Publications by authors named "T J Brinker"
Accurate melanoma diagnosis is crucial for patient outcomes and reliability of AI diagnostic tools. We assess interrater variability among eight expert pathologists reviewing histopathological images and clinical metadata of 792 melanoma-suspicious lesions prospectively collected at eight German hospitals. Moreover, we provide access to the largest panel-validated dataset featuring dermoscopic and histopathological images with metadata.
View Article and Find Full Text PDFArticle Synopsis
- Ovarian cancer patients with Homologous Recombination Deficiency (HRD) may benefit from PARP inhibitor therapy after platinum chemotherapy, and predicting this benefit through whole slide images (WSIs) could provide a quicker and less costly alternative to molecular tests.
- A Deep Learning (DL) model was trained on H&E stained WSIs using a specific HRD ground truth, and it was tested on a separate cohort to see how well it predicted HRD status and the benefit of olaparib treatment.
- Although the model showed potential, with a significant improvement in progression-free survival (PFS) for HRD positive patients treated with PARP inhibitors, its overall prediction accuracy was lower than desired, indicating that further
Large language models (LLMs) are undergoing intensive research for various healthcare domains. This systematic review and meta-analysis assesses current applications, methodologies, and the performance of LLMs in clinical oncology. A mixed-methods approach was used to extract, summarize, and compare methodological approaches and outcomes.
View Article and Find Full Text PDFEarly cutaneous squamous cell carcinoma (cSCC) diagnosis is essential to initiate adequate targeted treatment. Noninvasive diagnostic technologies could overcome the need of multiple biopsies and reduce tumor recurrence. To assess performance of noninvasive technologies for cSCC diagnostics, 947 relevant records were identified through a systematic literature search.
View Article and Find Full Text PDFArticle Synopsis
- Scientists are studying how well AI can help find melanoma, a serious skin cancer, by testing it against dermatologists using a wide variety of skin images from different hospitals.
- They found out that the AI was better at catching melanoma early compared to the dermatologists, which could help patients get treated faster.
- The researchers think that using AI could be a great tool for doctors, especially for tricky cases of skin cancer.