Abstract IA02: Cancer-specific foundation models: Friend or foe in healthcare AI?

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Motivation Many machine learning (ML) models developed to classify phenotype from gene expression data provide interpretations for their decisions, with the aim of understanding biological processes. For many models, including neural networks, interpretati ...

It is well-established that symptomatic cancers evade immune destruction by coalescing tumor microenvironments to suppress adaptive immunity. Additionally, mouse models of cervical and other cancers have revealed a capability of tumors to systemically indu ...

Young age is associated with increased risk of recurrence in hormone receptor (HR)–positive early-stage breast cancer (eBC). Lack of adherence to endocrine therapy (ET) is a potential reason for the lower survival proportions observed in younger patients, ...

To improve preclinical studies and their translation, patient-derived xenografts (PDXs) are increasingly used. They have human-specific tumor characteristics and reflect intra and inter-tumor heterogeneity. However, the endocrine milieu differs between hum ...

Data augmentation is vital in deep learning for enhancing model robustness by artificially expanding training datasets. However, advanced methods like CutMix blend images and assign labels based on pixel ratios, often introducing label noise by neglecting ...

Recent progress in computer vision has been driven by a simple yet transformative observation: the potential of 30-year-old neural networks can be unlocked by massively scaling their parameters and the amount of human-labeled training data. This breakthrou ...

This thesis focuses on understanding and improving the reasoning capabilities of neural networks. It develops theoretical results and empirical analyses to uncover reasoning potential and limitations, leveraging these insights to guide the design of improv ...

Introduction: Fat graft (FG) is widely used in breast reconstructive surgery (RS) following mastectomy or lumpectomy for breast cancer (BC); however, concerns persist about its oncological safety. This study evaluates the impact of FG reconstruction compar ...

Semi-supervised semantic segmentation methods leverage unlabeled data by pseudo-labeling them. Thus the success of these methods hinges on the reliability of the pseudo-labels. Existing methods mostly choose high-confidence pixels in an effort to avoid err ...

Training data mixtures greatly impact the generalization performance of large language models. Existing domain reweighting methods often rely on costly weight computations and require retraining when new data is introduced. To this end, we introduce a flex ...

Introduction: Cystic brain metastases (BMs) are often more challenging to treat than solid BMs. Stereotactic cyst aspiration for volume reduction followed by stereotactic radiosurgery (SRS) is an alternative treatment modality that may benefit patients wit ...

Proteins are the molecular machines of life, driving essential biological processes such as enzymatic catalysis, cellular signaling, and immune responses. The ability to design entirely new proteins with desired structures and functions has immense implica ...

Abstract IA02: Cancer-specific foundation models: Friend or foe in healthcare AI?

Chat with Graph Search

A comparative analysis of gene expression profiling by statistical and machine learning approaches

HPV16-Expressing Tumors Release Multiple IL-1 Ligands to Orchestrate Systemic Immunosuppression Whose Disruption Enables Efficacy of a Therapeutic Vaccine

Explaining the Relationships Between Age, Endocrine Therapy Persistence, and Risk of Recurrence in Hormone Receptor–Positive Early Breast Cancer: A Nationwide Cohort Study

Mimicking women’s endocrine milieu in mice for women’s health-related studies

SaliencyMix plus : Noise-Minimized Image Mixing Method With Saliency Map in Data Augmentation

Exploiting Representation Similarities in Self-Supervised Learning for Vision Tasks

Learning to Reason with Neural Networks: Principles and Methods

The impact of fat graft reconstructive surgery on prognosis in young women with breast cancer: a study from the French insurance databases

Weighting Pseudo-labels via High-Activation Feature Index Similarity and Object Detection for Semi-supervised Segmentation

CHAMELEON: A Flexible Data-mixing Framework for Language Model Pretraining and Finetuning

Stereotactic aspiration alone or Ommaya placement and aspiration followed by stereotactic radiosurgery for cystic brain metastasis: A systematic review and meta-analysis

Computational design of complex protein folds and soluble analogs of membrane proteins