Dataset Information

US-Based Deep Learning Model for Differentiating Hepatocellular Carcinoma (HCC) From Other Malignancy in Cirrhotic Patients.

ABSTRACT: The aim was to build a predictive model based on ultrasonography (US)-based deep learning model (US-DLM) and clinical features (Clin) for differentiating hepatocellular carcinoma (HCC) from other malignancy (OM) in cirrhotic patients. 112 patients with 120 HCCs and 60 patients with 61 OMs were included. They were randomly divided into training and test cohorts with a 4:1 ratio for developing and evaluating US-DLM model, respectively. Significant Clin predictors of OM in the training cohort were combined with US-DLM to build a nomogram predictive model (US-DLM+Clin). The diagnostic performance of US-DLM and US-DLM+Clin were compared with that of contrast enhanced magnetic resonance imaging (MRI) liver imaging and reporting system category M (MRI LR-M). US-DLM was the best independent predictor for evaluating OMs, followed by clinical information, including high cancer antigen 199 (CA199) level and female. The US-DLM achieved an AUC of 0.74 in the test cohort, which was comparable with that of MRI LR-M (AUC=0.84, p=0.232). The US-DLM+Clin for predicting OMs also had similar AUC value (0.81) compared with that of LR-M+Clin (0.83, p>0.05). US-DLM+Clin obtained a higher specificity, but a lower sensitivity, compared to that of LR-M +Clin (Specificity: 82.6% vs. 73.9%, p=0.007; Sensitivity: 78.6% vs. 92.9%, p=0.006) for evaluating OMs in the test set. The US-DLM+Clin model is valuable in differentiating HCC from OM in the setting of cirrhosis.

SUBMITTER: Zhou H

PROVIDER: S-EPMC8217663 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND: The laparoscopic approach for liver resections is still limited and controversial. Nevertheless the advantages connected with a mini-invasive approach are significant, especially in cirrhotic patients. In recent years the progress of laparoscopic procedures and the development of new and dedicated technologies have made endoscopic hepatic surgery feasible and safe. The aim of this study was to report the results of our experience in laparoscopic liver surgery for hepatocellular carcinoma (HCC) in cirrhotic patients. METHODS: From 2000 to 2003, 16 patients (10 male, 6 female; age 48-69 years; mean age 60.1 years) with HCC and associated severe but well compensated liver cirrhosis underwent laparoscopic hepatic resections at our department. Mean tumour size was 2.9 cm (range 1-3.9). Seven of these lesions were in the left liver and nine in the right lobe. Laparoscopy was performed under CO(2) pneumoperitoneum. The liver was always examined using laparoscopic ultrasound (US) to confirm the extension of the lesions and their relationships to the vasculature. The Pringle manoeuvre was not used. The transection of liver parenchyma was obtained by the use of a harmonic scalpel. The specimens were placed in a plastic bag and removed without contact to the abdominal wall. RESULTS: There was one conversion to laparotomy for inadequate exposure. In the remaining 15 patients we performed 13 non-anatomical resections, I segmentectomy and I anatomical left lobectomy. The mean operative time was 152 min (range 80-180). Mean blood loss was 280 ml and none of the patients required blood transfusions. In two patients the resection margin was <1 cm but the capsule was not infiltrated at histology. One patient died on the third postoperative day from a severe respiratory distress syndrome. Major morbidities occurred in two patients who developed moderate postoperative ascites, which resolved successfully with conservative treatment. The mean postoperative hospital stay was 8.8 days. Mean follow-up time has been 18 months, and to date no recurrences at the site of resection or port-site metastases have been observed. DISCUSSION: Limited laparoscopic liver resections in cirrhotic patients are technically feasible with a low complication rate when careful selection criteria are followed (hepatic involvement limited and located in the left or anterior right segments, tumour size smaller than 5 cm, Child-Pugh class A). This approach could be considered the best option for the treatment of small esophitic or subcapsular HCC on well compensated cirrhosis and a useful option when it is necessary to perform a left lateral anatomical resection or non-anatomical resection in well selected patients. In fact the mini-invasive approach can minimise the postoperative morbidity rate, which is still too high in this group of patients. It must be performed in highly specialised units by surgeons assisted by all requested technologies and with extensive experience in hepatobiliary and advanced laparoscopic surgery.

Project description:BackgroundThe diagnosis of hepatocellular carcinoma (HCC) often experiences latency, ultimately leading to unfavorable patient outcomes due to delayed therapeutic interventions. Our study is designed to develop and validate a model that employs triple-phase computerized tomography (CT)-based deep learning radiomics and clinical variables for early warning of HCC in patients with cirrhosis.MethodsWe studied 1858 patients with cirrhosis primarily from the PreCar cohort (NCT03588442) between June 2018 and January 2020 at 11 centres, and collected triple-phase CT images and laboratory results 3-12 months prior to HCC diagnosis or non-HCC final follow-up. Using radiomics and deep learning techniques, early warning model was developed in the discovery cohort (n = 924), and then validated in an internal validation cohort (n = 231), and an external validation cohort from 10 external centres (n = 703).FindingsWe developed a hybrid model, named ALARM model, which integrates deep learning radiomics with clinical variables, enabling early warning of the majority of HCC cases. The ALARM model effectively predicted short-term HCC development in cirrhotic patients with area under the curve (AUC) of 0.929 (95% confidence interval 0.918-0.941) in the discovery cohort, 0.902 (0.818-0.987) in the internal validation cohort, and 0.918 (0.898-0.961) in the external validation cohort. By applying optimal thresholds of 0.21 and 0.65, the high-risk (n = 221, 11.9%) and medium-risk (n = 433, 23.3%) groups, which covered 94.4% (84/89) of the patients who developed HCC, had significantly higher rates of HCC occurrence compared to the low-risk group (n = 1204, 64.8%) (24.3% vs 6.4% vs 0.42%, P < 0.001). Furthermore, ALARM also demonstrated consistent performance in subgroup analysis.InterpretationThe novel ALARM model, based on deep learning radiomics with clinical variables, provides reliable estimates of short-term HCC development for cirrhotic patients, and may have the potential to improve the precision in clinical decision-making and early initiation of HCC treatments.FundingThis work was supported by National Key Research and Development Program of China (2022YFC2303600, 2022YFC2304800), and the National Natural Science Foundation of China (82170610), Guangdong Basic and Applied Basic Research Foundation (2023A1515011211).

Dataset Information

US-Based Deep Learning Model for Differentiating Hepatocellular Carcinoma (HCC) From Other Malignancy in Cirrhotic Patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets