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 software program for automated compressive vertebral fracture detection on elderly women's lateral chest radiograph: Ofeye 1.0.

Background: Because osteoporotic vertebral fracture (OVF) on chest radiographs is commonly missed in radiological reports, we aimed to develop a software program which offers automated detection of compressive vertebral fracture (CVF) on lateral chest radiographs, and which emphasizes CVF detection specificity with a low false positivity rate. Methods: For model training, we retrieved 3,991 spine radiograph cases and 1,979 chest radiograph cases from 16 sources, with among them in total 1,404 cases had OVF. For model testing, we retrieved 542 chest radiograph cases and 162 spine radiograph cases from four independent clinics, with among them 215 cases had OVF. All cases were female subjects, and except for 31 training data cases which were spine trauma cases, all the remaining cases were post-menopausal women. Image data included DICOM (Digital Imaging and Communications in Medicine) format, hard film scanned PNG (Portable Network Graphics) format, DICOM exported PNG format, and PACS (Picture Archiving and Communication System) downloaded resolution reduced DICOM format. OVF classification included: minimal and mild grades with <20% or ≥20-25% vertebral height loss respectively, moderate grade with ≥25-40% vertebral height loss, severe grade with ≥40%-2/3 vertebral height loss, and collapsed grade with ≥2/3 vertebral height loss. The CVF detection base model was mainly composed of convolution layers that include convolution kernels of different sizes, pooling layers, up-sampling layers, feature merging layers, and residual modules. When the model loss function could not be further decreased with additional training, the model was considered to be optimal and termed 'base-model 1.0'. A user-friendly interface was also developed, with the synthesized software termed 'Ofeye 1.0'. Results: Counting cases and with minimal and mild OVFs included, base-model 1.0 demonstrated a specificity of 97.1%, a sensitivity of 86%, and an accuracy of 93.9% for the 704 testing cases. In total, 33 OVFs in 30 cases had a false negative reading, which constituted a false negative rate of 14.0% (30/215) by counting all OVF cases. Eighteen OVFs in 15 cases had OVFs of ≥ moderate grades missed, which constituted a false negative rate of 7.0% (15/215, i.e., sensitivity 93%) if only counting cases with ≥ moderate grade OVFs missed. False positive reading was recorded in 13 vertebrae in 13 cases (one vertebra in each case), which constituted a false positivity rate of 2.7% (13/489). These vertebrae with false positivity labeling could be readily differentiated from a true OVF by a human reader. The software Ofeye 1.0 allows 'batch processing', for example, 100 radiographs can be processed in a single operation. This software can be integrated into hospital PACS, or installed in a standalone personal computer. Conclusions: A user-friendly software program was developed for CVF detection on elderly women's lateral chest radiographs. It has an overall low false positivity rate, and for moderate and severe CVFs an acceptably low false negativity rate. The integration of this software into radiological practice is expected to improve osteoporosis management for elderly women.

Identification of Novel Target for Osteosarcoma by Network Analysis.

BACKGROUND Osteosarcoma (OS) is a highly complicated bone cancer involving imbalance of signaling transduction networks in cells. Development of new anti-osteosarcoma drugs is very challenging, mainly due to lack of known key targets. MATERIAL AND METHODS In this study, we attempted to reveal more promising targets for drug design by "Target-Pathway" network analysis, providing the new therapeutic strategy of osteosarcoma. The potential targets used for the treatment of OS were selected from 4 different sources: DrugBank, TCRD database, dbDEMC database, and recent scientific literature papers. Cytoscape was used for the establishment of the "Target-Pathway" network. RESULTS The obtained results suggest that tankyrase 2 (TNKS2) might be a very good potential protein target for the treatment of osteosarcoma. An in vitro MTT assay proved that it is an available option against OS by targeting the TNKS2 protein. Subsequently, cell cycle and apoptosis assay by flow cytometry showed the TNKS2 inhibitor can obviously induce cell cycle arrest, apoptosis, and mitotic cell death. CONCLUSIONS Tankyrase 2 (TNKS2), a member of the multifunctional poly(ADP-ribose) polymerases (PARPs), could be a very useful protein target for the treatment of osteosarcoma.

Asynchrony of Base-Pair Breaking and Nucleotide Releasing of Helicases in DNA Unwinding.

Helicases harness the energy of nucleotide triphosphate hydrolysis to unwind double-stranded DNA (dsDNA) in discrete steps. In spite of intensive studies, the mechanism of stepping is still poorly understood. Here, we applied single-molecule fluorescent resonant energy transfer to characterize the stepping of two nonring helicases, Escherichia coli RecQ ( E. coli RecQ) and Saccharomyces cerevisiae Pif1 (ScPif1). Our data showed that when forked dsDNA with free overhangs are used as substrates, both E. coli RecQ and ScPif1 unwind the dsDNA in nonuniform steps that distribute over broad ranges. When tension is exerted on the overhangs, the overall profile of the step-size distribution of ScPif1 is narrowed, whereas that of E. coli RecQ remains unchanged. Moreover, the measured step sizes of the both helicases concentrate on integral multiples of a half base pair. We propose a universal stepping mechanism, in which a helicase breaks one base pair at a time and sequesters the nascent nucleotides and then releases them after a random number of base-pair breaking events. The mechanism can interpret the observed unwinding patterns quantitatively and provides a general view of the helicase activity.

Hydroxytyrosol inhibits the inflammatory response of osteoarthritis chondrocytes via SIRT6-mediated autophagy.

Osteoarthritis (OA) is a common degenerative joint disease. Inflammation may exaggerate the catabolism and degeneration in the pathogenesis of OA. Hydroxytyrosol (HT) has been used in the management of inflammatory diseases. In addition, reports have revealed that autophagy was a therapeutic target of diseases caused by inflammation. Sirtuin 6 (SIRT6) has also been demonstrated to prevent OA development by reducing both the inflammatory response and chondrocyte senescence. However, the roles of SIRT6 and autophagy in cartilage and its underlying anti­inflammatory mechanism are unknown. Therefore, the present study aimed to determine the effects of HT on autophagy and inflammation in chondrocytes, and clarify whether HT regulates the inflammatory response through SIRT6­mediated autophagy. The expression of protein and mRNA were determined by western blot analysis and reverse transcription­quantitative polymerase chain reaction. The production of cytokines was detected by ELISA. It was demonstrated that HT inhibited the levels of interleukin (IL)­1ß and IL­6 in tumor necrosis factor (TNF)­α­stimulated chondrocytes in a concentration­dependent manner. In addition, HT promoted cell autophagy and increased the mRNA and protein expression levels of SIRT6 in chondrocytes stimulated with TNF-α. Autophagy inhibitor 3-methyladenine or knockdown of SIRT6 decreased the inhibitory effects of HT on the inflammatory response in chondrocytes. In addition, knockdown of SIRT6 attenuated the expression of microtubule-associated protein 1A/1B­light chain 3 and Beclin1 in chondrocytes. Overall, these findings suggested that HT inhibits the inflammatory response of chondrocytes through SIRT6­mediated autophagy. The present study provided a new drug target for the clinical treatment of inflammatory diseases.

Pif1 is a force-regulated helicase.

Pif1 is a prototypical member of the 5' to 3' DNA helicase family conserved from bacteria to human. It has a high binding affinity for DNA, but unwinds double-stranded DNA (dsDNA) with a low processivity. Efficient DNA unwinding has been observed only at high protein concentrations that favor dimerization of Pif1. In this research, we used single-molecule fluorescence resonance energy transfer (smFRET) and magnetic tweezers (MT) to study the DNA unwinding activity of Saccharomyces cerevisiae Pif1 (Pif1) under different forces exerted on the tails of a forked dsDNA. We found that Pif1 can unwind the forked DNA repetitively for many unwinding-rezipping cycles at zero force. However, Pif1 was found to have a very limited processivity in each cycle because it loosened its strong association with the tracking strand readily, which explains why Pif1 cannot be observed to unwind DNA efficiently in bulk assays at low protein concentrations. The force enhanced the unwinding rate and the total unwinding length of Pif1 significantly. With a force of 9 pN, the rate and length were enhanced by more than 3- and 20-fold, respectively. Our results imply that the DNA unwinding activity of Pif1 can be regulated by force. The relevance of this characteristic of Pif1 to its cellular functions is discussed.

No Superiority of High-Flexion vs Standard Total Knee Arthroplasty: An Update Meta-Analysis of Randomized Controlled Trials.

This meta-analysis was performed using a Cochrane systematic review approach to examine published data with an aim to clarify whether standard or high flexion prostheses increase the range of knee motion and clinical outcomes. 1778 patients from 17 randomized controlled trials were identified. No significant differences in the range of motion, weight-bearing flexion and hip functions scores were found between treatment groups. We also found no significant differences in complications with regard to revision, component loosening, deep infection, anterior knee pain, stiffness, post-operative bone fracture and post-operative patella clunk syndrome, but the high flexion prostheses group had a higher incidence of deep venous thrombosis. The results do not support the proposition that high flexion knee prostheses provide substantial clinical advantages over standard knee prostheses.