Introduction to radiomics for a clinical audience

Radiomics is a rapidly developing field of research focused on the extraction of quantitative features from medical images, thus converting these digital images into minable, high-dimensional data, which offer unique biological information that can enhance our understanding of disease processes and provide clinical decision support. To date, most radiomics research has been focused on oncological applications; however, it is increasingly being used in a raft of other diseases. This review gives an overview of radiomics for a clinical audience, including the radiomics pipeline and the common pitfalls associated with each stage. Key studies in oncology are presented with a focus on both those that use radiomics analysis alone and those that integrate its use with other multimodal data streams. Importantly, clinical applications outside oncology are also presented. Finally, we conclude by offering a vision for radiomics research in the future, including how it might impact our practice as radiologists.

Effectiveness of myocarditis therapy depending on the diagnosis approach (with or without myocardial biopsy)

Aim. To evaluate the effectiveness of myocarditis therapy depending on the diagnosis approach (with or without myocardial biopsy).

Material and methods. The study included 83 patients ≥18 years old with severe and moderate myocarditis (25 women and 58 men; mean age, 45,7±11,7 years), established by myocardial biopsy (group 1, n=36) or by a non-invasive diagnostic algorithm (group 2, n=47), for which immunosuppressive therapy (IST) was carried out. Inclusion criteria were left ventricular (LV) end-diastolic dimension >5,5 cm and ejection fraction (EF) <50%. An endomyocardial (n=31) or intraoperative (n=5) biopsy with a study of the viral genome and level of anticardiac antibodies were performed. Coronary angiography (29%), cardiac multislice computed tomography (75%), cardiac magnetic resonance imaging (41%), and 99mTc-MIBI scintigraphy (35%) were also carried out. The mean follow-up period was 3 years (36 [12; 65] months). The study was approved by the Intercollegiate Ethics Committee.

Results. The groups were completely comparable in age, baseline parameters (class III [2,25; 3] and III [2; 3] heart failure (HF); end-diastolic LV dimension, 6,7±0,7 and 6,4±0,7 cm; EF, 29,9±8,7 and 31,4±9,3%), the extent of cardiac therapy (excluding the administration rate of в-blockers — 94,4 and 78,7%, p<0,05) and 1ST (methylprednisolone in 91,7 and 89,4% of patients at a mean dose of 24 [16; 32] and 20 [15; 32] mg/day, azathioprine in 50,0 and 46,8% of patients at a mean dose of 150 mg/day or mycophenolate mofetil 2,0 g/day in 30,6% in group 1, hydroxychloroquine 0,2 g/day in 27,8 and 23,4%). Biopsy in group 1 revealed active/borderline (61/39%) myocarditis, in 8 patients — viral genome in the myocardium, including parvovirus B19 in 7 of them. Both groups showed a comparable significant increase in EF after 6 months up to 37,6±8,1 and 42,6±11,5% (p<0,001) and after 27 [12; 54] months up to 43,4±9,6 and 45,5±12,3% (p<0,001), as well as a significant decrease in HF class to 2 [1; 2] in both groups. An increase in EF by ≥10% was recorded in 70 and 72% of patients, respectively. The mortality rate was 13,9 and 12,8%. Taking into account the only transplantation in group 2, the death+transplantation endpoints reached 13,9 and 14,9% of patients (without significant differences between the groups).

Conclusion. In patients with severe and moderate myocarditis diagnosed with and without myocardial biopsy, the effectiveness of combined therapy, including IST, was comparable. If it is impossible to perform a biopsy, complex non-invasive strategy makes it possible to diagnose myocarditis with different probability rate and conduct an effective IST, the refusal of which mostly is not justified.

Anti-heart antibodies levels and their correlation with clinical symptoms and outcomes in patients with confirmed or suspected diagnosis COVID-19

The aim of this study is to evaluate the blood level of anti-heart antibodies (AHA) and its correlation with clinical outcomes in patients with severe and moderate coronavirus disease 2019 (COVID-19). The study included 34 patients (23 males; mean age 60.2 ± 16.6 years) with COVID-19 pneumonia. Besides standard medical examination, the AHA blood levels were observed, including antinuclear antibodies, antiendothelial cell antibodies, anti-cardiomyocyte antibodies (AbC), anti-smooth muscle antibodies (ASMA), and cardiac conducting tissue antibodies. Median hospital length of stay was 14 [13; 18] days. AHA levels were increased in 25 (73.5%) patients. Significant correlation (p < 0.05) of AHA levels with cardiovascular manifestations (r = 0.459) was found. AbC levels correlated with pneumonia severity (r = 0.472), respiratory failure (r = 0.387), need for invasive ventilation (r = 0.469), chest pain (r = 0.374), low QRS voltage (r = 0.415), and levels of C-reactive protein (r = 0.360) and lactate dehydrogenase (r = 0.360). ASMA levels were found to correlate with atrial fibrillation (r = 0.414, p < 0.05). Antinuclear antibodies and AbC levels correlated with pericardial effusion (r = 0.721 and r = 0.745, respectively, p < 0.05). The lethality rate was 8.8%. AbC and ASMA levels correlated significantly with lethality (r = 0.363 and r = 0.426, respectively, p < 0.05) and were prognostically important. AHA can be considered as part of the systemic immune and inflammatory response in COVID-19. Its possible role in the inflammatory heart disease requires further investigation.