Enhancement pattern mapping technique for improving contrast‐to‐noise ratios and detectability of hepatobiliary tumors on multiphase computed tomography

Abstract

Purpose-Currently, radiologists use tumor-to-normal tissue contrast across multiphase computed tomography (MPCT) for lesion detection. Here, we developed a novel voxel-based enhancement pattern mapping (EPM) technique and investigated its ability to improve contrast-tonoise ratios (CNRs) in a phantom study and in patients with hepatobiliary cancers. Methods-The EPM algorithm is based on the root mean square deviation between each voxel and a normal liver enhancement model using patient-specific (EPM-PA) or population data (EPM-PO). We created a phantom consisting of liver tissue and tumors with distinct enhancement signals under varying tumor sizes, motion, and noise. We also retrospectively evaluated 89 patients with hepatobiliary cancers who underwent active breath-hold MPCT between 2016 and 2017. MPCT phases were registered using a three-dimensional deformable image registration algorithm. For the patient study, CNRs of tumor to adjacent tissue across MPCT phases, EPM-PA and EPM-PO were measured and compared.Results-EPM resulted in statistically significant CNR improvement (P < 0.05) for tumor sizes down to 3 mm, but the CNR improvement was significantly affected by tumor motion and image noise. Eighty-two of 89 hepatobiliary cases showed CNR improvement with EPM (PA or PO) over grayscale MPCT, by an average factor of 1.4, 1.6, and 1.5 for cholangiocarcinoma, hepatocellular carcinoma, and colorectal liver metastasis, respectively (P < 0.05 for all).Conclusions-EPM increases CNR compared with grayscale MPCT for primary and secondary hepatobiliary cancers. This new visualization method derived from MPCT datasets may have applications for early cancer detection, radiomic characterization, tumor treatment response, and segmentation.Implications for patient care-We developed a voxel-wise enhancement pattern mapping (EPM) technique to improve the contrast-to-noise ratio (CNR) of multiphase CT. The improvement in CNR was observed in datasets of patients with cholangiocarcinoma, hepatocellular carcinoma, and colorectal liver metastasis. EPM has the potential to be clinically useful for cancers with regard to early detection, radiomic characterization, response, and segmentation.

Radiomics, deep learning and early diagnosis in oncology

“…In this mini-review article, I have primarily focused on breast cancer and reviewed how medical imaging, including screening mammography and MRI, and their quantitative modeling, including radiomics and deep learning, have advanced the early detection and treatment response prediction of breast cancer. Substantial progresses have also been made in quantitative modeling of medical imaging for other cancer sites, such as low-dose CT screening for lung cancer [ 37 ], pathology imaging for lung cancer diagnosis [ 38 ], diagnosis and treatment response prediction of liver cancer [ 39 , 40 ], to name a few. Despite the promising performance of deep learning models which often outperform experienced radiologists [ 6 , 25 ], they have been largely developed and studied in the academic and research settings, not yet implemented and integrated in the clinical setting.…”

Predictive Modeling for Voxel-Based Quantification of Imaging-Based Subtypes of Pancreatic Ductal Adenocarcinoma (PDAC): A Multi-Institutional Study

“…This disproportion might have influenced the model ability to elicit more significant differences in the clinical outcome in D3. The future directions for this work include identifying whether the molecular subtypes of PDAC associate with these imaging-based phenotypes, characterizing the stromal and immune cellular populations, evaluating the dynamic changes in these phenotypes in response to therapy, exploring the potential use of this voxel-based quantitative tool to characterize pre-malignant pancreatic lesions, such as intraductal papillary mucinous neoplasms (IPMNs), to differentiate benign from malignant mucinous pancreatic cysts, and finally, applying a similar classification to other hepatobiliary cancers, notably intrahepatic cholangiocarcinoma [28][29][30][31].…”

Imaging-Based Subtypes of Pancreatic Ductal Adenocarcinoma Exhibit Differential Growth and Metabolic Patterns in the Pre-Diagnostic Period: Implications for Early Detection

“…Finally, we acknowledge that the data was from a single institution with limited number of patients that requires further external validation. Future directions include multi-institutional validation, developing a deep learning-based technique to detect and classify the imaging-based subtypes of PDAC, investigating the molecular basis associated with different growth patterns, and enhancing CT imaging capacities to detect PDAC earlier through amplifying faint abnormal signals in the pancreas ( 31 ).…”