Abstract
Different scanners employ various image acquisition techniques and may store scanned images in proprietary formats or export them to a range of standard file formats. Understanding these technical limitations is essential for ensuring optimal scan quality and accurate image analysis. The present study compared image formats from two whole-slide imaging platforms-Leica's Aperio AT2 (.SVS) and 3DHistech's Panoramic P250 Flash III (.MRXS)-using artificial intelligence (AI) algorithms to quantify pixel-level, color-profile, and segmentation differences on 10 colorectal carcinoma (CRC) and 10 non-small cell lung carcinoma (NSCLC) cases. The same slides were scanned independently on both platforms at 20×, and native MRXS files were also converted to SVS using SlideMaster®, allowing us to isolate the effect of file-format translation (native MRXS vs. MRXS-to-SVS, same scanner) from that of scanner hardware (3DHistech-derived formats vs. native Aperio SVS). Native MRXS and MRXS-to-SVS files showed very high similarity in pixel values, color profile, and AI predictions, whereas native Aperio SVS files differed significantly across image size, pixel size, pixel number, and color profile-reflecting the combined effect of scanner hardware and file format rather than format alone. Given the limited sample size and absence of a pre-specified power analysis, these findings are exploratory and hypothesis-generating. We anticipate that an enterprise-level communication standard will emerge to harmonize image formats and support consistent, reproducible analysis by pathologists and AI software alike.