Immunotherapy represents a significant breakthrough in modern oncology, being successfully used in the treatment of various malignant neoplasms including those at advanced metastatic stages. This approach has demonstrates impressive therapeutic outcomes in the management of cancer; however, in certain cases, it may lead to the development of atypical reactions known as immune-related adverse events (irAEs). Toxic injury to the spinal cord and peripheral nervous system resulting from complications of antitumor therapy constitutes a serious clinical challenge. Among particularly relevant manifestations are demyelinating disorders, myelitis, Guillain-Barré syndrome, cranial neuropathies, plexopathies, and myositis. Timely detection of these complications using imaging modalities is essential for improving prognosis and clinical outcomes in patients receiving immunotherapy.

Radiation therapy plays an essential role in the treatment of oncological diseases; however, its application is associated with the risk of damage to surrounding healthy tissues, particularly the gastrointestinal tract and parenchymal organs of the abdominal cavity. A significant number of patients receiving radical radiation therapy to the abdomen and pelvis develop acute intestinal toxicity. Delayed complications, such as chronic enteropathy, radiation colitis, liver fibrosis, and esophageal strictures, can significantly reduce the quality of life of such patients and may manifest months or even years after treatment completion. This article provides a detailed review of the epidemiology, pathogenesis, and classification of post-radiation injuries of the abdominal and pelvic organs, as well as the key aspects of radiologic sings of these changes using radiography, computed tomography, and magnetic resonance imaging. Particular attention is given to differential diagnosis and modern imaging techniques that enable timely detection and evaluation of the severity of these complications.

Adverse events affecting the central and peripheral nervous systems of associated with antitumor therapy, including radiation therapy, immunotherapy, and chemotherapy, remain a complex diagnostic and clinical challenge. Magnetic resonance imaging (MRI) is the main tool for assessing central neurotoxicity, allowing prevention of tumor progression, infectious and drug-induced changes, and vascular lesions. This article reviews current data on the pathogenesis, clinical manifestations, and typical MRI patterns of the main cerebral complications of cancer treatment.

Chemotherapy remains a cornerstone in the treatment of oncologic diseases, evolving from traditional cytotoxic agents to modern targeted and immunotherapeutic strategies. Despite the high efficacy of current antitumor therapies, their use is frequently associated with a high risk of adverse effects resulting from systemic and local impacts on various organs and tissues. The liver, pancreas, and biliary tract are particularly susceptible to toxic injury due to their critical metabolic functions and heightened sensitivity to microenvironmental changes. Imaging modalities, such as ultrasonography, computed tomography, and magnetic resonance imaging, play a key role in the detection and monitoring of treatment-related complications. These techniques enable timely identification and comprehensive assessment of pathological changes within the hepatobiliary system and pancreas. Typical imaging manifestations associated with antitumor therapy include sinusoidal obstruction syndrome, hepatic steatosis, pseudocirrhosis, drug-induced hepatitis, pancreatitis, pancreatic atrophy, biliary fibrosis, and cholangitis.

Neurological toxicity is a rare but highly serious – and in some cases fatal – complication of cancer therapy. Hypophysitis is a manifestation of this spectrum of adverse effects, being not a classical complication. It is typically associated with the use of antiCTLA-4 agents. Magnetic resonance imaging (MRI) of the sellar region plays a key role in the diagnosis of this condition, enabling the detection of pituitary enlargement, structural alterations, and evaluation of disease dynamics during therapy.

Systemic anticancer therapy is a cornerstone of modern oncology, offering hope to millions of patients worldwide. Modern anticancer agents are associated with a broad spectrum of adverse effects, ranging from mild symptoms to life-threatening complications. Deterioration in a patient’s clinical condition is not always attributable exclusively to drug toxicity; it may also result from progression of the primary tumor, the development of secondary infections, or exacerbation of comorbid diseases. Contrast-enhanced magnetic resonance imaging plays a particularly important role in the accurate diagnosis of cardiotoxicity. Early recognition of complications and timely initiation of appropriate therapy can substantially improve the quality of life and increase the probability of favorable outcomes in cancer patients.

Timely detection of malignant neoplasms, competent patient referral, and determination of an optimal treatment strategy remain among the most relevant issues of modern oncology. An analysis of international and domestic literature yielded the following statistics: in 2022, approximately 20 million new cancer cases and 9.7 million cancer-related deaths were recorded worldwide. In Russia, over 4.4 million patients are currently being oncological follow-up, with recent years showing a 10.5% increase in the proportion of patients observed for more than five years. A promising approach to improving the quality of tumor diagnostics is the implementation of artificial intelligence (AI) in medical imaging. One of the principal challenges in the development and training of neural network models is the acquisition of large and diverse imaging datasets, including CT series, MRI scans, and ultrasound images. The manual annotation of anatomical landmarks required to train neural networks for accurate recognition of human anatomical structures is an extremely labor-intensive but essential step in the creation of AI systems. This review analyzed recent studies by domestic and international researchers on the implementation and application of artificial intelligence (AI) in medical imaging for the diagnosis of malignant neoplasms. Studies were selected based on the following inclusion criteria: publications from 2020 to 2025, full-text literature reviews, systematic reviews, meta-analyses, original articles, and randomized controlled trials published in peer-reviewed scientific journals. Duplicates, conference abstracts, and studies lacking full text or not meeting the inclusion criteria were excluded. A total of 36 sources were included in the analysis. The review of both international and domestic literature demonstrated that AI-based systems in radiologic diagnostics of malignant neoplasms have significant potential for routine clinical use, particularly in enhancing the quality of differential diagnosis between benign and malignant lesions. Key advantages include the automation and standardization of quality control for radiographic and ultrasound images according to predefined anatomical scanning planes, as well as the ability to perform biometric measurements and detect pathognomonic features.