Using Deep Learning to Distinguish Highly Malignant Uveal Melanoma from Benign Choroidal Nevi.

Background: This study aimed to evaluate the potential of human-machine interaction (HMI) in a deep learning software for discerning the malignancy of choroidal melanocytic lesions based on fundus photographs. Methods: The study enrolled individuals diagnosed with a choroidal melanocytic lesion at a tertiary clinic between 2011 and 2023, resulting in a cohort of 762 eligible cases. A deep learning-based assistant integrated into the software underwent training using a dataset comprising 762 color fundus photographs (CFPs) of choroidal lesions captured by various fundus cameras. The dataset was categorized into benign nevi, untreated choroidal melanomas, and irradiated choroidal melanomas. The reference standard for evaluation was established by retinal specialists using multimodal imaging. Trinary and binary models were trained, and their classification performance was evaluated on a test set consisting of 100 independent images. The discriminative performance of deep learning models was evaluated based on accuracy, recall, and specificity. Results: The final accuracy rates on the independent test set for multi-class and binary (benign vs. malignant) classification were 84.8% and 90.9%, respectively. Recall and specificity ranged from 0.85 to 0.90 and 0.91 to 0.92, respectively. The mean area under the curve (AUC) values were 0.96 and 0.99, respectively. Optimal discriminative performance was observed in binary classification with the incorporation of a single imaging modality, achieving an accuracy of 95.8%. Conclusions: The deep learning models demonstrated commendable performance in distinguishing the malignancy of choroidal lesions. The software exhibits promise for resource-efficient and cost-effective pre-stratification.

[Benefits of participatory involvement of patients in the development of a dermatological treatment app-A report from the practice]. / Nutzen der partizipatorischen Mitwirkung von PatientInnen an der Entwicklung einer dermatologischen Therapie-App ­ ein Bericht aus der Praxis.

Approximately 2% of the German population suffer from psoriasis. HybridVITA has developed a mobile application (app) that enables psoriasis patients to independently document the progression of the disease and the current psychological stress at home. The HybridVITA app was created in close collaboration with user groups to ensure optimal adaptation to their needs. Two interactive workshops were held with the user groups and the technical developers of the app as a core element of the developmental process. The workshops identified the needs and suggestions for improvement of the various user groups and formulated user stories for the further development of the app using the Scrum method. The participatory approach of the workshop enabled the project team to gather valuable practical knowledge at an early stage of development. The team's awareness of potential obstacles during the early stages of the project enabled them to proactively identify and address these issues prior to implementing the app in dermatological care. We are confident that a patient-centered and participatory approach to health app development can provide valuable insights for developers.

The classical pathway triggers pathogenic complement activation in membranous nephropathy.

Membranous nephropathy (MN) is an antibody-mediated autoimmune disease characterized by glomerular immune complexes containing complement components. However, both the initiation pathways and the pathogenic significance of complement activation in MN are poorly understood. Here, we show that components from all three complement pathways (alternative, classical and lectin) are found in renal biopsies from patients with MN. Proximity ligation assays to directly visualize complement assembly in the tissue reveal dominant activation via the classical pathway, with a close correlation to the degree of glomerular C1q-binding IgG subclasses. In an antigen-specific autoimmune mouse model of MN, glomerular damage and proteinuria are reduced in complement-deficient mice compared with wild-type littermates. Severe disease with progressive ascites, accompanied by extensive loss of the integral podocyte slit diaphragm proteins, nephrin and neph1, only occur in wild-type animals. Finally, targeted silencing of C3 using RNA interference after the onset of proteinuria significantly attenuates disease. Our study shows that, in MN, complement is primarily activated via the classical pathway and targeting complement components such as C3 may represent a promising therapeutic strategy.

Resemblance-Ranking Peptide Library to Screen for Binders to Antibodies on a Peptidomic Scale.

A novel resemblance-ranking peptide library with 160,000 10-meric peptides was designed to search for selective binders to antibodies. The resemblance-ranking principle enabled the selection of sequences that are most similar to the human peptidome. The library was synthesized with ultra-high-density peptide arrays. As proof of principle, screens for selective binders were performed for the therapeutic anti-CD20 antibody rituximab. Several features in the amino acid composition of antibody-binding peptides were identified. The selective affinity of rituximab increased with an increase in the number of hydrophobic amino acids in a peptide, mainly tryptophan and phenylalanine, while a total charge of the peptide remained relatively small. Peptides with a higher affinity exhibited a lower sum helix propensity. For the 30 strongest peptide binders, a substitutional analysis was performed to determine dissociation constants and the invariant amino acids for binding to rituximab. The strongest selective peptides had a dissociation constant in the hundreds of the nano-molar range. The substitutional analysis revealed a specific hydrophobic epitope for rituximab. To show that conformational binders can, in principle, be detected in array format, cyclic peptide substitutions that are similar to the target of rituximab were investigated. Since the specific binders selected via the resemblance-ranking peptide library were based on the hydrophobic interactions that are widespread in the world of biomolecules, the library can be used to screen for potential linear epitopes that may provide information about the cross-reactivity of antibodies.