Correlation between nodules mentioned in medical reports and CT images

Medical reports are a rich source of data, but their use in computer vision often requires additional annotations, marking points on images anew. This study examines the relationship between pulmonary nodules references in medical reports and their presence in CT scan images. It found that while radiologists tend to make more manual image annotations, this does not change follow-up recommendations compared to what is written in the medical reports. This highlights the potential for reusing existing data in medical reports to train AI algorithms, improving efficiency without compromising the accuracy of clinical decisions.

Authors and Affiliations:

Carlos A. Ferreira^1,2, Célia Sousa³, Inês Dias Marques³, Pedro Sousa³, Isabel Ramos^4,5, Miguel Coimbra^1,6 & Aurélio Campilho^1,2

¹ INESC TEC

² FEUP

³ ULS Gaia Espinho

⁴ FMUP

⁵ ULS São João

⁶ FCUP

Abstract:

Given the high prevalence of lung cancer, an accurate diagnosis is crucial. In the diagnosis process, radiologists play an important role by examining numerous radiology exams to identify different types of nodules. To aid the clinicians' analytical efforts, computer-aided diagnosis can streamline the process of identifying pulmonary nodules. For this purpose, medical reports can serve as valuable sources for automatically retrieving image annotations. Our study focused on converting medical reports into nodule annotations, matching textual information with manually annotated data from the Lung Nodule Database (LNDb)—a comprehensive repository of lung scans and nodule annotations. As a result of this study, we have released a tabular data file containing information from 292 medical reports in the LNDb, along with files detailing nodule characteristics and corresponding matches to the manually annotated data. The objective is to enable further research studies in lung cancer by bridging the gap between existing reports and additional manual annotations that may be collected, thereby fostering discussions about the advantages and disadvantages between these two data types.

Journal: Nature Scientific Data

Link: https://www.nature.com/articles/s41597-024-03345-6