Osteolytic lesions can be seen in both multiple myeloma (MM), and osteolytic bone metastasis on computed tomography (CT) scans. We sought to assess the feasibility of a CT-based radiomics model to distinguish MM from metastasis. This study retrospectively included patients with pre-treatment thoracic or abdominal contrast-enhanced CT from institution 1 (training set: 175 patients with 425 lesions) and institution 2 (external test set: 50 patients with 85 lesions). After segmenting osteolytic lesions on CT images, 1218 radiomics features were extracted. A random forest (RF) classifier was used to build the radiomics model with 10-fold cross-validation. Three radiologists distinguished MM from metastasis using a five-point scale, both with and without the assistance of RF model results. Diagnostic performance was evaluated using the area under the curve (AUC). The AUC of the RF model was 0.807 and 0.762 for the training and test set, respectively. The AUC of the RF model and the radiologists (0.653–0.778) was not significantly different for the test set (p ≥ 0.179). The AUC of all radiologists was significantly increased (0.833–0.900) when they were assisted by RF model results (p < 0.001). In conclusion, the CT-based radiomics model can differentiate MM from osteolytic bone metastasis and improve radiologists’ diagnostic performance.

It is difficult to detect multiple myeloma (MM) infiltration of the bone marrow on computed tomography (CT) scans of patients with osteopenia. Our aim is to determine the feasibility of using radiomics analysis to detect MM infiltration of the bone marrow on CT scans of patients with osteopenia. The contrast-enhanced thoracic CT scans of 104 patients with MM and 104 age- and sex-matched controls were retrospectively evaluated. All individuals had decreased bone density on radiography. The study group was divided into development (n = 160) and temporal validation sets (n = 48). The radiomics model was developed using 805 texture features extracted from the bone marrow for a development set, using a Random Forest algorithm. The developed models were applied to evaluate a temporal validation set. For comparison, three radiologists evaluated the CTs for the possibility of MM infiltration in the bone marrow. The diagnostic performances were assessed and compared using an area under the receiver operating characteristic curve (AUC) analysis. The AUC of the radiomics model was not significantly different from those of the radiologists (p = 0.056–0.821). The radiomics analysis results showed potential for detecting MM infiltration in the bone marrow on CT scans of patients with osteopenia.

Purpose Colorectal cancer (CRC) remains a leading cause of cancer morbidity and mortality in the United States and shows substantial geographic variation. Socioeconomically disadvantaged communities experience elevated CRC incidence, yet few studies have analyzed multi-decade poverty measures for long-term structural disadvantage. Methods We analyzed CRC incidence from 2017 to 2021 across Texas using Texas Cancer Registry data. Age-sex-race/ethnicity standardized cases were incorporated as offsets in Bayesian spatial models to generate tract-level posterior mean relative risks. We evaluated four tract-level poverty measures (high poverty in 2021; persistent poverty since 1990; enduring poverty since 1980 and 1970), Rural–Urban Commuting Area (RUCA) classifications, and CRC screening rates among adults aged 50–75 years. Results Long-term poverty and rurality were independently associated with elevated CRC risk. Compared with urban tracts, micropolitan and rural tracts had 7–8% higher risks. Poverty measures defined over longer durations showed stronger associations with CRC incidence: high poverty in 2017–2021 (RR = 1.04, 95% CrI: 1.01–1.07), persistent poverty since 1990 (RR = 1.04, 1.00–1.08), enduring poverty since 1980 (RR = 1.06, 1.01–1.11), and enduring poverty since 1970 (RR = 1.09, 1.04–1.15). Higher tract-level CRC screening prevalence was inversely associated with CRC incidence (RR per 1% increase = 0.99). Conclusion Long-term poverty and rural residence were associated with elevated CRC risk in Texas, even after adjusting for screening prevalence. Multi-decade poverty measures and updated RUCA classifications identified geographic disparities not captured by single-year poverty indicators and supported geographically targeted screening, prevention, and resource allocation efforts. These results can inform geographically targeted, efficiency-focused screening and prevention strategies, particularly in communities experiencing decades of structural disadvantage.