Current Applications of Artificial Intelligence in Sarcoidosis

Lew, Dana; Klang, Eyal; Soffer, Shelly; Morgenthau, Adam S.

doi:10.1007/s00408-023-00641-7

Cited by 6 publications

(4 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For cardiac and neurosarcoidosis, the feel, function and inflammation domain might partly be the same, but at the function domain differ from pulmonary sarcoidosis. consists of pulmonary function testing including FVC, FEV1, and DLCO, 6MWD, activity tracking devices [52] and HRCT parameters ("radiomics" [53]). In the "inflammation" domain, both imaging biomarkers such as FDG-PET as well as serum biomarkers such as ACE and sIL-2R are important.…”

Section: Discussionmentioning

confidence: 99%

“…The domain "feel" consists of questionnaires such as King's Sarcoidosis Questionnaire (KSQ), FAS, patient reported outcome specifically on side effects on drugs as well as physician noted side effects. The domain "function" consists of pulmonary function testing including FVC, FEV1, and DLCO, 6MWD, activity tracking devices[52] and HRCT parameters ("radiomics"[53]). In the "inflammation" domain, both imaging biomarkers such as FDG-PET as well as serum biomarkers such as ACE and sIL-2R are important.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Clinical trials in pulmonary sarcoidosis; what is needed, what is happening and what is next?

Veltkamp

2024

Current Opinion in Pulmonary Medicine

View full text Add to dashboard Cite

Purpose of review There is a clinical unmet need to improve treatment for patients with pulmonary sarcoidosis. Both retrospective and prospective drug trials are hampered by the fact that patients with sarcoidosis are characterized by a heterogeneous presentation and disease course. In this review, an overview is given of different drug trials in pulmonary sarcoidosis with an emphasis on different primary endpoints and the problems related to them. Recent findings In recent years, using significant input from patients with sarcoidosis, different task-forces/studies tried to develop a core set of most important outcomes to measure in future studies on treatment of sarcoidosis. Furthermore, at present, three major clinical trials are being conducted on new drugs for treatment of pulmonary sarcoidosis. Summary Progress has been made to develop a core set of outcomes measures that can be used in making a combined primary endpoint in future drug trials in sarcoidosis.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

Clinical trials in pulmonary sarcoidosis; what is needed, what is happening and what is next?

Veltkamp

2024

Current Opinion in Pulmonary Medicine

View full text Add to dashboard Cite

show abstract

“…Early work in the field of artificial intelligence also holds promise for future prognostic and management biomarkers, although it is currently predominately focused on diagnosis [108]. Radiomics, the interpretation of imaging characteristics not seen by the human eye, has been able to help differentiate sarcoidosis from malignancy and other granulomatous diseases.…”

Section: Biomarkers In the Management Of Therapymentioning

confidence: 99%

Treatment of Granulomatous Inflammation in Pulmonary Sarcoidosis

Gerke

2024

JCM

View full text Add to dashboard Cite

The management of pulmonary sarcoidosis is a complex interplay of disease characteristics, the impact of medications, and patient preferences. Foremost, it is important to weigh the risk of anti-granulomatous treatment with the benefits of lung preservation and improvement in quality of life. Because of its high spontaneous resolution rate, pulmonary sarcoidosis should only be treated in cases of significant symptoms due to granulomatous inflammation, lung function decline, or substantial inflammation on imaging that can lead to irreversible fibrosis. The longstanding basis of treatment has historically been corticosteroid therapy for the control of granulomatous inflammation. However, several corticosteroid-sparing options have increasing evidence for use in refractory disease, inability to taper steroids to an acceptable dose, or in those with toxicity to corticosteroids. Treatment of sarcoidosis should be individualized for each patient due to the heterogeneity of the clinical course, comorbid conditions, response to therapy, and tolerance of medication side effects.

show abstract

“…Qualitative visual assessment has been shown to have low inter- and intra-rater reliability (Van den Heuvel et al 2015, Lovinfosse et al 2022, Benn et al 2024). Reliable quantification of disease related textures from images could support ongoing efforts to identify meaningful phenotypes of pulmonary sarcoidosis (Desai et al 2023, Carlson et al 2024, Lin et al 2022, Schupp et al 2018, Lew et al 2023, Rubio-Rivas & Corbella 2020).…”

Section: Introductionmentioning

confidence: 99%

The textures of sarcoidosis: quantifying lung disease through variograms

Lippitt,

Maier,

Fingerlin

et al. 2024

Preprint

View full text Add to dashboard Cite

Objective: Sarcoidosis is a granulomatous disease affecting the lungs in over 90% of patients. Qualitative assessment of chest CT by radiologists is standard clinical practice and reliable quantification of disease from CT would support ongoing efforts to identify sarcoidosis phenotypes. Standard imaging feature engineering techniques such as radiomics suffer from extreme sensitivity to image acquisition and processing, potentially impeding generalizability of research to clinical populations. In this work, we instead investigate approaches to engineering variogram-based features with the intent to identify a robust, generalizable pipeline for image quantification in the study of sarcoidosis. Approach: For a cohort of more than 300 individuals with sarcoidosis, we investigated 24 feature engineering pipelines differing by decisions for image registration to a template lung, empirical and model variogram estimation methods, and feature harmonization for CT scanner model, and subsequently 48 sets of phenotypes produced through unsupervised clustering. We then assessed sensitivity of engineered features, phenotypes produced through unsupervised clustering, and sarcoidosis disease signal strength to pipeline. Main results: We found that variogram features had low to mild association with scanner model and associations were reduced by image registration. For each feature type, features were also typically robust to all pipeline decisions except image registration. Strength of disease signal as measured by association with pulmonary function testing and some radiologist visual assessments was strong (optimistic AUC 0.9, p 0.0001 in models for architectural distortion, conglomerate mass, fibrotic abnormality, and traction bronchiectasis) and fairly consistent across engineering approaches regardless of registration and harmonization for CT scanner. Significance: Variogram-based features appear to be a suitable approach to image quantification in support of generalizable research in pulmonary sarcoidosis.

show abstract

Current Applications of Artificial Intelligence in Sarcoidosis

Cited by 6 publications

References 49 publications

Clinical trials in pulmonary sarcoidosis; what is needed, what is happening and what is next?

Clinical trials in pulmonary sarcoidosis; what is needed, what is happening and what is next?

Treatment of Granulomatous Inflammation in Pulmonary Sarcoidosis

The textures of sarcoidosis: quantifying lung disease through variograms

Contact Info

Product

Resources

About