Radiomics model based on intratumoral and peritumoral features for predicting major pathological response in non-small cell lung cancer receiving neoadjuvant immunochemotherapy.

Objective: To establish a radiomics model based on intratumoral and peritumoral features extracted from pre-treatment CT to predict the major pathological response (MPR) in patients with non-small cell lung cancer (NSCLC) receiving neoadjuvant immunochemotherapy. Methods: A total of 148 NSCLC patients who underwent neoadjuvant immunochemotherapy from two centers (SRRSH and ZCH) were retrospectively included. The SRRSH dataset (n=105) was used as the training and internal validation cohort. Radiomics features of intratumoral (T) and peritumoral regions (P1 = 0-5mm, P2 = 5-10mm, and P3 = 10-15mm) were extracted from pre-treatment CT. Intra- and inter- class correlation coefficients and least absolute shrinkage and selection operator were used to feature selection. Four single ROI models mentioned above and a combined radiomics (CR: T+P1+P2+P3) model were established by using machine learning algorithms. Clinical factors were selected to construct the combined radiomics-clinical (CRC) model, which was validated in the external center ZCH (n=43). The performance of the models was assessed by DeLong test, calibration curve and decision curve analysis. Results: Histopathological type was the only independent clinical risk factor. The model CR with eight selected radiomics features demonstrated a good predictive performance in the internal validation (AUC=0.810) and significantly improved than the model T (AUC=0.810 vs 0.619, p<0.05). The model CRC yielded the best predictive capability (AUC=0.814) and obtained satisfactory performance in the independent external test set (AUC=0.768, 95% CI: 0.62-0.91). Conclusion: We established a CRC model that incorporates intratumoral and peritumoral features and histopathological type, providing an effective approach for selecting NSCLC patients suitable for neoadjuvant immunochemotherapy.

Convolutional neural network applied to preoperative venous-phase CT images predicts risk category in patients with gastric gastrointestinal stromal tumors.

OBJECTIVE: The risk category of gastric gastrointestinal stromal tumors (GISTs) are closely related to the surgical method, the scope of resection, and the need for preoperative chemotherapy. We aimed to develop and validate convolutional neural network (CNN) models based on preoperative venous-phase CT images to predict the risk category of gastric GISTs. METHOD: A total of 425 patients pathologically diagnosed with gastric GISTs at the authors' medical centers between January 2012 and July 2021 were split into a training set (154, 84, and 59 with very low/low, intermediate, and high-risk, respectively) and a validation set (67, 35, and 26, respectively). Three CNN models were constructed by obtaining the upper and lower 1, 4, and 7 layers of the maximum tumour mask slice based on venous-phase CT Images and models of CNN_layer3, CNN_layer9, and CNN_layer15 established, respectively. The area under the receiver operating characteristics curve (AUROC) and the Obuchowski index were calculated to compare the diagnostic performance of the CNN models. RESULTS: In the validation set, CNN_layer3, CNN_layer9, and CNN_layer15 had AUROCs of 0.89, 0.90, and 0.90, respectively, for low-risk gastric GISTs; 0.82, 0.83, and 0.83 for intermediate-risk gastric GISTs; and 0.86, 0.86, and 0.85 for high-risk gastric GISTs. In the validation dataset, CNN_layer3 (Obuchowski index, 0.871) provided similar performance than CNN_layer9 and CNN_layer15 (Obuchowski index, 0.875 and 0.873, respectively) in prediction of the gastric GIST risk category (All P >.05). CONCLUSIONS: The CNN based on preoperative venous-phase CT images showed good performance for predicting the risk category of gastric GISTs.

Multitask deep learning for prediction of microvascular invasion and recurrence-free survival in hepatocellular carcinoma based on MRI images.

BACKGROUND AND AIMS: Accurate preoperative prediction of microvascular invasion (MVI) and recurrence-free survival (RFS) is vital for personalised hepatocellular carcinoma (HCC) management. We developed a multitask deep learning model to predict MVI and RFS using preoperative MRI scans. METHODS: Utilising a retrospective dataset of 725 HCC patients from seven institutions, we developed and validated a multitask deep learning model focused on predicting MVI and RFS. The model employs a transformer architecture to extract critical features from preoperative MRI scans. It was trained on a set of 234 patients and internally validated on a set of 58 patients. External validation was performed using three independent sets (n = 212, 111, 110). RESULTS: The multitask deep learning model yielded high MVI prediction accuracy, with AUC values of 0.918 for the training set and 0.800 for the internal test set. In external test sets, AUC values were 0.837, 0.815 and 0.800. Radiologists' sensitivity and inter-rater agreement for MVI prediction improved significantly when integrated with the model. For RFS, the model achieved C-index values of 0.763 in the training set and ranged between 0.628 and 0.728 in external test sets. Notably, PA-TACE improved RFS only in patients predicted to have high MVI risk and low survival scores (p < .001). CONCLUSIONS: Our deep learning model allows accurate MVI and survival prediction in HCC patients. Prospective studies are warranted to assess the clinical utility of this model in guiding personalised treatment in conjunction with clinical criteria.

A multicenter clinical AI system study for detection and diagnosis of focal liver lesions.

Early and accurate diagnosis of focal liver lesions is crucial for effective treatment and prognosis. We developed and validated a fully automated diagnostic system named Liver Artificial Intelligence Diagnosis System (LiAIDS) based on a diverse sample of 12,610 patients from 18 hospitals, both retrospectively and prospectively. In this study, LiAIDS achieved an F1-score of 0.940 for benign and 0.692 for malignant lesions, outperforming junior radiologists (benign: 0.830-0.890, malignant: 0.230-0.360) and being on par with senior radiologists (benign: 0.920-0.950, malignant: 0.550-0.650). Furthermore, with the assistance of LiAIDS, the diagnostic accuracy of all radiologists improved. For benign and malignant lesions, junior radiologists' F1-scores improved to 0.936-0.946 and 0.667-0.680 respectively, while seniors improved to 0.950-0.961 and 0.679-0.753. Additionally, in a triage study of 13,192 consecutive patients, LiAIDS automatically classified 76.46% of patients as low risk with a high NPV of 99.0%. The evidence suggests that LiAIDS can serve as a routine diagnostic tool and enhance the diagnostic capabilities of radiologists for liver lesions.

Radiomics analysis of contrast-enhanced computerized tomography for differentiation of gastric schwannomas from gastric gastrointestinal stromal tumors.

PURPOSE: To assess the performance of radiomics-based analysis of contrast-enhanced computerized tomography (CE-CT) images for distinguishing GS from gastric GIST. METHODS: Forty-nine patients with GS and two hundred fifty-three with GIST were enrolled in this retrospective study. CT features were evaluated by two associate chief radiologists. Radiomics features were extracted from portal venous phase images using Pyradiomics software. A non-radiomics dataset (combination of clinical characteristics and radiologist-determined CT features) and a radiomics dataset were used to build stepwise logistic regression and least absolute shrinkage and selection operator (LASSO) logistic regression models, respectively. Model performance was evaluated according to sensitivity, specificity, accuracy, and receiver operating characteristic (ROC) curve, and Delong's test was applied to compare the area under the curve (AUC) between different models. RESULTS: A total of 1223 radiomics features were extracted from portal venous phase images. After reducing dimensions by calculating Pearson correlation coefficients (PCCs), 20 radiomics features, 20 clinical characteristics + CT features were used to build the models, respectively. The AUC values for the models using radiomics features and those using clinical features were more than 0.900 for both the training and validation groups. There were no significant differences in predictive performance between the radiomic and clinical data models according to Delong's test. CONCLUSION: A radiomics-based model applied to CE-CT images showed comparable predictive performance to senior physicians in the differentiation of GS from GIST.

Imaging Features of Biliary Adenofibroma With Malignant Transformation: A Case Report and Literature Review.

Biliary adenofibroma (BAF) is a rare benign tumor, but it has the potential for malignant transformation. The differentiation between benign and malignant forms of BAF before surgery is of great importance for clinical decision-making. We report a case of BAF with invasive carcinoma. The patient did not present any clinical symptoms but had a history of hepatitis B virus infection for more than twenty years. Magnetic resonance imaging (MRI) revealed a solid and cystic 4 cm mass in segment II of the liver exhibiting hypointense signals on T1-weighted images and intermediate-to-high intensity signals on T2-weighted images. Enhancement scanning revealed markedly rim-like enhancement on the arterial phase, with the left inter-hepatic artery as the tumor-feeding artery, and wash-out on the venous and delayed phases. To the best of our knowledge, BAF with invasive carcinoma is uncommon. Preoperative qualitative diagnosis based on imaging features can achieve the maximum benefit for patients.

A deep learning model based on MRI for prediction of vessels encapsulating tumour clusters and prognosis in hepatocellular carcinoma.

PURPOSE: This study aimed to build and evaluate a deep learning (DL) model to predict vessels encapsulating tumor clusters (VETC) and prognosis preoperatively in patients with hepatocellular carcinoma (HCC). METHODS: 320 pathologically confirmed HCC patients (58 women and 262 men) from two hospitals were included in this retrospective study. Institution 1 (n = 219) and Institution 2 (n = 101) served as the training and external test cohorts, respectively. Tumors were evaluated three-dimensionally and regions of interest were segmented manually in the arterial, portal venous, and delayed phases (AP, PP, and DP). Three ResNet-34 DL models were developed, consisting of three models based on a single sequence. The fusion model was developed by inputting the prediction probability of the output from the three single-sequence models into logistic regression. The area under the receiver operating characteristic curve (AUC) was used to compare performance, and the Delong test was used to compare AUCs. Early recurrence (ER) was defined as recurrence within two years of surgery and early recurrence-free survival (ERFS) rate was evaluated by Kaplan-Meier survival analysis. RESULTS: Among the 320 HCC patients, 227 were VETC- and 93 were VETC+ . In the external test cohort, the fusion model showed an AUC of 0.772, a sensitivity of 0.80, and a specificity of 0.61. The fusion model-based prediction of VETC high-risk and low-risk categories exhibits a significant difference in ERFS rates, akin to the outcomes observed in VETC + and VETC- confirmed through pathological analyses (p < 0.05). CONCLUSIONS: A DL framework based on ResNet-34 has demonstrated potential in facilitating non-invasive prediction of VETC as well as patient prognosis.

MSPA-DLA++: A Multi-Scale Phase Attention Deep Layer Aggregation for Lesion Detection in Multi-Phase CT Images.

Object detection using convolutional neural networks (CNNs) has achieved high performance and achieved state-of-the-art results with natural images. Compared to natural images, medical images present several challenges for lesion detection. First, the sizes of lesions vary tremendously, from several millimeters to several centimeters. Scale variations significantly affect lesion detection accuracy, especially for the detection of small lesions. Moreover, the effective extraction of temporal and spatial features from multi-phase CT images is also an important issue. In this paper, we propose a group-based deep layer aggregation method with multiphase attention for liver lesion detection in multi-phase CT images. The method, which is called MSPA-DLA++, is a backbone feature extraction network for anchor-free liver lesion detection in multi-phase CT images that addresses scale variations and extracts hidden features from such images. The effectiveness of the proposed method is demonstrated on public datasets (LiTS2017) and our private multiphase dataset. The results of the experiments show that MSPA-DLA++ can improve upon the performance of state-of-the-art networks by approximately 3.7%.

Recurrence and malignant risk of ameloblastoma: A demographic study of 1626 cases from east China.

BACKGROUND: Ameloblastoma is characterized by aggressive nature, high recurrence rate, occasional malignant transformation, but recurrence and malignant incidence of ameloblastoma are not yet addressed by a large-scale case series study. MATERIALS AND METHODS: This study provided a detailed description of the relationship between demographic characteristics and recurrence and malignant cases with different clinical types of ameloblastoma (n = 1626). RESULTS: The overall incidence of recurrence and malignancy was 17.2 % and 3.4 %, respectively. Notably, we observed that there were multiple recurrent episodes (mean time, 24.3-28.7 months) among ameloblastoma patients. Multivariate analysis revealed that age of > 45 years (odds ratios (OR), 2.10; 95 % confidence interval (CI), 1.17-3.76), male (OR, 3.24; 95 %CI, 1.49-6.99), maxilla (OR, 5.58; 95 %CI, 3.11-10.0), and pre-existing recurrence (OR, 3.79; 95 %CI, 2.05-7.01) as independent factors were associated significantly with increased risk of malignancy. CONCLUSION: Identification of the clinical factors responsible for increased risk of malignancy provides better insight in management planning for ameloblastoma.

Unsupervised Domain Adaptation Using Fourier Phase Enhanced Training Images for Liver Tumors Detection in Multi-phase CT Images.

Computer-aided diagnostic methods, such as automatic and precise liver tumor detection, have a significant impact on healthcare. In recent years, deep learning-based liver tumor detection methods in multi-phase computed tomography (CT) images have achieved noticeable performance. Deep learning frameworks require a substantial amount of annotated training data but obtaining enough training data with high quality annotations is a major issue in medical imaging. Additionally, deep learning frameworks experience domain shift problems when they are trained using one dataset (source domain) and applied to new test data (target domain). To address the lack of training data and domain shift issues in multiphase CT images, here, we present an adversarial learning-based strategy to mitigate the domain gap across different phases of multiphase CT scans. We introduce to use Fourier phase component of CT images in order to improve the semantic information and more reliably identify the tumor tissues. Our approach eliminates the requirement for distinct annotations for each phase of CT scans. The experiment results show that our proposed method performs noticeably better than conventional training and other methods.

Contrastive Learning for Preoperative Early Recurrence Prediction of Hepatocellular Carcinoma with Liver CT Image and Tumor Mask.

High early recurrence (ER) rate is the main factor leading to the poor outcome of patients with hepatocellular carcinoma (HCC). Accurate preoperative prediction of ER is thus highly desired for HCC treatment. Many radiomics solutions have been proposed for the preoperative prediction of HCC using CT images based on machine learning and deep learning methods. Nevertheless, most current radiomics approaches extract features only from segmented tumor regions that neglect the liver tissue information which is useful for HCC prognosis. In this work, we propose a deep prediction network based on CT images of full liver combined with tumor mask that provides tumor location information for better feature extraction to predict the ER of HCC. While, due to the complex imaging characteristics of HCC, the image-based ER prediction methods suffer from limited capability. Therefore, on the one hand, we propose to employ supervised contrastive loss to jointly train the deep prediction model with cross-entropy loss to alleviate the problem of intra-class variation and inter-class similarity of HCC. On the other hand, we incorporate the clinical data to further improve the prediction ability of the model. Experiments are extensively conducted to verify the effectiveness of our proposed deep prediction model and the contribution of liver tissue for prognosis assessment of HCC.

Single-Molecule Dendritic MRI Nanoprobes Reveal the Size-Dependent Tumor Entrance.

The tumor entrance of drug delivery systems, including therapeutic proteins and nanomedicine, plays an essential role in affecting the treatment outcome. Nanoparticle size is a critical but contradictory factor in making a trade-off among blood circulation, tumor accumulation, and penetration. Here, this work designs a series of single-molecule gadolinium (Gd)-based magnetic resonance imaging (MRI) nanoprobes with well-defined sizes to precisely explore the size-dependent tumor entrance in vivo. The MRI nanoprobes obtained by divergent synthesis contain a core molecule of macrocyclic Gd(III)-chelate and different layers of dendritic lysine units, mimicking globular protein. This work finds that the r1 relaxivity and MR imaging signals increase with the nanoparticle size. The nanoprobe with a lower limit of critical size threshold ≈8.0 nm achieves superior tumor accumulation and penetration. These single-molecule MRI nanoprobes can be served to precisely examine the size-related nanoparticle-biological interactions.

Surface chemistry mediates the tumor entrance of nanoparticles probed using single-molecule dual-imaging nanodots.

The active transport of nanoparticles into solid tumors through transcytosis has been recognized as a promising way to enhance tumor accumulation and penetration, but the effect of the physicochemical properties of nanoparticles remains unclear. Herein, we develop a type of single-molecule dual imaging nanodot by divergent growth of perylenediimide (PDI)-dye-cored polylysine dendrimers and internal orthogonal conjugation of Gd(III)-based macrocyclic probes for fluorescence imaging and magnetic resonance imaging (MRI) of surface chemistry-dependent tumor entrance. The MRI and fluorescence imaging show that sixth-generation nanodots with acetylated (G6-Ac) and oligo ethylene glycol (G6-OEG) surfaces exhibit similar high tumor accumulation but different intratumor distribution. Cellular uptake and transport experiments suggest that G6-Ac nanodots have lower lysosomal entrapment (61% vs. 83%) and a higher exocytotic rate (47% vs. 29%) than G6-OEG. Therefore, G6-Ac is more likely to undergo intercellular transport through cell transcytosis, and is able to reach a tumor area distant from blood vessels, while G6-OEG mainly enters the tumor through enhanced permeability and retention (EPR) effect-based passive transport, and is not able to deliver to distant tumor areas. This study suggests that it is possible to boost the tumor entrance of nanoparticles by engineering surface chemistry for active transport.

A Boundary-Enhanced Liver Segmentation Network for Multi-Phase CT Images with Unsupervised Domain Adaptation.

Multi-phase computed tomography (CT) images have gained significant popularity in the diagnosis of hepatic disease. There are several challenges in the liver segmentation of multi-phase CT images. (1) Annotation: due to the distinct contrast enhancements observed in different phases (i.e., each phase is considered a different domain), annotating all phase images in multi-phase CT images for liver or tumor segmentation is a task that consumes substantial time and labor resources. (2) Poor contrast: some phase images may have poor contrast, making it difficult to distinguish the liver boundary. In this paper, we propose a boundary-enhanced liver segmentation network for multi-phase CT images with unsupervised domain adaptation. The first contribution is that we propose DD-UDA, a dual discriminator-based unsupervised domain adaptation, for liver segmentation on multi-phase images without multi-phase annotations, effectively tackling the annotation problem. To improve accuracy by reducing distribution differences between the source and target domains, we perform domain adaptation at two levels by employing two discriminators, one at the feature level and the other at the output level. The second contribution is that we introduce an additional boundary-enhanced decoder to the encoder-decoder backbone segmentation network to effectively recognize the boundary region, thereby addressing the problem of poor contrast. In our study, we employ the public LiTS dataset as the source domain and our private MPCT-FLLs dataset as the target domain. The experimental findings validate the efficacy of our proposed methods, producing substantially improved results when tested on each phase of the multi-phase CT image even without the multi-phase annotations. As evaluated on the MPCT-FLLs dataset, the existing baseline (UDA) method achieved IoU scores of 0.785, 0.796, and 0.772 for the PV, ART, and NC phases, respectively, while our proposed approach exhibited superior performance, surpassing both the baseline and other state-of-the-art methods. Notably, our method achieved remarkable IoU scores of 0.823, 0.811, and 0.800 for the PV, ART, and NC phases, respectively, emphasizing its effectiveness in achieving accurate image segmentation.

Multi-Modal Tumor Segmentation With Deformable Aggregation and Uncertain Region Inpainting.

Multi-modal tumor segmentation exploits complementary information from different modalities to help recognize tumor regions. Known multi-modal segmentation methods mainly have deficiencies in two aspects: First, the adopted multi-modal fusion strategies are built upon well-aligned input images, which are vulnerable to spatial misalignment between modalities (caused by respiratory motions, different scanning parameters, registration errors, etc). Second, the performance of known methods remains subject to the uncertainty of segmentation, which is particularly acute in tumor boundary regions. To tackle these issues, in this paper, we propose a novel multi-modal tumor segmentation method with deformable feature fusion and uncertain region refinement. Concretely, we introduce a deformable aggregation module, which integrates feature alignment and feature aggregation in an ensemble, to reduce inter-modality misalignment and make full use of cross-modal information. Moreover, we devise an uncertain region inpainting module to refine uncertain pixels using neighboring discriminative features. Experiments on two clinical multi-modal tumor datasets demonstrate that our method achieves promising tumor segmentation results and outperforms state-of-the-art methods.

Sodium tanshinone IIA sulfonate attenuates sepsis-associated brain injury via inhibiting NOD-like receptor 3/caspase-1/gasdermin D-mediated pyroptosis.

BACKGROUND: Sodium tanshinone IIA sulfonate (STS) has been reported to protect organ function in sepsis. However, the attenuation of sepsis-associated brain injury and its underlying mechanisms by STS has not been established. METHODS: C57BL/6 mice were used to establish the cecal ligation perforation (CLP) model, and STS was injected intraperitoneally 30 min before the surgery. The BV2 cells were stimulated by lipopolysaccharide after being pre-treated with STS for 4 h. The STS protective effects against brain injury and in vivo anti-neuroinflammatory effects were investigated using the 48-hour survival rate and body weight changes, brain water content, histopathological staining, immunohistochemistry, ELISA, RT-qPCR, and transmission electron microscopy. The pro-inflammatory cytokines of BV2 cells were detected by ELISA and RT-qPCR. At last, the levels of NOD-like receptor 3 (NLRP3) inflammasome activation and pyroptosis in brain tissues of the CLP model and BV2 cells were detected using western blotting. RESULTS: STS increased the survival rate, decreased brain water content, and improved brain pathological damage in the CLP models. STS increased the expressions of tight junction proteins ZO-1 and Claudin5 while reducing the expressions of tumor necrosis factor α (TNF-α), interleukin-1ß(IL-1ß), and interleukin-18 (IL-18) in the brain tissues of the CLP models. Meanwhile, STS inhibited microglial activation and M1-type polarization in vitro and in vivo. The NLRP3/caspase-1/ gasdermin D (GSDMD)-mediated pyroptosis was activated in the brain tissues of the CLP models and lipopolysaccharide (LPS)-treated BV2 cells, which was significantly inhibited by STS. CONCLUSIONS: The activation of NLRP3/caspase-1/GSDMD-mediated pyroptosis and subsequent secretion of proinflammatory cytokines may be the underlying mechanisms of STS against sepsis-associated brain injury and neuroinflammatory response.

Frontotemporal giant extradural dermoid cyst: illustrative case.

BACKGROUND: Dermoid cyst is a rare benign tumor exhibiting a typical radiological pattern and most commonly located along the midline. Laboratory examination was always normal. However, the features of some rare cases are atypical that can be easily misdiagnosed as other tumors. OBSERVATIONS: A 58-year-old patient presented with tinnitus, dizziness, blurred vision, and gait unsteadiness. Laboratory examination showed the serum levels of carbohydrate antigen 19-9 (CA19-9) were significantly increased (186 U/mL). A computed tomography (CT) scan revealed a predominant hypodense lesion in the left frontotemporal region with a hyperdense mural nodule. The lesion appeared as an intracranial extradural mass with a mural nodule on the sagittal image, displaying mixed signal on T1- and T2-weighted imaging. A left frontotemporal craniotomy was performed for cyst resection. Histological results confirmed a diagnosis of dermoid cyst. No tumor recurrences were observed at the 9-month follow-up. LESSONS: Extradural dermoid cyst with a mural nodule is extremely rare. When a hypodense lesion on CT shows mixed signal on T1- and T2-weighted imaging with a mural nodule, even if it is located in the extradural areas, it is important to consider a dermoid cyst. Serum CA19-9 combined with atypical imaging features may contribute to the diagnosis of dermoid cysts. Only recognition of atypical radiological features can avoid misdiagnosis.

Applicability of multidimensional convolutional neural networks on automated detection of diverse focal liver lesions in multiphase CT images.

PURPOSE: To investigate the applicability of multidimensional convolutional neural networks (CNNs) together with multiphase contrast-enhanced CT images on automated detection of diverse focal liver lesions (FLLs). METHODS: We trained detection models based on 2.5D and 3D CNN frameworks using 567 patients with 3892 FLLs and validated on a relatively large independent cohort of 1436 patients with 4723 lesions. The detection performance across different phases (arterial, portal venous [PV], and combined phases) was assessed for the 2.5D model. The lesions were divided into two groups with a cutoff size of 20 mm, and further subdivided into four subgroups of <10, 10-20, 20-50, and ≥50 mm, to verify the detection rates for lesions of different sizes for the 2.5D and 3D models. McNemar's test was used to compare the detection sensitivities among different methods. In addition, sensitivity with 95% confidence intervals and free-response receiver operating characteristics (FROC) curves were plotted for visualization of the detectability. RESULTS: In the 2.5D model, the detection rate of PV phase outperformed arterial phase, and a combination of the two phases further improved the performance over a single phase. The detection sensitivities in the arterial, PV, and combined phases were 0.737 versus 0.802 versus 0.832 for all lesions. The 3D model was superior to the 2.5D model for detecting benign lesions (0.896 vs. 0.807, p < 0.001), malignant lesions (0.940 vs. 0.918, p = 0.013), and all lesions (0.902 vs. 0.832, p < 0.001) regardless of size division. Particularly, the 3D model showed higher sensitivity than the 2.5D model in detecting lesions smaller than 20 mm (0.868 vs. 0.759, p < 0.001). For lesions larger than 20 mm, both the 3D and the 2.5D models achieved excellent detection performance. CONCLUSIONS: The proposed CNN detection model was demonstrated to adaptively learn the feature representations of diverse FLLs and generalize well to a large-scale validation dataset. The use of multiphase significantly improved the detectability of FLLs compared to single phase. 3D CNN framework showed an enhanced capability over the 2.5D in the detection of FLLs, particularly small lesions. The promising performance shows that the proposed CNN detection system could be a powerful clinical tool for the early detection of hepatic tumors.

A novel multimodal deep learning model for preoperative prediction of microvascular invasion and outcome in hepatocellular carcinoma.

BACKGROUND: Accurate preoperative identification of the microvascular invasion (MVI) can relieve the pressure from personalized treatment adaptation and improve the poor prognosis for hepatocellular carcinoma (HCC). This study aimed to develop and validate a novel multimodal deep learning (DL) model for predicting MVI based on multi-parameter magnetic resonance imaging (MRI) and contrast-enhanced computed tomography (CT). METHODS: A total of 397 HCC patients underwent both CT and MRI examinations before surgery. We established the radiological models (RCT, RMRI) by support vector machine (SVM), DL models (DLCT_ALL, DLMRI_ALL, DLCT + MRI) by ResNet18. The comprehensive model (CALL) involving multi-modality DL features and clinical and radiological features was constructed using SVM. Model performance was quantified by the area under the receiver operating characteristic curve (AUC) and compared by net reclassification index (NRI) and integrated discrimination improvement (IDI). RESULTS: The DLCT + MRI model exhibited superior predicted efficiency over single-modality models, especially over the DLCT_ALL model (AUC: 0.819 vs. 0.742, NRI > 0, IDI > 0). The DLMRI_ALL model improved the performance over the RMRI model (AUC: 0.794 vs. 0.766, NRI > 0, IDI < 0), but no such difference was found between the DLCT_ALL model and RCT model (AUC: 0.742 vs. 0.710, NRI < 0, IDI < 0). Furthermore, both the DLCT + MRI and CALL models revealed the prognostic power in recurrence-free survival stratification (P < 0.001). CONCLUSION: The proposed DLCT + MRI model showed robust capability in predicting MVI and outcomes for HCC. Besides, the identification ability of the multi-modality DL model was better than any single modality, especially for CT.

Novel manganese and polyester dendrimer-based theranostic nanoparticles for MRI and breast cancer therapy.

Therapeutic nanoplatforms are widely used in the diagnosis and treatment of breast cancer due to the merits of enabling high soft-tissue resolution and the availability of numerous therapeutic nanoparticles. It is thus vital to develop multifunctional theranostic nanoparticles for the visualization and dynamic monitoring of tumor therapy. In this study, we designed a manganese-based and hypericin-loaded polyester dendrimer nanoparticle (MHD) for magnetic resonance imaging (MRI) and hypericin-based photodynamic therapy (PDT) enhancement. We found that MHD could greatly enhance MRI contrast with a longitudinal relaxivity of 5.8 mM-1 s-1 due to the Mn-based paramagnetic dendrimer carrier. Meanwhile, the MRI-guided PDT inhibition of breast tumors could be achieved by the hypericin-carrying MHD and further improved by Mn2+-mediated alleviation of the hypoxic microenvironment and the enhancement of cellular ROS. Besides, MHD showed excellent biocompatibility and biosafety with liver and kidney clearance mechanisms. Thus, the high efficiency in MRI contrast enhancement and excellent tumor-inhibiting effects indicate MHD's potential as a novel, stable, and multifunctional nanotheranostic agent for breast cancer.