Prognostic Factors for Patients with Proliferative Hepatocellular Carcinoma After Liver Resection.

Purpose: There is a scarcity of predictive models currently accessible for prognosticating proliferative hepatocellular carcinoma (HCC), an integrated class of subtype, characterized by a dismal prognosis. Consequently, this study aimed to develop and validate a novel prognostic model capable of accurately predicting the prognosis of proliferative HCC after curative resection. Patients and Methods: This retrospective multicenter study included patients with solitary HCC who underwent curative liver resection from August 2014 to December 2020 (n = 816). Patients were stratified into either the proliferative HCC cohort (n = 259) or the nonproliferative HCC cohort (n = 557) based on histological criteria. Disease-free survival (DFS) was compared between the two groups before and after one-to-one propensity score matching (PSM). Of all the proliferative HCC patients, 203 patients were assigned to training cohort, and 56 patients were assigned to validation cohort. Univariate and multivariate analyses were performed in training cohort to identify risk factors associated with worse DFS. Thereafter, a predictive model was constructed, subsequently validated in the validation cohort. Results: The DFS of proliferative HCC was significantly worse than nonproliferative HCC before and after PSM. Meanwhile, multivariate regression analysis revealed that liver cirrhosis (P = 0.032) and larger tumor size (P = 0.000) were independent risk factors of worse DFS. Lastly, the discriminative abilities of the predictive model for 1, 3, 5-year DFS rates, as determined by receiver operating characteristic (ROC) curves, were 0.702, 0.720, and 0.809 in the training cohort and 0.752, 0.776, and 0.851 in the validation cohort, respectively. Conclusion: This study developed a predictive model with satisfactory accuracy to predict the worse DFS in proliferative HCCs after liver resection. Moreover, this predictive model may serve as a valuable tool for clinicians to predict postoperative HCC recurrence, thereby enabling them to implement early preventative strategies.

Transarterial chemoembolization with PD-(L)1 inhibitors plus molecular targeted therapies for hepatocellular carcinoma (CHANCE001).

There is considerable potential for integrating transarterial chemoembolization (TACE), programmed death-(ligand)1 (PD-[L]1) inhibitors, and molecular targeted treatments (MTT) in hepatocellular carcinoma (HCC). It is necessary to investigate the therapeutic efficacy and safety of TACE combined with PD-(L)1 inhibitors and MTT in real-world situations. In this nationwide, retrospective, cohort study, 826 HCC patients receiving either TACE plus PD-(L)1 blockades and MTT (combination group, n = 376) or TACE monotherapy (monotherapy group, n = 450) were included from January 2018 to May 2021. The primary endpoint was progression-free survival (PFS) according to modified RECIST. The secondary outcomes included overall survival (OS), objective response rate (ORR), and safety. We performed propensity score matching approaches to reduce bias between two groups. After matching, 228 pairs were included with a predominantly advanced disease population. Median PFS in combination group was 9.5 months (95% confidence interval [CI], 8.4-11.0) versus 8.0 months (95% CI, 6.6-9.5) (adjusted hazard ratio [HR], 0.70, P = 0.002). OS and ORR were also significantly higher in combination group (median OS, 19.2 [16.1-27.3] vs. 15.7 months [13.0-20.2]; adjusted HR, 0.63, P = 0.001; ORR, 60.1% vs. 32.0%; P < 0.001). Grade 3/4 adverse events were observed at a rate of 15.8% and 7.5% in combination and monotherapy groups, respectively. Our results suggest that TACE plus PD-(L)1 blockades and MTT could significantly improve PFS, OS, and ORR versus TACE monotherapy for Chinese patients with predominantly advanced HCC in real-world practice, with an acceptable safety profile.

Ginsenoside Rh1 regulates gastric cancer cell biological behaviours and transplanted tumour growth in nude mice via the TGF-ß/Smad pathway.

Gastric cancer (GC) is one of the most prevalent malignancies of the digestive tract. Ginsenoside Rh1 was reported to exert effects on GC. The current study set out to explore the mechanism underlying Ginsenoside Rh1 effects on GC. With oxaliplatin (OXA) serving as the positive control, human GC cells AGS were treated with 0, 10, 25, 50, 74, or 100 µM of ginsenoside Rh1 for 48 h. Proliferation, migration, invasion, and apoptosis were subsequently assessed by means of MTT, scratch test, Transwell, and TUNEL, respectively. AGS cells were further jointly treated with Rh1 and the TGF-ß/Smad pathway activator Kartogenin, followed by detection of TGF-ß/Smad pathway effects on AGS biological behaviours. Moreover, TGF-ß/Smad pathway activation was detected with a Western blot assay. Furthermore, xenograft tumour models were established and tumour growth was recorded. Ki-67 expression patterns and apoptosis were detected with immunohistochemistry and TUNEL, respectively. In vitro, Ginsenoside Rh1 repressed AGS cell proliferation, migration, and invasion, and further promoted apoptosis, with a concentration of 50 µM Rh1 exerting the equivalent effects as OXA. In vivo, Ginsenoside Rh1 inhibited GC proliferation and induced tumour cell apoptosis. Mechanistically, Ginsenoside Rh1 reduced TGF-ß1 and TGF-ß2 levels and Smad2 and Smad3 phosphorylation levels. Collectively, our findings highlighted that ginsenoside Rh1 inhibited GC cell growth and tumour growth in xenograft tumour models via inhibition of the TGF-ß/Smad pathway.

Bioactive Components and Potential Mechanism Prediction of Kui Jie Kang against Ulcerative Colitis via Systematic Pharmacology and UPLC-QE-MS Analysis.

Kui Jie Kang (KJK)-a traditional Chinese medicine-has demonstrated clinical therapeutic efficacy against ulcerative colitis (UC). However, the active compounds and their underlying mechanisms have not yet been fully characterized. Therefore, the current study sought to identify the volatile compounds in KJK responsible for eliciting the therapeutic effect against UC, while also analyzing key targets and potential mechanisms. To this end, systematic network pharmacology analysis was employed to obtain UC targets by using GeneCards, DisGeNET, OMIM, among others. A total of 145 candidate ingredients, 412 potential targets of KJK (12 herbs), and 1605 UC targets were identified. Of these KJK and UC targets, 205 intersected and further identified AKT1, JUN, MAPK, ESR, and TNF as the core targets and the PI3K/AKT signaling pathway as the top enriched pathway. Moreover, molecular docking and ultra-performance liquid chromatography Q Exactive-mass spectrometry analysis identified quercetin, kaempferol, luteolin, wogonin, and nobiletin as the core effective compounds of KJK. In vivo murine studies revealed that KJK exposure increases the body weight and colon length, while reducing colonic epithelial injury, and the expression of inflammatory factors in colitis tissues such as TNF-α, IL-6, and IL-1ß. Furthermore, KJK treatment downregulates the expression of pi3k and akt genes, as well as p-PI3K/PI3K and p-AKT/AKT proteins. Collectively, these findings describe the therapeutic effects and mechanisms of KJK in UC and highlight KJK as a potentially valuable therapeutic option for UC via modulation of the PI3K/AKT signaling pathway, thus providing a theoretical reference for the broader application of KJK in the clinical management of UC.

Impaired white matter microstructure associated with severe depressive symptoms in patients with PD.

Depression is a common occurrence in patients with Parkinson's disease (PD); however, its pathophysiology is still unclear. This study assessed the association between the integrity of white matter and depressive symptoms in patients with PD. 67 patients with PD were divided into a non-depressed PD group (ndPD, n = 30) and a depressed PD group (dPD, n = 37). The dPD group was further subdivided into a mild-moderately depressed PD (mdPD, n = 22) and a severely depressed PD group (sdPD, n = 15). Tract-Based Spatial Statistics was used to compare fractional anisotropy (FA) between groups. Region-of-interest analysis was used to explore changes in diffusivity indices in the regions showing FA abnormalities. The sdPD patients exhibited significantly reduced FA in the left superior longitudinal fasciculus, uncinate fasciculus, anterior corona radiata, corticospinal tract, and bilateral inferior fronto-occipital fasciculus when compared with the ndPD patients, but the decreased FA was within a smaller area when compared with the mdPD patients. No significant difference in FA was found between the mdPD and ndPD groups. Among the dPD patients, FA values in the left superior longitudinal fasciculus negatively correlated with BDI scores. Impaired white matter integrity in the prefronto-limbic/temporal circuitry, mainly in the left hemisphere, is associated with severe, but not mild-moderate depressive symptoms in patients with PD.

Combined transarterial iodized oil injection and computed tomography-guided thermal ablation for hepatocellular carcinoma: utility of the iodized oil retention pattern.

PURPOSE: To investigate whether the iodized oil (Lipiodol, Guerbet Group, Villepinte, France) retention pattern influences the treatment efficacy of combined transarterial Lipiodol injection (TLI) and thermal ablation in patients with hepatocellular carcinoma (HCC). METHODS: Data of 198 patients (280 HCC lesions), who underwent TLI plus computed tomography (CT)-guided thermal ablation at three separate medical institutions between June 2014 and September 2020, were reviewed and analyzed. The Lipiodol retention pattern was classified as complete or incomplete based on non-enhanced CT at the time of ablation. The primary outcome was local recurrence-free survival (LRFS) for lesions; the secondary outcome was overall survival (OS) for patients. Propensity score matching (PSM) was performed using a caliper width of 0.1 between the two groups. Differences in LRFS and OS between the two groups were compared using the log-rank test. RESULTS: A total of 133 lesions exhibited a complete Lipiodol retention pattern, while 147 exhibited an incomplete pattern. After PSM analysis of baseline characteristics of the lesions, 121 pairs of lesions were matched. LRFS was significantly longer for lesions exhibiting complete retention than for those exhibiting incomplete retention (P = 0.030). After PSM analysis of patient baseline characteristics, 74 pairs of patients were matched. There was no significant difference in OS between the two groups (P = 0.456). CONCLUSION: Lipiodol retention patterns may influence the treatment efficacy of combined TLI and thermal ablation for HCC lesions. However, a survival benefit for the Lipiodol retention pattern among HCC patients was not observed and needs further confirmation.

Initial Incomplete Thermal Ablation Is Associated With a High Risk of Tumor Progression in Patients With Hepatocellular Carcinoma.

PURPOSE: To investigate whether incomplete thermal ablation is associated with a high risk of tumor progression in patients with hepatocellular carcinoma (HCC), and to compare the efficacy of repeated thermal ablation and transarterial chemoembolization (TACE) for residual tumor after incomplete ablation. METHODS: This retrospective study included 284 patients with unresectable HCC who underwent thermal ablation from June 2014 to September 2020. The response of the initially attempted ablation was classified into complete (n=236) and incomplete (n=48). The progression-free survival (PFS) and overall survival (OS) were compared between patients with complete and incomplete responses, before and after a one-to-one propensity score-matching (PSM), and between patients in whom repeated ablation or TACE was performed after a first attempt incomplete ablation. RESULTS: After PSM of the 284 patients, 46 pairs of patients were matched. The PFS was significantly higher in the complete response group than in the incomplete response group (P<0.001). No difference in OS was noted between two groups (P=0.181). After a first attempt incomplete ablation, 29 and 19 patients underwent repeated ablation and TACE, respectively. There were no significant differences in PFS (P=0.424) and OS (P=0.178) between patients who underwent repeated ablation and TACE. In multivariate Cox regression analysis, incomplete response (P<0.001) and Child-Pugh class B (P=0.017) were independent risk factors for tumor progression, while higher AFP level (P=0.011) and Child-Pugh class B (P=0.026) were independent risk factors for poor OS. CONCLUSION: Although patients with incomplete ablation are associated with tumor progression compared with those with complete ablation, their OS is not affected by incomplete ablation. When patients present with residual tumors, TACE may be an alternative if repeated ablation is infeasible.

Predicting early refractoriness of transarterial chemoembolization in patients with hepatocellular carcinoma using a random forest algorithm: A pilot study.

Purpose: To develop and validate a random forest (RF) based predictive model of early refractoriness to transarterial chemoembolization (TACE) in patients with unresectable hepatocellular carcinoma (HCC). Methods: A total of 227 patients with unresectable HCC who initially treated with TACE from three independent institutions were retrospectively included. Following a random split, 158 patients (70%) were assigned to a training cohort and the remaining 69 patients (30%) were assigned to a validation cohort. The process of variables selection was based on the importance variable scores generated by RF algorithm. A RF predictive model incorporating the selected variables was developed, and five-fold cross-validation was performed. The discrimination and calibration of the RF model were measured by a receiver operating characteristic (ROC) curve and the Hosmer-Lemeshow test. Results: The potential variables selected by RF algorithm for developing predictive model of early TACE refractoriness included patients' age, number of tumors, tumor distribution, platelet count (PLT), and neutrophil-to-lymphocyte ratio (NLR). The results showed that the RF predictive model had good discrimination ability, with an area under curve (AUC) of 0.863 in the training cohort and 0.767 in the validation cohort, respectively. In Hosmer-Lemeshow test, the RF model had a satisfactory calibration with P values of 0.538 and 0.068 in training cohort and validation cohort, respectively. Conclusion: The RF algorithm-based model has a good predictive performance in the prediction of early TACE refractoriness, which may easily be deployed in clinical routine and help to determine the optimal patient of care.

Development and Validation of a Predictive Model for Early Refractoriness of Transarterial Chemoembolization in Patients With Hepatocellular Carcinoma.

Objectives: To develop and validate a predictive model for early refractoriness of transarterial chemoembolization (TACE) in patients with hepatocellular carcinoma (HCC). Methods: In this multicenter retrospective study, a total of 204 consecutive patients who initially underwent TACE were included. Early TACE refractoriness was defined as patients presented with TACE refractoriness after initial two consecutive TACE procedures. Of all patients, 147 patients (approximately 70%) were assigned to a training set, and the remaining 57 patients (approximately 30%) were assigned to a validation set. Predictive model was established using forward stepwise logistic regression and nomogram. Based on factors selected by logistic regression, a one-to-one propensity score matching (PSM) was conducted to compare progression-free survival (PFS) between patients who were present or absent of early TACE refractoriness. PFS curve was estimated by Kaplan-Meier method and compared by log-rank test. Results: Logistic regression revealed that bilobar tumor distribution (p = 0.002), more than three tumors (p = 0.005) and beyond up-to-seven criteria (p = 0.001) were significantly related to early TACE refractoriness. The discriminative abilities, as determined by the area under the receiver operating characteristic (ROC) curve, were 0.788 in the training cohort and 0.706 in the validation cohort. After PSM, the result showed that patients who were absent of early TACE refractoriness had a significantly higher PFS rate than those of patients who were present (p < 0.001). Conclusion: This study presents a predictive model with moderate accuracy to identify patients with high risk of early TACE refractoriness, and patients with early TACE refractoriness may have a poor prognosis.

Integrated Liver Inflammatory Score Predicts the Therapeutic Outcome of Patients with Hepatocellular Carcinoma after Transarterial Chemoembolization.

PURPOSE: To evaluate the performance of the integrated liver inflammatory score (ILIS) in predicting survival in patients with hepatocellular carcinoma (HCC) who received transarterial chemoembolization, and to compare ILIS to other prognostic scoring systems and inflammatory indices. MATERIALS AND METHODS: This study included 192 patients with unresectable HCC who underwent transarterial chemoembolization from 3 medical centers. The potential risk factors of the patients' overall survival (OS) were determined by multivariate Cox regression analysis. The predictive performances of ILIS in 1-, 2-, 3-, 4-, and 5-year survival were evaluated using receiver operating characteristic curves. The discriminatory power in the OS of ILIS and the other known scoring systems or inflammatory indices was determined by C-statistic. RESULTS: Multivariate regression analysis showed that high ILIS (P = .047), low lymphocyte count (P = .034), beyond up-to-seven criteria (P = .021), and nonresponse to the first transarterial chemoembolization session (P = .039) were risk factors for poor prognosis after transarterial chemoembolization. The predictive performances of ILIS for 1-, 2-, 3-, 4-, and 5-year survival were good, with area under the curve values of 0.627, 0.631, 0.621, 0.577, and 0.681, respectively. ILIS outperformed other standard scoring systems and inflammatory indices in predicting OS, with a C-statistic of 0.625. CONCLUSIONS: ILIS is a powerful prognostic index for predicting the survival of patients with HCC after transarterial chemoembolization, which suggests that ILIS before treatment should be considered during the patient evaluation process.

Deep learning for differentiation of benign and malignant solid liver lesions on ultrasonography.

PURPOSE: The ability to reliably distinguish benign from malignant solid liver lesions on ultrasonography can increase access, decrease costs, and help to better triage patients for biopsy. In this study, we used deep learning to differentiate benign from malignant focal solid liver lesions based on their ultrasound appearance. METHODS: Among the 596 patients who met the inclusion criteria, there were 911 images of individual liver lesions, of which 535 were malignant and 376 were benign. Our training set contained 660 lesions augmented dynamically during training for a total of 330,000 images; our test set contained 79 images. A neural network with ResNet50 architecture was fine-tuned using pre-trained weights on ImageNet. Non-cystic liver lesions with definite diagnosis by histopathology or MRI were included. Accuracy of the final model was compared with expert interpretation. Two separate datasets were used in training and evaluation, one with all lesions and one with lesions deemed to be of uncertain diagnosis based on the Code Abdomen rating system. RESULTS: Our model trained on the complete set of all lesions achieved a test accuracy of 0.84 (95% CI 0.74-0.90) compared to expert 1 with a test accuracy of 0.80 (95% CI 0.70-0.87) and expert 2 with a test accuracy of 0.73 (95% CI 0.63-0.82). Our model trained on the uncertain set of lesions achieved a test accuracy of 0.79 (95% CI 0.69-0.87) compared to expert 1 with a test accuracy of 0.70 (95% CI 0.59-0.78) and expert 2 with a test accuracy of 0.66 (95% CI 0.55-0.75). On the uncertain dataset, compared to all experts averaged, the model had higher test accuracy (0.79 vs. 0.68, p = 0.025). CONCLUSION: Deep learning algorithms proposed in the current study improve differentiation of benign from malignant ultrasound-captured solid liver lesions and perform comparably to expert radiologists. Deep learning tools can potentially be used to improve the accuracy and efficiency of clinical workflows.

Evaluation of a convolutional neural network for ovarian tumor differentiation based on magnetic resonance imaging.

OBJECTIVES: There currently lacks a noninvasive and accurate method to distinguish benign and malignant ovarian lesion prior to treatment. This study developed a deep learning algorithm that distinguishes benign from malignant ovarian lesion by applying a convolutional neural network on routine MR imaging. METHODS: Five hundred forty-five lesions (379 benign and 166 malignant) from 451 patients from a single institution were divided into training, validation, and testing set in a 7:2:1 ratio. Model performance was compared with four junior and three senior radiologists on the test set. RESULTS: Compared with junior radiologists averaged, the final ensemble model combining MR imaging and clinical variables had a higher test accuracy (0.87 vs 0.64, p < 0.001) and specificity (0.92 vs 0.64, p < 0.001) with comparable sensitivity (0.75 vs 0.63, p = 0.407). Against the senior radiologists averaged, the final ensemble model also had a higher test accuracy (0.87 vs 0.74, p = 0.033) and specificity (0.92 vs 0.70, p < 0.001) with comparable sensitivity (0.75 vs 0.83, p = 0.557). Assisted by the model's probabilities, the junior radiologists achieved a higher average test accuracy (0.77 vs 0.64, Δ = 0.13, p < 0.001) and specificity (0.81 vs 0.64, Δ = 0.17, p < 0.001) with unchanged sensitivity (0.69 vs 0.63, Δ = 0.06, p = 0.302). With the AI probabilities, the junior radiologists had higher specificity (0.81 vs 0.70, Δ = 0.11, p = 0.005) but similar accuracy (0.77 vs 0.74, Δ = 0.03, p = 0.409) and sensitivity (0.69 vs 0.83, Δ = -0.146, p = 0.097) when compared with the senior radiologists. CONCLUSIONS: These results demonstrate that artificial intelligence based on deep learning can assist radiologists in assessing the nature of ovarian lesions and improve their performance. KEY POINTS: • Artificial Intelligence based on deep learning can assess the nature of ovarian lesions on routine MRI with higher accuracy and specificity than radiologists. • Assisted by the deep learning model's probabilities, junior radiologists achieved better performance that matched those of senior radiologists.

Comprehensive predictive factors for CalliSpheres® microspheres (CSM) drug-eluting bead-transarterial chemoembolization and conventional transarterial chemoembolization on treatment response and survival in hepatocellular carcinoma patients.

BACKGROUND: Transarterial chemoembolization (TACE) is widely applied in hepatocellular carcinoma (HCC) patients who are not suitable for surgical treatment. We aimed to investigate the treatment outcomes and comprehensive prognostic factors of CalliSpheres® microspheres (CSM) drug-eluting bead TACE (DEB-TACE) treatment and conventional TACE (cTACE) treatment in HCC patients. METHODS: Three hundred and thirty-five HCC patients received DEB-TACE or cTACE treatment were consecutively enrolled in multi-center, retrospective cohort study. Treatment response was conducted at M1, M3 or M6 after treatment. Progression free survival (PFS) and overall survival (OS) were recorded. Thirty-seven baseline factors including demographic characteristics, clinical features, biochemical indexes and previous treatment histories were selected. RESULTS: In total patients, history of drink and largest nodule size≥7cm independently predicted worse ORR, DEB-TACE predicted better OS, while largest nodule size≥7cm, increased Child-Pugh stage, ALB abnormal, ALP abnormal or AFP abnormal predicted worse survival. For DEB-TACE group, previous cTACE and ANC abnormal independently predicted worse ORR, and hepatic vein invasion, increased Child-Pugh stage or AFP abnormal independently predicted poor survival. For cTACE group, largest nodule size≥7cm independently predicted poor ORR, and multifocal disease as well as ALB abnormal predicted poor OS. CONCLUSIONS: History of drink, largest nodule size≥7cm, DEB-TACE, increased Child-Pugh stage, abnormal ALB, ALP or AFP are potential prognostic factors in total patients, previous cTACE and ANC abnormal, hepatic vein invasion, increased Child-Pugh stage or AFP abnormal are potential prognostic factors in DEB-TA group, and largest nodule size≥7cm, multifocal disease and ALB abnormal are potential prognostic factors in cTACE group.

A predictive model of incomplete response after transarterial chemoembolization for early or intermediate stage of hepatocellular carcinoma: consideration of hepatic angiographic and cross-sectional imaging.

OBJECTIVES: The purpose of the present study is to develop a predictive model for incomplete response (IR) after conventional transarterial chemoembolization (cTACE) for hepatocellular carcinoma (HCC) based on hepatic angiographic and cross-sectional imaging. METHODS: Sixty patients with 139 target HCC lesions who underwent cTACE from February 2013 to March 2019 were included in this retrospective study. Hepatic angiographic features were identified: the number of feeding arteries, vascularity of the tumor, tumor staining on angiography, vascular lake phenomenon, and hepatic arterio-portal shunt. Cross-sectional imaging features were also identified: tumor extent, location, size, and enhancement pattern. Treatment response was assessed by the modified Response Evaluation Criteria in Solid Tumors (mRECIST) criteria. Logistic regression analysis was performed to determine the potential predictive factors for treatment response. To validate the predictive value of potential factors, the means of a decision tree were also calculated by Classification and Regression Tree (CART). P < 0.05 was considered statistically significant. RESULTS: The IR rate was 43.2% (60/139) in the entire study population. Logistic regression analysis showed that a tumor size > 50 mm (P = 0.005; odds ratio, 7.25; 95% CI 1.79-29.33), central location (P = 0.007; odds ratio, 0.14; 95% CI 0.03-0.59), and nondense tumor staining (P < 0.001; odds ratio, 0.08; 95% CI 0.02-0.28) were predictors of IR after cTACE. Decision tree analysis showed a good ability to classify treatment response with an accuracy of 78.4%. CONCLUSION: Tumor size > 50 mm, central tumor location, and nondense tumor staining were predictors of IR after cTACE. These factors should be taken into consideration when performing cTACE.

Differentiation of low and high grade renal cell carcinoma on routine MRI with an externally validated automatic machine learning algorithm.

Pre-treatment determination of renal cell carcinoma aggressiveness may help guide clinical decision-making. We aimed to differentiate low-grade (Fuhrman I-II) from high-grade (Fuhrman III-IV) renal cell carcinoma using radiomics features extracted from routine MRI. 482 pathologically confirmed renal cell carcinoma lesions from 2008 to 2019 in a multicenter cohort were retrospectively identified. 439 lesions with information on Fuhrman grade from 4 institutions were divided into training and test sets with an 8:2 split for model development and internal validation. Another 43 lesions from a separate institution were set aside for independent external validation. The performance of TPOT (Tree-Based Pipeline Optimization Tool), an automatic machine learning pipeline optimizer, was compared to hand-optimized machine learning pipeline. The best-performing hand-optimized pipeline was a Bayesian classifier with Fischer Score feature selection, achieving an external validation ROC AUC of 0.59 (95% CI 0.49-0.68), accuracy of 0.77 (95% CI 0.68-0.84), sensitivity of 0.38 (95% CI 0.29-0.48), and specificity of 0.86 (95% CI 0.78-0.92). The best-performing TPOT pipeline achieved an external validation ROC AUC of 0.60 (95% CI 0.50-0.69), accuracy of 0.81 (95% CI 0.72-0.88), sensitivity of 0.12 (95% CI 0.14-0.30), and specificity of 0.97 (95% CI 0.87-0.97). Automated machine learning pipelines can perform equivalent to or better than hand-optimized pipeline on an external validation test non-invasively predicting Fuhrman grade of renal cell carcinoma using conventional MRI.

Deep learning-based classification of primary bone tumors on radiographs: A preliminary study.

BACKGROUND: To develop a deep learning model to classify primary bone tumors from preoperative radiographs and compare performance with radiologists. METHODS: A total of 1356 patients (2899 images) with histologically confirmed primary bone tumors and pre-operative radiographs were identified from five institutions' pathology databases. Manual cropping was performed by radiologists to label the lesions. Binary discriminatory capacity (benign versus not-benign and malignant versus not-malignant) and three-way classification (benign versus intermediate versus malignant) performance of our model were evaluated. The generalizability of our model was investigated on data from external test set. Final model performance was compared with interpretation from five radiologists of varying level of experience using the Permutations tests. FINDINGS: For benign vs. not benign, model achieved area under curve (AUC) of 0•894 and 0•877 on cross-validation and external testing, respectively. For malignant vs. not malignant, model achieved AUC of 0•907 and 0•916 on cross-validation and external testing, respectively. For three-way classification, model achieved 72•1% accuracy vs. 74•6% and 72•1% for the two subspecialists on cross-validation (p = 0•03 and p = 0•52, respectively). On external testing, model achieved 73•4% accuracy vs. 69•3%, 73•4%, 73•1%, 67•9%, and 63•4% for the two subspecialists and three junior radiologists (p = 0•14, p = 0•89, p = 0•93, p = 0•02, p < 0•01 for radiologists 1-5, respectively). INTERPRETATION: Deep learning can classify primary bone tumors using conventional radiographs in a multi-institutional dataset with similar accuracy compared to subspecialists, and better performance than junior radiologists. FUNDING: The project described was supported by RSNA Research & Education Foundation, through grant number RSCH2004 to Harrison X. Bai.

Facile synthesis of N,B-co-doped carbon dots with the gram-scale yield for detection of iron (III) and E. coli.

A simple method was developed to prepare fluorescent nitrogen/boron-doped carbon dots (N,B-CDs) in the gram scale. The results showed that the CDs exhibited blue photoluminescence (PL) under 365 nm ultraviolet radiation and excitation-dependent emission. Heteroatoms entered the CDs to enhance the photochemical properties, and their positive properties can be attributed to the presence of guanidino group and functionalized with boronic acid for realizing their utilization in certain applications. These materials could be applied to monitor Fe3+ via static PL quenching, yielding a limit of detection (LOD) of 0.74 µM. Furthermore, the charged and boronic acid groups on the prepared N,B-CDs enabled their use as recognition elements to bind with the bacteria through electrostatic interaction and allowed covalent interactions to form the corresponding boronate ester with E. coli (E. coli) bacterial membrane. This method could satisfy a linear range of 102-107 with LOD of 165 cfu ml-1 for E. coli. This method was applied for the determination of E. coli in tap water and orange juice samples, and satisfactory results were obtained.