China
Africa
Explore chapters and articles related to this topic
Translation of Radiopharmaceuticals
Published in Michael Ljungberg, Handbook of Nuclear Medicine and Molecular Imaging for Physicists, 2022
Pedro Fragoso Costa, Latifa Rbah-Vidal, An Aerts, Fijs W.B. van Leeuwen, Margret Schottelius
Finally, in the context of precision medicine, radiomics is expected to provide a significant contribution to both clinical and translational research [49]. The construction of predictive models is based on image acquisition, computation of radiomics features, and statistical analysis, all of which are generally accepted MPE domains. All translational steps could be subject to data mining and computer aided decision-making, potentially increasing the speed and possibly the efficacy of the global process [49]. One of the key aspects for the success of radiomics workflows is the standardization of computation methods [50], emphasizing the fact that high-quality, properly designed, and transparent radiomics research should be perused by responsible researchers for whom new guidelines start to become available [51].
Radiomics and quantitative imaging
Published in Jun Deng, Lei Xing, Big Data in Radiation Oncology, 2019
Dennis Mackin, Laurence E. Court
In contrast to prior quantitative imaging approaches designed to target specific information, radiomics is a more general approach that attempts to maximize the information extracted from standard-of-care images and make it available for data mining (Gillies et al. 2015). Advances in computer hardware such as multicore computers and graphics processing units have made it possible to process thousands of images in seconds. Image processing software is widely and freely available. Further, high-quality medical images are now routine, especially in oncology. Even though these advances alone are enough to stimulate renewed interest in quantitative imaging, radiomics is more than faster quantitative imaging: radiomics aims to personalized medicine by using quantitative imaging, much like genomics aims to personalize medicine by using genetic markers. However, unlike genomics, which is limited to the information obtained at the biopsy site, radiomics can sample the entire tumor (Gillies et al. 2015). Further, radiomics has the potential to identify and quantify gene signatures expressed as intra-tumoral heterogeneity, a process referred to as radiogenomics (Rutman and Kuo 2009) (discussed in Chapter 13, “Radiogenomics”). This relationship is a central hypothesis of radiomics: imaging features can probe the phenotype of tissues, and this phenotype is related to the underlying genotype (Lambin et al. 2012).
Precision Imaging of Prostate Cancer
Published in Ayman El-Baz, Gyan Pareek, Jasjit S. Suri, Prostate Cancer Imaging, 2018
Radiomics is an emerging field for the quantification of tumor phenotypes by applying a large number of quantitative image features [113,114]. Radiomics can provide complementary and interchangeable information to improve individualized treatment selection and monitoring. Since medical imaging technology is routinely used in clinical practice worldwide, radiomics may have a high clinical impact on future patient management. The workflow of radiomics consists of three steps [113]. The first step is the acquisition of standardized images for diagnostic or planning purposes. On the images, the tumor regions are extracted by an algorithm or an experienced radiologist. Second, quantitative imaging features are extracted from the tumor regions. These features involve tumor image intensity, texture, and shape and size of the tumor. Last, all the extracted features are analyzed and selected by a model. The most informative features are identified and incorporated into predictive models for treatment outcome. Radiomics, as a high-dimensional mineable feature space, can be used for prostate cancer. Cameron et al. constructed a comprehensive radiomics feature model to detect tumorous regions using mpMRI [115]. New radiomics-driven texture feature models have been developed for the detection of prostate cancer and for the classification of prostate cancer Gleason scores by utilizing mpMRI data [116–118].
Radiomics and theranostics with molecular and metabolic probes in prostate cancer: toward a personalized approach
Published in Expert Review of Molecular Diagnostics, 2023
Luca Filippi, Luca Urso, Francesco Bianconi, Barbara Palumbo, Maria Cristina Marzola, Laura Evangelista, Orazio Schillaci
Radiomics can be defined as the extraction, from medical images, of quantitative and reproducible parameters (features) that are not easily perceived by the naked eye. The purpose of radiomics is to use such features for building prediction models that should ideally support physicians in clinical decision-making [24,25]. Put into a historical perspective, radiomics can be regarded as the latest step of an evolution process which started with qualitative, manual visual assessment of medical images – essentially based on the physician’s skills and expertise; evolved into semi-quantitative analysis (i.e. visual assessment supported by some quantitative parameters such as SUV and MTV) and terminated in completely quantitative analysis (radiomics). Radiomics relies on the assumption – strongly supported by increasing amount of evidence – that certain visual characteristics of a suspicious lesion as it appears at the imaging (such as shape and texture) are strong indicators of disease aggressiveness and predictors of survival. The ultimate task of radiomics is therefore to describe the visual appearance of a lesion through a set of features that should ideally correlate with the clinical endpoint of interest.
The predictive value of conventional MRI combined with radiomics in the immediate ablation rate of HIFU treatment for uterine fibroids
Published in International Journal of Hyperthermia, 2022
Chao Wei, Naiyu Li, Bin Shi, Chuanbin Wang, Yaoyuan Wu, Tingting Lin, Yulan Chen, Yaqiong Ge, Yongqiang Yu, Jiangning Dong
Radiomics reflects the functional state and heterogeneity of tissues by extracting and analyzing high-throughput information from conventional grayscale images. In recent years, radiomics has become widely applied in clinical research, confirming that, as a new tool, it can be an important supplement to conventional imaging. Currently, the application of radiomics for uterine fibroids is relatively limited; most applications are restricted to the differential diagnosis of different pathological types of uterine fibroids or the differentiation of atypical uterine fibroids from uterine sarcomas. Most of the methods used are relatively simple, such as histogram and texture analyses [11,12]. Preliminary results have shown that these methods have certain value in identifying cellular uterine fibroids and differentiating degenerative uterine fibroids from uterine sarcomas; thus, radiomics may have potential value in predicting the HIFU ablation rate of uterine fibroids. However, to the best of our knowledge, there have been no reports on the application of radiomics parameters for predicting the efficacy of HIFU ablation for uterine fibroids, which thus warrants further study. Therefore, based on the findings of previous studies, the principal objective of this study was to incorporate radiomics into the conventional MR model of NPVR prediction and explore its additional potential diagnostic value.
An updated review on the diagnosis and assessment of post-treatment relapse in brain metastases using PET
Published in Expert Review of Neurotherapeutics, 2022
Norbert Galldiks, Michael Wollring, Jan-Michael Werner, Michel Friedrich, Gereon R. Fink, Karl-Josef Langen, Philipp Lohmann
Radiomics is a method from the field of artificial intelligence that allows the extraction of quantitative imaging features that are not accessible by conventional visual image analysis. Importantly, radiomics can be fully automated applied to any medical imaging modality (e.g. MRI, PET, or CT), which are routinely acquired during clinical follow-up [49]. These features can be combined with clinical data (e.g. molecular markers, survival time) to generate mathematical models for radiomics analysis [49–51]. These models can be used for various clinical purposes, such as to estimate the prognosis, predict molecular biomarkers non-invasively, or evaluate post-treatment relapse. Therefore, radiomics provides additional diagnostic information with great potential to support clinical decision-making, especially in combination with other clinical parameters.