This retrospective study aimed to develop and validate deep-learning-based models for grading clear cell renal cell carcinoma (ccRCC) patients. A cohort enrolling 706 patients (n = 706) with pathologically verified ccRCC was used in this study. A temporal split was applied to verify our models: the first 83.9% of the cases (years 2010–2017) for development and the last 16.1% (year 2018–2019) for validation (development cohort: n = 592; validation cohort: n = 114). Here, we demonstrated a deep learning(DL) framework initialized by a self-supervised pre-training method, developed with the addition of mixed loss strategy and sample reweighting to identify patients with high grade for ccRCC. Four types of DL networks were developed separately and further combined with different weights for better prediction. The single DL model achieved up to an area under curve (AUC) of 0.864 in the validation cohort, while the ensembled model yielded the best predictive performance with an AUC of 0.882. These findings confirms that our DL approach performs either favorably or comparably in terms of grade assessment of ccRCC with biopsies whilst enjoying the non-invasive and labor-saving property.

Background: Clear cell Renal Cell Carcinoma (ccRCC) is the most common malignant tumor in the urinary system and the predominant subtype of malignant renal tumors with high mortality. Biopsy is the main examination to determine ccRCC grade, but it can lead to unavoidable complications and sampling bias. Therefore, non-invasive technology (e.g., CT examination) for ccRCC grading is attracting more and more attention. However, noise labels on CT images containing multiple grades but only one label make prediction difficult. However, noise labels exist in CT images, which contain multiple grades but only one label, making prediction difficult.Aim: We proposed a Transformer-based deep learning algorithm with CT images to improve the diagnostic accuracy of grading prediction and to improve the diagnostic accuracy of ccRCC grading.Methods: We integrate different training models to improve robustness and predict Fuhrman nuclear grade. Then, we conducted experiments on a collected ccRCC dataset containing 759 patients and used average classification accuracy, sensitivity, specificity, and AreaUnderCurve as indicators to evaluate the quality of research. In the comparative experiments, we further performed various current deep learning algorithms to show the advantages of the proposed method. We collected patients with pathologically proven ccRCC diagnosed from April 2010 to December 2018 as the training and internal test dataset, containing 759 patients. We propose a transformer-based network architecture that efficiently employs convolutional neural networks (CNNs) and self-attention mechanisms to extract a persuasive feature automatically. And then, a nonlinear classifier is applied to classify. We integrate different training models to improve the accuracy and robustness of the model. The average classification accuracy, sensitivity, specificity, and area under curve are used as indicators to evaluate the quality of a model.Results: The mean accuracy, sensitivity, specificity, and Area Under Curve achieved by CNN were 82.3%, 89.4%, 83.2%, and 85.7%, respectively. In contrast, the proposed Transformer-based model obtains a mean accuracy of 87.1% with a sensitivity of 91.3%, a specificity of 85.3%, and an Area Under Curve (AUC) of 90.3%. The integrated model acquires a better performance (86.5% ACC and an AUC of 91.2%).Conclusion: A transformer-based network performs better than traditional deep learning algorithms in terms of the accuracy of ccRCC prediction. Meanwhile, the transformer has a certain advantage in dealing with noise labels existing in CT images of ccRCC. This method is promising to be applied to other medical tasks (e.g., the grade of neurogliomas and meningiomas).

Objective: The aim of this study was to assess the potential role of fractal analysis derived from Gd-EOB-DTPA-enhanced MRI in predicting vessels that encapsulate tumor clusters (VETC) in patients with hepatocellular carcinoma (HCC). Methods: This retrospective study included 505 patients with HCC who underwent Gd-EOB-DTPA-enhanced MRI before surgical resection at two medical centers (training set: 253 patients, internal test set: 108 patients, external test set: 144 patients). The fractal dimension (FD) and lacunarity were extracted from the hepatobiliary phase of the tumor using box-counting algorithms. Additionally, conventional imaging features were evaluated. Univariate and multivariate logistic regression analyses were conducted in the training set to identify independent predictors for VETC, and a nomogram was created to visualize the final predictive model. The performance of these models was tested in the internal and external test sets. Recurrence-free survival (RFS) and overall survival (OS) were analyzed using the Kaplan–Meier method along with the log-rank test. Results: VETC-positive HCC exhibited higher FD and lacunarity than VETC-negative HCC ( P < 0 .001). The FD-lacunarity model achieved an area under receiver operating characteristics curve (AUC) of 0.78 (95% confidence interval [CI]: 0.70–0.87) in the internal test set and 0.79 (95%CI: 0.70–0.86) in the external test set. Multivariate logistic regression analysis identified serum alpha-fetoprotein, tumor size, intratumor artery, FD, and lacunarity as independent predictors for VETC, which were used for constructing the hybrid model. A clinical model was established using AFP, tumor size, and intratumor artery alone. The diagnostic performance of the hybrid model was significantly surpassed that of the clinical-radiological model when fractal parameters were incorporated, with AUCs increasing from 0.72 to 0.80 in the internal test set and from 0.65 to 0.84 in the external test set (all P < 0.05). Patients predicted by the hybrid model to have VETC-positive HCC exhibited significantly shorter RFS and OS compared to those predicted to have VETC-negative HCC ( P < 0.05). Conclusion: Fractal analysis based on Gd-EOB-DTPA-enhanced MRI enabled the quantitative characterization of VETC status by fractal dimension and lacunarity. The hybrid model may assist in estimating VETC and stratifying prognosis in patients with HCC.

Background and purpose: Programmed cell death protein-1 (PD-1) and programmed cell death-ligand-1 (PD-L1) expression status, determined by immunohistochemistry (IHC) of specimens, can discriminate patients with hepatocellular carcinoma (HCC) who can derive the most benefits from immune checkpoint inhibitor (ICI) therapy. A non-invasive method of measuring PD-1/PD-L1 expression is urgently needed for clinical decision support.Materials and methods: We included a cohort of 87 patients with HCC from the West China Hospital and analyzed 3094 CT images to develop and validate our prediction model. We propose a novel deep learning-based predictor, Contrastive Learning Network (CLNet), which is trained with self-supervised contrastive learning to better extract deep representations of computed tomography (CT) images for the prediction of PD-1 and PD-L1 expression.Results: Our results show that CLNet exhibited an AUC of 86.56% for PD-1 expression and an AUC of 83.93% for PD-L1 expression, outperforming other deep learning and machine learning models.Conclusions: We demonstrated that a non-invasive deep learning-based model trained with self-supervised contrastive learning could accurately predict the PD-1 and PD-L1 expression status, and might assist the precision treatment of patients withHCC, in particular the use of immune checkpoint inhibitors.

Background: The transcription factor SOX9 plays a critical role in various diseases, including hepatocellular carcinoma (HCC), and has been implicated in resistance to sorafenib treatment. Accurate assessment of SOX9 expression is important for guiding personalized therapy in HCC patients; however, a reliable non-invasive method for evaluating SOX9 status remains lacking. This study aims to develop a deep learning (DL) model capable of preoperatively and non-invasively predicting SOX9 expression from CT images in HCC patients. Methods: We retrospectively analyzed a dataset comprising 4011 CT images from 101 HCC patients who underwent surgical resection followed by sorafenib therapy at West China Hospital, Sichuan University. A deep reinforcement learning (DRL) approach was proposed to enhance prediction accuracy by identifying and focusing on image regions highly correlated with SOX9 expression, thereby reducing the impact of background noise. Results: Our DRL-based model achieved an area under the curve (AUC) of 91.00% (95% confidence interval: 88.64–93.15%), outperforming conventional DL methods by over 10%. Furthermore, survival analysis revealed that patients with SOX9-positive tumors had significantly shorter recurrence-free survival (RFS) and overall survival (OS) compared to SOX9-negative patients, highlighting the prognostic value of SOX9 status. Conclusions: This study demonstrates that a DRL-enhanced DL model can accurately and non-invasively predict SOX9 expression in HCC patients using preoperative CT images. These findings support the clinical utility of imaging-based SOX9 assessment in informing treatment strategies and prognostic evaluation for patients with advanced HCC.