Breast Tumor Tissue Image Classification Using Single-Task Meta Learning with Auxiliary Network.

Breast cancer has a high mortality rate among cancers. If the type of breast tumor can be correctly diagnosed at an early stage, the survival rate of the patients will be greatly improved. Considering the actual clinical needs, the classification model of breast pathology images needs to have the ability to make a correct classification, even in facing image data with different characteristics. The existing convolutional neural network (CNN)-based models for the classification of breast tumor pathology images lack the requisite generalization capability to maintain high accuracy when confronted with pathology images of varied characteristics. Consequently, this study introduces a new classification model, STMLAN (Single-Task Meta Learning with Auxiliary Network), which integrates Meta Learning and an auxiliary network. Single-Task Meta Learning was proposed to endow the model with generalization ability, and the auxiliary network was used to enhance the feature characteristics of breast pathology images. The experimental results demonstrate that the STMLAN model proposed in this study improves accuracy by at least 1.85% in challenging multi-classification tasks compared to the existing methods. Furthermore, the Silhouette Score corresponding to the features learned by the model has increased by 31.85%, reflecting that the proposed model can learn more discriminative features, and the generalization ability of the overall model is also improved.

Reference Values for Paravertebral Muscle Size and Myosteatosis in Chinese Adults, a Nationwide Multicenter Study.

RATIONALE AND OBJECTIVES: The paravertebral muscles, characterized by their susceptibility to severe size loss and fat infiltration in old age, lack established reference values for age-related variations in muscle parameters. This study aims to fill this gap by establishing reference values for paravertebral muscles in a Chinese adult population. MATERIALS AND METHODS: This cross-sectional study utilized the baseline data from the prospective cohort China Action on Spine and Hip (CASH). A total of 4305 community-dwelling participants aged 21-80 years in China were recruited between 2013 and 2017. Pregnant women, individuals with metal implants, limited mobility or diseases/conditions (spinal tumor, infection, etc.) affecting lumbar vertebra were excluded from the study. Psoas and paraspinal muscles were measured in quantitative computed tomography (QCT) images at the L3 and L5 levels using Osirix software. Age-related reference values for muscle area, density, and fat fraction were constructed as percentile charts using the lambda-mu-sigma (LMS) method. RESULTS: The paravertebral muscles exhibited an age-related decline in muscle area and density, coupled with an increase in muscle fat fraction. Between the ages of 25 and 75, the reductions in psoas and paraspinal muscle cross-sectional area at the L3 level were - 0.47%/yr and - 0.53%/yr in men, and - 0.19%/yr and - 0.23%/yr in women, respectively. Notably, accelerated muscle loss was observed during menopause and postmenopause in women (45-75 years) and intermittently during middle and old age in men (35-55 and 60-75 years). Besides, the age-related decreases in PSMA, PMA, and PSMD and the increases in PSMFF were more pronounced in L5 than in L3 CONCLUSION: This study shows distinct patterns of accelerated muscle loss were identified in menopausal and postmenopausal women and in middle-aged and old men. The findings contribute valuable information for future investigations on paravertebral muscle loss and myosteatosis.

Breast Tumor Tissue Image Classification Using DIU-Net.

Inspired by the observation that pathologists pay more attention to the nuclei regions when analyzing pathological images, this study utilized soft segmentation to imitate the visual focus mechanism and proposed a new segmentation-classification joint model to achieve superior classification performance for breast cancer pathology images. Aiming at the characteristics of different sizes of nuclei in pathological images, this study developed a new segmentation network with excellent cross-scale description ability called DIU-Net. To enhance the generalization ability of the segmentation network, that is, to avoid the segmentation network from learning low-level features, we proposed the Complementary Color Conversion Scheme in the training phase. In addition, due to the disparity between the area of the nucleus and the background in the pathology image, there is an inherent data imbalance phenomenon, dice loss and focal loss were used to overcome this problem. In order to further strengthen the classification performance of the model, this study adopted a joint training scheme, so that the output of the classification network can not only be used to optimize the classification network itself, but also optimize the segmentation network. In addition, this model can also provide the pathologist model's attention area, increasing the model's interpretability. The classification performance verification of the proposed method was carried out with the BreaKHis dataset. Our method obtains binary/multi-class classification accuracy 97.24/93.75 and 98.19/94.43 for 200× and 400× images, outperforming existing methods.

Emerging role of ferroptosis in glioblastoma: Therapeutic opportunities and challenges.

Glioblastoma (GBM) is the most common malignant craniocerebral tumor. The treatment of this cancer is difficult due to its high heterogeneity and immunosuppressive microenvironment. Ferroptosis is a newly found non-apoptotic regulatory cell death process that plays a vital role in a variety of brain diseases, including cerebral hemorrhage, neurodegenerative diseases, and primary or metastatic brain tumors. Recent studies have shown that targeting ferroptosis can be an effective strategy to overcome resistance to tumor therapy and immune escape mechanisms. This suggests that combining ferroptosis-based therapies with other treatments may be an effective strategy to improve the treatment of GBM. Here, we critically reviewed existing studies on the effect of ferroptosis on GBM therapies such as chemotherapy, radiotherapy, immunotherapy, and targeted therapy. In particular, this review discussed the potential of ferroptosis inducers to reverse drug resistance and enhance the sensitivity of conventional cancer therapy in combination with ferroptosis. Finally, we highlighted the therapeutic opportunities and challenges facing the clinical application of ferroptosis-based therapies in GBM. The data generated here provide new insights and directions for future research on the significance of ferroptosis-based therapies in GBM.

Exposure of zebra mussels to radial extracorporeal shock waves: implications for treatment of fracture nonunions.

BACKGROUND: Radial extracorporeal shock wave therapy (rESWT) is an attractive, non-invasive therapy option to manage fracture nonunions of superficial bones, with a reported success rate of approximately 75%. Using zebra mussels (Dreissena polymorpha), we recently demonstrated that induction of biomineralization after exposure to focused extracorporeal shock waves (fESWs) is not restricted to the region of direct energy transfer into calcified tissue. This study tested the hypothesis that radial extracorporeal shock waves (rESWs) also induce biomineralization in regions not directly exposed to the shock wave energy in zebra mussels. METHODS: Zebra mussels were exposed on the left valve to 1000 rESWs at different air pressure (between 0 and 4 bar), followed by incubation in calcein solution for 24 h. Biomineralization was evaluated by investigating the fluorescence signal intensity found on sections of the left and right valves prepared two weeks after exposure. RESULTS: General linear model analysis demonstrated statistically significant (p < 0.05) effects of the applied shock wave energy as well as of the side (left/exposed vs. right/unexposed) and the investigated region of the valve (at the position of exposure vs. positions at a distance to the exposure) on the mean fluorescence signal intensity values, as well as statistically significant combined energy × region and energy × side × region effects. The highest mean fluorescence signal intensity value was found next to the umbo, i.e., not at the position of direct exposure to rESWs. CONCLUSIONS: As in the application of fESWs, induction of biomineralization by exposure to rESWs may not be restricted to the region of direct energy transfer into calcified tissue. Furthermore, the results of this study may contribute to better understand why the application of higher energy flux densities beyond a certain threshold does not necessarily lead to higher success rates when treating fracture nonunions with extracorporeal shock wave therapy.

Modified posterior percutaneous endoscopic cervical discectomy for lateral cervical disc herniation: the vertical anchoring technique.

PURPOSE: During the long-term practice of percutaneous endoscopic cervical discectomy (PECD) at our institution, we have modified the protocol to include the vertical anchoring technique (VAT), which we will describe in detail in this article. The objective of this study was to compare the clinical outcomes associated with the conventional posterior PECD technique with that associated with the modified technique to determine the safety and efficacy of the latter technique. METHODS: From December 2014 to January 2016, a total of 44 patients with single cervical disc herniation were randomly divided into two groups. One group underwent conventional posterior PECD, and the other group underwent posterior PECD combined with VAT. The operative time, fluoroscopy times and perioperative complications were recorded. The visual analog scale (VAS) for neck and arm pain and the modified MacNab criteria at 1 day, 3, 6, and 12 months after surgery were used to evaluate the postoperative outcomes. RESULTS: All patients underwent surgery successfully without severe complications. The operative time and intraoperative fluoroscopy times were significantly less in patients treated with VAT than in those who underwent conventional posterior PECD (P < 0.05). Both types of surgery significantly improved the symptoms of patients. According to the results of the follow-up period, there were no significant differences in VAS scores for neck and arm pain or the modified MacNab criteria between the two groups (P > 0.05). There was no recurrence in either group during the follow-up period. CONCLUSIONS: Although the clinical outcomes of the two surgical techniques were similar, the VAT decreased the operative time and intraoperative fluoroscopy times in posterior PECD surgery. The learning curve for posterior PECD could be shortened by using the VAT. These slides can be retrieved under Electronic Supplementary Material.

A multicenter clinical trial on the diagnostic value of dual-tracer PET/CT in pulmonary lesions using 3'-deoxy-3'-18F-fluorothymidine and 18F-FDG.

UNLABELLED: Some new radiotracers might add useful information and improve diagnostic confidence of (18)F-FDG imaging in tumors. A multicenter clinical trial was designed to investigate the diagnostic performance of dual-tracer ((18)F-FDG and 3'-deoxy-3'-(18)F-fluorothymidine [(18)F-FLT]) PET/CT in pulmonary nodules. METHODS: Fifty-five patients underwent dual-tracer imaging in 6 imaging centers using the same models of equipment and standardized protocols. The images were interpreted by a collective group of readers who were unaware of the clinical data. The diagnostic performance using either tracer alone or dual-tracers together, with or without CT, was compared. The histological diagnosis or clinical findings in a 12-mo follow-up period served as the standard of truth. RESULTS: In 16 patients with malignant tumor, 16 with tuberculosis, and 23 with other benign lesions, the sensitivity and specificity of (18)F-FDG and (18)F-FLT were 87.5% and 58.97% and 68.75% and 76.92%, respectively. The combination of dual-tracer PET/CT improved the sensitivity and specificity up to 100% and 89.74%. The 3 subgroups of patients could be best separated when the (18)F-FLT/(18)F-FDG standardized uptake value ratio of 0.4-0.90 was used as the threshold. CONCLUSION: By reflecting different biologic features, the dual-tracer PET/CT using (18)F-FDG and (18)F-FLT favorably affected the diagnosis of lung nodules.