DeepImageTranslator V2: Analysis of Multimodal Medical Images using Semantic Segmentation Maps Generated through Deep Learning

Ye, En Zhou; Ye, En Hui; Bouthillier, Maxime; Ye, Run Zhou

doi:10.28991/hij-2022-03-03-07

Cited by 8 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the development of deep learning techniques in imaging disciplines, progress has been made in the noninvasive diagnosis of many diseases, such as heart failure and tumors. [43–45] We believe that there is a trend towards fitting liver stiffness using validated variables such as serum ferritin. However, there were still some limitations to this study.…”

Section: Discussionmentioning

confidence: 99%

Association between serum ferritin and liver stiffness in adults aged ≥20 years: A cross-sectional study based on NHANES

Han,

Chen,

Zhang

et al. 2023

Medicine

View full text Add to dashboard Cite

The importance of serum ferritin has been demonstrated in many liver diseases, but its relationship with liver stiffness remains unclear. The objective of this study was to investigate the association between serum ferritin levels and participants’ liver stiffness measurement (LSM) in the United States population. We conducted a screening of participants from National Health and Nutrition Examination Survey (NHANES) 2017.1 to 2020.3 to ensure that participants included in this study had complete serum ferritin and LSM information. Association between the independent variable (serum ferritin) and the dependent variable (LSM) was investigated by multiple linear regression and subgroup analysis was performed to identify sensitive individuals, and we subsequently assessed whether there was a non-linear relationship between the 2 using smoothed curve fitting and threshold effect models. The final 7143 participants were included in this study. There was a positive association between participants’ serum ferritin concentration and LSM, with an effect value of (β = 0.0007, 95% confidence interval (CI): 0.0002–0.0011) in the all-adjusted model. The smoothing curve and threshold effect models indicated a non-linear positive correlation between serum ferritin and LSM, which was more pronounced when serum ferritin concentration exceeded 440 ng/mL. Subsequent subgroup analysis showed that this positive correlation was more pronounced in males (β = 0.0007, 95% CI: 0.0001–0.0012), age >60 years (β = 0.00015, 95% CI: 0.0007–0.0023), black participants (β = 0.00018, 95% CI: 0.0009–0.0026), and participants with body mass index (BMI) <25 kg/m2 (β = 0.00012, 95% CI: 0.0005–0.0020). In U.S. adults, there was a positive correlation between serum ferritin levels and liver stiffness, which was more pronounced when serum ferritin exceeded 440 ng/mL. Our study suggested that regular serum ferritin testing would be beneficial in monitoring changes in liver stiffness. Male, age >60 years, black participants, and those with a BMI < 25 kg/m2 should be of greater consideration.

show abstract

Section: Discussionmentioning

confidence: 99%

Association between serum ferritin and liver stiffness in adults aged ≥20 years: A cross-sectional study based on NHANES

Han,

Chen,

Zhang

et al. 2023

Medicine

View full text Add to dashboard Cite

show abstract

“…The strength of the CNN algorithm lies in its capability to identify patterns in data, particularly image data, making it suitable for image and text classification. However, it tends to overfit when data are scarce and interpreting its results can be challenging [31][32][33]. The advantage of the RNN algorithm lies in its ability to handle sequential data such as text or speech, producing reasonably accurate outcomes in recognizing these data patterns.…”

Section: Research Stepsmentioning

confidence: 99%

Exploring the Flexibility and Accuracy of Sentiment Scoring Models through a Hybrid KNN-RNN-CNN Algorithm and ChatGPT

Hariguna,

Ruangkanjanases

2023

HighTech. Innov. J.

View full text Add to dashboard Cite

This study aimed to address the limitations of sentiment analysis by developing a more accurate and flexible sentiment scoring model using ChatGPT in combination with KNN, RNN, and CNN algorithms. To achieve this, primary data from ChatGPT and secondary data from Kaggle were utilized for training. The model's performance was evaluated, yielding an impressive accuracy rate of 88.17%. This research underscores ChatGPT's pivotal role in offering theoretical insights and precise data for diverse applications. The novelty of this study lies in its innovative approach of combining KNN, RNN, and CNN algorithms to create a more adaptable and accurate sentiment scoring model. Additionally, the primary data from ChatGPT greatly enhances the creation of precise and relevant training data across various topics and languages. Despite these achievements, there remains a need for further exploration of testing methods to mitigate the impact of data limitations on result generalizability. Moreover, it is acknowledged that the model's effectiveness may be diminished when applied to languages other than English. Nevertheless, this research provides a promising avenue for users seeking enhanced and precise sentiment analysis by integrating KNN, RNN, and CNN algorithms with ChatGPT. The findings of this study can serve as a solid foundation for future research endeavors in the advancement of sophisticated and effective sentiment analysis technologies. Doi: 10.28991/HIJ-2023-04-02-06 Full Text: PDF

show abstract

“…[13][14][15][16][17] For clinical research data integration, machine learning and meta-analysis have become critical. [18][19][20] Meta-analysis by Sahebkar et al [21] suggests that statins were safe in treatment of systemic lupus erythematosus patients and may reduce cardiovascular risk through lowering C-reactive protein (CRP) levels.…”

Section: Introductionmentioning

confidence: 99%

The efficacy of statins in the treatment of rheumatoid arthritis: A systematic review and meta-analysis

Ren,

2023

Medicine

View full text Add to dashboard Cite

Background: A large body of research has investigated the use of statins in rheumatoid arthritis (RA); however, the therapeutic effects of statins remain uncertain. Thus, we designed a systematic review and meta-analysis to evaluate the role of statins in patients with RA. Methods: Databases searched to detect clinical randomized controlled trials or clinical controlled trials on the interaction between statins and RA before January 2020 included PubMed, Web of Sciences, Embase, Cochrane Library, CNKI, Wan Fang Database. Efficacy was measured by Disease Activity Score in 28 Joints (DAS28), erythrocyte sedimentation rate (ESR), C-reactive protein (CRP), tenderness of the joint (TJ), swelling of the joint (SJ), and interleukin-6. The level of blood lipid was also evaluated. STATA 12.0 was used for the meta-analysis. The Cochrane method was used for quality assessment. Heterogeneity was considered to determine fixed effects or random effects models. Results: Nineteen clinical trials with a total of 22,906 subjects were included in the meta-analysis. Sixteen studies reported a change in DAS28 after statin treatment. The pooled analysis showed that statins reduced DAS28 in RA patients. Change in ESR after statin treatment was reported in 9 studies. The summary analysis showed that statins lowered ESR in RA patients. Twelve studies reported a change in CRP after statin treatment. The results of the entire analysis showed that statins lowered CRP in RA patients. Seven studies reported a change in TJ after statin treatment. The combined analysis showed that statins reduced TJ at RA patients. Six studies reported changes in IL6 after statin therapy. The results showed that statins failed to reduce IL6 in RA patients. Seven studies reported changes in SJ after statin therapy, which showed that statins failed to reduce SJ in RA patients. We also found that statins can reduce blood lipid levels in RA patients. Conclusion: In conclusion, statins were able to reduce DAS28, ESR, CRP, TJ, and blood lipids. It indicated that stains can benefit patients with RA by inhibiting the expression of inflammatory factors and reducing the levels of lipids in the blood. Our study may offer a new perspective on the treatment of RA and provide research ideas for future larger multi-center clinical trials.

show abstract

DeepImageTranslator V2: Analysis of Multimodal Medical Images using Semantic Segmentation Maps Generated through Deep Learning

Cited by 8 publications

References 22 publications

Association between serum ferritin and liver stiffness in adults aged ≥20 years: A cross-sectional study based on NHANES

Association between serum ferritin and liver stiffness in adults aged ≥20 years: A cross-sectional study based on NHANES

Exploring the Flexibility and Accuracy of Sentiment Scoring Models through a Hybrid KNN-RNN-CNN Algorithm and ChatGPT

The efficacy of statins in the treatment of rheumatoid arthritis: A systematic review and meta-analysis

Contact Info

Product

Resources

About