BackgroundWe attempted to train and validate a model of deep learning for the preoperative prediction of the response of patients with intermediate-stage hepatocellular carcinoma (HCC) undergoing transarterial chemoembolization (TACE).MethodAll computed tomography (CT) images were acquired for 562 patients from the Nan Fang Hospital (NFH), 89 patients from Zhu Hai Hospital Affiliated with Jinan University (ZHHAJU), and 138 patients from the Sun Yat-sen University Cancer Center (SYUCC). We built a predictive model from the outputs using the transfer learning techniques of a residual convolutional neural network (ResNet50). The prediction accuracy for each patch was revaluated in two independent validation cohorts.ResultsIn the training set (NFH), the deep learning model had an accuracy of 84.3% and areas under curves (AUCs) of 0.97, 0.96, 0.95, and 0.96 for complete response (CR), partial response (PR), stable disease (SD), and progressive disease (PD), respectively. In the other two validation sets (ZHHAJU and SYUCC), the deep learning model had accuracies of 85.1% and 82.8% for CR, PR, SD, and PD. The ResNet50 model also had high AUCs for predicting the objective response of TACE therapy in patches and patients of three cohorts. Decision curve analysis (DCA) showed that the ResNet50 model had a high net benefit in the two validation cohorts.ConclusionThe deep learning model presented a good performance for predicting the response of TACE therapy and could help clinicians in better screening patients with HCC who can benefit from the interventional treatment.Key Points• Therapy response of TACE can be predicted by a deep learning model based on CT images. • The probability value from a trained or validation deep learning model showed significant correlation with different therapy responses. • Further improvement is necessary before clinical utilization. Electronic supplementary materialThe online version of this article (10.1007/s00330-019-06318-1) contains supplementary material, which is available to authorized users.

BACKGROUND: High-intensity focused ultrasound (HIFU) is a new, noninvasive technique with potential to ablate and inactivate tumors. Treatment of solid tumors with HIFU has been reported. In this study, the safety and effects of HIFU in the clinical therapy of malignant bone tumors were assessed. METHODS: Biochemical markers and magnetic resonance imaging (MRI) or positron emission tomography (PET)-computed tomography (CT) were used to evaluate 25 patients with malignant bone tumors before and after HIFU treatment. RESULTS: HIFU resulted in significant improvement in biochemical markers, and no severe complications were observed. After HIFU treatment, 21 (87.5%) patients were completely relieved of pain, and 24 (100%) experienced significant relief. On the basis of MRI or PET-CT, HIFU was effective: For patients with primary bone tumors, 6 (46.2%) had a complete response, 5 (38.4%) had a partial response, 1 (7.8%) had a moderate response, and 1 suffered progressive disease; the response rate was 84.6%. For patients with metastatic bone tumors, 5 (41.7%) had complete response, 4 (33.3%) had partial response, 1 (8.3%) had a moderate response, 1 (8.3%) had stable disease, and 1 suffered progressive disease; the response rate was 75.0%. The 1-, 2-, 3-, and 5-year survival rates were 100.0%, 84.6%, 69.2%, and 38.5%, respectively, for patients with primary bone tumors and 83.3%, 16.7%, 0%, and 0%, respectively, for patients with metastatic bone tumors. The survival rates for patients with primary bone tumors were significantly better than for those with metastatic tumors. CONCLUSIONS: HIFU safely and noninvasively ablated malignant bone tumors and relieved pain. HIFU ablation should be further investigated, as it appears to be successful in the treatment of primary malignant bone tumors. Cancer 2010;116:3934-42.

BACKGROUND. Despite an increasing appreciation of the roles that myeloid cells play in tumor progression and therapy, challenges remain in interpreting the tumor-associated myeloid response balance and its translational value. We aimed to construct a simple and reliable myeloid signature for hepatocellular carcinoma (HCC). METHODS. Using in situ immunohistochemistry, we assessed the distribution of major myeloid subtypes in both peri-and intratumoral regions of HCC. A 2-feature-based, myeloid-specific prognostic signature, named the myeloid response score (MRS), was constructed using an L1-penalized Cox regression model based on data from a training subset (n = 244), a test subset (n = 244), and an independent internal (n = 341) and 2 external (n = 94; n = 254) cohorts. RESULTS. The MRS and the MRS-based nomograms displayed remarkable discriminatory power, accuracy, and clinical usefulness for predicting recurrence and patient survival, superior to current staging algorithms. Moreover, an increase in MRS was associated with a shift in the myeloid response balance from antitumor to protumor activities, accompanied by enhanced CD8 + T cell exhaustion patterns. Additionally, we provide evidence that the MRS was associated with the efficacy of sorafenib treatment for recurrent HCC. CONCLUSION. We identified and validated a simple myeloid signature for HCC that showed remarkable prognostic potential and may serve as a basis for the stratification of HCC immune subtypes.

Hepatocellular carcinoma recurrence and metastasis after microwave ablation (MWA) are challenges in the clinic. This study showed that mannose-derived carbon dots (Man-CDs) could effectively capture several "danger signals" (DS) after MWA treatment and then deliver DS specifically to dendritic cells (DCs). This improved delivery of DS to DCs enhanced the processing and presentation of tumor-associated antigens by DCs. The results demonstrated that intratumoral injection of Man-CDs after MWA therapy elicited a potent tumor-specific immune response and finally led to the effective suppression of both primary and distant tumors. MWA + Man-CD treatment could efficiently reject tumor cell rechallenge in vivo. This study demonstrated that Man-CD nanoparticles are effective adjuvants that can improve MWA therapy by eliciting a tumor-specific immune response.

BACKGROUND:Microwave ablation has recently been developed as a safe and effective treatment for a variety of tumors. The authors evaluated the safety and efficacy of computed tomography (CT)‐guided percutaneous microwave ablation of adrenal malignant tumors.METHODS:Nine patients between 41 and 83 years of age (average age, 54 years) with adrenal carcinoma (a total of 10 lesions) received CT‐guided percutaneous water‐cooled microwave ablation. The 9 cases included 1 primary adrenocortical carcinoma and 8 metastatic carcinomas (4 from lung cancer, 2 from hepatocellular carcinoma, 1 from intrahepatic cholangiocarcinoma, and 1 from left tibial osteosarcoma). Of the 8 metastatic cases, 7 were unilateral, and 1 was bilateral. All cases were pathologically confirmed by aspiration biopsy or postsurgical biopsy. The tumor diameters ranged from 2.1 cm to 6.1 cm (average, 3.8 cm). The average number of ablation sites was 1.5 sites (1‐3 sites), and the average accumulated ablation time was 7.7 minutes (4‐15 minutes). The procedures were performed using a cooled‐shaft antenna.RESULTS:The patients were followed for 3‐37 months, with an average of 11.3 months. Nine of 10 lesions were completely necrotized after first treatment. The other lesion was completely necrotized after 2 treatments. One of the patients experienced hypertensive crisis during treatment. No patient experienced recurrent tumor at the treated site, and this lack of recurrence indicated effective local control. All patients had progression of metastatic disease at extra‐adrenal sites.CONCLUSIONS:CT‐guided percutaneous water‐cooled microwave ablation is a minimally invasive and effective method for the treatment of adrenal carcinoma. Cancer 2011;. © 2011 American Cancer Society.