Clinical Imaging Research: Higher Evidence, Global Collaboration, Improved Reporting, and Data Sharing Are the Grand Challenges

Clinical, Cultural, Computational, and Regulatory Considerations to Deploy AI in Radiology: Perspectives of RSNA and MICCAI Experts

The Radiological Society of North of America (RSNA) and the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society have led a series of joint panels and seminars focused on the present impact and future directions of artificial intelligence (AI) in radiology. These conversations have collected viewpoints from multidisciplinary experts in radiology, medical imaging, and machine learning on the current clinical penetration of AI technology in radiology and how it is impacted by trust, reproducibility, explainability, and accountability. The collective points-both practical and philosophical-define the cultural changes for radiologists and AI scientists working together and describe the challenges ahead for AI technologies to meet broad approval. This article presents the perspectives of experts from MICCAI and RSNA on the clinical, cultural, computational, and regulatory considerations-coupled with recommended reading materials-essential to adopt AI technology successfully in radiology and, more generally, in clinical practice. The report emphasizes the importance of collaboration to improve clinical deployment, highlights the need to integrate clinical and medical imaging data, and introduces strategies to ensure smooth and incentivized integration. Keywords: Adults and Pediatrics, Computer Applications-General (Informatics), Diagnosis, Prognosis © RSNA, 2024.

Body composition and cancer survival: a narrative review

Interest in understanding the relationship between body composition and cancer survival has remained strong for decades, with a number of recent systematic reviews on the topic. However, the current state of evidence is based on heterogeneous exposure definitions based on anthropometry, yielding inconsistent findings with regard to this association. Recently the field has taken an exciting direction with the application of radiological assessments to measure specific aspects of body composition, yet reconciliation of findings from these modern assessment tools with those from the historic use of anthropometric data proves challenging. In this paper, I briefly review the biological basis for a link between body composition and cancer survival and summarize the epidemiological evidence with consideration to specific exposure measures. As enthusiasm is building around novel assessments, I conclude with a discussion of issues that researchers should be aware of when interpreting results from these new modalities.

Predicting the pharmacokinetics and pharmacodynamics of antisense oligonucleotides: an overview of various approaches and opportunities for PBPK/PD modelling

INTRODUCTION

Advances in research and development (R&D) have enabled many approvals of antisense oligonucleotides (ASOs). Its administration expanded from systemic to local for treating various diseases, where predicting target tissue exposures and pharmacokinetics (PK) and pharmacodynamics (PD) in human can be critical.

AREAS COVERED

A literature search for PBPK/PD models of ASOs was conducted using PubMed and Embase (to 1 April 2023). ASO PK and PD in animals and humans and modeling approaches including physiologically based (PB) are summarized; and relevance and impacts of PBPK/PD modeling are assessed.

EXPERT OPINION

Allometric scaling and compartmental PK/PD modeling have been successful to predict human ASO PK/PD, addressing most R&D needs. Understanding tissue distribution of ASOs can be crucial for their efficacy and safety especially for intrathecal (IT), pulmonary, or other local routes. PBPK/PD modeling is expected to improve such understanding, for which, efforts have been sporadic. However, developing a PBPK/PD model requires careful review of known biology/pharmacology and thoughtful experimental designs. Resulting models have the potential to predict target/specified tissue exposures and responses in human adults and pediatrics. Ultimately, a PBPK/PD modeling approach can lead to more efficient and rational clinical development, resulting in well-informed decision making and a shortened timeline.

An overview of meta-analyses on radiomics: more evidence is needed to support clinical translation

OBJECTIVE

To conduct an overview of meta-analyses of radiomics studies assessing their study quality and evidence level.

METHODS

A systematical search was updated via peer-reviewed electronic databases, preprint servers, and systematic review protocol registers until 15 November 2022. Systematic reviews with meta-analysis of primary radiomics studies were included. Their reporting transparency, methodological quality, and risk of bias were assessed by PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) 2020 checklist, AMSTAR-2 (A MeaSurement Tool to Assess systematic Reviews, version 2) tool, and ROBIS (Risk Of Bias In Systematic reviews) tool, respectively. The evidence level supporting the radiomics for clinical use was rated.

RESULTS

We identified 44 systematic reviews with meta-analyses on radiomics research. The mean ± standard deviation of PRISMA adherence rate was 65 ± 9%. The AMSTAR-2 tool rated 5 and 39 systematic reviews as low and critically low confidence, respectively. The ROBIS assessment resulted low, unclear and high risk in 5, 11, and 28 systematic reviews, respectively. We reperformed 53 meta-analyses in 38 included systematic reviews. There were 3, 7, and 43 meta-analyses rated as convincing, highly suggestive, and weak levels of evidence, respectively. The convincing level of evidence was rated in (1) T2-FLAIR radiomics for IDH-mutant vs IDH-wide type differentiation in low-grade glioma, (2) CT radiomics for COVID-19 vs other viral pneumonia differentiation, and (3) MRI radiomics for high-grade glioma vs brain metastasis differentiation.

CONCLUSIONS

The systematic reviews on radiomics were with suboptimal quality. A limited number of radiomics approaches were supported by convincing level of evidence.

CLINICAL RELEVANCE STATEMENT

The evidence supporting the clinical application of radiomics are insufficient, calling for researches translating radiomics from an academic tool to a practicable adjunct towards clinical deployment.

Adiposity and cancer survival: a systematic review and meta-analysis

PURPOSE

The increasing availability of clinical imaging tests (especially CT and MRI) that directly quantify adipose tissue has led to a rapid increase in studies examining the relationship of visceral, subcutaneous, and overall adiposity to cancer survival. To summarize this emerging body of literature, we conducted a systematic review and meta-analysis of imaging-measured as well as anthropometric proxies for adipose tissue distribution and cancer survival across a wide range of cancer types.

METHODS

Using keywords related to adiposity, cancer, and survival, we conducted a systematic search of the literature in PubMed and MEDLINE, Embase, and Web of Science Core Collection databases from database inception to 30 June 2021. We used a random-effect method to calculate pooled hazard ratios (HR) and corresponding 95% confidence intervals (CI) within each cancer type and tested for heterogeneity using Cochran's Q test and the I2 test.

RESULTS

We included 203 records for this review, of which 128 records were utilized for quantitative analysis among 10 cancer types: breast, colorectal, gastroesophageal, head and neck, hepatocellular carcinoma, lung, ovarian, pancreatic, prostate, and renal cancer. We found that imaging-measured visceral, subcutaneous, and total adiposity were not significantly associated with increased risk of overall mortality, death from primary cancer, or cancer progression among patients diagnosed with these 10 cancer types; however, we found significant or high heterogeneity for many cancer types. For example, heterogeneity was similarly high when the pooled HRs (95% CI) for overall mortality associated with visceral adiposity were essentially null as in 1.03 (0.55, 1.92; I2 = 58%) for breast, 0.99 (0.81, 1.21; I2 = 71%) for colorectal, versus when they demonstrated a potential increased risk 1.17 (0.85, 1.60; I2 = 78%) for hepatocellular carcinoma and 1.62 (0.90, 2.95; I2 = 84%) for renal cancer.

CONCLUSION

Greater adiposity at diagnosis (directly measured by imaging) is not associated with worse survival among cancer survivors. However, heterogeneity and other potential limitations were noted across studies, suggesting differences in study design and adiposity measurement approaches, making interpretation of meta-analyses challenging. Future work to standardize imaging measurements and data analyses will strengthen research on the role of adiposity in cancer survival.

Open Innovation as the Catalyst in the Personalized Medicine to Personalized Digital Medicine Transition

Personalized medicine (PM) bridges several disciplines for understanding and addressing prevalent, complex, or rare situations in human health (e.g., complex phenotyping, risk stratification, etc.); therefore, digital and technological solutions have been integrated in the field to boost innovation and new knowledge generation. The open innovation (OI) paradigm proposes a method by which to respectfully manage disruptive change in biomedical organizations, as experienced by many organizations during digital transformation and the COVID-19 pandemic. In this article, we focus on how this paradigm has catalyzed the transition from PM to personalized digital medicine in a large-volume research hospital. Methods, challenges, and results are discussed. This case study is an endeavor to confirm that OI strategies could help manage urgent needs from the healthcare environment, while achieving sustainability-oriented, accountable innovation.

Reproducibility for Hepatocellular Carcinoma CT Radiomic Features: Influence of Delineation Variability Based on 3D-CT, 4D-CT and Multiple-Parameter MR Images

Purpose

Accurate lesion segmentation is a prerequisite for radiomic feature extraction. It helps to reduce the features variability so as to improve the reporting quality of radiomics study. In this research, we aimed to conduct a radiomic feature reproducibility test of inter-/intra-observer delineation variability in hepatocellular carcinoma using 3D-CT images, 4D-CT images and multiple-parameter MR images.

Materials and Methods

For this retrospective study, 19 HCC patients undergoing 3D-CT, 4D-CT and multiple-parameter MR scans were included in this study. The gross tumor volume (GTV) was independently delineated twice by two observers based on contrast-enhanced computed tomography (CECT), maximum intensity projection (MIP), LAVA-Flex, T2W FRFSE and DWI-EPI images. We also delineated the peritumoral region, which was defined as 0 to 5 mm radius surrounding the GTV. 107 radiomic features were automatically extracted from CECT images using 3D-Slicer software. Quartile coefficient of dispersion (QCD) and intraclass correlation coefficient (ICC) were applied to assess the variability of each radiomic feature. QCD<10% and ICC≥0.75 were considered small variations and excellent reliability. Finally, the principal component analysis (PCA) was used to test the feasibility of dimensionality reduction.

Results

For tumor tissues, the numbers of radiomic features with QCD<10% indicated no obvious inter-/intra-observer differences or discrepancies in 3D-CT, 4D-CT and multiple-parameter MR delineation. However, the number of radiomic features (mean 89) with ICC≥0.75 was the highest in the multiple-parameter MR group, followed by the 3DCT group (mean 77) and the MIP group (mean 73). The peritumor tissues also showed similar results. A total of 15 and 7 radiomic features presented excellent reproducibility and small variation in tumor and peritumoral tissues, respectively. Two robust features showed excellent reproducibility and small variation in tumor and peritumoral tissues. In addition, the values of the two features both represented statistically significant differences among tumor and peritumoral tissues (P<0.05). The PCA results indicated that the first seven principal components could preserve at least 90% of the variance of the original set of features.

Conclusion

Delineation on multiple-parameter MR images could help to improve the reproducibility of the HCC CT radiomic features and weaken the inter-/intra-observer influence.

The Role of Radiomics in Lung Cancer: From Screening to Treatment and Follow-Up

PURPOSE

Lung cancer represents the first cause of cancer-related death in the world. Radiomics studies arise rapidly in this late decade. The aim of this review is to identify important recent publications to be synthesized into a comprehensive review of the current status of radiomics in lung cancer at each step of the patients' care.

METHODS

A literature review was conducted using PubMed/Medline for search of relevant peer-reviewed publications from January 2012 to June 2020.

RESULTS

We identified several studies at each point of patient's care: detection and classification of lung nodules (n=16), determination of histology and genomic (n=10) and finally treatment outcomes predictions (=23). We reported the methodology of those studies and their results and discuss the limitations and the progress to be made for clinical routine applications.

CONCLUSION

Promising perspectives arise from machine learning applications and radiomics based models in lung cancers, yet further data are necessary for their implementation in daily care. Multicentric collaboration and attention to quality and reproductivity of radiomics studies should be further consider.

A decade of radiomics research: are images really data or just patterns in the noise?

KEY POINTS

• Although radiomics is potentially a promising approach to analyze medical image data, many pitfalls need to be considered to avoid a reproducibility crisis.• There is a translation gap in radiomics research, with many studies being published but so far little to no translation into clinical practice.• Going forward, more studies with higher levels of evidence are needed, ideally also focusing on prospective studies with relevant clinical impact.

Prospective Clinical Trials: 10-year Trends in Radiology

Online supplemental material is available for this article.

Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations

Artificial intelligence (AI) has the potential to significantly disrupt the way radiology will be practiced in the near future, but several issues need to be resolved before AI can be widely implemented in daily practice. These include the role of the different stakeholders in the development of AI for imaging, the ethical development and use of AI in healthcare, the appropriate validation of each developed AI algorithm, the development of effective data sharing mechanisms, regulatory hurdles for the clearance of AI algorithms, and the development of AI educational resources for both practicing radiologists and radiology trainees. This paper details these issues and presents possible solutions based on discussions held at the 2019 meeting of the International Society for Strategic Studies in Radiology. KEY POINTS: • Radiologists should be aware of the different types of bias commonly encountered in AI studies, and understand their possible effects. • Methods for effective data sharing to train, validate, and test AI algorithms need to be developed. • It is essential for all radiologists to gain an understanding of the basic principles, potentials, and limits of AI.

The Bionic Radiologist: avoiding blurry pictures and providing greater insights

Radiology images and reports have long been digitalized. However, the potential of the more than 3.6 billion radiology examinations performed annually worldwide has largely gone unused in the effort to digitally transform health care. The Bionic Radiologist is a concept that combines humanity and digitalization for better health care integration of radiology. At a practical level, this concept will achieve critical goals: (1) testing decisions being made scientifically on the basis of disease probabilities and patient preferences; (2) image analysis done consistently at any time and at any site; and (3) treatment suggestions that are closely linked to imaging results and are seamlessly integrated with other information. The Bionic Radiologist will thus help avoiding missed care opportunities, will provide continuous learning in the work process, and will also allow more time for radiologists' primary roles: interacting with patients and referring physicians. To achieve that potential, one has to cope with many implementation barriers at both the individual and institutional levels. These include: reluctance to delegate decision making, a possible decrease in image interpretation knowledge and the perception that patient safety and trust are at stake. To facilitate implementation of the Bionic Radiologist the following will be helpful: uncertainty quantifications for suggestions, shared decision making, changes in organizational culture and leadership style, maintained expertise through continuous learning systems for training, and role development of the involved experts. With the support of the Bionic Radiologist, disparities are reduced and the delivery of care is provided in a humane and personalized fashion.