Dual-energy Computed Tomography for the Evaluation of Calcinosis in Systemic Sclerosis

Calcinosis Prevalence in Autoimmune Connective Tissue Diseases-A Retrospective Study

Background/Objectives: Calcinosis cutis is the deposition of insoluble calcium salts, which may cause inflammation, ulceration, pain, and restricted joint mobility. It rarely develops in damaged tissues (dystrophic subtype), most frequently in autoimmune connective tissue diseases (CTDs), but there is very limited data on the prevalence. Also, therapy remains an unsolved issue. In this study, we aimed to collect data on the prevalence of calcinosis in CTD patients to highlight that it is a considerable problem. Methods: A retrospective study was conducted in our department to assess the epidemiology of dystrophic calcinosis in CTDs between January 2003 and January 2024. Results: A total of 839 CTD patients were identified, of whom 56 had calcinosis (6.67%). The mean age of the calcinosis patients at diagnosis of underlying CTD was 41.16 ± 19.47 years. The mean time interval from the onset of calcinosis was 5.96 ± 8.62 years. Systemic sclerosis was the most common CTD complicated by calcinosis (n = 22). Conclusions: Our results are comparable to those reported previously in the literature. Although calcinosis is rare in the overall population, it is a present and unsolved problem in CTD patients. Therefore, further studies are needed on the factors involved in the development and progression of calcinosis as well as its treatment.

Calcinosis in systemic sclerosis: An update on pathogenesis, related complications, and management: A heavy burden still waiting to be lifted off patients' hands

In SSc, dystrophic calcinosis is one of the major clinical manifestations, characterized by the deposition of insoluble calcific substances in tissues, predominantly in the chemical form of calcium hydroxyapatite. Furthermore, calcinosis might lead to compressive neuropathies and severe pain. Current evidence suggests that tissue ischemia and repeated trauma are implicated in the development of calcinosis; however, there are still too many unknown areas that need to be investigated. Detection of calcinosis is commonly performed using X-ray or ultrasound. Moreover, quantification of calcinosis with X-ray and dual-energy computed tomography might be useful for the assessment of disease burden and monitoring of the disease. Despite its prevalence and clinical outcomes, there are no approved disease-modifying treatments for calcinosis in SSc. Debulking or surgical intervention might be preferred for calcinosis complicated with infection, compressive symptoms, or relief of pain. Therefore, innovative investigations and tailored therapeutic approaches are urgently needed to lift the burden of calcinosis from the hands of SSc patients.

Subcutaneous calcinosis: Is it different between systemic sclerosis and dermatomyositis?

Calcinosis cutis is the deposition of insoluble calcium in the skin and subcutaneous tissues. It is a manifestation of several autoimmune connective tissue diseases, most frequently with systemic sclerosis and juvenile dermatomyositis, followed by adult dermatomyositis. Autoimmune connective tissue disease-associated calcinosis is of the dystrophic subtype, which occurs at sites of damaged tissue in the setting of normal serum calcium and phosphate levels. In juvenile dermatomyositis, calcinosis is considered a marker of ongoing disease activity and possibly inadequate treatment, while in adult dermatomyositis, it is a hallmark of skin damage due to chronic rather than active disease. Calcinosis is associated with long disease duration in systemic sclerosis and dermatomyositis, anti-polymyositis/sclerosis autoantibodies in systemic sclerosis and NXP-2 and melanoma differentiation-associated gene 5 in dermatomyositis. Calcinosis in systemic sclerosis occurs most frequently in the hands, particularly the fingers, whereas in dermatomyositis, it affects mainly the trunk and extremities. The primary mineral component of calcinosis is hydroxyapatite in systemic sclerosis and carbonate apatite in dermatomyositis. Calcinosis in dermatomyositis and systemic sclerosis share some pathogenic mechanisms, but vascular hypoxia seems to play a more important role in systemic sclerosis, whereas the release of calcium from mitochondria in muscle cells damaged by myopathy may be a primary mechanism contributing to dermatomyositis-related calcinosis. Multiple treatment strategies for dermatomyositis and systemic sclerosis-related calcinosis have been used with variable results. Early aggressive treatment of underlying myositis in patients with dermatomyositis may improve long-term outcomes of calcinosis. A better understanding of the pathogenesis of calcinosis is needed to improve treatment options.

Computer vision applied to dual-energy computed tomography images for precise calcinosis cutis quantification in patients with systemic sclerosis

Background

Although treatments have been proposed for calcinosis cutis (CC) in patients with systemic sclerosis (SSc), a standardized and validated method for CC burden quantification is necessary to enable valid clinical trials. We tested the hypothesis that computer vision applied to dual-energy computed tomography (DECT) finger images is a useful approach for precise and accurate CC quantification in SSc patients.

Methods

De-identified 2-dimensional (2D) DECT images from SSc patients with clinically evident lesser finger CC lesions were obtained. An expert musculoskeletal radiologist confirmed accurate manual segmentation (subtraction) of the phalanges for each image as a gold standard, and a U-Net Convolutional Neural Network (CNN) computer vision model for segmentation of healthy phalanges was developed and tested. A validation study was performed in an independent dataset whereby two independent radiologists manually measured the longest length and perpendicular short axis of each lesion and then calculated an estimated area by assuming the lesion was elliptical using the formula long axis/2 × short axis/2 × π, and a computer scientist used a region growing technique to calculate the area of CC lesions. Spearman’s correlation coefficient, Lin’s concordance correlation coefficient with 95% confidence intervals (CI), and a Bland-Altman plot (Stata V 15.1, College Station, TX) were used to test for equivalence between the radiologists’ and the CNN algorithm-generated area estimates.

Results

Forty de-identified 2D DECT images from SSc patients with clinically evident finger CC lesions were obtained and divided into training (N = 30 with image rotation × 3 to expand the set to N = 120) and test sets (N = 10). In the training set, five hundred epochs (iterations) were required to train the CNN algorithm to segment phalanges from adjacent CC, and accurate segmentation was evaluated using the ten held-out images. To test model performance, CC lesional area estimates calculated by two independent radiologists and a computer scientist were compared (radiologist 1 vs. radiologist 2 and radiologist 1 vs. computer vision approach) using an independent test dataset comprised of 31 images (8 index finger and 23 other fingers). For the two radiologists’, and the radiologist vs. computer vision measurements, Spearman’s rho was 0.91 and 0.94, respectively, both p < 0.0001; Lin’s concordance correlation coefficient was 0.91 (95% CI 0.85–0.98, p < 0.001) and 0.95 (95% CI 0.91–0.99, p < 0.001); and Bland-Altman plots demonstrated a mean difference between radiologist vs. radiologist, and radiologist vs. computer vision area estimates of − 0.5 mm² (95% limits of agreement − 10.0–9.0 mm²) and 1.7 mm² (95% limits of agreement − 6.0–9.5 mm², respectively.

Conclusions

We demonstrate that CNN quantification has a high degree of correlation with expert radiologist measurement of finger CC area measurements. Future work will include segmentation of 3-dimensional (3D) images for volumetric and density quantification, as well as validation in larger, independent cohorts.