Application of Lossy and Lossless Compression to DICOM Files

The Digital Imaging and Communications in Medicine (DICOM) standard is widely utilized for the management, storage, and transfer of medical images. However, the substantial file sizes associated with DICOM data present challenges in terms of storage and data transmission. Data reduction techniques help address these challenges by minimizing the size of the data while preserving its integrity. This thesis examines various compression methods aimed at reducing the size of DICOM files. We evaluate five lossless compressors and four lossy compressors on DICOM data to compare and assess their performance. Through an analysis of each compressor’s compression efficiency and resulting image fidelity, this research aims to determine the most effective compression strategy. The results demonstrate that SZ3 achieves a compression ratio of 183.74× with an error bound of 1e−7, while ZFP achieves a compression bandwidth of 303.82 MB/s with the same error bound. Another thesis focuses on applying lossy compression to a Convolutional Neural Network (CNN) model for detecting lung anomalies using DICOM files. Due to their ability to store detailed metadata alongside image data, DICOM files are extensively employed in medical imaging applica- tions, making them well-suited for this task format-wise as well.The CNN model was trained on a dataset comprising CT scans of human lungs categorized into cancerous and non-cancerous cases. Data preprocessing steps such as lossy compression and normalization were applied to enhance model performance. Subsequently,the model underwent evaluation using separate training, validation,and testing datasets ensuring robustness.