-
European Radiology Oct 2023Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field... (Review)
Review
OBJECTIVES
Machine learning (ML) for medical imaging is emerging for several organs and image modalities. Our objectives were to provide clinicians with an overview of this field by answering the following questions: (1) How is ML applied in liver computed tomography (CT) imaging? (2) How well do ML systems perform in liver CT imaging? (3) What are the clinical applications of ML in liver CT imaging?
METHODS
A systematic review was carried out according to the guidelines from the PRISMA-P statement. The search string focused on studies containing content relating to artificial intelligence, liver, and computed tomography.
RESULTS
One hundred ninety-one studies were included in the study. ML was applied to CT liver imaging by image analysis without clinicians' intervention in majority of studies while in newer studies the fusion of ML method with clinical intervention have been identified. Several were documented to perform very accurately on reliable but small data. Most models identified were deep learning-based, mainly using convolutional neural networks. Potentially many clinical applications of ML to CT liver imaging have been identified through our review including liver and its lesion segmentation and classification, segmentation of vascular structure inside the liver, fibrosis and cirrhosis staging, metastasis prediction, and evaluation of chemotherapy.
CONCLUSION
Several studies attempted to provide transparent result of the model. To make the model convenient for a clinical application, prospective clinical validation studies are in urgent call. Computer scientists and engineers should seek to cooperate with health professionals to ensure this.
KEY POINTS
• ML shows great potential for CT liver image tasks such as pixel-wise segmentation and classification of liver and liver lesions, fibrosis staging, metastasis prediction, and retrieval of relevant liver lesions from similar cases of other patients. • Despite presenting the result is not standardized, many studies have attempted to provide transparent results to interpret the machine learning method performance in the literature. • Prospective studies are in urgent call for clinical validation of ML method, preferably carried out by cooperation between clinicians and computer scientists.
Topics: Humans; Artificial Intelligence; Liver Neoplasms; Machine Learning; Prospective Studies; Tomography, X-Ray Computed
PubMed: 37171491
DOI: 10.1007/s00330-023-09609-w -
Radiotherapy and Oncology : Journal of... Jan 2022To suggest PTV margins for liver SBRT with different motion management strategies based on a systematic review and meta-analysis. (Meta-Analysis)
Meta-Analysis Review
PURPOSE
To suggest PTV margins for liver SBRT with different motion management strategies based on a systematic review and meta-analysis.
METHODS
In accordance with Preferred-Reporting-Items-for-Systematic-Reviews-and-Meta-Analyses (PRISMA), a systematic review in PubMed, Embase and Medline databases was performed for liver tumor position variability. From an initial 533 studies published before October 2020, 36 studies were categorized as 18 free-breathing (FB; n = 401), 9 abdominal compression (AC; n = 145) and 9 breath-hold (BH; n = 126). A meta-analysis was performed on inter- and intra-fraction position variability to report weighted-mean with 95% confidence interval (CI) in superior-inferior (SI), left-right (LR) and anterior-posterior (AP) directions. Furthermore, weighted-mean ITV margins were computed for FB (n = 15, n = 373) and AC (n = 6, n = 97) and PTV margins were computed for FB (n = 6, n = 95), AC (n = 7, n = 106) and BH (n = 8, n = 133).
RESULTS
The FB weighted-mean intra-fraction variability, ITV margins and weighted-standard-deviation in mm were SI-9.7, CI = 9.3-10.1, 13.5 ± 4.9; LR-5.4, CI = 5.3-5.6, 7.3 ± 7.9; and AP-4.2, CI = 4.0-4.4, 6.3 ± 7.6. The inter-fraction-based results were SI-4.7, CI = 4.3-5.1, 5.7 ± 1.7; LR-1.4, CI = 1.1-1.6, 3.6 ± 2.7; and AP-2.8, CI = 2.5-3.1, 4.8 ± 2.1. For AC intra-fraction results in mm were SI-1.8, CI = 1.6-2.0, 2.6 ± 1.2; LR-0.7, CI = 0.6-0.8, 1.7 ± 1.5; and AP-0.9, CI = 0.8-1.0, 1.9 ± 1.7. The inter-fraction results were SI-2.6, CI = 2.3-3.0, 5.2 ± 2.9; LR-1.9, CI = 1.7-2.1, 4.0 ± 2.2; and AP-2.9, CI = 2.5-3.2, 5.8 ± 2.7. For BH the inter-fraction variability, and the weighted-mean PTV margins and weighted-standard-deviation in mm were SI-2.4, CI = 2.1-2.7, 5.6 ± 2.9; LR-1.8, CI = 1.3-2.2, 5.5 ± 1.7; and AP-1.4; CI = 1.2-1.7, 6.1 ± 2.1.
CONCLUSION
Our meta-analysis suggests a symmetric weighted-mean PTV margin of 6 mm might be appropriate for BH. For AC and FB, asymmetric PTV margins (weighted-mean margin of 4 mm (AP), 6 mm (SI/LR)) might be appropriate. For FB, if larger (>ITV margin) intra-fraction variability observed, the additional intra- and inter-fraction variability should be accounted in the PTV margin.
Topics: Breath Holding; Humans; Liver Neoplasms; Motion; Radiosurgery; Radiotherapy Planning, Computer-Assisted
PubMed: 34843841
DOI: 10.1016/j.radonc.2021.11.022 -
Transplantation Reviews (Orlando, Fla.) Oct 2020Liver transplantation (LT) has gained interest in the treatment of unresectable colorectal liver metastases (CRLM) over the last two decades. Despite the initial poor... (Review)
Review
BACKGROUND
Liver transplantation (LT) has gained interest in the treatment of unresectable colorectal liver metastases (CRLM) over the last two decades. Despite the initial poor outcomes, recent reports from countries with graft abundance have provided further insights in the potential of LT as a treatment for unresectable CRLM.
METHODS
A systematic literature search was conducted in the MEDLINE (PubMed), Embase, Scopus, Cochrane Library, Google Scholar, Virtual Health Library, Clinicaltrials.gov, and Web of Science databases (end-of-search date: January 27th, 2020) to identify relevant studies. Pooled overall and recurrence-free survival analysis at 6 months, 1, 2, 3, and 5 years was conducted with the Kaplan-Meier (Product Limit) method.
RESULTS
Eighteen studies comprising 110 patients were included. The population consisted of 59.8% males with a mean age of 52.3 ± 9.3 years. CRLM diagnosis was synchronous in 83%, while 99% received chemotherapy, and 39% received liver resection prior to LT. The mean time from primary tumor resection to LT was 39.5 ± 32.5 months, the mean post-LT follow-up was 32.1 ± 22.2 months, and the mean time to recurrence was 15.0 ± 11.3 months. The pooled 6-month, 1-, 2-, 3-, and 5-year overall survival rates were 95.7% (95%CI: 89.1%-98.4%), 88.1% (95%CI: 79.6%-93.2%), 74.6% (95%CI: 64.2%-82.3%), 58.4% (95%CI: 47.2%-62.0%), and 50.5% (95%CI: 39.0%-61.0%), respectively. The pooled 6-months, 1-, 2-, 3-, and 5-year recurrence-free survival rates were 77.2% (95%CI: 67.2%-84.5%), 59.9% (95%CI: 49.0%-69.2%), 42.4% (95%CI: 31.8%-52.6%), 30.7% (95%CI: 20.9%-41.1%), and 25.6% (95%CI: 16.2%-36.0%), respectively.
CONCLUSION
LT should be considered in patients with unresectable liver-only CRLM under strict selection criteria and only under well-designed research protocols. Ongoing studies are expected to further elucidate the indications and prognosis of patients undergoing LT for unresectable CRLM.
Topics: Adult; Colorectal Neoplasms; Female; Hepatectomy; Humans; Liver Neoplasms; Liver Transplantation; Male; Middle Aged; Neoplasm Recurrence, Local
PubMed: 33002670
DOI: 10.1016/j.trre.2020.100570 -
Annals of Medicine 2023The aim of this study was to compare and rank different targeted therapies or immunotherapies for advanced hepatocellular carcinoma based on efficacy. (Meta-Analysis)
Meta-Analysis Review
Molecular targeted therapy and immunotherapy in advanced hepatocellular carcinoma: a systematic review and Bayesian network meta-analysis based on randomized controlled trials.
OBJECTIVE
The aim of this study was to compare and rank different targeted therapies or immunotherapies for advanced hepatocellular carcinoma based on efficacy.
METHODS
A systematic search of the PubMed, EMBASE, and Cochrane Library databases was conducted. All systematic treatment regimens that reported comparisons with sorafenib were included in this analysis. The primary outcome measures were overall survival (OS) and progression-free survival (PFS), and other outcome measures included the objective response rate (ORR) and safety analysis according to reported treatment-related adverse events.
RESULTS
A total of 29 RCTs involving 13376 patients were included in the analysis, including 10 single-agent therapies and 17 combination therapies. Compared with sorafenib, sintilimab plus IBI305 (HR: 0.57, 95% CI: 0.43-0.75), camrelizumab plus rivoceranib (HR: 0.62, 95% CI: 0.49-0.78), and atezolizumab plus bevacizumab (HR: 0.66, 95% CI: 0.52-0.83) ranked in the top three in terms of OS.
CONCLUSIONS
PD-1/PD-L1 inhibitors combined with anti-vascular endothelial growth factor (anti-VEGF)-targeting drugs have shown better therapeutic effects in the systematic treatment of patients with advanced hepatocellular carcinoma, and the combination of targeted and immune therapy modes should be further developed.
Topics: Humans; Bayes Theorem; Carcinoma, Hepatocellular; Immunotherapy; Liver Neoplasms; Molecular Targeted Therapy; Network Meta-Analysis; Randomized Controlled Trials as Topic; Sorafenib
PubMed: 37557186
DOI: 10.1080/07853890.2023.2242384 -
Journal of Gastrointestinal Cancer Mar 2021Gastric schwannomas (GSs) are rare mesenchymal neoplasms of the gastrointestinal tract. Diagnosis is often achieved postoperatively, based on pathology reports of... (Comparative Study)
Comparative Study
PURPOSE
Gastric schwannomas (GSs) are rare mesenchymal neoplasms of the gastrointestinal tract. Diagnosis is often achieved postoperatively, based on pathology reports of retrieved specimens. The aim of the present study is to follow up all patients with gastric schwannoma (Gs) undergoing endoscopic, partial, or more extended surgery and to evaluate the appearance of local or distant recurrence.
METHODS
A PubMed, Cochrane, and Embase systematic review of the literature has been performed. Original papers, review articles, and case reports published between 1988 and 2019 were considered eligible. All the studies who met the inclusion criteria were analyzed. Statistical analysis of data has been performed using GraphPad Prism 7 software.
RESULTS
Three hundred twenty-eight articles were found, and a total of 102 were included and analyzed in depth. Fifty-three papers reported the follow-up information, ranging from 1 to 417 months across different studies. Among them, 31 patients underwent endoscopic removal of the gastric lesions; 140 patients underwent local surgery, including wedge resection or partial gastrectomy; and 148 patients underwent subtotal or total gastrectomy. The median follow-up was of 27-38-33 months, respectively. No recurrence or distant metastasis was detected in the endoscopy group. Among local surgery group, liver metastasis was reported in one case; in extended surgery group, one patient died for multiple liver metastases.
CONCLUSIONS
Local or more extended surgery involved a larger cohort of patients and reported satisfactory long-term results compared with endoscopy group. Surgery in absence of a definite preoperative diagnosis is considered the gold standard treatment for resectable Gs.
Topics: Follow-Up Studies; Gastrectomy; Gastroscopy; Humans; Incidental Findings; Liver Neoplasms; Neoplasm Recurrence, Local; Neurilemmoma; Stomach; Stomach Neoplasms; Treatment Outcome
PubMed: 32964322
DOI: 10.1007/s12029-020-00456-2 -
European Review For Medical and... Dec 2023This study aimed to systematically review and quantitatively synthesize the existing evidence to better identify the high-risk population of hepatocellular carcinoma... (Meta-Analysis)
Meta-Analysis
OBJECTIVE
This study aimed to systematically review and quantitatively synthesize the existing evidence to better identify the high-risk population of hepatocellular carcinoma (HCC) in nonalcoholic fatty liver disease (NAFLD).
MATERIALS AND METHODS
We searched databases including MEDLINE, EMBASE, Web of Science, Cochrane Library, and ClinicalTrials.gov up to February 2023. The meta-analysis was performed using RevMan5.3 software, and we calculated the estimated combined effect using inverse variance weighting of OR. I2 statistics were used to quantify the inter-study heterogeneity. Funnel plots and Egger test were used to assess publication bias, and sensitivity analysis was carried out through the transformation effect model or the removal of literature one by one.
RESULTS
Finally, 29 articles were included in the study, which involved a total of 726,656 patients with NAFLD. A total of 15 major risk factors were evaluated. Statistically significant risk factors were: advanced liver fibrosis (OR=6.40), diabetes (OR=2.38), obesity (OR=1.46), hypertension (OR=1.75), older age (OR=3.57), male (OR=2.45), alcohol intake (OR=2.98), smoking (OR=1.44), PNPLA3 genotype variation (OR=1.76), elevated liver enzymes (OR=2.92), low platelet counts (OR=4.61), and low albumin levels (OR=2.11).
CONCLUSIONS
Our results showed that advanced liver fibrosis, diabetes, obesity, hypertension, older age, male, alcohol intake, smoking, PNPLA3 genotype variation, elevated liver enzymes, low platelet counts, and low albumin levels were all significant risk factors for HCC in NAFLD. However, dyslipidemia was not found to be a risk factor. Further exploration is needed to confirm whether Hispanic ethnicity and high ferritin levels are also risk factors.
Topics: Humans; Male; Albumins; Carcinoma, Hepatocellular; Diabetes Complications; Hypertension; Liver Cirrhosis; Liver Neoplasms; Non-alcoholic Fatty Liver Disease; Obesity; Risk Factors; Female; Sex Factors
PubMed: 38164853
DOI: 10.26355/eurrev_202312_34788 -
Clinics and Research in Hepatology and... Aug 2023To study the efficacy of microwave ablation (MWA) and radiofrequency ablation (RFA) for colorectal liver metastases (CRLM) by meta-analysis. (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
To study the efficacy of microwave ablation (MWA) and radiofrequency ablation (RFA) for colorectal liver metastases (CRLM) by meta-analysis.
METHODS
PubMed, Web of Science, Embase, CNKI and the Cochrane Library were searched from the establishment to May 2023, and studies that report outcomes with comparison between MWA and RFA in CRLM treatment were selected by inclusion and exclusion criteria. Furthermore, the perioperative and survival data were statistically summarized and analyzed by Review Manager 5.4.
RESULTS
Five studies (MWA: 316 patients; RFA: 332 patients) were evaluated. The results of meta-analysis showed that local tumor progression in MWA group was significantly lower than that in RFA group (P < 0.05). The1-year and 2-year disease-free survival (DFS) of the MWA group was significantly better than that of the RFA group with HR of 1.77 (95% CI: 1.04-3.02; P = 0.04) and1.60 (95% CI: 1.09-2.35; P = 0.02), respectively.
CONCLUSION
The local tumor progression and 1-year and 2-year DFS of MWA were superior to RFA. The included articles were retrospective, offering low-quality evidence and limited conclusions.
Topics: Humans; Retrospective Studies; Microwaves; Treatment Outcome; Radiofrequency Ablation; Liver Neoplasms; Colorectal Neoplasms; Catheter Ablation; Carcinoma, Hepatocellular
PubMed: 37479137
DOI: 10.1016/j.clinre.2023.102182 -
Diagnostic and Interventional Imaging 2020The purpose of this study was to perform a systematic review of current literature describing the efficacy and technical outcomes of transarterial liver therapies using... (Meta-Analysis)
Meta-Analysis Review
PURPOSE
The purpose of this study was to perform a systematic review of current literature describing the efficacy and technical outcomes of transarterial liver therapies using automated feeder detection (AFD) software.
MATERIALS AND METHODS
This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. A structured search was performed in the PubMed, SCOPUS, and Embase databases of patients undergoing locoregional therapy of liver tumors utilizing AFD software. Demographic data, procedure data (including radiometrics) and tumor response rate were recorded. Where available, performance of AFD was compared to conventional digital subtraction angiography (DSA) and cone-beam CT (CBCT) without AFD.
RESULTS
A total of 14 full-text manuscripts met inclusion criteria, comprising 1042 tumors in 604 patients (305 men, 156 women; mean age, 68.6±6.0 [SD] years), including 537 patients with hepatocellular carcinoma, 8 with metastases from neuroendocrine tumors, and 59 patients without reported etiology. Reported sensitivity of AFD ranged between 86% and 98.5%, compared to DSA alone (38% - 64%) or DSA in combination with CBCT (69% - 81%). Three studies reported tumor response by modified response evaluation criteria in solid tumors (mRECIST) guidelines, with complete response in the range of 60% - 69%.
CONCLUSION
AFD is a promising new technology for the identification of intrahepatic and extrahepatic tumor-feeding arteries and should be considered a useful adjunct to conventional DSA and CBCT in the treatment of liver tumors.
Topics: Aged; Angiography, Digital Subtraction; Carcinoma, Hepatocellular; Chemoembolization, Therapeutic; Cone-Beam Computed Tomography; Female; Humans; Liver Neoplasms; Male; Middle Aged; Software
PubMed: 32035822
DOI: 10.1016/j.diii.2020.01.011 -
Cardiovascular and Interventional... Dec 2021Performing a systematic review and meta-analysis to assess the evidence of intra-arterial therapies in liver metastatic breast cancer (LMBC) patients. (Meta-Analysis)
Meta-Analysis Review
PURPOSE
Performing a systematic review and meta-analysis to assess the evidence of intra-arterial therapies in liver metastatic breast cancer (LMBC) patients.
METHODS
A systemic literature search was performed in PubMed, EMBASE, SCOPUS for studies regarding intra-arterial therapies in LMBC patients. Full text studies of LMBC patients (n ≥ 10) published between January 2010 and December 2020 were included when at least one outcome among response rate, adverse events or survival was available. Response rates were pooled using generalized linear mixed models. A weighted estimate of the population median overall survival (OS) was obtained under the assumption of exponentially distributed survival times.
RESULTS
A total of 26 studies (1266 patients) were included. Eleven articles reported on transarterial radioembolization (TARE), ten on transarterial chemoembolization (TACE) and four on chemo-infusion. One retrospective study compared TARE and TACE. Pooled response rates were 49% for TARE (95%CI 32-67%), 34% for TACE (95%CI 22-50%) and 19% for chemo-infusion (95%CI 14-25%). Pooled median survival was 9.2 months (range 6.1-35.4 months) for TARE, 17.8 months (range 4.6-47.0) for TACE and 7.9 months (range 7.0-14.2) for chemo-infusion. No comparison for OS was possible due to missing survival rates at specific time points (1 and 2 year OS) and the large heterogeneity.
CONCLUSION
Although results have to be interpreted with caution due to the large heterogeneity, the superior response rate of TARE and TACE compared to chemo-infusion suggests first choice of TARE or TACE in chemorefractory LMBC patients. Chemo-infusion could be considered in LMBC patients not suitable for TARE or TACE.
LEVEL OF EVIDENCE
3a.
Topics: Breast Neoplasms; Carcinoma, Hepatocellular; Chemoembolization, Therapeutic; Female; Humans; Liver Neoplasms; Retrospective Studies; Treatment Outcome
PubMed: 34322751
DOI: 10.1007/s00270-021-02906-1 -
Langenbeck's Archives of Surgery Dec 2022Historically , liver metastases due to melanoma have been associated with dismal prognosis. Moreover, the actual survival benefit from the treatment of melanoma liver... (Meta-Analysis)
Meta-Analysis
BACKGROUND
Historically , liver metastases due to melanoma have been associated with dismal prognosis. Moreover, the actual survival benefit from the treatment of melanoma liver metastases is still controversial. Hence, this study aims to evaluate the difference in surgical versus non-surgical options for melanoma liver metastases.
METHODS
Four databases (PubMed, EMBASE, Scopus, and Cochrane Library) were searched from inception to July 17, 2022. Studies were included if they compared outcomes between surgical and non-surgical treatment for patients with liver metastases from resectable melanoma. Meta-analyses were performed for the outcomes of 1-year, 2-year, 3-year and 5-year OS. Sensitivity analyses were performed for outcomes with substantial statistical heterogeneity. To account for possible moderators that might contribute to statistical heterogeneity, univariate meta-regression with mixed-effects models and subgroup analyses were conducted for the outcome of 2-year OS.
RESULTS
The search yielded 6610 articles; 13 studies were included in our analysis. Meta-analyses showed that survival outcomes were in favour of patients undergoing surgery as compared to non-surgery: 1-year OS (HR = 0.29, 95%CI 0.19-0.44, p < 0.00001), 2-year OS (HR = 0.19, 95%CI 0.09-0.38, p < 0.00001), 3-year OS (HR = 0.07, 95%CI 0.03-0.19, p < 0.00001) and 5-year OS (HR = 0.07, 95%CI 0.02-0.22, p < 0.00001). All included studies were of high quality. There was moderate-to-high statistical heterogeneity. Findings were robust to sensitivity analyses. Subgroup analyses and univariate meta-regression revealed neoadjuvant therapy and age as statistically significant subgroup and moderator respectively.
CONCLUSIONS
This study suggests that surgical treatment of melanoma liver metastases could offer better OS outcomes compared with non-surgical treatment.
Topics: Humans; Disease-Free Survival; Melanoma; Liver Neoplasms; Neoadjuvant Therapy; Prognosis
PubMed: 36201022
DOI: 10.1007/s00423-022-02658-7