Loading Now

Summary of Lce: a Framework For Explainability Of Dnns For Ultrasound Image Based on Concept Discovery, by Weiji Kong et al.


LCE: A Framework for Explainability of DNNs for Ultrasound Image Based on Concept Discovery

by Weiji Kong, Xun Gong, Juan Wang

First submitted to arxiv on: 19 Aug 2024

Categories

  • Main: Artificial Intelligence (cs.AI)
  • Secondary: Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
The proposed Lesion Concept Explainer (LCE) framework combines attribution and concept-based methods to explain the decisions of Deep Neural Networks (DNNs) for medical images. The framework utilizes the Segment Anything Model (SAM), fine-tuned on a large number of medical images, for concept discovery. This enables meaningful explanations of ultrasound image DNNs. The LCE is evaluated in terms of faithfulness and understandability, with a new evaluation metric proposed to address deficiencies in existing metrics. The framework is tested on public and private breast ultrasound datasets (BUSI and FG-US-B), outperforming commonly-used explainability methods. Additionally, the LCE provides reliable explanations for fine-grained diagnostic tasks in breast ultrasound.
Low GrooveSquid.com (original content) Low Difficulty Summary
This paper helps doctors understand how deep learning models make decisions about medical images. Right now, it’s hard to know why a model is saying something is normal or abnormal. The researchers created a new way to explain this called Lesion Concept Explainer (LCE). They used a big dataset of medical images and trained their method on it. This lets doctors see what features the model is using to make its decisions. The paper shows that LCE works well compared to other methods and can even help with making more accurate diagnoses.

Keywords

» Artificial intelligence  » Deep learning  » Sam