Artificial intelligence (AI), a field of research in which computers are applied to mimic humans, is continuously expanding and influencing many aspects of our lives. From electric cars to search motors, AI helps us manage our daily lives by simplifying functions and activities that would be more complex otherwise. Even in the medical field, and specifically in oncology, many studies in recent years have highlighted the possible helping role that AI could play in clinical and therapeutic patient management. In specific contexts, clinical decisions are supported by “intelligent” machines and the development of specific softwares that assist the specialist in the management of the oncology patient. Melanoma, a highly heterogeneous disease influenced by several genetic and environmental factors, to date is still difficult to manage clinically in its advanced stages. Therapies often fail, due to the establishment of intrinsic or secondary resistance, making clinical decisions complex. In this sense, although much work still needs to be conducted, numerous evidence shows that AI (through the processing of large available data) could positively influence the management of the patient with advanced melanoma, helping the clinician in the most favorable therapeutic choice and avoiding unnecessary treatments that are sure to fail. In this review, the most recent applications of AI in melanoma will be described, focusing especially on the possible finding of this field in the management of drug treatments.

Lung tumors are often associated with a poor prognosis although different schedules and treatment modalities have been extensively tested in the clinical practice. The complexity of this disease and the use of combined therapeutic approaches have been investigated and the use of high dose-rates is emerging as effective strategy. Technological improvements of clinical linear accelerators allow combining high dose-rate and a more conformal dose delivery with accurate imaging modalities pre- and during therapy. This paper aims at reporting the state of the art and future direction in the use of radiobiological models and radiobiological-based optimizations in the clinical practice for the treatment of lung cancer. To address this issue, a search was carried out on PubMed database to identify potential papers reporting tumor control probability and normal tissue complication probability for lung tumors. Full articles were retrieved when the abstract was considered relevant, and only papers published in English language were considered. The bibliographies of retrieved papers were also searched and relevant articles included. At the state of the art, dose–response relationships have been reported in literature for local tumor control and survival in stage III non-small cell lung cancer. Due to the lack of published radiobiological models for SBRT, several authors used dose constraints and models derived for conventional fractionation schemes. Recently, several radiobiological models and parameters for SBRT have been published and could be used in prospective trials although external validations are recommended to improve the robustness of model predictive capability. Moreover, radiobiological-based functions have been used within treatment planning systems for plan optimization but the advantages of using this strategy in the clinical practice are still under discussion. Future research should be directed toward combined regimens, in order to potentially improve both local tumor control and survival. Indeed, accurate knowledge of the relevant parameters describing tumor biology and normal tissue response is mandatory to correctly address this issue. In this context, the role of medical physicists and the AAPM in the development of radiobiological models is crucial for the progress of developing specific tool for radiobiological-based optimization treatment planning.

Over the last few decades, the need to reduce and optimize patient medical radiation exposure has prompted the introduction of novel reconstruction algorithms in computed tomography (CT). Against this backdrop, the present study aimed to assess whether reduced radiation dose CT images reconstructed with the new-generation adaptive statistical iterative reconstruction (ASiR-V) maintain the same image quality as that of routine image reconstruction. In addition, the optimization of image quality parameters for the ASiR-V algorithm (e.g., an optimal combination of blending percentage and noise index (NI)) was investigated. An abdominal reference phantom was imaged using the routine clinical protocol (fixed noise index of 18 and 40% ASiR reconstruction). Reduced radiation dose CT scans were performed with varying NI (22, 24, and 30) and using the ASiR-V reconstruction algorithm. Quantitative and qualitative analyses of image noise, contrast, and resolution were performed against NI and reconstruction blending percentages. Our results confirm the ability of the ASiR-V algorithm to provide images of high diagnostic quality while reducing the patient dose. All the parameters were improved in ASiR-V images as compared to ASiR. Both quantitative and qualitative analyses showed that the best agreement was obtained for the images reconstructed using ASiR-V with NI24 and a high percentage of blending (70–100%). This preliminary study results show that ASiR-V allows for a significant reduction in patient dose (about 40%) while maintaining a good overall image quality when appropriate NI (i.e., 24) is used.

Cytosine arabinoside (Ara-C) is one of the key drugs for treating acute myeloid leukemia (AML). High intravenous doses may produce a number of central nervous system (CNS) toxicities and contribute to modifications in brain functional connectivity. sLORETA is a software used for localizing brain electrical activity and functional connectivity. The aim of this study was to apply sLORETA in the evaluation of possible effects of Ara-C on brain connectivity in patients with AML without CNS involvement. We studied eight patients with AML; four were administered standard doses of Ara-C while the other four received high doses. sLORETA was computed from computerized EEG data before treatment and after six months of treatment. Three regions of interest, corresponding to specific combinations of Brodmann areas, were defined.