Comparison of a novel algorithm quantitatively estimating epifascial fibrosis in three-dimensional computed tomography images to other clinical lymphedema grading methods

Deep learning-based quantitative estimation of lymphedema-induced fibrosis using three-dimensional computed tomography images

In lymphedema, proinflammatory cytokine-mediated progressive cascades always occur, leading to macroscopic fibrosis. However, no methods are practically available for measuring lymphedema-induced fibrosis before its deterioration. Technically, CT can visualize fibrosis in superficial and deep locations. For standardized measurement, verification of deep learning (DL)-based recognition was performed. A cross-sectional, observational cohort trial was conducted. After narrowing window width of the absorptive values in CT images, SegNet-based semantic segmentation model of every pixel into 5 classes (air, skin, muscle/water, fat, and fibrosis) was trained (65%), validated (15%), and tested (20%). Then, 4 indices were formulated and compared with the standardized circumference difference ratio (SCDR) and bioelectrical impedance (BEI) results. In total, 2138 CT images of 27 chronic unilateral lymphedema patients were analyzed. Regarding fibrosis segmentation, the mean boundary F1 score and accuracy were 0.868 and 0.776, respectively. Among 19 subindices of the 4 indices, 73.7% were correlated with the BEI (partial correlation coefficient: 0.420–0.875), and 13.2% were correlated with the SCDR (0.406–0.460). The mean subindex of Index 2 \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\left( {\frac{{P_{Fibrosis\, in\, Affected} - P_{Fibrosis\, in\, Unaffected} }}{{P_{Limb\, in\, Unaffected} }}} \right)$$\end{document}PFibrosisinAffected-PFibrosisinUnaffectedPLimbinUnaffected presented the highest correlation. DL has potential applications in CT image-based lymphedema-induced fibrosis recognition. The subtraction-type formula might be the most promising estimation method.

Relationship between lymphedema after breast cancer treatment and biophysical characteristics of the affected tissue

The treatment of breast cancer is often complicated by lymphedema of the upper limbs. Standard lymphedema evaluation methodologies are not able to measure tissue fibrosis. The ultrasound aspects related to tissue microstructures of lymphedema are neglected in clinical evaluations. The objective of this study was to identify and measure the degree of impairment, topography, and biophysical alterations of subcutaneous lymphedema tissue secondary to the treatment of breast cancer by ultrasonography. Forty-two women at a mean age of 58 (±9.7) years, with unilateral lymphedema due to breast cancer treatment, were evaluated. The upper limbs were divided into affected (affected by lymphedema) and control (contralateral limb). Each limb was subdivided into seven areas, defined by perimetry, evaluated in pairs. The biophysical characteristics thickness, entropy, and echogenicity were evaluated by ultrasonography. The results showed a significant difference in the echogenicity and thickness variables between the affected and unaffected upper limb, in all the extent of the upper limb, while entropy showed no significant difference. The findings indicate that the data presented were consistent both in identifying and measuring the degree of impairment and biophysical changes in the subcutaneous tissue of lymphedema secondary to the treatment of breast cancer.

Computed Tomography-Based Quantitative Analysis of Fibrotic Changes in Skin and Subcutaneous Tissue in Lower Extremity Lymphedema Following Gynecologic Cancer Surgery

Background: Lymphedema produces protein-rich fluids that aggravate inflammation in the skin and subcutaneous tissue. Inflammation then induces fibroadipose tissue deposition and fibrosis. However, few methods have been developed to evaluate the severity of fibrosis. Therefore, we aimed to evaluate the subcutaneous fibrotic changes in lower extremity lymphedema following gynecologic cancer surgery using an image analysis tool, the FIJI software. Methods and Results: Seventy-four patients with lymphedema following gynecologic surgery were enrolled in this study. We quantitatively analyzed the cross-sectional area (CSA) of soft tissue compartments, including subcutaneous tissue with the skin, muscle volume, fibrotic changes in subcutaneous tissue, and the perimeter of skin boundaries. The limb circumference and the CSA of the subcutaneous tissue and skin on the affected side were significantly larger than those on the unaffected side. Fibrotic changes showed the same trend. However, muscle volume patterns were different from those of the other compartments. Some patients showed lower muscle volume on the unaffected side than on the affected side. Circumference and cellulitis significantly affected the extent of fibrotic changes in the skin and subcutaneous tissues. Age and duration of lymphedema did not affect fibrosis. Conclusion: Fibrosis of subcutaneous regions with the skin can be quantitatively calculated using an image analysis tool in lower extremity lymphedema following gynecologic cancer surgery. Edema and cellulitis increase fibrotic changes in the subcutaneous tissue with the skin.