A visual-language foundation model for computational pathology

Nature Medicine, Journal Year: 2024, Volume and Issue: 30(3), P. 863 - 874

Published: March 1, 2024

Language: Английский

---

A Survey of Large Language Models for Healthcare: From Data, Technology, and Applications to Accountability and Ethics

Published: Jan. 1, 2024

Language: Английский

---

ChatCAD+: Toward a Universal and Reliable Interactive CAD Using LLMs

IEEE Transactions on Medical Imaging, Journal Year: 2024, Volume and Issue: 43(11), P. 3755 - 3766

Published: May 8, 2024

The integration of Computer-Aided Diagnosis (CAD) with Large Language Models (LLMs) presents a promising frontier in clinical applications, notably automating diagnostic processes akin to those performed by radiologists and providing consultations similar virtual family doctor. Despite the potential this integration, current works face at least two limitations: (1) From perspective radiologist, existing studies typically have restricted scope applicable imaging domains, failing meet needs different patients. Also, insufficient capability LLMs further undermine quality reliability generated medical reports. (2) Current lack requisite depth expertise, rendering them less effective as doctors due unreliability advice provided during patient consultations. To address these limitations, we introduce ChatCAD+, be universal reliable. Specifically, it is featured main modules: Reliable Report Generation Interaction. module capable interpreting images from diverse domains generate high-quality reports via our proposed hierarchical in-context learning. Concurrently, interaction leverages up-to-date information reputable websites provide reliable advice. Together, designed modules synergize closely align expertise human professionals, offering enhanced consistency for interpretation source code available GitHub.

Language: Английский

---

PathAsst: A Generative Foundation AI Assistant towards Artificial General Intelligence of Pathology

Proceedings of the AAAI Conference on Artificial Intelligence, Journal Year: 2024, Volume and Issue: 38(5), P. 5034 - 5042

Published: March 24, 2024

As advances in large language models (LLMs) and multimodal techniques continue to mature, the development of general-purpose (MLLMs) has surged, offering significant applications interpreting natural images. However, field pathology largely remained untapped, particularly gathering high-quality data designing comprehensive model frameworks. To bridge gap MLLMs, we present PathAsst, a generative foundation AI assistant revolutionize diagnostic predictive analytics pathology. The PathAsst involves three pivotal steps: acquisition, CLIP adaptation, training PathAsst's capabilities. Firstly, collect over 207K image-text pairs from authoritative sources. Leveraging advanced power ChatGPT, generate 180K instruction-following samples. Furthermore, devise additional specifically tailored for invoking eight pathology-specific sub-models prepared, allowing effectively collaborate with these models, enhancing its ability. Secondly, by leveraging collected data, construct PathCLIP, pathology-dedicated CLIP, enhance capabilities Finally, integrate PathCLIP Vicuna-13b utilize instruction-tuning generation capacity bolster synergistic interactions sub-models. experimental results show potential harnessing AI-powered improve diagnosis treatment processes. We open-source our dataset, as well toolkit extensive collection preprocessing at https://github.com/superjamessyx/Generative-Foundation-AI-Assistant-for-Pathology.

Language: Английский

---

A survey of large language models for healthcare: from data, technology, and applications to accountability and ethics

Information Fusion, Journal Year: 2025, Volume and Issue: unknown, P. 102963 - 102963

Published: Jan. 1, 2025

Language: Английский

---

Large language models illuminate a progressive pathway to artificial intelligent healthcare assistant

Medicine Plus, Journal Year: 2024, Volume and Issue: 1(2), P. 100030 - 100030

Published: May 17, 2024

With the rapid development of artificial intelligence, large language models (LLMs) have shown promising capabilities in mimicking human-level comprehension and reasoning. This has sparked significant interest applying LLMs to enhance various aspects healthcare, ranging from medical education clinical decision support. However, medicine involves multifaceted data modalities nuanced reasoning skills, presenting challenges for integrating LLMs. review introduces fundamental applications general-purpose specialized LLMs, demonstrating their utilities knowledge retrieval, research support, workflow automation, diagnostic assistance. Recognizing inherent multimodality medicine, emphasizes multimodal discusses ability process diverse types like imaging electronic health records augment accuracy. To address LLMs' limitations regarding personalization complex reasoning, further explores emerging LLM-powered autonomous agents healthcare. Moreover, it summarizes evaluation methodologies assessing reliability safety contexts. transformative potential medicine; however, there is a pivotal need continuous optimizations ethical oversight before these can be effectively integrated into practice.

Language: Английский

---

ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset

Scientific Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: June 26, 2024

Language: Английский

---

Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports

Meta-Radiology, Journal Year: 2024, Volume and Issue: unknown, P. 100103 - 100103

Published: Sept. 1, 2024

Language: Английский

---

Exploring scalable medical image encoders beyond text supervision

Nature Machine Intelligence, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 13, 2025

Language: Английский

---

Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets

Scientific Data, Journal Year: 2025, Volume and Issue: 12(1)

Published: Feb. 1, 2025

Language: Английский

---