Data infrastructures for AI in medical imaging: a report on the experiences of five EU projects.

Artificial intelligence (AI) is transforming the field of medical imaging and has the potential to bring medicine from the era of 'sick-care' to the era of healthcare and prevention. The development of AI requires access to large, complete, and harmonized real-world datasets, representative of the population, and disease diversity. However, to date, efforts are fragmented, based on single-institution, size-limited, and annotation-limited datasets. Available public datasets (e.g., The Cancer Imaging Archive, TCIA, USA) are limited in scope, making model generalizability really difficult. In this direction, five European Union projects are currently working on the development of big data infrastructures that will enable European, ethically and General Data Protection Regulation-compliant, quality-controlled, cancer-related, medical imaging platforms, in which both large-scale data and AI algorithms will coexist. The vision is to create sustainable AI cloud-based platforms for the development, implementation, verification, and validation of trustable, usable, and reliable AI models for addressing specific unmet needs regarding cancer care provision. In this paper, we present an overview of the development efforts highlighting challenges and approaches selected providing valuable feedback to future attempts in the area.Key points• Artificial intelligence models for health imaging require access to large amounts of harmonized imaging data and metadata.• Main infrastructures adopted either collect centrally anonymized data or enable access to pseudonymized distributed data.• Developing a common data model for storing all relevant information is a challenge.• Trust of data providers in data sharing initiatives is essential.• An online European Union meta-tool-repository is a necessity minimizing effort duplication for the various projects in the area.

MAIC-10 brief quality checklist for publications using artificial intelligence and medical images.

The use of artificial intelligence (AI) with medical images to solve clinical problems is becoming increasingly common, and the development of new AI solutions is leading to more studies and publications using this computational technology. As a novel research area, the use of common standards to aid AI developers and reviewers as quality control criteria will improve the peer review process. Although some guidelines do exist, their heterogeneity and extension advocate that more explicit and simple schemes should be applied on the publication practice. Based on a review of existing AI guidelines, a proposal which collects, unifies, and simplifies the most relevant criteria was developed. The MAIC-10 (Must AI Criteria-10) checklist with 10 items was implemented as a guide to design studies and evaluate publications related to AI in the field of medical imaging. Articles published in Insights into Imaging in 2021 were selected to calculate their corresponding MAIC-10 quality score. The mean score was found to be 5.6 ± 1.6, with critical items present in most articles, such as "Clinical need", "Data annotation", "Robustness", and "Transparency" present in more than 80% of papers, while improvements in other areas were identified. MAIC-10 was also observed to achieve the highest intra-observer reproducibility when compared to other existing checklists, with an overall reduction in terms of checklist length and complexity. In summary, MAIC-10 represents a short and simple quality assessment tool which is objective, robust and widely applicable to AI studies in medical imaging.

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.

A phase I dose-finding, pharmacokinetics and genotyping study of olaparib and lurbinectedin in patients with advanced solid tumors.

The poly (ADP-Ribose) polymerase (PARP) inhibitor olaparib has shown antitumor activity in patients with ovarian or breast cancer with or without BRCA1/2 mutations. Lurbinectedin is an ecteinascidin that generates DNA double-strand breaks. We hypothesized that the combination of olaparib and lurbinectedin maximizes the DNA damage increasing the efficacy. A 3 + 3 dose-escalation study examined olaparib tablets with lurbinectedin every 21 days. The purpose of this phase I study is to determine the dose-limiting toxicities (DLTs) of the combination, to investigate the maximum tolerated dose (MTD), the recommended phase II dose (RP2D), efficacy, pharmacokinetics, in addition to genotyping and translational studies. In total, 20 patients with ovarian and endometrial cancers were included. The most common adverse events were asthenia, nausea, vomiting, constipation, abdominal pain, neutropenia, anemia. DLT grade 4 neutropenia was observed in two patients in dose level (DL) 5, DL4 was defined as the MTD, and the RP2D was lurbinectedin 1.5 mg/m2 + olaparib 250 mg twice a day (BID). Mutational analysis revealed a median of 2 mutations/case, 53% of patients with mutations in the homologous recombination (HR) pathway. None of the patients reached a complete or partial response; however, 60% of stable disease was achieved. In conclusion, olaparib in combination with lurbinectedin was well tolerated with a disease control rate of 60%. These results deserve further evaluation of the combination in a phase II trial.

Multicenter retrospective study to evaluate the impact of trabectedin plus pegylated liposomal doxorubicin on the subsequent treatment in women with recurrent, platinum-sensitive ovarian cancer.

Debulking surgery, followed by taxane/platinum-based chemotherapy has traditionally been the first-line treatment for advanced ovarian cancer. However, most patients will experience recurrence afterwards, and receive subsequent lines of therapy. It has been proposed that extending the treatment-free interval of platinum can improve the response to a subsequent platinum-based chemotherapy, and reduce associated toxicities in women with recurrent, platinum-sensitive ovarian cancer. The aim was to determine the impact, in clinical practice, of trabectedin with pegylated liposomal doxorubicin (trabectedin/PLD) on the subsequent platinum-based therapy in these patients, and to explore the prognosis for breast cancer gene status and the expression of diverse genes. This was a multicenter, retrospective, postauthorization study that involved 79 patients. Germline or somatic mutations of breast cancer gene 1/2 were present in 21.5%. The median time between trabectedin/PLD and the onset of the subsequent treatment was 6.7 months. The overall response rate during the trabectedin/PLD period was 36.7%. In the subsequent first-line platinum-based therapy, the overall response rate was 51.4%. Progression-free survival and overall survival were 11.8 and 25.4 months, respectively, from the onset of trabectedin/PLD treatment. Partially platinum-sensitive (between 6 and 12 months) and platinum-sensitive patients (treatment-free interval of platinum≥12 months) showed no differences in progression-free survival and overall survival. Grade 3 neutropenia and asthenia were reported in 15.2 and 10.1% of patients, respectively. Most frequent adverse events in more than 10% of patients were neutropenia (45.6%), asthenia (43.0%), nausea (25.3%), and anemia (13.9%). The intercalation with a nonplatinum regimen may improve the response to a subsequent platinum-based therapy in women with recurrent, platinum-sensitive ovarian cancer.