Spatially resolved transcriptomics is a relatively new technique that maps transcriptional information within a tissue. Analysis of these datasets is challenging because gene expression values are highly sparse due to dropout events, and there is a lack of tools to facilitate in silico detection and annotation of regions based on their molecular content. Therefore, we develop a computational tool for detecting molecular regions and region-based Missing value Imputation for Spatially Transcriptomics (MIST). We validate MIST-identified regions across multiple datasets produced by 10x Visium Spatial Transcriptomics, using manually annotated histological images as references. We benchmark MIST against a spatial k-nearest neighboring baseline and other imputation methods designed for single-cell RNA sequencing. We use holdout experiments to demonstrate that MIST accurately recovers spatial transcriptomics missing values. MIST facilitates identifying intra-tissue heterogeneity and recovering spatial gene-gene co-expression signals. Using MIST before downstream analysis thus provides unbiased region detections to facilitate annotations with the associated functional analyses and produces accurately denoised spatial gene expression profiles.