will be able to reflect the potentially conflicting clinical trade-offs; these will occur as multimodal distributions of dose in areas where there is a high variance. At RaySearch, the current method for doing this uses probabilistic random forests, an augmentation of the classical random forest algorithm. A current direction of research is learning the probability distribution using deep learning. A novel parametric approach to this is letting a suitable deep neural network approximate the parameters of a Gaussian mixture model in each volume element. Such a neural network is known as a mixture density network. This thesis establishes theoretical results of artificial neural networks, mainly the universal approximation theorem, applied to the activation functions used in the thesis. It will then proceed to investigate the power of deep learning in predicting dose distributions, both deterministically and stochastically. The primary objective is to investigate the feasibility of mixture density networks for stochastic prediction. The research question is the following. U-nets and Mixture Density Networks will be combined to predict stochastic doses. Does there exist such a network, powerful enough to detect and model bimodality? The experiments and investigations performed in this thesis demonstrate that there is indeed such a network. / Under de senaste åren har maskininlärning börjat nyttjas i extern strålbehandlingsplanering. Detta involverar automatisk generering av behandlingsplaner baserade på datortomografibilder och annan rumslig information, såsom placering av tumörer och organ. Nyttan ligger i att avlasta klinisk personal från arbetet med manuellt eller halvmanuellt skapa sådana planer. I stället för att predicera en deterministisk plan finns det stort värde att modellera den stokastiskt, det vill säga predicera en sannolikhetsfördelning av dos utifrån datortomografibilder och konturerade biologiska strukturer. Stokasticiteten som förekommer i strålterapibehandlingsproblemet beror på att en rad olika planer kan vara adekvata för en patient. Den särskilda fördelningen kan betraktas som förekomsten av preferenser bland klinisk personal. Att ha mer information om utbudet av möjliga planer representerat i en modell innebär att det finns mer flexibilitet i utformningen av en slutlig plan. Dessutom kommer modellen att kunna återspegla de potentiellt motstridiga kliniska avvägningarna; dessa kommer påträffas som multimodala fördelningar av dosen i områden där det finns en hög varians. På RaySearch används en probabilistisk random forest för att skapa dessa fördelningar, denna metod är en utökning av den klassiska random forest-algoritmen. En aktuell forskningsriktning är att generera in sannolikhetsfördelningen med hjälp av djupinlärning. Ett oprövat parametriskt tillvägagångssätt för detta är att låta ett lämpligt djupt neuralt nätverk approximera parametrarna för en Gaussisk mixturmodell i varje volymelement. Ett sådant neuralt nätverk är känt som ett mixturdensitetsnätverk. Den här uppsatsen fastställer teoretiska resultat för artificiella neurala nätverk, främst det universella approximationsteoremet, tillämpat på de aktiveringsfunktioner som används i uppsatsen. Den fortsätter sedan att utforska styrkan av djupinlärning i att predicera dosfördelningar, både deterministiskt och stokastiskt. Det primära målet är att undersöka lämpligheten av mixturdensitetsnätverk för stokastisk prediktion. Forskningsfrågan är följande. U-nets och mixturdensitetsnätverk kommer att kombineras för att predicera stokastiska doser. Finns det ett sådant nätverk som är tillräckligt kraftfullt för att upptäcka och modellera bimodalitet? Experimenten och undersökningarna som utförts i denna uppsats visar att det faktiskt finns ett sådant nätverk.

Vor jeder Radioiodtherapie (RIT) sowohl bei Patienten mit einer funktionell relevanten Schilddrüsenautonomie als auch bei Patienten mit einem Morbus Basedow schreibt der Gesetzgeber in Deutschland eine individuelle Dosimetrie zu Vermeidung einer unnötigen Strahlenbelastung vor. Das Ziel des Radioiodtests ist es, eine möglichst genaue Vorhersage der individuellen Radioiodkinetik zu treffen. Ziel dieser Arbeit war es neben der theoretischen Begründung und Beschreibung der 1-Punkt-Messung, den Nachweis der Machbarkeit und Effektivität dieses neuen dosimetrischen Ansatzes im klinischen Kontext zu führen. In einem weiteren Schritt wurden die klinischen Ergebnisse der hier ausgewerteten Patienten mit publizierten Daten verglichen. Desweiteren wurden Einflussfaktoren auf den Erfolg bzw. Misserfolg der RIT evaluiert. Dieser neue dosimetrische Ansatz nach Prof. Luig verwendet eine späte Uptake-Messung nach 7 Tage und geht von einem krankheitsspezifischen Erreichen der Aktivitätsmaxima in der Schilddrüse aus. In dieser retrospektiven Auswertung wurde die Daten von 169 Patienten ausgewertet, die im Zeitraum von April 2006 bis Dezember 2008 in der Nuklearmedizin der UMG aufgrund einer funktionellen Autonomie oder einer Immunogenen Hyperthyreose einer präradioiodtherapeutischen Dosimetrie mittels einer einzigen Uptake-Messung unterzogen wurden. Die Erfolgsrate nach einmaliger RIT lag bei Patienten mit einer Autonomie bei 92,2% und bei Patienten mit einem Morbus Basedow bei 85,7%. Als statistisch signifikanter Einflussfaktor für den Misserfolg einer RIT zeigte sich bei beiden Krankheitsbildern ein erhöhter Technetiumsuppressionsuptake (TcTUs). Zusammenfassend liegt der Vorteil 1-Punkt-Messung beim Radioiodtest in der guten Durchführbarkeit und vor allem in seiner klinischen Effizienz.