Review

Authors: Marius E Mayerhoefer, Andrzej Materka, Georg Langs...

Radiomics is a rapidly evolving field of research concerned with the extraction of quantitative metrics-the so-called radiomic features-within medical images. Radiomic features capture tissue and lesion characteristics such as heterogeneity and shape and may, alone or in combination with demographic, histologic, genomic, or proteomic data, be used for clinical problem solving. The goal of this continuing education article is to provide an introduction to the field, covering the basic radiomics workflow: feature calculation and selection, dimensionality reduction, and data processing. Potential clinical applications in nuclear medicine that include PET radiomics-based prediction of treatment response and survival will be discussed. Current limitations of radiomics, such as sensitivity to acquisition parameter variations, and common pitfalls will also be covered.

Topics: Humans; Image Processing, Computer-Assisted; Nuclear Medicine

PubMed: 32060219
DOI: 10.2967/jnumed.118.222893

Authors: Rami S Vanguri, Jia Luo, Andrew T Aukerman...

Immunotherapy is used to treat almost all patients with advanced non-small cell lung cancer (NSCLC); however, identifying robust predictive biomarkers remains challenging. Here we show the predictive capacity of integrating medical imaging, histopathologic and genomic features to predict immunotherapy response using a cohort of 247 patients with advanced NSCLC with multimodal baseline data obtained during diagnostic clinical workup, including computed tomography scan images, digitized programmed death ligand-1 immunohistochemistry slides and known outcomes to immunotherapy. Using domain expert annotations, we developed a computational workflow to extract patient-level features and used a machine-learning approach to integrate multimodal features into a risk prediction model. Our multimodal model (area under the curve (AUC) = 0.80, 95% confidence interval (CI) 0.74-0.86) outperformed unimodal measures, including tumor mutational burden (AUC = 0.61, 95% CI 0.52-0.70) and programmed death ligand-1 immunohistochemistry score (AUC = 0.73, 95% CI 0.65-0.81). Our study therefore provides a quantitative rationale for using multimodal features to improve prediction of immunotherapy response in patients with NSCLC using expert-guided machine learning.

Topics: Humans; Carcinoma, Non-Small-Cell Lung; Lung Neoplasms; Programmed Cell Death 1 Receptor; Radiology; Genomics

PubMed: 36038778
DOI: 10.1038/s43018-022-00416-8

Authors: Shing Fung Lee, Peter J Hoskin

Indications for re-irradiation are increasing both for palliation and potentially curative attempts to achieve durable local control. This has been in part driven by the technological advances in the last decade including image-guided brachytherapy, volumetric-modulated arc therapy and stereotactic body radiotherapy. These enable high dose focal irradiation to be delivered to a limited target volume with minimal normal tissue re-irradiation. The European Society for Radiotherapy and Oncology (ESTRO) and the European Organisation for Research and Treatment of Cancer (EORTC) have collaboratively developed a comprehensive consensus on re-irradiation practices, aiming to standardise definitions, reporting, and clinical decision-making processes. The document introduces a universally applicable definition for re-irradiation, categorised into two primary types based on the presence of geometric overlap of irradiated volumes and concerns for cumulative dose toxicity. It also identifies "repeat organ irradiation" and "repeat irradiation" for cases without such overlap, emphasising the need to consider toxicity risks associated with cumulative doses. Additionally, the document presents detailed reporting guidelines for re-irradiation studies, specifying essential patient and tumour characteristics, treatment planning and delivery details, and follow-up protocols. These guidelines are designed to improve the quality and reproducibility of clinical research, thus fostering a more robust evidence base for future re-irradiation practices. The consensus underscores the necessity of interdisciplinary collaboration and shared decision-making, highlighting performance status, patient survival estimates, and response to initial radiotherapy as critical factors in determining eligibility for re-irradiation. It advocates for a patient-centric approach, with transparent communication about treatment intent and potential risks. Radiobiological considerations, including the application of the linear-quadratic model, are recommended for assessing cumulative doses and guiding re-irradiation strategies. By providing these comprehensive recommendations, the ESTRO-EORTC consensus aims to enhance the safety, efficacy, and quality of life for patients undergoing re-irradiation, while paving the way for future research and refinement of treatment protocols in the field of oncology.

Topics: Humans; Re-Irradiation; Neoplasms; Consensus; Radiation Oncology; Palliative Care; Practice Guidelines as Topic

PubMed: 38859596
DOI: 10.21037/apm-24-4

Authors: Amulya Yalamanchili, Bishwambhar Sengupta, Joshua Song...

IMPORTANCE

Artificial intelligence (AI) large language models (LLMs) demonstrate potential in simulating human-like dialogue. Their efficacy in accurate patient-clinician communication within radiation oncology has yet to be explored.

OBJECTIVE

To determine an LLM's quality of responses to radiation oncology patient care questions using both domain-specific expertise and domain-agnostic metrics.

DESIGN, SETTING, AND PARTICIPANTS

This cross-sectional study retrieved questions and answers from websites (accessed February 1 to March 20, 2023) affiliated with the National Cancer Institute and the Radiological Society of North America. These questions were used as queries for an AI LLM, ChatGPT version 3.5 (accessed February 20 to April 20, 2023), to prompt LLM-generated responses. Three radiation oncologists and 3 radiation physicists ranked the LLM-generated responses for relative factual correctness, relative completeness, and relative conciseness compared with online expert answers. Statistical analysis was performed from July to October 2023.

MAIN OUTCOMES AND MEASURES

The LLM's responses were ranked by experts using domain-specific metrics such as relative correctness, conciseness, completeness, and potential harm compared with online expert answers on a 5-point Likert scale. Domain-agnostic metrics encompassing cosine similarity scores, readability scores, word count, lexicon, and syllable counts were computed as independent quality checks for LLM-generated responses.

RESULTS

Of the 115 radiation oncology questions retrieved from 4 professional society websites, the LLM performed the same or better in 108 responses (94%) for relative correctness, 89 responses (77%) for completeness, and 105 responses (91%) for conciseness compared with expert answers. Only 2 LLM responses were ranked as having potential harm. The mean (SD) readability consensus score for expert answers was 10.63 (3.17) vs 13.64 (2.22) for LLM answers (P < .001), indicating 10th grade and college reading levels, respectively. The mean (SD) number of syllables was 327.35 (277.15) for expert vs 376.21 (107.89) for LLM answers (P = .07), the mean (SD) word count was 226.33 (191.92) for expert vs 246.26 (69.36) for LLM answers (P = .27), and the mean (SD) lexicon score was 200.15 (171.28) for expert vs 219.10 (61.59) for LLM answers (P = .24).

CONCLUSIONS AND RELEVANCE

In this cross-sectional study, the LLM generated accurate, comprehensive, and concise responses with minimal risk of harm, using language similar to human experts but at a higher reading level. These findings suggest the LLM's potential, with some retraining, as a valuable resource for patient queries in radiation oncology and other medical fields.

Topics: Humans; Radiation Oncology; Artificial Intelligence; Cross-Sectional Studies; Language; Patient Care

PubMed: 38564215
DOI: 10.1001/jamanetworkopen.2024.4630

Authors: Arya Rao, John Kim, Meghana Kamineni...

OBJECTIVE

Despite rising popularity and performance, studies evaluating the use of large language models for clinical decision support are lacking. Here, we evaluate ChatGPT (Generative Pre-trained Transformer)-3.5 and GPT-4's (OpenAI, San Francisco, California) capacity for clinical decision support in radiology via the identification of appropriate imaging services for two important clinical presentations: breast cancer screening and breast pain.

METHODS

We compared ChatGPT's responses to the ACR Appropriateness Criteria for breast pain and breast cancer screening. Our prompt formats included an open-ended (OE) and a select all that apply (SATA) format. Scoring criteria evaluated whether proposed imaging modalities were in accordance with ACR guidelines. Three replicate entries were conducted for each prompt, and the average of these was used to determine final scores.

RESULTS

Both ChatGPT-3.5 and ChatGPT-4 achieved an average OE score of 1.830 (out of 2) for breast cancer screening prompts. ChatGPT-3.5 achieved a SATA average percentage correct of 88.9%, compared with ChatGPT-4's average percentage correct of 98.4% for breast cancer screening prompts. For breast pain, ChatGPT-3.5 achieved an average OE score of 1.125 (out of 2) and a SATA average percentage correct of 58.3%, as compared with an average OE score of 1.666 (out of 2) and a SATA average percentage correct of 77.7%.

DISCUSSION

Our results demonstrate the eventual feasibility of using large language models like ChatGPT for radiologic decision making, with the potential to improve clinical workflow and responsible use of radiology services. More use cases and greater accuracy are necessary to evaluate and implement such tools.

Topics: Humans; Female; Mastodynia; Radiology; Breast Neoplasms; Decision Making

PubMed: 37356806
DOI: 10.1016/j.jacr.2023.05.003

Review

Authors: Hayley Barnes, Stephen M Humphries, Peter M George...

Challenges for the effective management of interstitial lung diseases (ILDs) include difficulties with the early detection of disease, accurate prognostication with baseline data, and accurate and precise response to therapy. The purpose of this Review is to describe the clinical and research gaps in the diagnosis and prognosis of ILD, and how machine learning can be applied to image biomarker research to close these gaps. Machine-learning algorithms can identify ILD in at-risk populations, predict the extent of lung fibrosis, correlate radiological abnormalities with lung function decline, and be used as endpoints in treatment trials, exemplifying how this technology can be used in care for people with ILD. Advances in image processing and analysis provide further opportunities to use machine learning that incorporates deep-learning-based image analysis and radiomics. Collaboration and consistency are required to develop optimal algorithms, and candidate radiological biomarkers should be validated against appropriate predictors of disease outcomes.

Topics: Humans; Lung Diseases, Interstitial; Prognosis; Risk Factors; Biomarkers; Radiology

PubMed: 36517410
DOI: 10.1016/S2589-7500(22)00230-8

Authors: Sofia C Vaz, John Patrick Pilkington Woll, Fatima Cardoso...

INTRODUCTION

There is much literature about the role of 2-[F]FDG PET/CT in patients with breast cancer (BC). However, there exists no international guideline with involvement of the nuclear medicine societies about this subject.

PURPOSE

To provide an organized, international, state-of-the-art, and multidisciplinary guideline, led by experts of two nuclear medicine societies (EANM and SNMMI) and representation of important societies in the field of BC (ACR, ESSO, ESTRO, EUSOBI/ESR, and EUSOMA).

METHODS

Literature review and expert discussion were performed with the aim of collecting updated information regarding the role of 2-[F]FDG PET/CT in patients with no special type (NST) BC and summarizing its indications according to scientific evidence. Recommendations were scored according to the National Institute for Health and Care Excellence (NICE) criteria.

RESULTS

Quantitative PET features (SUV, MTV, TLG) are valuable prognostic parameters. In baseline staging, 2-[F]FDG PET/CT plays a role from stage IIB through stage IV. When assessing response to therapy, 2-[F]FDG PET/CT should be performed on certified scanners, and reported either according to PERCIST, EORTC PET, or EANM immunotherapy response criteria, as appropriate. 2-[F]FDG PET/CT may be useful to assess early metabolic response, particularly in non-metastatic triple-negative and HER2+ tumours. 2-[F]FDG PET/CT is useful to detect the site and extent of recurrence when conventional imaging methods are equivocal and when there is clinical and/or laboratorial suspicion of relapse. Recent developments are promising.

CONCLUSION

2-[F]FDG PET/CT is extremely useful in BC management, as supported by extensive evidence of its utility compared to other imaging modalities in several clinical scenarios.

Topics: Positron Emission Tomography Computed Tomography; Humans; Fluorodeoxyglucose F18; Breast Neoplasms; Nuclear Medicine; Female; Societies, Medical

PubMed: 38740576
DOI: 10.1007/s00259-024-06696-9

Review

Authors: Edward I Bluth, Donald P Frush, M Elizabeth Oates...

This section focuses on the professional workforce comprised of the primary medical specialties that utilize ionizing radiation in their practices. Those discussed include the specialties of radiology and radiation oncology, as well as the subspecialties of radiology, namely diagnostic radiology, interventional radiology, nuclear radiology, and nuclear medicine. These professionals provide essential health care services, for example, the interpretation of imaging studies, the provision of interventional procedures, radionuclide therapeutic treatments, and radiation therapy. In addition, they may be called on to function as part of a radiologic emergency response team to care for potentially exposed persons following radiation events, for example, detonation of a nuclear weapon, nuclear power plant accidents, and transportation incidents. For these reasons, maintenance of an adequate workforce in each of these professions is essential to meeting the nation's future needs. Currently, there is a shortage for all physicians in the medical radiology workforce.

Topics: Humans; United States; Medicine; Nuclear Medicine; Diagnostic Imaging; Radiology, Interventional; Workforce

PubMed: 36382354
DOI: 10.1002/acm2.13799

Review

Authors: J Cervera Deval

Biomedical imaging makes it possible not only to diagnose and stage cancer, but also to follow up patients and evaluate the response to treatment. RECIST (Response Evaluation Criteria In Solid Tumors) provides a method to monitor the response to treatment based on one dimensional measurements of tumors obtained with reproducible imaging techniques like CT, MRI, and PET. The metabolic changes induced by new treatments modify the biology and behavior of the tumor; occasionally, there is a discrepancy between the patient's clinical condition and the response measured by RECIST, which indicates that functional tests need to be included in the evaluation of the response to treatment. The objective is to review the RECIST criteria to include the contribution of functional imaging to enable the efficacy and effects of the treatment in patients with solid tumors.

Topics: Diagnostic Imaging; Humans; Neoplasms; Radiology; Response Evaluation Criteria in Solid Tumors

PubMed: 22902252
DOI: 10.1016/j.rx.2012.03.010

Review

Authors: Oliver J Gurney-Champion, Faisal Mahmood, Marcel van Schie...

Quantitative imaging biomarkers show great potential for use in radiotherapy. Quantitative images based on microscopic tissue properties and tissue function can be used to improve contouring of the radiotherapy targets. Furthermore, quantitative imaging biomarkers might be used to predict treatment response for several treatment regimens and hence be used as a tool for treatment stratification, either to determine which treatment modality is most promising or to determine patient-specific radiation dose. Finally, patient-specific radiation doses can be further tailored to a tissue/voxel specific radiation dose when quantitative imaging is used for dose painting. In this review, published standards, guidelines and recommendations on quantitative imaging assessment using CT, PET and MRI are discussed. Furthermore, critical issues regarding the use of quantitative imaging for radiation oncology purposes and resultant pending research topics are identified.

Topics: Humans; Magnetic Resonance Imaging; Positron-Emission Tomography; Radiation Oncology; Radiotherapy Planning, Computer-Assisted

PubMed: 32114268
DOI: 10.1016/j.radonc.2020.01.026