Learning objectives
Understand the requirements for the different forms of immune-related disease response criteria.
Comprehend how structured reporting be used to automate the calculation of these criteria.
Background
The advent of immunotherapies for the treatment of cancer has required the creation of new disease response criteria,
including irRC,
irRECIST,
and iRECIST (Figure 1).
Many radiologists are familiar with RECIST version 1.1 which involves the monitoring of unidimensional measurements from up to five target lesions over time to determine a percent change in the sum of diameters that will indicate a complete response (CR),
partial response (PR),
stable disease (SD),
or progressive disease (PD) (1).
The appearance of any new lesions in RECIST implies...
Findings and procedure details
We created a structured reporting system that records key images and a radiologist’s voice descriptions of image findings,
tags the images with metadata using natural language processing (NLP) referenced to an ontology (i.e.,
controlled vocabulary),
and assembles a multimedia report with related findings from serial exams linked in timelines (Figure 2).
The disease measurements made by a radiologist using a PACS system can be input into the reporting system either by (1) voice input during the dictation of a finding description,
or by (2) direct...
Conclusion
Automation of immune-related response criteria utilizing structured report data is essential for the clinical implementation of these new forms of disease assessment.
Structured reporting may enable the development of more sophisticated disease response criteria in the future utilizing artificial intelligence image processing for the analysis of total tumor burden.
References
Eisenhauer EA et al.
New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1).
Eur J Cancer 2009;45:228–247.
Wolchok JD,
Hoos A,
O'Day S,
et.
al.
Guidelines for the evaluation of immune therapy activity in solid tumors: immune-related response criteria.
Clin Cancer Res 2009;15:7412-7420.
Litière S,
ColletteS,
de Vries EGE,
et.
al.
RECIST — learning from the past to build the future.
Nature Reviews Clinical Oncology 2017;14:187–192.
Le Lay J,
Jarraya H,
Lebellec L,
Penel N.
irRECIST and iRECIST: the devil is in...