Introduction to radiomics for a clinical audience

Clinical Radiology, Journal Year: 2023, Volume and Issue: 78(2), P. 83 - 98

Published: Jan. 11, 2023

Radiomics is a rapidly developing field of research focused on the extraction quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding disease processes and provide clinical decision support. To date, most radiomics has been oncological applications; however, it increasingly being used in raft other diseases. This review gives an overview for audience, including pipeline common pitfalls associated with each stage. Key studies oncology are presented focus both those use analysis alone integrate its multimodal data streams. Importantly, applications outside also presented. Finally, we conclude by offering vision future, how might impact practice as radiologists.

Language: Английский

---

Imaging to Predict Prognosis in Hepatocellular Carcinoma: Current and Future Perspectives

Radiology, Journal Year: 2023, Volume and Issue: 307(3)

Published: April 4, 2023

The focus of hepatocellular carcinoma (HCC) research for many years has been on noninvasive diagnosis. Standardized systematic algorithms composed combinations precise features now serve as diagnostic imaging markers HCC and constitute a major innovation liver imaging. In clinical practice, the diagnosis is based primarily secondarily pathologic analysis if are not specific. Whereas accurate essential, next phase will likely encompass predictive prognostic markers. biologically heterogeneous malignancy because complex molecular, pathologic, patient-level factors that impact outcomes treatment. recent years, there have advances in systemic therapy to augment extend existing large cache local regional options. However, guideposts treatment decisions neither sophisticated nor individualized. This review provides an overview prognosis from patient feature level with future directions toward more individualized guidance. © RSNA, 2023 See also editorial by Fowler et al this issue.

Language: Английский

---

Radiogenomics: a key component of precision cancer medicine

British Journal of Cancer, Journal Year: 2023, Volume and Issue: 129(5), P. 741 - 753

Published: July 6, 2023

Language: Английский

---

Application of artificial intelligence radiomics in the diagnosis, treatment, and prognosis of hepatocellular carcinoma

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 173, P. 108337 - 108337

Published: March 24, 2024

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer, with an increasing incidence and poor prognosis. In past decade, artificial intelligence (AI) technology has undergone rapid development in field clinical medicine, bringing advantages efficient data processing accurate model construction. Promisingly, AI-based radiomics played increasingly important role decision-making HCC patients, providing new technical guarantees for prediction, diagnosis, prognostication. this review, we evaluated current landscape AI management HCC, including its individual treatment, survival Furthermore, discussed remaining challenges future perspectives regarding application HCC.

Language: Английский

---

Advancing precision medicine: the transformative role of artificial intelligence in immunogenomics, radiomics, and pathomics for biomarker discovery and immunotherapy optimization

Cancer Biology and Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 15

Published: Jan. 2, 2025

Artificial intelligence (AI) is significantly advancing precision medicine, particularly in the fields of immunogenomics, radiomics, and pathomics. In AI can process vast amounts genomic multi-omic data to identify biomarkers associated with immunotherapy responses disease prognosis, thus providing strong support for personalized treatments. analyze high-dimensional features from computed tomography (CT), magnetic resonance imaging (MRI), positron emission tomography/computed (PET/CT) images discover tumor heterogeneity, treatment response, progression, thereby enabling non-invasive, real-time assessments therapy. Pathomics leverages deep analysis digital pathology images, uncover subtle changes tissue microenvironments, cellular characteristics, morphological features, offer unique insights into response prediction biomarker discovery. These AI-driven technologies not only enhance speed, accuracy, robustness discovery but also improve precision, personalization, effectiveness clinical treatments, are driving a shift empirical medicine. Despite challenges such as quality, model interpretability, integration multi-modal data, privacy protection, ongoing advancements AI, coupled interdisciplinary collaboration, poised further AI’s roles prediction. improvements expected lead more accurate, strategies ultimately better patient outcomes, marking significant step forward evolution

Language: Английский

---

Preoperative identification of microvascular invasion in hepatocellular carcinoma by XGBoost and deep learning

Journal of Cancer Research and Clinical Oncology, Journal Year: 2020, Volume and Issue: 147(3), P. 821 - 833

Published: Aug. 27, 2020

Microvascular invasion (MVI) is a valuable predictor of survival in hepatocellular carcinoma (HCC) patients. This study developed predictive models using eXtreme Gradient Boosting (XGBoost) and deep learning based on CT images to predict MVI preoperatively. In total, 405 patients were included. A total 7302 radiomic features 17 radiological extracted by radiomics feature extraction package radiologists, respectively. We XGBoost model features, clinical variables three-dimensional convolutional neural network (3D-CNN) status. Next, we compared the efficacy two models. Of patients, 220 (54.3%) positive, 185 (45.7%) negative. The areas under receiver operating characteristic curves (AUROCs) Radiomics-Radiological-Clinical (RRC) Model 3D-CNN training set 0.952 (95% confidence interval (CI) 0.923-0.973) 0.980 CI 0.959-0.993), respectively (p = 0.14). AUROCs RRC validation 0.887 0.797-0.947) 0.906 0.821-0.960), 0.83). Based status predicted Models, mean recurrence-free (RFS) was significantly better MVI-negative group than that MVI-positive (RRC Model: 69.95 vs. 24.80 months, p < 0.001; 64.06 31.05 0.027). showed considerable identifying These machine may facilitate decision-making HCC treatment but requires further validation.

Language: Английский

---

Liver transplantation for hepatocellular carcinoma: Management after the transplant

American Journal of Transplantation, Journal Year: 2019, Volume and Issue: 20(2), P. 333 - 347

Published: Nov. 11, 2019

Hepatocellular carcinoma (HCC) is an increasingly common indication for liver transplantation (LT) in the United States and many parts of world. In last decade, significant work has been done to better understand how risk stratify LT candidates recurrence HCC following transplant using a combination biomarker imaging findings. However, despite high frequency population, guidance regarding posttransplant management lacking. particular, there no current evidence support specific post-LT surveillance strategies, leading heterogeneity practices. addition, are recommendations prevention, including immunosuppression regimen or secondary prevention with adjuvant chemotherapy. Finally, on treatment disease also lacking controversy about use immunotherapy recipients due rejection. Thus, outcomes patients poor. This paper therefore provides comprehensive review literature identifies gaps our knowledge that urgent need further investigation.

Language: Английский

---

Radiomics and Deep Learning: Hepatic Applications

Korean Journal of Radiology, Journal Year: 2020, Volume and Issue: 21(4), P. 387 - 387

Published: Jan. 1, 2020

Radiomics and deep learning have recently gained attention in the imaging assessment of various liver diseases.Recent research has demonstrated potential utility radiomics staging fibroses, detecting portal hypertension, characterizing focal hepatic lesions, prognosticating malignant tumors, segmenting tumors.In this review, we outline basic technical aspects summarize recent investigations application these techniques disease.

Language: Английский

---

Multiphase Liver MRI for Identifying the Macrotrabecular-Massive Subtype of Hepatocellular Carcinoma

Radiology, Journal Year: 2020, Volume and Issue: 295(3), P. 562 - 571

Published: March 31, 2020

Background The recently described "macrotrabecular-massive" (MTM) histologic subtype of hepatocellular carcinoma (HCC) (MTM-HCC) represents an aggressive form HCC and is associated with poor survival. Purpose To investigate whether preoperative MRI can help identify MTM-HCCs in patients HCC. Materials Methods This retrospective study included treated surgical resection between January 2008 February 2018 who underwent multiphase contrast material-enhanced MRI. Least absolute shrinkage selection operator (LASSO)-penalized multivariable logistic regression analyses were performed to clinical, biologic, imaging features the MTM-HCC subtype. Early recurrence (within 2 years) overall evaluated by using Kaplan-Meier analysis. Multivariable Cox analysis was determine predictors early recurrence. Results One hundred fifty-two (median age, 64 years; interquartile range, 56-72 126 men) 152 HCCs evaluated. Twenty-six (17%) MTM-HCCs. LASSO-penalized identified substantial necrosis, high serum α-fetoprotein (AFP) level (>100 ng/mL), Barcelona Clinic Liver Cancer (BCLC) stage B or C as independent At analysis, necrosis (odds ratio = 32; 95% confidence interval [CI] 8.9, 114; P < .001), AFP 4.4; CI 1.3, 16; .02), BCLC 4.2; 1.2, 15; .03) Substantial helped 65% (17 26; CI: 44%, 83%) (sensitivity) a specificity 93% (117 126; 87%, 97%). In adjusted models, only presence satellite nodules independently both (hazard 3.7; 1.5, 9.4; .006) 3.0; 7.2; .01) tumor Conclusion contrast-enhanced MRI, macrotrabecular-massive specificity. © RSNA, 2020.

Language: Английский

---

Systematic review: radiomics for the diagnosis and prognosis of hepatocellular carcinoma

Alimentary Pharmacology & Therapeutics, Journal Year: 2021, Volume and Issue: 54(7), P. 890 - 901

Published: Aug. 12, 2021

Summary Background Advances in imaging technology have the potential to transform early diagnosis and treatment of hepatocellular carcinoma (HCC) through quantitative image analysis. Computational “radiomic” techniques extract biomarker information from images which can be used improve predict tumour biology. Aims To perform a systematic review on radiomic features HCC prognosis, with focus reporting metrics methodologic standardisation. Methods We performed all full‐text articles published inception December 1, 2019. Standardised data extraction quality assessment were applied studies. Results A total 54 studies included for Radiomic demonstrated good discriminatory performance differentiate other solid lesions (c‐statistics 0.66‐0.95), microvascular invasion (c‐statistic 0.76‐0.92), recurrence after hepatectomy 0.71‐0.86), prognosis locoregional or systemic therapies 0.74‐0.81). Common stratifying diagnostic prognostic tools analyses skewness, analysis peritumoural region, feature arterial phase. The overall was low, common deficiencies both internal external validation, standardised segmentation, lack comparison gold standard. Conclusions Quantitative demonstrates promise as non‐invasive management. However, standardisation protocols outcome measurement, sharing algorithms analytic methods, validation are necessary prior widespread application radiomics clinical practice.

Language: Английский

---