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

Abstract

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.

An updated systematic review of radiomics in osteosarcoma: utilizing CLAIM to adapt the increasing trend of deep learning application in radiomics

“…The CLAIM has seldomly been employed for quality assessment of radiomics studies [20,21]. However, we assumed that CLAIM is suitable for radiomics studies evaluation, as radiomics is a subset of AI application in medical imaging [15][16][17][18]. The QUADAS-2 tool was tailored to our review by modifying the signaling questions [8].…”

“…An additional evaluation using the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist [ 10 ] has been recommended to identify several significant items for reporting transparency of radiomics studies [ 11 – 14 ]. Further, RQS and TRIPOD may not be totally suitable for current radiomics studies, since recently developed deep radiomics applies convolutional neural networks to analyze these extracted features [ 15 – 18 ]. The Checklist for Artificial Intelligence in Medical Imaging (CLAIM) [ 19 ] has been demonstrated as a useful tool to improve design and reporting of deep learning research [ 20 , 21 ].…”

Translating radiological research into practice—from discovery to clinical impact

“…Techniques to measure the value of imaging investigations, including health technology assessment, are even more important at this time of implementation of artificial intelligence (AI) in radiology [ 23 ]. The value of imaging in the patient experience is also an essential aspect of measuring our impact on value-based care [ 24 , 25 ].…”

Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach

“…Another significant problem is that deep learning structures are black box models that map a given input to a target output [37][38][39]. Due to the complexity of the architecture, the large number of parameters and the specificity of the algorithms employed, they suffer from a lack of transparency during the training and decision-making processes.…”