{"title":"Artificial Intelligence and Radiomics in Molecular Oncology Imaging.","authors":"Daniel Truhn, Sven Nebelung","doi":"10.1007/978-3-032-15314-2_12","DOIUrl":"10.1007/978-3-032-15314-2_12","url":null,"abstract":"<p><p>In this chapter, we explore the landscape of artificial intelligence and radiomics in molecular oncology imaging. Advances in molecular imaging methods offer powerful insights into tumor biology but generate complex data beyond the capability of traditional visual interpretation alone. To address this complexity, radiomics emerged as a structured method to quantify imaging features, transforming subtle textures and tumor shapes into meaningful biomarkers. More recently, deep learning approaches-particularly convolutional neural networks-have taken this concept further, automatically learning intricate patterns directly from imaging data. Additionally, we introduce transformer architectures, a newer AI approach, capable of capturing global image context and integrating imaging information seamlessly with other clinical data. Throughout, we discuss the strengths and limitations of each method, highlighting challenges such as large data requirements, standardization, interpretability, and rigorous validation needed for clinical translation. Finally, we emphasize emerging techniques, such as self-supervised and multimodal learning, which promise to overcome these limitations and push molecular imaging toward genuinely personalized cancer care.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"224 ","pages":"379-399"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147965032","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Advanced X-Ray Imaging Technology.","authors":"Daniela Pfeiffer, Ernst Rummeny, Franz Pfeiffer","doi":"10.1007/978-3-032-15314-2_1","DOIUrl":"10.1007/978-3-032-15314-2_1","url":null,"abstract":"<p><p>Since their discovery by Wilhelm Conrad Röntgen in 1895, X-rays have become the most widely available, typically fastest, and usually most cost-effective medical imaging modality today. From the early radiographic approaches using X-ray films as detectors, the portfolio of medical X-ray imaging devices developed into a large range of dedicated instrumentation for various applications. While X-ray imaging has come a long way, there are some physical properties of X-rays that have not yet been fully exploited, and which may offer quite some room for further enhancements of current X-ray imaging equipment. Firstly, X-ray imaging today is mainly black and white, despite the fact that X-ray generators actually create a full spectrum of X-ray energies, and that the interactions of X-rays that occur within the human body are not the same for all energies and every material. Exploiting these spectral dependencies allows to not only obtain a black and white CT image, but also to obtain more molecularly specific information, which is relevant particularly in oncological precision radiology. The second aspect of X-rays, and so far in radiology mainly neglected and unused, is the physical fact that X-rays can also be interpreted in the wave picture, and not only as presently done in the particle picture. If interpreted as waves, X-rays-just like visible light-experience a phase shift in matter, and this-if exploited correctly-can produce a new class of X-ray images, which then depict the wave interactions of X-rays with matter, rather than only the attenuating properties, as done until now.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"224 ","pages":"3-37"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147964951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Samuel M Vorbach, Stephanie E Combs, Benedikt Wiestler, Jan C Peeken
{"title":"Image-Guided Radiooncology: The Potential of Artificial Intelligence in Clinical Application.","authors":"Samuel M Vorbach, Stephanie E Combs, Benedikt Wiestler, Jan C Peeken","doi":"10.1007/978-3-032-21415-7_9","DOIUrl":"10.1007/978-3-032-21415-7_9","url":null,"abstract":"<p><p>Defining artificial intelligence (AI) remains a complex challenge, given its rapidly evolving nature. Nevertheless, one broadly accepted definition-endorsed by the European Union-describes AI as a suite of algorithms that learn from data to make predictions. Since the early 2010s, AI has emerged as a highly effective approach for analyzing, processing, and even generating medical image data.In this chapter, we provide an overview of key AI paradigms-radiomics, deep learning (DL), and foundation models-and examine their current and potential applications in medical image analysis within radiation oncology. We focus on topics, such as image classification, treatment planning, and response assessment, as well as novel strategies involving vision language models (VLMs). Through this exploration, we offer insights into how AI is transforming clinical workflows and shaping future directions in radiation oncology.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"225 ","pages":"835-858"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147983824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Priscilla Guglielmo, Stefano Fanti, Laura Evangelista
{"title":"Non-FDG PET/CT.","authors":"Priscilla Guglielmo, Stefano Fanti, Laura Evangelista","doi":"10.1007/978-3-032-21415-7_4","DOIUrl":"10.1007/978-3-032-21415-7_4","url":null,"abstract":"<p><p>The principal role of molecular imaging with positron emission tomography (PET) in contemporary clinical practice is centered on oncological applications. Among radiopharmaceuticals, [<sup>18</sup>F]FDG continues to serve as the cornerstone of nuclear oncology, maintaining its position as the most extensively utilized positron-emitting agent to date. Nevertheless, the progressive elucidation of cancer biology over recent decades has unveiled numerous metabolic and pathogenic pathways within malignant cells, thereby catalyzing the innovation of a diverse array of novel PET tracers. This chapter provides an overview of a curated selection of non-FDG PET tracers, highlighting their integration into clinical workflows and their respective contributions to advancing oncological imaging.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"225 ","pages":"721-748"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147983800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Clinical Applications of Theranostics.","authors":"Jonathan Kuten, Lisa Bodei, Jason S Lewis","doi":"10.1007/978-3-032-21415-7_17","DOIUrl":"10.1007/978-3-032-21415-7_17","url":null,"abstract":"<p><p>Radiotheranostics integrates molecular imaging and targeted radionuclide therapy to provide personalized cancer treatment. By using radiolabeled agents that bind tumor-specific targets, clinicians can both visualize and treat malignancies, guided by the principle of \"treat what you see.\" Diagnostic tools such as positron emission tomography (PET) and single-photon emission computed tomography (SPECT) confirm target presence, while therapeutic radioisotopes deliver cytotoxic radiation to tumor cells, enabling real-time monitoring and individualized treatment.These agents pair a targeting molecule-such as a peptide, small molecule, or antibody-with either a diagnostic or therapeutic radioisotope. Beta and alpha emitters offer different radiation profiles, suited for specific clinical needs. This strategy has already improved outcomes in diseases like neuroendocrine tumors and prostate cancer, and new applications are rapidly emerging. Radiotheranostics provides a systemic alternative to external beam radiotherapy, allowing for personalized dosimetry to enhance efficacy and minimize side effects.The field has evolved significantly from early radioiodine therapy, driven by advances in radiochemistry and imaging. While treatments are generally safe, potential toxicities-such as bone marrow suppression or glandular damage-require careful management. As radiotheranostics advances toward broader clinical use, overcoming challenges in isotope supply, infrastructure, and workforce training will be critical. Its integration into multidisciplinary oncology teams promises to make it a cornerstone of precision cancer care.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"225 ","pages":"1043-1077"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147983813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Microbubble Contrast Agents for Molecular Ultrasound Imaging of Tumor Vasculature.","authors":"Alexander L Klibanov","doi":"10.1007/978-3-032-15314-2_10","DOIUrl":"10.1007/978-3-032-15314-2_10","url":null,"abstract":"<p><p>Molecular ultrasound imaging was proposed more than two decades ago. The ultrasound contrast agents used for selective targeting of vascular biomarkers of disease are formulated as gas microbubbles surrounded by a thin shell.Microbubbles are decorated by the ligands that specifically bind to the biomarkers of disease overexpressed on the surface of vascular endothelium. The microbubble gas core is most often a poorly soluble perfluorinated gas (preferably C<sub>4</sub>F<sub>10</sub> as the least soluble), to assure circulation lifetime for at least several minutes. The gas from circulating bubbles is exhaled via the lungs; bubbles collapse and lose echogenicity. As the circulating bubbles clear from the bloodstream, adherent targeted bubbles are still retained in the tumor microvasculature and provide strong acoustic backscatter and ultrasound detection capability. A critical feature that enables ultrasound use in molecular imaging, specifically in the oncology setting, is the detection sensitivity, already enabled in medical imaging equipment. Individual microbubbles, with sub-picogram mass, can be visualized in real time, many cm deep in the body. This chapter discusses microbubble preparation and attachment of targeting ligands to the microbubble shell. The logic of the performance of ultrasound molecular imaging is discussed, followed by an assessment of a number of imaging tools.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"224 ","pages":"343-355"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147965024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Future Challenges of Molecular Imaging in Oncology.","authors":"Otmar Schober, Fabian Kiessling, Jürgen Debus","doi":"10.1007/978-3-032-21415-7_18","DOIUrl":"10.1007/978-3-032-21415-7_18","url":null,"abstract":"<p><p>Molecular imaging in oncology sits at the intersection of science, technology, and patient care, offering powerful tools for advancing diagnosis and personalized treatment. Future developments are driven by scientific ambition and clinical need, aiming to improve patient outcomes by translating complex biological insights into practical applications. Key opportunities include improved biomarkers, higher-resolution imaging, and multimodal integration. Chronobiology adds the time dimension, enabling dynamic monitoring of tumor processes, though challenges remain in quantifying kinetics due to technical and procedural constraints. Risks include tool-driven research, where technology dictates clinical questions, rather than vice versa. This calls for needs-based development guided by clear scientific objectives. AI, especially deep learning, promises integration of complex datasets, though ethical and professional responsibility in its use is critical. Barriers include high costs, limited reimbursement, regulatory hurdles, and logistical challenges. Clinical translation is often delayed by insufficient funding and a lack of standardized protocols. Despite these, real-world clinical benefit is increasingly influencing adoption. Interdisciplinary collaboration is essential, supported by translational centers and data-sharing networks. Ultimately, molecular imaging enhances the continuum between anatomical imaging, histology, and molecular profiling. It enables dynamic, noninvasive assessment of cancer biology, supporting adaptive and personalized treatment strategies and reinforcing its role in precision oncology.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"225 ","pages":"1081-1088"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147983754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Stephanie Schipmann, Michael Schwake, Walter Stummer
{"title":"Image-Guided Brain Tumor Surgery.","authors":"Stephanie Schipmann, Michael Schwake, Walter Stummer","doi":"10.1007/978-3-032-21415-7_11","DOIUrl":"10.1007/978-3-032-21415-7_11","url":null,"abstract":"<p><p>In neurosurgery, the extent of resection (EOR) is crucial, particularly in the management of malignant gliomas. These tumors are characterized by a diffuse infiltration into the surrounding brain parenchyma. Delineation between tumor and normal brain parenchyma can therefore often be challenging. In recent years, researchers and surgeons have developed and implemented various techniques to improve the visualization of tumors during surgery. This chapter explores current approaches to intraoperative imaging in brain tumor surgery, comprising conventional techniques such as neuronavigation, techniques using fluorescence guided surgery, and further highly precise developments such as targeted-fluorescence, Raman spectroscopy, and hyperspectral imaging. These innovative methods aim to enhance surgeons' ability to identify and remove tumor tissue more effectively, potentially improving patient outcomes.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"225 ","pages":"881-909"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147983768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Caner Civan, Wolfgang P Fendler, Bernd J Krause, Ken Herrmann
{"title":"FDG PET Hybrid Imaging.","authors":"Caner Civan, Wolfgang P Fendler, Bernd J Krause, Ken Herrmann","doi":"10.1007/978-3-032-21415-7_3","DOIUrl":"10.1007/978-3-032-21415-7_3","url":null,"abstract":"<p><p>Molecular imaging with positron emission tomography (PET) using tumour-targeting radiopharmaceuticals has gained widespread acceptance in oncology with numerous clinical applications. The hybrid imaging modality PET/CT (computed tomography) allows simultaneous assessment of both molecular and morphologic information. Therefore, PET/CT represents an efficient tool for comprehensive whole-body staging and restaging within single imaging session. In oncology, the glucose analogue 18-F-fluorodeoxyglucose (FDG) is the most widely used PET/CT radiopharmaceutical in clinical routine. FDG PET and FDG PET/CT have been used for staging and restaging of tumour patients in numerous studies. This chapter will discuss the applications and primary indications of FDG PET/CT in oncology with particular emphasis on lung cancer, lymphoma, head and neck cancer, melanoma and breast cancer, among other tumour entities. A review of the current literature is presented, focusing on primary diagnosis, staging and detection of recurrent disease. Besides its established role in diagnosis, staging and restaging of disease in oncology, there is growing evidence that FDG PET/CT is valuable in assessment of therapy response, potentially influencing treatment planning and therapeutic decision making by evaluating tumour control, which will also be discussed in this chapter.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"225 ","pages":"673-719"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147983772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Teresa Lemainque, Nicolas Gross-Weege, Volkmar Schulz
{"title":"(Hybrid) SPECT and PET Technologies.","authors":"Teresa Lemainque, Nicolas Gross-Weege, Volkmar Schulz","doi":"10.1007/978-3-032-15314-2_3","DOIUrl":"10.1007/978-3-032-15314-2_3","url":null,"abstract":"<p><p>SPECT and PET are nuclear tomographic imaging modalities that visualize functional information based on the accumulation of radioactive tracer molecules. However, SPECT and PET lack anatomical information, which has motivated their combination with an anatomical imaging modality such as CT or MRI. This chapter begins with an overview of the fundamental physics of SPECT and PET, followed by a presentation of the respective detector technologies, including detection requirements, principles, and different detector concepts. The reader is subsequently provided with an introduction to hybrid imaging concepts, before a dedicated section presents the challenges that arise when hybridizing SPECT or PET with MRI, namely, mutual distortions of the different electromagnetic fields in MRI on the nuclear imaging system and vice versa, and MR-based attenuation correction. The chapter then gives an overview about current hybrid imaging systems of both clinical and preclinical kinds and recent technological developments such as total body PET-CT, before describing the role of artificial intelligence in hybrid imaging. Finally, future developments in hybrid SPECT and PET technology are discussed.</p>","PeriodicalId":39880,"journal":{"name":"Recent Results in Cancer Research","volume":"224 ","pages":"87-114"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147964916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
