RAD-PHI2: Instruction Tuning PHI-2 for Radiology

• URL: http://arxiv.org/abs/2403.09725v1
• Date: Tue, 12 Mar 2024 17:27:22 GMT
• Title: RAD-PHI2: Instruction Tuning PHI-2 for Radiology
• Authors: Mercy Ranjit, Gopinath Ganapathy, Shaury Srivastav, Tanuja Ganu, Srujana Oruganti,
• Abstract summary: Small Language Models (SLMs) have shown remarkable performance in general domain language understanding, reasoning and coding tasks. This study investigates the application of SLMs for general radiology knowledge specifically question answering related to understanding of symptoms. By fine-tuning Phi-2 on both general domain tasks and radiology-specific tasks related to chest X-ray reports, we create Rad-Phi2.
• Score: 2.774342358600601
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Small Language Models (SLMs) have shown remarkable performance in general domain language understanding, reasoning and coding tasks, but their capabilities in the medical domain, particularly concerning radiology text, is less explored. In this study, we investigate the application of SLMs for general radiology knowledge specifically question answering related to understanding of symptoms, radiological appearances of findings, differential diagnosis, assessing prognosis, and suggesting treatments w.r.t diseases pertaining to different organ systems. Additionally, we explore the utility of SLMs in handling text-related tasks with respect to radiology reports within AI-driven radiology workflows. We fine-tune Phi-2, a SLM with 2.7 billion parameters using high-quality educational content from Radiopaedia, a collaborative online radiology resource. The resulting language model, RadPhi-2-Base, exhibits the ability to address general radiology queries across various systems (e.g., chest, cardiac). Furthermore, we investigate Phi-2 for instruction tuning, enabling it to perform specific tasks. By fine-tuning Phi-2 on both general domain tasks and radiology-specific tasks related to chest X-ray reports, we create Rad-Phi2. Our empirical results reveal that Rad-Phi2 Base and Rad-Phi2 perform comparably or even outperform larger models such as Mistral-7B-Instruct-v0.2 and GPT-4 providing concise and precise answers. In summary, our work demonstrates the feasibility and effectiveness of utilizing SLMs in radiology workflows both for knowledge related queries as well as for performing specific tasks related to radiology reports thereby opening up new avenues for enhancing the quality and efficiency of radiology practice.

Related papers

• RadPhi-3: Small Language Models for Radiology [3.2515490312812623]
  In this work, we present RadPhi-3, a Small Language Model instruction tuned from Phi-3-mini-4k-instruct with 3.8B parameters to assist with various tasks in radiology. While impression summary generation has been the primary task which has been explored in prior works, we also explore other useful tasks like summary generation comparing the current radiology report and its prior report, section extraction from radiology reports, tagging the reports with various pathologies and tubes, lines or devices present in them etc.
  arXiv  Detail & Related papers  (2024-11-19T11:24:28Z)
• Summarizing Radiology Reports Findings into Impressions [1.8964110318127383]
  We present a model with state-of-art radiology report summarization performance. We also provide an analysis of the model limitations and radiology knowledge gain. Our best performing model was a fine-tuned BERT-to-BERT encoder-decoder with 58.75/100 ROUGE-L F1.
  arXiv  Detail & Related papers  (2024-05-10T20:29:25Z)
• ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data [115.0747462486285]
  ChatRadio-Valuer is a tailored model for automatic radiology report generation that learns generalizable representations. The clinical dataset utilized in this study encompasses a remarkable total of textbf332,673 observations. ChatRadio-Valuer consistently outperforms state-of-the-art models, especially ChatGPT (GPT-3.5-Turbo) and GPT-4 et al.
  arXiv  Detail & Related papers  (2023-10-08T17:23:17Z)
• RadOnc-GPT: A Large Language Model for Radiation Oncology [42.92077650252404]
  RadOnc-GPT was finetuned on a large dataset of radiation oncology patient records from the Mayo Clinic in Arizona. The model employs instruction tuning on three key tasks - generating radiotherapy treatment regimens, determining optimal radiation modalities, and providing diagnostic descriptions/ICD codes.
  arXiv  Detail & Related papers  (2023-09-18T21:15:02Z)
• Radiology-Llama2: Best-in-Class Large Language Model for Radiology [71.27700230067168]
  This paper introduces Radiology-Llama2, a large language model specialized for radiology through a process known as instruction tuning. Quantitative evaluations using ROUGE metrics on the MIMIC-CXR and OpenI datasets demonstrate that Radiology-Llama2 achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-08-29T17:44:28Z)
• Radiology-GPT: A Large Language Model for Radiology [74.07944784968372]
  We introduce Radiology-GPT, a large language model for radiology. It demonstrates superior performance compared to general language models such as StableLM, Dolly and LLaMA. It exhibits significant versatility in radiological diagnosis, research, and communication.
  arXiv  Detail & Related papers  (2023-06-14T17:57:24Z)
• Act Like a Radiologist: Radiology Report Generation across Anatomical Regions [50.13206214694885]
  X-RGen is a radiologist-minded report generation framework across six anatomical regions. In X-RGen, we seek to mimic the behaviour of human radiologists, breaking them down into four principal phases. We enhance the recognition capacity of the image encoder by analysing images and reports across various regions.
  arXiv  Detail & Related papers  (2023-05-26T07:12:35Z)
• Medical Image Captioning via Generative Pretrained Transformers [57.308920993032274]
  We combine two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The proposed model is tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO.
  arXiv  Detail & Related papers  (2022-09-28T10:27:10Z)
• Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation [55.00308939833555]
  The PPKED includes three modules: Posterior Knowledge Explorer (PoKE), Prior Knowledge Explorer (PrKE) and Multi-domain Knowledge Distiller (MKD) PoKE explores the posterior knowledge, which provides explicit abnormal visual regions to alleviate visual data bias. PrKE explores the prior knowledge from the prior medical knowledge graph (medical knowledge) and prior radiology reports (working experience) to alleviate textual data bias.
  arXiv  Detail & Related papers  (2021-06-13T11:10:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.