Search Results - "Haslum, Johan Fredin"

Cell Painting-based bioactivity prediction boosts high-throughput screening hit-rates and compound diversity by Fredin Haslum, Johan, Lardeau, Charles-Hugues, Karlsson, Johan, Turkki, Riku, Leuchowius, Karl-Johan, Smith, Kevin, Müllers, Erik

“…Identifying active compounds for a target is a time- and resource-intensive task in early drug discovery. Accurate bioactivity prediction using morphological…”
Get full text

Bridging Generalization Gaps in High Content Imaging Through Online Self-Supervised Domain Adaptation by Haslum, Johan Fredin, Matsoukas, Christos, Leuchowius, Karl-Johan, Smith, Kevin

“…High Content Imaging (HCI) plays a vital role in modern drug discovery and development pipelines, facilitating various stages from hit identification to…”
Get full text

Are Natural Domain Foundation Models Useful for Medical Image Classification? by Huix, Joana Pales, Ganeshan, Adithya Raju, Haslum, Johan Fredin, Soderberg, Magnus, Matsoukas, Christos, Smith, Kevin

“…The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has…”
Get full text

What Makes Transfer Learning Work for Medical Images: Feature Reuse & Other Factors by Matsoukas, Christos, Haslum, Johan Fredin, Sorkhei, Moein, Soderberg, Magnus, Smith, Kevin

“…Transfer learning is a standard technique to transfer knowledge from one domain to another. For applications in medical imaging, transfer from ImageNet has…”
Get full text

Bridging Generalization Gaps in High Content Imaging Through Online Self-Supervised Domain Adaptation by Haslum, Johan Fredin, Matsoukas, Christos, Leuchowius, Karl-Johan, Smith, Kevin

“…High Content Imaging (HCI) plays a vital role in modern drug discovery and development pipelines, facilitating various stages from hit identification to…”
Get full text

Are Natural Domain Foundation Models Useful for Medical Image Classification? by Huix, Joana Palés, Ganeshan, Adithya Raju, Haslum, Johan Fredin, Söderberg, Magnus, Matsoukas, Christos, Smith, Kevin

“…The deep learning field is converging towards the use of general foundation models that can be easily adapted for diverse tasks. While this paradigm shift has…”
Get full text

Is it Time to Replace CNNs with Transformers for Medical Images? by Matsoukas, Christos, Haslum, Johan Fredin, Söderberg, Magnus, Smith, Kevin

“…Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis. Recently, vision transformers…”
Get full text

Metadata-guided Consistency Learning for High Content Images by Haslum, Johan Fredin, Matsoukas, Christos, Leuchowius, Karl-Johan, Müllers, Erik, Smith, Kevin

“…High content imaging assays can capture rich phenotypic response data for large sets of compound treatments, aiding in the characterization and discovery of…”
Get full text

What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors by Matsoukas, Christos, Haslum, Johan Fredin, Sorkhei, Moein, Söderberg, Magnus, Smith, Kevin

“…Transfer learning is a standard technique to transfer knowledge from one domain to another. For applications in medical imaging, transfer from ImageNet has…”
Get full text

Pretrained ViTs Yield Versatile Representations For Medical Images by Matsoukas, Christos, Haslum, Johan Fredin, Sorkhei, Moein, Söderberg, Magnus, Smith, Kevin

“…Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in…”
Get full text

Adding Seemingly Uninformative Labels Helps in Low Data Regimes by Matsoukas, Christos, Hernandez, Albert Bou I, Liu, Yue, Dembrower, Karin, Miranda, Gisele, Konuk, Emir, Haslum, Johan Fredin, Zouzos, Athanasios, Lindholm, Peter, Strand, Fredrik, Smith, Kevin

“…Evidence suggests that networks trained on large datasets generalize well not solely because of the numerous training examples, but also class diversity which…”
Get full text