A nomogram integrating hepatic reserve and tumor characteristics for hepatocellular carcinoma following curative liver resection

Pancreatic cancer pathology image segmentation with channel and spatial long-range dependencies

Based on deep learning, pancreatic cancer pathology image segmentation technology effectively assists pathologists in achieving improved treatment outcomes. However, compared to traditional image segmentation tasks, the large size of tissues in pathology images requires a larger receptive field. While methods based on dilated convolutions or attention mechanisms can enhance the receptive field, they cannot capture long-range feature dependencies. Directly applying self-attention mechanisms to capture long-range dependencies results in intolerable computational complexity. To address these challenges, we introduce a channel and spatial self-attention (CS) Module designed for efficiently capturing both channel and spatial long-range feature dependencies in pancreatic cancer pathological images. Specifically, the channel and spatial self-attention module consists of an adaptive channel self-attention module and a window-shift spatial self-attention module. The adaptive channel self-attention module adaptively pools features to a fixed size to capture long-range feature dependencies. While the window-shift spatial self-attention module captures spatial long-range dependencies in a window-based manner. Additionally, we propose a re-weighted cross-entropy loss to mitigate the impact of long-tail distribution on performance. Our proposed method surpasses state-of-the-art on both our Pancreatic Cancer Pathology Image (PCPI) dataset and the GlaS challenge dataset. The mDice and mIoU have achieved 73.93% and 59.42% in our PCPI dataset.

Prognostic nomograms for HBV-related BCLC 0-a stage hepatocellular carcinoma incorporating aspartate aminotransferase to albumin ratio

BACKGROUND

Curative hepatectomy is currently the first-line treatment for hepatocellular carcinoma (HCC), but the prognosis is still not optimistic. The prediction model for prognosis of hepatitis B virus (HBV)-related BCLC 0-A stage HCC has not been well established. Therefore, we aimed to develop new nomograms to predict recurrence and survival in these patients.

METHODS

A total of 982 patients with HBV-related BCLC 0-A stage HCC who underwent curative hepatectomy at West China Hospital from February 2007 to February 2016 were retrospectively collected and randomly allocated to a training set and a validation set in a ratio of 4:1. Prognostic nomograms using data from the training set were developed using a Cox regression model and validated on the validation set.

RESULTS

We constructed nomograms based on independent factors for recurrence-free survival (RFS) (tumor size, satellite, microvascular invasion, capsular invasion, differentiation and aspartate aminotransferase to albumin ratio (ASAR)) and overall survival (OS) (gender, tumor size, satellite, microvascular invasion, differentiation, lymphocyte count, and ASAR). Compared with conventional HCC staging systems and other nomograms reported by previous literature, our ASAR integrated nomograms predicted RFS and OS with the highest C-indexes (0.682 (95%CI: 0.646-0.709), 0.729 (95%CI: 0.691-0.766), respectively) and had well-fitted calibration curves in the training set. Concurrently, the nomograms also obtained consistent results in the validation set. DCA revealed that our nomograms provided the largest clinical net benefits.

CONCLUSION

We first constructed ASAR integrated nomograms to predict the prognosis of HBV-related BCLC 0-A stage HCC patients after curative hepatectomy with good performance.

Model to Predict Overall Survival in Patients With Hepatocellular Carcinoma After Curative Hepatectomy

Background

The prognosis of patients with hepatocellular carcinoma (HCC) remains difficult to accurately predict. The purpose of this study was to establish a prognostic model for HCC based on a novel scoring system.

Methods

Five hundred and sixty patients who underwent a curative hepatectomy for treatment of HCC at our hospital between January 2007 and January 2014 were included in this study. Univariate and multivariate analyses were used to screen for prognostic risk factors. The nomogram construction was based on Cox proportional hazard regression models, and the development of the new scoring model was analyzed using receiver operating characteristic (ROC) curve analysis and then compared with other clinical indexes. The novel scoring system was then validated with an external dataset from a different medical institution.

Results

Multivariate analysis showed that tumor size, portal vein tumor thrombus (PVTT), invasion of adjacent tissues, microvascular invasion, and levels of fibrinogen and total bilirubin were independent prognostic factors. The new scoring model had higher area under the curve (AUC) values compared to other systems, and the C-index of the nomogram was highly consistent for evaluating the survival of HCC patients in the validation and training datasets, as well as the external validation dataset.

Conclusions

Based on serum markers and other clinical indicators, a precise model to predict the prognosis of patients with HCC was developed. This novel scoring system can be an effective tool for both surgeons and patients.

Prognostic Nomograms for Patients with Hepatocellular Carcinoma After Curative Hepatectomy, with a Focus on Recurrence Timing and Post-Recurrence Management

Background

Prognoses of patients with hepatocellular carcinoma (HCC) after curative hepatectomy remain unsatisfactory because of the high incidence of postoperative recurrence. Published predictive systems focus on pre-resection oncological characteristics, ignoring post-recurrence factors.

Purpose

This study aimed to develop prognostic nomograms for 3- and 5-year overall survival (OS) of patients with HCC after curative hepatectomy, focusing on potentially influential post-recurrence factors.

Patients and Methods

Clinicopathological and postoperative follow-up data were extracted from 494 patients with HCC who underwent curative hepatectomy between January 2012 and June 2019. Early recurrence (ER) and late recurrence (LR) were defined as recurrence at ≤2 and >2 years, respectively, after curative hepatectomy. Nomograms for the prediction of 3- and 5-year OS were established based on multivariate analysis. The areas under time-dependent receiver operating characteristic curves (AUCs) for the nomograms were calculated independently to verify predictive accuracy. The nomograms were internally validated based on 2000 bootstrap resampling of 75% of the original data.

Results

In total, 494 patients with HCC who underwent curative hepatectomy met the eligibility criteria. Cox proportional hazard regression analysis identified factors potentially influencing 3- and 5-year OS. Multivariate analysis indicated that patient age, Hong Kong Liver Cancer stage, γ-glutamyl transferase (γ-GGT) level, METAVIR inflammation activity grade, ER and post-recurrence treatment modality were influencing factors for 3-year OS (AUC, 0.891; 95% CI, 0.8364-0.9447). γ-GGT > 60 U/L, hepatectomy extent, LR and post-recurrence treatment modality were influencing factors for 5-year OS (AUC, 0.864; 95% CI, 0.8041-0.9237). Calibration plots showed satisfactory concordance between the predicted and actual observation cohorts.

Conclusion

We propose new prognostic nomograms for OS prediction with a focus on the differentiation of recurrence timing and post-recurrence management. These nomograms overcome the shortcomings of previous predictive nomograms and significantly improve predictive accuracy.

Development and validation of a risk score for predicting mortality after resection of primary hepatocellular carcinoma

Background: Primary hepatocellular carcinoma (PHCC) has a poor prognosis and high short-term mortality rate, even after resection. Thus, early diagnosis in PHCC cases can help improve quality of life via personalized management strategies.

Results: The risk score system (RSS) were classified as low risk (<5 points), medium risk (5–10 points), or high risk (>10 points). The areas under the receiver operating characteristic curves were 0.80 in the training cohort and 0.69 in the validation cohort, which indicated satisfactory prognostic performance. The Hosmer-Lemeshow goodness of fit test (P>0.05) revealed consistent performance in both groups. The concordance index (C-index: 0.663, 95% CI: 0.618–0.708) revealed excellent discrimination and good calibration in the validation cohort.

Conclusions: This simple RSS, which is based on clinical and laboratory data from patients undergoing resection of PHCC, might allow clinicians and medical staff to better manage PHCC.

Materials and Methods: A total of 672 PHCC cases were retrospectively obtained from the First Affiliated Hospital of Wenzhou Medical University between January 2007 and February 2015. Cox proportional hazard models were used to identify independent predictors of mortality. Kaplan-Meier curves and the log-rank test were used to examine the relationships between the prognostic factors and overall mortality.

Clinical characteristics analysis of 1180 patients with hepatocellular carcinoma secondary to hepatitis B, hepatitis C and alcoholic liver disease

Objective

To determine the clinical and liver stiffness characteristics of a cohort of Chinese patients with Hepatocellular carcinoma in different stages of Barcelona clinic liver cancer.

Methods

Details of 1180 patients with Hepatocellular carcinoma referred from October 2014 to November 2017 were collected retrospectively. Demographic data, etiology, clinical, and biochemical details were retrospectively analyzed. The changes of liver stiffness in different etiologies and different stages of Barcelona clinic liver cancer were especially analyzed.

Results

The onset age was 60.33 ± 9.11 (range 24‐84) years, 9 cases were ≤40 years, 572 cases were 41‐60 years, males accounted for 83.92%, females accounted for 16.08%; 599 cases were ≥61 years, males accounted for 78.25%, females accounted for 21.75%. Compared with males, the proportion of females ≥61 is higher than that of men. Majority (n = 787; 66.69%) had HBV infection; second commonest cause was HCV infection (n = 217; 18.39%). More patients with HBV infection were 41‐60 years (69.06%) and were younger than HCV patients. There was no statistical difference in etiology, age, gender, and distribution of diabetes mellitus among different Barcelona clinic liver cancer stages (P > .05). The overall Hepatocellular carcinoma (HCC) was found to be positively correlated with alkaline phosphatase, γ‐glutamyltransferase, and alpha‐fetoprotein and liver stiffness measurement values from stage A to stage D (P < .05). ANOVA analysis showed that the overall liver stiffness measurement among the four BCLC stages was found to be statistically significant different in HBV‐infected and HCV‐infected HCC patients.

Conclusion

Majority (99.24%) were patients aged >40 years old. Male is a high incidence population. In etiological analysis, HBV dominates HCC occurrence, HBV‐, HCV‐, and alcohol‐associated HCC have distinct clinical and biochemical characteristics, necessitating different screening policies to optimize HCC surveillance and management.

Use of a novel index, the A-index, and its associated nomogram to predict overall survival rates after resection of primary hepatocellular carcinoma

BACKGROUND

Several international staging or scoring systems don't accurately predict overall survival (OS) after resection of primary hepatocellular carcinoma (PHCC). Therefore, we attempted to overcome this limitation by constructing the A-index and its associated nomogram.

METHODS

We selected 672 patients who underwent curative resection of PHCC between January 2007 and February 2015 at the first affiliated hospital of the Wenzhou medical university. These subjects were randomly divided into the training (n = 470) and the validation group (n = 202) according to the ratio of 7:3.

RESULTS

We prepared the nomogram using eight independent risk factors including the A-index (calculated by 100 × aspartate transaminase /albumin /albumin) in the training cohort. The concordance index (C-index) of the nomogram for both training and validation set was similar in indicating the OS rate. The nomogram showed the strongest predictive power for the 1-year, 3-year, and 5-year OS, with the area under the ROC curve being 0.8182, 0.7892, and 0.7669, respectively. Correction curves showed consistent performance for both groups, stratification of the Kaplan-Meier curve was significant (P < 0.001), and decision curve analysis (DCA) showed the superiority of nomograms considering clinical effects.

CONCLUSIONS

The predictive power of the nomogram integrating the A-index for OS was optimal.

Nomogram for predicting the survival of patients with malignant melanoma: A population analysis

The aim of the current study was to develop and validate a nomogram based on a large population to estimate the 3- and 5-year survival rates of patients with malignant melanoma (MM). Patients were selected from the Surveillance, Epidemiology and End Results database and randomly divided into the training and validation cohorts. A nomogram was developed, and was used to assess the accuracy of the model. Independent prognostic factors associated with overall survival (OS) rate were identified through multivariate analysis, and were included in the internal validation of the nomogram. The nomogram provided high C-indexes for the training cohort [area under the time-dependent receiver operating characteristic curve (AUC) of 0.877 for 3-year OS rate and 0.872 for 5-year OS rate] and the validation cohort (AUC of 0.880 for 3-year OS rate and 0.874 for 5-year OS rate), indicating that the model had good discrimination ability. Calibration plots showed that the predicted 3- and 5-year OS rates probabilities for the training and validation groups were almost identical to the actual observations. The 3- and 5-year decision curves indicated net benefits for both the training and validation cohorts. The nomogram may aid clinicians to provide more accurate prognosis prediction in patient consultations and more personalized postoperative management plans.

A sample model established by S-index predicting overall survival after curative resection of primary hepatocellular carcinoma

Purpose

Prognostic prediction after curative resection of primary hepatocellular carcinoma (PHCC) remains an arduous task. The S-index calculated from γ-glutamyl transpeptidase, albumin, and platelets is reported to predict the severity of liver fibrosis. We constructed a nomogram for predicting the survival probability of PHCC based on a new indicator, the S-index, combined with other routine clinical parameters.

Patients and methods

We selected 490 patients with PHCC postradical surgery at the First Affiliated Hospital of Wenzhou Medical University between January 2007 and January 2014. The subjects were randomly allocated into the training cohort and the validation cohort in the ratio 7:3 by the digital method. Important variables screened by univariate analysis were included in multivariate analysis to obtain independent risk factors for predicting the prognosis of PHCC. The construction of the nomogram was based on Cox proportional hazard regression models. The concordance index (C-index) was used in the nomogram for evaluating the model performance for prognosis. We drew time-dependent receiver operating characteristic curves to compare our model with other staging systems.

Results

The nomogram based on six independent risk factors after multivariate analyses had good predictive power after radical surgery of PHCC. In the training and validation groups, the C-index of the nomogram was highly consistent for evaluating survival from PHCC. Compared with the traditional scoring system, the areas under time-dependent receiver operating characteristic curves were 0.7382, 0.7293, and 0.7520 for 1-, 3-, and 5-year overall survival, respectively. In summary, the nomogram showed excellent results in terms of prognosis of PHCC.

Conclusion

Based on the S-index and the other clinical indicators, we developed a precise nomogram that predicts the survival probability of patients with PHCC after radical surgery. This tool can provide effective information for surgeons and patients.