Imaging Pearls ❯ Liver ❯ Radiomics
|
-- OR -- |
|
- “Radiomics is the high-throughput extraction of quantitative features from radiological images through data characterization algorithms. These features contain information representing pathophysiological mechanisms imperceptible to the human eye. Radiomic features have been linked to metabolic dysfunction– associated steatotic liver disease, cirrhosis, and tumor biological processes like hypoxia, angiogenesis, and inflammation. Quantitative assessment of these features can be used to predict the behavior of cancer, postoperative course, and surgical morbidity.”
Radiomics for Treatment Planning in Liver Cancers.
Mian A, Kamnitsas K, Gordon-Weeks A.
JAMA Surg. 2025 Feb 26. doi: 10.1001/jamasurg.2024.4346. Epub ahead of print. PMID: 40009391. - “Radiomics enables the noninvasive profiling of tumors through routine radiological images. By characterizing the tumor biological phenotype through imaging data, radiomics can provide personalized pretreatment prognostication. It can eliminate invasive biopsies and outperforms somatic sequence variation testing for selection of biological therapies—a particularly important consideration for colorectal liver metastases (CRLMs), where biopsy significantly risks tumor cell seeding, and for cholangiocarcinoma, which is technically challenging to sample. Implementation does not require specialist diagnostic or biochemical expertise and is, in principal, cost-effective compared with competitor prognostics, including circulating tumor DNA or cancer cells.”
Radiomics for Treatment Planning in Liver Cancers.
Mian A, Kamnitsas K, Gordon-Weeks A.
JAMA Surg. 2025 Feb 26. doi: 10.1001/jamasurg.2024.4346. Epub ahead of print. PMID: 40009391. - “Similarly, in HCC, computed tomography (CT) radiomic texture analysis, maybe used to facilitate therapeutic decision-making alongside the Barcelona Clinic Liver Cancer (BCLC) criteria when considering surgical resection, transplant, or other liver-directed therapies. In CRLM, radiomics may also assist in determining optimal surgical resection margins by predicting KRAS sequence variations or identifying replacement-type growth, both of which require wider resection margins. Finally, radiomics approaches could aid in forecasting the volume and health of the future liver remnant post–major hepatectomy.”
Radiomics for Treatment Planning in Liver Cancers.
Mian A, Kamnitsas K, Gordon-Weeks A.
JAMA Surg. 2025 Feb 26. doi: 10.1001/jamasurg.2024.4346. Epub ahead of print. PMID: 40009391. - “Radiomics has demonstrated multiple uses in liver cancers. One large, prospective study demonstrated that a radiomics signature derived from CRLM CT scans outperformed the Response Evaluation Criteria in Solid Tumors (RECIST) criteria for predicting folinic acid, fluorouracil, and irinotecan (FOLFIRI) and bevacizumab response. These findings were supported by another study, where radiomics features outperformed RECIST and KRAS sequence variation status, with the radiomics signature predicting response to FOLFIRI and cetuximab with an area under the curve (AUC) of 0.80 compared with only 0.67 for KRAS status and 0.75 for 8-week tumor shrinkage measured by RECIST. This information can guide early chemotherapy regimen switching in nonresponders and identify patients for resection based on favorable biology. Futurework should explore if radiomics provides relevant insights into the biology of KRAS mutant vs wild-type CRLM.”
Radiomics for Treatment Planning in Liver Cancers.
Mian A, Kamnitsas K, Gordon-Weeks A.
JAMA Surg. 2025 Feb 26. doi: 10.1001/jamasurg.2024.4346. Epub ahead of print. PMID: 40009391. - “In HCC, radiomics and clinical features predicted transarterial chemoembolization (TACE) response with an AUC of 0.90, which was linked to improved survival in the external validation cohort (hazard ratio, 2.43; P < .05). This study, which focused on patients with BCLC stage B disease, raises the question of whether a selection of patients may benefit from liver transplant outside the Milan criteria vs palliative TACE alone. For cholangiocarcinoma, a combination of radiomics and clinical features improved recurrence-free survival prediction (C index: 0.75) vs clinical features alone (C index: 0.69) in external validation. Given high rates of postsurgical recurrence in this patient cohort, further improvements will identify a subset of high-risk patients who should be offered neoadjuvant systemic therapy as a test of biological behavior rather than up-front resection.”
Radiomics for Treatment Planning in Liver Cancers.
Mian A, Kamnitsas K, Gordon-Weeks A.
JAMA Surg. 2025 Feb 26. doi: 10.1001/jamasurg.2024.4346. Epub ahead of print. PMID: 40009391. - “A major challenge in radiomics is limited generalizability of models due to reliance on single-center data, which fails to account for variability in patient characteristics (eg, ethnicity, age, tumor biology), imaging protocols, and the scanners differences. Some radiomic features are sensitive to these variations, reducing reproducibility across institutions. Solutions include using robust features, multiinstitutional data, standardized imaging protocols, data augmentation (eg, generative adversarial networks), and harmonization techniques likeComBat. The Image Biomarker Standardization Initiative has played a key role in standardizing radiomic biomarker nomenclature and definitions. It has also created benchmark datasets and benchmarking values to verify image processing and biomarker calculations, while also developing robust reporting guidelines high-throughput image analysis. This is now helping drive the reliability and reproducibility of radiomic analyses across diverse datasets to develop generalizable radiomic models.”
Radiomics for Treatment Planning in Liver Cancers.
Mian A, Kamnitsas K, Gordon-Weeks A.
JAMA Surg. 2025 Feb 26. doi: 10.1001/jamasurg.2024.4346. Epub ahead of print. PMID: 40009391.
- Purpose: To enhance clinician’s decision-making by diagnosing hepatocellular carcinoma (HCC) in cirrhotic patients with indeterminate liver nodules using quantitative imaging features extracted from triphasic CT scans.
Conclusion: A signature using a single feature was validated in a multicenter retrospective cohort to diagnose HCC in cirrhotic patients with indeterminate liver nodules. Artificial intelligence could enhance clinicians’ decision by identifying a subgroup of patients with high HCC risk.
Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules
Fatima-Zohra Mokrane et al.
European Radiology (2020) 30:558–570 - "Our study assembled the largest radiomics dataset of indeterminate cirrhotic liver nodules to date and offers a proof of concept that machine-learning-based radiomics signature using change in quantitative CT features across the arterial and portal venous phases can allow a non-invasive accurate diagnosis of HCCs in cirrhotic patients with indeterminate nodules. This signature would allow for identification of high HCC–risk patients, who should be prioritized for therapy, allowing thus clinically significant benefits.”
Radiomics machine-learning signature for diagnosis of hepatocellular carcinoma in cirrhotic patients with indeterminate liver nodules
Fatima-Zohra Mokrane et al.
European Radiology (2020) 30:558–570
- “Radiomics is a new field in medical imaging with the potential of changing medical practice. Radiomics is characterized by the extraction of several quantitative imaging features which are not visible to the naked eye from conventional imaging modalities, and its correlation with specific relevant clinical endpoints, such as pathology, therapeutic response, and survival. Several studies have evaluated the use of radiomics in patients with hepatocellular carcinoma (HCC) with encouraging results, particularly in the pretreatment prediction of tumor biological characteristics, risk of recurrence, and survival.”
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press) - Radiomics is an emerging field that converts medical imaging into high‐dimensional mineable features, providing a quantitative assessment of the image. These features can then be associated to clinical endpoints, such as pathology, therapeutic response, and survival. With the quantitative analysis of digital imaging, radiomics can potentially detect specific characteristics of a disease that otherwise could not be accessed visually with a potential to inform future precision medicine.”
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press) - “Radiomics is characterized by the extraction of quantitative imaging features from conventional imaging modalities using computer based algorithms and the correlation of these features with relevant clinical endpoints, such as pathology, therapeutic response, and survival. These quantitative data are called radiomics features, of which texture features are a subset.”
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press) 
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press)- “Morphological features reflect volume, shape, and 3D geometric properties of the segmented ROI/VOI. Examples include diameter, surface area, volume, surface‐to‐volume ratio (an indirect measurement to assess spiculations), compactness, and sphericity. It also describes certain tumor characteristics, including location, vascularization, and presence of necrosis. These features are especially useful in tumor prognostication and diagnosis, including in the differentiation of benign and malignant lesions.”
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press) - "First-order statistics features are based on the first‐order histogram that describes distribution of voxel intensities in an image. The most common first‐order features are as fol‐ lows: (a) mean/median, average intensity of the pixels in the ROI/VOI; (b) standard deviation, dispersion of the mean, higher values indicate a wide range of intensity of the pixels in the ROI/VOI; (c) skewness, asymmetry of histogram, with positive values corresponding to a longer right tail of the his‐ togram; (d) kurtosis, magnitude of the histogram, with posi‐ tive values indicating that the curve is taller than a normal distribution; and (e) entropy, irregularity or randomness of the intensities, high values demonstrate a more heterogeneous area.”
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press) - "Second-order statistics features consider the inter‐voxel relationships in an image. Using grey level dependence matrices, the second‐order statistical features can be classi‐ fied into three groups: (a) grey level co‐occurrence matrix (GLCM); (b) grey level run length matrix (GLRLM); and (c) grey level size zone matrix (GLSZM). While GLCM considers the incidence of voxels of the same grey value at a predetermined distance along a fixed direction, GLRLM considers the incidence of voxels of the more than one grey alue using a fixed direction and GLSZM uses all matrix directions in the same evaluation.”
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press) - “Superior or higher-order statistics features these features have the advantage of considering the relationship with neighboring voxels [36] and are obtained using neighbor‐ hood grayscale difference matrices [32]. In this process, higher‐order statistical methods impose filter grids on the image to extract repetitive or nonrepetitive patterns.”
State‐of‐the‐art in radiomics of hepatocellular carcinoma: a review of basic principles, applications, and limitations
Santos JM et al.
Abdominal Radiology 2019 (in press)
- Objectives: To assess whether radiomics signature can identify aggressive behavior and predict recurrence of hepatocellular carcinoma (HCC) after liver transplantation.
Results: The stable radiomics features associated with the recurrence of HCC were simply found in arterial phase and portal phase. The prediction model based on the radiomics features extracted from the arterial phase showed better prediction performance than the portal vein phase or the fusion signature combining both of arterial and portal vein phase. A radiomics nomogram based on combined model consisting of the radiomics signature and clinical risk factors showed good predictive performance for RFS with a C-index of 0.785 (95% confidence interval [CI]: 0.674-0.895) in the training dataset and 0.789 (95% CI: 0.620-0.957) in the validation dataset. The calibration curves showed agreement in both training (p = 0.121) and validation cohorts (p = 0.164).
Conclusions: Radiomics signature extracted from CT images may be a potential imaging biomarker for liver cancer invasion and enable accurate prediction of HCC recurrence after liver transplantation.
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 - “Microvascular invasion (MVI) and consequently, early tumor recurrence, is noted in 20% of patients undergoing liver transplantation, reducing the 5-year survival from 80% to 40% after liver transplantation . Recurrence has been the main factor that affects the curative effect of HCC after liver transplantation. Prospective identification of recurrence in patients with HCC thus has direct implications for organ allocation, surgical techniques, prognosis, and public policy.”
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 - “Previous reports have indicated that some radiomic features extracted from tumor regions of CT images, especially characteristics of arterial and portal phases, can surpass traditional indicators such as Barcelona Clinic Liver Cancer (BCLC) for assessing the efficacy of HCC hepatectomy. These high-throughput characteristics related to MVI (Microvascular invasion) or prognosis of HCC may be potential independent predictors of HCC recurrence after liver transplantation.”
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 - Radiomics signature was built with the rad-score of arterial phase. A combined predictive model was built by incorporating the clinical risk factors and radiomics signature with multivariable Cox regression model. Patients were finally stratified into high-risk and low-risk groups based on the combined model with cut-off values at the median of the training dataset in arterial phase. The Log- rank test was computed to compare the two separated KM survival curves.”
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 - “A multi-feature-based radiomics signature was identified to be an effective biomarker for the prediction of HCC recurrence after liver transplantation in this study, with potential prognosis value for individualized RFS. The radiomics signature successfully stratified patients with HCC into high-risk and low-risk groups, with significant differences in RFS. Furthermore, the radiomics nomogram based on the combined model which integrates effective clinical characteristics and radiomics signature showed good discrimination and prominent predictive performance for RFS in HCC patients after liver transplantation.”
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 - “For patients with high recurrence, liver transplantation is not recommended, so that the scarce donor liver resources can be allocated to patients who urgently need liver transplantation and have a good prognosis.”
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 - “ It is conducive to fully exploit potential images using artificial intelligence and big data technology to overcome limitations of traditional evaluation methods, improve the predictive performance of HCC recurrence after liver transplantation, facilitate the rational distribution of donors in clinical practice, and conduct neces- sary intraoperative or postoperative prophylactic treatment for patients with high recurrence.”
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 - Although the usefulness of the proposed nomogram lacks external validation, calibration curve analysis demonstrated that the radiomics nomogram was consistent with actual observations for the probability of tumor recurrence at 1, 2, or 3 years. This indicates that radiomics signature has the potential to be used as a biomarker for recurrence in HCC patients after liver transplantation. Further, radiomics can be used to predict MVI and histopathological differentiation closely related to prognosis of HCC. Radiomics technique is expected to become an important cornerstone of accurate diagnosis and treatment of HCC.
Radiomics analysis enables recurrence prediction for hepatocellular carcinoma after liver transplantation
Donghui Guo et al.
European Journal of Radiology 117 (2019) 33–40 