Metastatic pulmonary nodules of undefined primary origin can be incidentally detected on chest computed tomography (CT). Radiologists evaluate metastatic nodules based on a limited set of imaging characteristics, such as size, shape, and contrast enhancement. These characteristics of the nodules are mostly insufficient to determine the primary tumor. Identifying the primary tumor requires comprehensive diagnostic evaluations, including laboratory tests, radiological imaging, biopsies, and endoscopic procedures. These assessments are costly, time-consuming, and associated with risks due to invasive interventions. Early detection of the primary tumor facilitates timely initiation of treatment, potentially improving patient survival. Radiomics extracts a large number of quantitative features that reflect the biological behavior of tumors. Breast cancer, colorectal cancer, and renal cell carcinoma are among the most common causes of lung metastases.

This study aims to differentiate lung metastases originating from breast cancer, colorectal cancer, and renal cell carcinoma using radiomics features combined with various clinical and radiological parameters.