MAM-E: Mammographic Synthetic Image Generation with Diffusion Models.

Generative models are used as an alternative data augmentation technique to alleviate the data scarcity problem faced in the medical imaging field. Diffusion models have gathered special attention due to their innovative generation approach, the high quality of the generated images, and their relatively less complex training process compared with Generative Adversarial Networks. Still, the implementation of such models in the medical domain remains at an early stage. In this work, we propose exploring the use of diffusion models for the generation of high-quality, full-field digital mammograms using state-of-the-art conditional diffusion pipelines. Additionally, we propose using stable diffusion models for the inpainting of synthetic mass-like lesions on healthy mammograms. We introduce MAM-E, a pipeline of generative models for high-quality mammography synthesis controlled by a text prompt and capable of generating synthetic mass-like lesions on specific regions of the breast. Finally, we provide quantitative and qualitative assessment of the generated images and easy-to-use graphical user interfaces for mammography synthesis.

Teaching radiology in integrated educational programs.

Radiology is a medical discipline, an area of transversal knowledge integrated into any clinical situation. The optimal training of learning knowledge, skills and aptitudes in Radiology in the Degree in Medicine requires the integration of any imaging modality in the different areas of knowledge; from the basic subjects to any clinical subject of the Degree. This article describes the integration of Radiology teaching into the curriculum throughout the Medicine Degree at the University of Girona (UdG), describing the different radiology teaching activities that are taught. The specific activities of the subject "Radiology" are detailed; through workshops, seminars, practices, interactive computer game; and describing the characteristics of the main teaching methodological activity of the UdG, Problem-Based Learning.

La enseñanza de la radiología en los programas docentes integrados / Teaching Radiology in integrated educational programs

La radiología es una disciplina médica, un área de conocimiento transversal integrada en cualquier situación clínica. El aprendizaje óptimo del conocimiento, habilidades y aptitudes en radiología en el Grado en Medicina requiere la integración de cualquier modalidad de imagen en las distintas áreas del conocimiento: desde las asignaturas básicas hasta cualquier asignatura clínica del grado. El presente artículo describe la integración de la docencia en radiología del plan de estudios en todo el grado de medicina de la Universidad de Girona (UdG), describiendo las distintas actividades docentes de radiología que se imparten en las distintas asignaturas; desde primero a sexto curso. Se detallan las actividades específicas de la asignatura de «radiología», incluyendo talleres, seminarios, prácticas, juego de ordenador interactivo, y describiendo las características de la actividad metodológica docente principal de la UdG, el aprendizaje basado en problemas.(AU)

Radiology is a medical discipline, an area of transversal knowledge integrated into any clinical situation. The optimal training of learning knowledge, skills and aptitudes in Radiology in the Degree in Medicine requires the integration of any imaging modality in the different areas of knowledge; from the basic subjects to any clinical subject of the Degree. This article describes the integration of Radiology teaching into the curriculum throughout the Medicine Degree at the University of Girona (UdG), describing the different radiology teaching activities that are taught. The specific activities of the subject «Radiology» are detailed; through workshops, seminars, practices, interactive computer game; and describing the characteristics of the main teaching methodological activity of the UdG, Problem-Based Learning.(AU)

How Imaging Advances Are Defining the Future of Precision Radiation Therapy.

Radiation therapy is fundamental in the treatment of cancer. Imaging has always played a central role in radiation oncology. Integrating imaging technology into irradiation devices has increased the precision and accuracy of dose delivery and decreased the toxic effects of the treatment. Although CT has become the standard imaging modality in radiation therapy, the development of recently introduced next-generation imaging techniques has improved diagnostic and therapeutic decision making in radiation oncology. Functional and molecular imaging techniques, as well as other advanced imaging modalities such as SPECT, yield information about the anatomic and biologic characteristics of tumors for the radiation therapy workflow. In clinical practice, they can be useful for characterizing tumor phenotypes, delineating volumes, planning treatment, determining patients' prognoses, predicting toxic effects, assessing responses to therapy, and detecting tumor relapse. Next-generation imaging can enable personalization of radiation therapy based on a greater understanding of tumor biologic factors. It can be used to map tumor characteristics, such as metabolic pathways, vascularity, cellular proliferation, and hypoxia, that are known to define tumor phenotype. It can also be used to consider tumor heterogeneity by highlighting areas at risk for radiation resistance for focused biologic dose escalation, which can impact the radiation planning process and patient outcomes. The authors review the possible contributions of next-generation imaging to the treatment of patients undergoing radiation therapy. In addition, the possible roles of radio(geno)mics in radiation therapy, the limitations of these techniques, and hurdles in introducing them into clinical practice are discussed. ©RSNA, 2024 Test Your Knowledge questions for this article are available in the supplemental material.

Soft tissue tumor imaging in adults: European Society of Musculoskeletal Radiology-Guidelines 2023-overview, and primary local imaging: how and where?

OBJECTIVES: Early, accurate diagnosis is crucial for the prognosis of patients with soft tissue sarcomas. To this end, standardization of imaging algorithms, technical requirements, and reporting is therefore a prerequisite. Since the first European Society of Musculoskeletal Radiology (ESSR) consensus in 2015, technical achievements, further insights into specific entities, and the revised WHO-classification (2020) and AJCC staging system (2017) made an update necessary. The guidelines are intended to support radiologists in their decision-making and contribute to interdisciplinary tumor board discussions. MATERIALS AND METHODS: A validated Delphi method based on peer-reviewed literature was used to derive consensus among a panel of 46 specialized musculoskeletal radiologists from 12 European countries. Statements were scored online by level of agreement (0 to 10) during two iterative rounds. Either "group consensus," "group agreement," or "lack of agreement" was achieved. RESULTS: Eight sections were defined that finally contained 145 statements with comments. Overall, group consensus was reached in 95.9%, and group agreement in 4.1%. This communication contains the first part consisting of the imaging algorithm for suspected soft tissue tumors, methods for local imaging, and the role of tumor centers. CONCLUSION: Ultrasound represents the initial triage imaging modality for accessible and small tumors. MRI is the modality of choice for the characterization and local staging of most soft tissue tumors. CT is indicated in special situations. In suspicious or likely malignant tumors, a specialist tumor center should be contacted for referral or teleradiologic second opinion. This should be done before performing a biopsy, without exception. CLINICAL RELEVANCE: The updated ESSR soft tissue tumor imaging guidelines aim to provide best practice expert consensus for standardized imaging, to support radiologists in their decision-making, and to improve examination comparability both in individual patients and in future studies on individualized strategies. KEY POINTS: • Ultrasound remains the best initial triage imaging modality for accessible and small suspected soft tissue tumors. • MRI is the modality of choice for the characterization and local staging of soft tissue tumors in most cases; CT is indicated in special situations. Suspicious or likely malignant tumors should undergo biopsy. • In patients with large, indeterminate or suspicious tumors, a tumor reference center should be contacted for referral or teleradiologic second opinion; this must be done before a biopsy.

How to do and evaluate DWI and DCE-MRI sequences for diabetic foot assessment.

MRI evaluation of the diabetic foot is still a challenge not only from an interpretative but also from a technical point of view. The incorporation of advanced sequences such as diffusion-weighted imaging (DWI) and dynamic contrast-enhanced (DCE) MRI into standard protocols for diabetic foot assessment could aid radiologists in differentiating between neuropathic osteoarthropathy (Charcot's foot) and osteomyelitis. This distinction is crucial as both conditions can coexist in diabetic patients, and they require markedly different clinical management and have distinct prognoses. Over the past decade, several studies have explored the effectiveness of DWI and dynamic contrast-enhanced MRI (DCE-MRI) in distinguishing between septic and reactive bone marrow, as well as soft tissue involvement in diabetic patients, yielding promising results. DWI, without the need for exogenous contrast, can provide insights into the cellularity of bone marrow and soft tissues. DCE-MRI allows for a more precise evaluation of soft tissue and bone marrow perfusion compared to conventional post-gadolinium imaging. The data obtained from these sequences will complement the traditional MRI approach in assessing the diabetic foot. The objective of this review is to familiarize readers with the fundamental concepts of DWI and DCE-MRI, including technical adjustments and practical tips for image interpretation in diabetic foot cases.

Plasma acylcarnitines and gut-derived aromatic amino acids as sex-specific hub metabolites of the human aging metabolome.

Aging biology entails a cell/tissue deregulated metabolism that affects all levels of biological organization. Therefore, the application of "omic" techniques that are closer to phenotype, such as metabolomics, to the study of the aging process should be a turning point in the definition of cellular processes involved. The main objective of the present study was to describe the changes in plasma metabolome associated with biological aging and the role of sex in the metabolic regulation during aging. A high-throughput untargeted metabolomic analysis was applied in plasma samples to detect hub metabolites and biomarkers of aging incorporating a sex/gender perspective. A cohort of 1030 healthy human adults (45.9% females, and 54.1% males) from 50 to 98 years of age was used. Results were validated using two independent cohorts (1: n = 146, 53% females, 30-100 years old; 2: n = 68, 70% females, 19-107 years old). Metabolites related to lipid and aromatic amino acid (AAA) metabolisms arose as the main metabolic pathways affected by age, with a high influence of sex. Globally, we describe changes in bioenergetic pathways that point to a decrease in mitochondrial ß-oxidation and an accumulation of unsaturated fatty acids and acylcarnitines that could be responsible for the increment of oxidative damage and inflammation characteristic of this physiological process. Furthermore, we describe for the first time the importance of gut-derived AAA catabolites in the aging process describing novel biomarkers that could contribute to better understand this physiological process but also age-related diseases.

Current and Advanced Applications of Gadoxetic Acid-enhanced MRI in Hepatobiliary Disorders.

Gadoxetic acid is an MRI contrast agent that has specific applications in the study of hepatobiliary disease. After being distributed in the vascular and extravascular spaces during the dynamic phase, gadoxetic acid is progressively taken up by hepatocytes and excreted to the bile ducts during the hepatobiliary phase. The information derived from the enhancement characteristics during dynamic and hepatobiliary phases is particularly relevant in the detection and characterization of focal liver lesions and in the evaluation of the structure and function of the liver and biliary system. The use of new MRI sequences and advanced imaging techniques (eg, relaxometry, multiparametric imaging, and analysis of heterogeneity), the introduction of artificial intelligence, and the development of biomarkers and radiomic and radiogenomic tools based on gadoxetic acid-enhanced MRI findings will play an important role in the future in assessing liver function, chronic liver disease, and focal liver lesions; in studying biliary pathologic conditions; and in predicting treatment responses and prognosis. © RSNA, 2023 Quiz questions for this article are available in the supplemental material.

The role of Artificial intelligence in the assessment of the spine and spinal cord.

Artificial intelligence (AI) application development is underway in all areas of radiology where many promising tools are focused on the spine and spinal cord. In the past decade, multiple spine AI algorithms have been created based on radiographs, computed tomography, and magnetic resonance imaging. These algorithms have wide-ranging purposes including automatic labeling of vertebral levels, automated description of disc degenerative changes, detection and classification of spine trauma, identification of osseous lesions, and the assessment of cord pathology. The overarching goals for these algorithms include improved patient throughput, reducing radiologist workload burden, and improving diagnostic accuracy. There are several pre-requisite tasks required in order to achieve these goals, such as automatic image segmentation, facilitating image acquisition and postprocessing. In this narrative review, we discuss some of the important imaging AI solutions that have been developed for the assessment of the spine and spinal cord. We focus on their practical applications and briefly discuss some key requirements for the successful integration of these tools into practice. The potential impact of AI in the imaging assessment of the spine and cord is vast and promises to provide broad reaching improvements for clinicians, radiologists, and patients alike.

Usefulness of balanced SSFP sequence in robot-assisted MRI-guided prostate biopsy: Beyond scouting.

OBJECTIVES: To determine whether bSSFP images are useful for visualizing prostatic lesionsin MRI-guided in-bore transrectal biopsy. METHODS: This retrospective studyincluded 67 men witha single suspected cancer on MRI (PI-RADS 2.1 category ≥ 3) who underwent in-bore transrectal MRI-guided biopsy. Two uroradiologists independently rated lesion conspicuity on a 3-point scale (1:non-visible, 2:slightly visible, 3:clearly visible) on T2WI, DWI, and balanced SSFP.We used measures of frequency to compare lesion conspicuity in 3 sequences. We used Cohen's kappa to assess inter-rater reliability. RESULTS: Lesions were rated (1) non-visible in 18 % (12/67) of T2WI, 5 % (3/67) of DWI, and 10 % (7/67) of balanced SSFP images, (2) slightly visible in 56 % (37/67) on T2WI, 13 % (9/67) on DWI, and 48 % (32/67) on bSSFP, and (3) clearly visible in 27 %(18/67) on T2WI, 82 % (55/67) on DWI, and 42 % (28/67) on bSSFP. Lesions classified as prostate cancer at histology were slightly-clearly visible in 85 % (41/48) on T2WI, 100 % (48/48) on DWI, and 94 % (45/48) on bSSFP. Lesions classified as PI-RADS ≥ 4 were visible in 87 % (47/54) of T2WI, 100 % (54/54) of DWI, and 93 % (50/54) of bSSFP. Gleason ≥ 3 + 4 lesions were visible in 85 % (37/43) of T2WI, 100 % (43/43) of DWI, and 95 % (41/43) of bSSFP. Inter-rater agreement was excellent for T2WI (k = 0.97) and bSSFP (k = 0.94), and good for DWI (k = 0.75). CONCLUSION: Balanced SSFP is useful for visualizing prostatic lesions. Replacing T2WI with balanced SSFP can reduce the duration of in-bore transrectal MRI-guided biopsy.

Considerations for artificial intelligence clinical impact in oncologic imaging: an AI4HI position paper.

To achieve clinical impact in daily oncological practice, emerging AI-based cancer imaging research needs to have clearly defined medical focus, AI methods, and outcomes to be estimated. AI-supported cancer imaging should predict major relevant clinical endpoints, aiming to extract associations and draw inferences in a fair, robust, and trustworthy way. AI-assisted solutions as medical devices, developed using multicenter heterogeneous datasets, should be targeted to have an impact on the clinical care pathway. When designing an AI-based research study in oncologic imaging, ensuring clinical impact in AI solutions requires careful consideration of key aspects, including target population selection, sample size definition, standards, and common data elements utilization, balanced dataset splitting, appropriate validation methodology, adequate ground truth, and careful selection of clinical endpoints. Endpoints may be pathology hallmarks, disease behavior, treatment response, or patient prognosis. Ensuring ethical, safety, and privacy considerations are also mandatory before clinical validation is performed. The Artificial Intelligence for Health Imaging (AI4HI) Clinical Working Group has discussed and present in this paper some indicative Machine Learning (ML) enabled decision-support solutions currently under research in the AI4HI projects, as well as the main considerations and requirements that AI solutions should have from a clinical perspective, which can be adopted into clinical practice. If effectively designed, implemented, and validated, cancer imaging AI-supported tools will have the potential to revolutionize the field of precision medicine in oncology.

The effect of external stimulation on functional networks in the aging healthy human brain.

Understanding the brain changes occurring during aging can provide new insights for developing treatments that alleviate or reverse cognitive decline. Neurostimulation techniques have emerged as potential treatments for brain disorders and to improve cognitive functions. Nevertheless, given the ethical restrictions of neurostimulation approaches, in silico perturbation protocols based on causal whole-brain models are fundamental to gaining a mechanistic understanding of brain dynamics. Furthermore, this strategy could serve to identify neurophysiological biomarkers differentiating between age groups through an exhaustive exploration of the global effect of all possible local perturbations. Here, we used a resting-state fMRI dataset divided into middle-aged (N =310, <65 years) and older adults (N =310, $\geq $65) to characterize brain states in each group as a probabilistic metastable substate (PMS) space. We showed that the older group exhibited a reduced capability to access a metastable substate that overlaps with the rich club. Then, we fitted the PMS to a whole-brain model and applied in silico stimulations in each node to force transitions from the brain states of the older- to the middle-aged group. We found that the precuneus was the best stimulation target. Overall, these findings could have important implications for designing neurostimulation interventions for reversing the effects of aging on whole-brain dynamics.

The challenge of prostate biopsy guidance in the era of mpMRI detected lesion: ultrasound-guided versus in-bore biopsy.

The current recommendation in patients with a clinical suspicion for prostate cancer is to perform systematic biopsies extended with targeted biopsies, depending on mpMRI results. Following a positive mpMRI [i.e. Prostate Imaging Reporting and Data System (PI-RADS) ≥3], three targeted biopsy approaches can be performed: visual registration of the MRI images with real-time ultrasound imaging; software-assisted fusion of the MRI images and real-time ultrasound images, and in-bore biopsy within the MR scanner. This collaborative review discusses the advantages and disadvantages of each targeting approach and elaborates on future developments. Cancer detection rates seem to mostly depend on practitioner experience and selection criteria (biopsy naïve, previous negative biopsy, prostate-specific antigen (PSA) selection criteria, presence of a lesion on MRI), and to a lesser extent dependent on biopsy technique. There is no clear consensus on the optimal targeting approach. The choice of technique depends on local experience and availability of equipment, individual patient characteristics, and onsite cost-benefit analysis. Innovations in imaging techniques and software-based algorithms may lead to further improvements in this field.

A U-Net Ensemble for breast lesion segmentation in DCE MRI.

Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) has been recognized as an effective tool for Breast Cancer (BC) diagnosis. Automatic BC analysis from DCE-MRI depends on features extracted particularly from lesions, hence, lesions need to be accurately segmented as a prior step. Due to the time and experience required to manually segment lesions in 4D DCE-MRI, automating this task is expected to reduce the workload, reduce observer variability and improve diagnostic accuracy. In this paper we propose an automated method for breast lesion segmentation from DCE-MRI based on a U-Net framework. The contributions of this work are the proposal of a modified U-Net architecture and the analysis of the input DCE information. In that sense, we propose the use of an ensemble method combining three U-Net models, each using a different input combination, outperforming all individual methods and other existing approaches. For evaluation, we use a subset of 46 cases from the TCGA-BRCA dataset, a challenging and publicly available dataset not reported to date for this task. Due to the incomplete annotations provided, we complement them with the help of a radiologist in order to include secondary lesions that were not originally segmented. The proposed ensemble method obtains a mean Dice Similarity Coefficient (DSC) of 0.680 (0.802 for main lesions) which outperforms state-of-the art methods using the same dataset, demonstrating the effectiveness of our method considering the complexity of the dataset.

International Multi-Site Initiative to Develop an MRI-Inclusive Nomogram for Side-Specific Prediction of Extraprostatic Extension of Prostate Cancer.

BACKGROUND: To develop an international, multi-site nomogram for side-specific prediction of extraprostatic extension (EPE) of prostate cancer based on clinical, biopsy, and magnetic resonance imaging- (MRI) derived data. METHODS: Ten institutions from the USA and Europe contributed clinical and side-specific biopsy and MRI variables of consecutive patients who underwent prostatectomy. A logistic regression model was used to develop a nomogram for predicting side-specific EPE on prostatectomy specimens. The performance of the statistical model was evaluated by bootstrap resampling and cross validation and compared with the performance of benchmark models that do not incorporate MRI findings. RESULTS: Data from 840 patients were analyzed; pathologic EPE was found in 320/840 (31.8%). The nomogram model included patient age, prostate-specific antigen density, side-specific biopsy data (i.e., Gleason grade group, percent positive cores, tumor extent), and side-specific MRI features (i.e., presence of a PI-RADSv2 4 or 5 lesion, level of suspicion for EPE, length of capsular contact). The area under the receiver operating characteristic curve of the new, MRI-inclusive model (0.828, 95% confidence limits: 0.805, 0.852) was significantly higher than that of any of the benchmark models (p < 0.001 for all). CONCLUSIONS: In an international, multi-site study, we developed an MRI-inclusive nomogram for the side-specific prediction of EPE of prostate cancer that demonstrated significantly greater accuracy than clinical benchmark models.

Assessing the Accuracy and Reproducibility of PARIETAL: A Deep Learning Brain Extraction Algorithm.

BACKGROUND: Manual brain extraction from magnetic resonance (MR) images is time-consuming and prone to intra- and inter-rater variability. Several automated approaches have been developed to alleviate these constraints, including deep learning pipelines. However, these methods tend to reduce their performance in unseen magnetic resonance imaging (MRI) scanner vendors and different imaging protocols. PURPOSE: To present and evaluate for clinical use PARIETAL, a pre-trained deep learning brain extraction method. We compare its reproducibility in a scan/rescan analysis and its robustness among scanners of different manufacturers. STUDY TYPE: Retrospective. POPULATION: Twenty-one subjects (12 women) with age range 22-48 years acquired using three different MRI scanner machines including scan/rescan in each of them. FIELD STRENGTH/SEQUENCE: T1-weighted images acquired in a 3-T Siemens with magnetization prepared rapid gradient-echo sequence and two 1.5 T scanners, Philips and GE, with spin-echo and spoiled gradient-recalled (SPGR) sequences, respectively. ASSESSMENT: Analysis of the intracranial cavity volumes obtained for each subject on the three different scanners and the scan/rescan acquisitions. STATISTICAL TESTS: Parametric permutation tests of the differences in volumes to rank and statistically evaluate the performance of PARIETAL compared to state-of-the-art methods. RESULTS: The mean absolute intracranial volume differences obtained by PARIETAL in the scan/rescan analysis were 1.88 mL, 3.91 mL, and 4.71 mL for Siemens, GE, and Philips scanners, respectively. PARIETAL was the best-ranked method on Siemens and GE scanners, while decreasing to Rank 2 on the Philips images. Intracranial differences for the same subject between scanners were 5.46 mL, 27.16 mL, and 30.44 mL for GE/Philips, Siemens/Philips, and Siemens/GE comparison, respectively. The permutation tests revealed that PARIETAL was always in Rank 1, obtaining the most similar volumetric results between scanners. DATA CONCLUSION: PARIETAL accurately segments the brain and it generalizes to images acquired at different sites without the need of training or fine-tuning it again. PARIETAL is publicly available. LEVEL OF EVIDENCE: 2 TECHNICAL EFFICACY STAGE: 2.

Obesity-associated deficits in inhibitory control are phenocopied to mice through gut microbiota changes in one-carbon and aromatic amino acids metabolic pathways.

BACKGROUND: Inhibitory control (IC) is critical to keep long-term goals in everyday life. Bidirectional relationships between IC deficits and obesity are behind unhealthy eating and physical exercise habits. METHODS: We studied gut microbiome composition and functionality, and plasma and faecal metabolomics in association with cognitive tests evaluating inhibitory control (Stroop test) and brain structure in a discovery (n=156), both cross-sectionally and longitudinally, and in an independent replication cohort (n=970). Faecal microbiota transplantation (FMT) in mice evaluated the impact on reversal learning and medial prefrontal cortex (mPFC) transcriptomics. RESULTS: An interplay among IC, brain structure (in humans) and mPFC transcriptomics (in mice), plasma/faecal metabolomics and the gut metagenome was found. Obesity-dependent alterations in one-carbon metabolism, tryptophan and histidine pathways were associated with IC in the two independent cohorts. Bacterial functions linked to one-carbon metabolism (thyX,dut, exodeoxyribonuclease V), and the anterior cingulate cortex volume were associated with IC, cross-sectionally and longitudinally. FMT from individuals with obesity led to alterations in mice reversal learning. In an independent FMT experiment, human donor's bacterial functions related to IC deficits were associated with mPFC expression of one-carbon metabolism-related genes of recipient's mice. CONCLUSION: These results highlight the importance of targeting obesity-related impulsive behaviour through the induction of gut microbiota shifts.

Whole-Brain Dynamics in Aging: Disruptions in Functional Connectivity and the Role of the Rich Club.

Normal aging causes disruptions in the brain that can lead to cognitive decline. Resting-state functional magnetic resonance imaging studies have found significant age-related alterations in functional connectivity across various networks. Nevertheless, most of the studies have focused mainly on static functional connectivity. Studying the dynamics of resting-state brain activity across the whole-brain functional network can provide a better characterization of age-related changes. Here, we employed two data-driven whole-brain approaches based on the phase synchronization of blood-oxygen-level-dependent signals to analyze resting-state fMRI data from 620 subjects divided into two groups (middle-age group (n = 310); age range, 50-64 years versus older group (n = 310); age range, 65-91 years). Applying the intrinsic-ignition framework to assess the effect of spontaneous local activation events on local-global integration, we found that the older group showed higher intrinsic ignition across the whole-brain functional network, but lower metastability. Using Leading Eigenvector Dynamics Analysis, we found that the older group showed reduced ability to access a metastable substate that closely overlaps with the so-called rich club. These findings suggest that functional whole-brain dynamics are altered in aging, probably due to a deficiency in a metastable substate that is key for efficient global communication in the brain.

Assessing Immunotherapy with Functional and Molecular Imaging and Radiomics.

Immunotherapy is changing the treatment paradigm for cancer and has introduced new challenges in medical imaging. Because not all patients benefit from immunotherapy, pretreatment imaging should be performed to identify not only prognostic factors but also factors that allow prediction of response to immunotherapy. Follow-up studies must allow detection of nonresponders, without confusion of pseudoprogression with real progression to prevent premature discontinuation of treatment that can benefit the patient. Conventional imaging techniques and classic tumor response criteria are limited for the evaluation of the unusual patterns of response that arise from the specific mechanisms of action of immunotherapy, so advanced imaging methods must be developed to overcome these shortcomings. The authors present the fundamentals of the tumor immune microenvironment and immunotherapy and how they influence imaging findings. They also discuss advances in functional and molecular imaging techniques for the assessment of immunotherapy in clinical practice, including their use to characterize immune phenotypes, assess patient prognosis and response to therapy, and evaluate immune-related adverse events. Finally, the development of radiomics and radiogenomics in these therapies and the future role of imaging biomarkers for immunotherapy are discussed. Online supplemental material is available for this article. ©RSNA, 2020.