Scholarlink

PURPOSE <p>This study aims to investigate microstructural changes in the corpus callosum (CC) of multiple sclerosis (MS) patients using texture analysis (TA), even in the absence of visible lesions on conventional MRI, and to assess its diagnostic value in distinguishing patients from healthy controls.</p> METHODS <p>A retrospective analysis was conducted on midsagittal T2-weighted MRI scans of 54 MS patients without CC lesions and 50 healthy controls. Histogram-based texture analysis was performed using MATLAB software, and statistical evaluations were conducted with SPSS version 25. Texture parameters were compared between groups, and a logistic regression model was developed to predict MS diagnosis. Given that our study involves a retrospective radiology analysis, obtaining consent forms is not necessary.</p> RESULTS <p>Statistically significant differences were found between MS patients and controls in most histogram-derived texture features, including mean, median, standard deviation, and multiple percentiles (<i>p</i> &lt; 0.001). The logistic regression model incorporating selected parameters achieved a diagnostic accuracy of 94.23%, successfully identifying patients with MS despite the absence of radiologically visible lesions.</p> CONCLUSION <p>Texture analysis of the CC can detect subtle tissue changes in MS patients, offering a promising, non-invasive method for early diagnosis. These findings highlight the potential of TA as a complementary imaging tool in MS diagnostics and warrant further research in larger populations.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Corpus callosum texture analysis: a different perspective approach for diagnosing multiple sclerosis

  • 期刊论文

  • 发表日期：

    2025年10月11日

查看全文
  • Burak Karip,
  • Fatma Ok,
  • Ceyda Ören,
  • Kürşad Nuri Baydili,
  • Murat Baykara

摘要

PURPOSE

This study aims to investigate microstructural changes in the corpus callosum (CC) of multiple sclerosis (MS) patients using texture analysis (TA), even in the absence of visible lesions on conventional MRI, and to assess its diagnostic value in distinguishing patients from healthy controls.

METHODS

A retrospective analysis was conducted on midsagittal T2-weighted MRI scans of 54 MS patients without CC lesions and 50 healthy controls. Histogram-based texture analysis was performed using MATLAB software, and statistical evaluations were conducted with SPSS version 25. Texture parameters were compared between groups, and a logistic regression model was developed to predict MS diagnosis. Given that our study involves a retrospective radiology analysis, obtaining consent forms is not necessary.

RESULTS

Statistically significant differences were found between MS patients and controls in most histogram-derived texture features, including mean, median, standard deviation, and multiple percentiles (p < 0.001). The logistic regression model incorporating selected parameters achieved a diagnostic accuracy of 94.23%, successfully identifying patients with MS despite the absence of radiologically visible lesions.

CONCLUSION

Texture analysis of the CC can detect subtle tissue changes in MS patients, offering a promising, non-invasive method for early diagnosis. These findings highlight the potential of TA as a complementary imaging tool in MS diagnostics and warrant further research in larger populations.