The deposition and mixing of carbonates and siliciclastics in the Cisco Group of the Eastern Shelf of the Permian Basin are complicated by the temporal overlap between icehouse eustatic sea-level oscillations and fluctuations in sediment influx due to the rejuvenation of the Ouachita fold belt. Previous investigators have used well-log correlation as the primary tool in their interpretations of the area’s reciprocal depositional model, but well-log correlation alone cannot explain the full range of spatial lithology variations in the system. To better understand the lithology variation in the area, we used an integrated technique that combined wireline log information from 17 wells with 625 km2 3D seismic data through post-stack seismic inversion, probabilistic neural networks, and Bayesian classification. We used deterministic matrix inversion to derive lithology classes from well logs. Cross-plot analyses revealed that the acoustic impedance and neutron porosity log pair could be used to differentiate lithologies. We performed model-based post-stack inversion to generate a P-impedance volume and used probabilistic neural networks to generate a neutron porosity volume. We combined these volumes through supervised Bayesian classification to generate lithology probability volumes for each lithology and a most probable lithology volume throughout the seismic data. The lithology volumes highlight dominant lithologies (carbonate, shale, sand, and mixed) that allowed interpretation of major carbonate platforms, sand-to-shale ratio variations, carbonate build-ups between wells, and channel fill lithologies. Our proposed semi-automated lithology detection workflow applies to regional studies and is also valid for reservoir-scale studies to determine variations in lithologies.