Purpose <p>This study pioneers the application of chaotic compressed sensing (CCS) to density imaging in ultrasound tomography, an approach not previously explored. CCS reduces the number of required measurements, enhancing efficiency without compromising image quality. Simultaneously, incorporating tissue density parameters significantly improves soft tissue visualization, critical for detecting small objects like tumors. By addressing computational and hardware challenges, this research introduces an efficient combination of CCS and density imaging, advancing the effectiveness and practicality of ultrasound tomography for diagnostic applications.</p> Methods <p>The proposed approach integrates CCS with sparse signal recovery, utilizing pseudo-random sampling to reduce measurement complexity. Density parameters are included in an extended DBIM framework for better soft tissue contrast. Simulations were conducted to compare CCS-DBIM with traditional DBIM, evaluating performance across varying compression ratios and noise levels to demonstrate improvements in efficiency and imaging quality.</p> Results <p>CCS-DBIM reduced normalization errors by 40% compared to traditional DBIM, even at compression ratios of 0.5. Incorporating density imaging enhanced soft tissue contrast, crucial for detecting small objects. Although CCS increased computation times, it provided superior noise suppression and accurate reconstructions in early iterations, highlighting its potential for practical diagnostic applications.</p> Conclusion <p>Combining CCS and density imaging revolutionizes ultrasound tomography by enhancing efficiency and soft tissue visualization. CCS reduces hardware and computational demands, while density imaging improves diagnostic reliability. Despite longer computation times, advancements in parallel processing ensure feasibility. This approach significantly advances the accuracy and practicality of ultrasound tomography for medical diagnostics.</p>