Research Scientist, Medical Image Analysis & Machine Learning

You are a motivated PhD candidate interested in machine learning for histopathology image analysis. You will contribute to developing and optimizing deep learning models to analyze digitized H&E slides for cancer classification and spatial mapping. This role is well-suited for researchers aiming to apply advanced computational methods to biomedical challenges. Responsibilities: - Design, develop, and train convolutional neural networks (CNNs) and related ML models on H&E-stained histology images. - Use and extend tools such as QuPath for cell annotations, segmentation models, and dataset curation. - Preprocess, annotate, and manage large image datasets to support model training and validation. - Collaborate with cross-disciplinary teams to integrate image-based predictions with molecular and clinical data. - Analyze model performance and contribute to improving accuracy, efficiency, and robustness. - Document research findings and contribute to publications in peer-reviewed journals. Qualifications: - PhD in Computer Science, Biomedical Engineering, Data Science, Computational Biology, or a related discipline. - Demonstrated research experience in machine learning, deep learning, or biomedical image analysis (e.g., publications, thesis projects, or conference presentations). - Solid programming skills in Python and experience with ML frameworks such as TensorFlow or PyTorch. - Familiarity with digital pathology workflows, image preprocessing/augmentation, and annotation tools. - Ability to work collaboratively in a multidisciplinary research environment. Preferred: - Background in cancer histopathology or biomedical image analysis. - Knowledge of multimodal data integration, including spatial transcriptomics. You are a motivated PhD candidate interested in machine learning for histopathology image analysis. You will contribute to developing and optimizing deep learning models to analyze digitized H&E slides for cancer classification and spatial mapping. This role is well-suited for researchers aiming to apply advanced computational methods to biomedical challenges. Responsibilities: - Design, develop, and train convolutional neural networks (CNNs) and related ML models on H&E-stained histology images. - Use and extend tools such as QuPath for cell annotations, segmentation models, and dataset curation. - Preprocess, annotate, and manage large image datasets to support model training and validation. - Collaborate with cross-disciplinary teams to integrate image-based predictions with molecular and clinical data. - Analyze model performance and contribute to improving accuracy, efficiency, and robustness. - Document research findings and contribute to publications in peer-reviewed journals. Qualifications: - PhD in Computer Science, Biomedical Engineering, Data Science, Computational Biology, or a related discipline. - Demonstrated research experience in machine learning, deep learning, or biomedical image analysis (e.g., publications, thesis projects, or conference presentations). - Solid programming skills in Python and experience with ML frameworks such as TensorFlow or PyTorch. - Familiarity with digital pathology workflows, image preprocessing/augmentation, and annotation tools. - Ability to work collaboratively in a multidisciplinary research environment. Preferred: - Background in cancer histopathology or biomedical image analysis. - Knowledge of multimodal data integration, including spatial transcriptomics.