Medical Imaging Technology
Online ISSN : 2185-3193
Print ISSN : 0288-450X
ISSN-L : 0288-450X
Current issue
Showing 1-8 articles out of 8 articles from the selected issue
Main Topics / Towards Explainable Artificial Intelligence
  • Hironobu FUJIYOSHI, Masahiro ODA
    2021 Volume 39 Issue 3 Pages 97-98
    Published: May 25, 2021
    Released: June 26, 2021
    JOURNALS RESTRICTED ACCESS
    Download PDF (686K)
  • Satoshi HARA
    2021 Volume 39 Issue 3 Pages 99-104
    Published: May 25, 2021
    Released: June 26, 2021
    JOURNALS RESTRICTED ACCESS

    The innovations of highly accurate machine learning models (such as deep neural networks) boosted their use in society. However, the structures of such high-end models are highly complex and it is difficult to understand their inference processes nor decision criteria. In this paper, I introduce some popular approaches for explaining the decisions of complex machine learning models.

    Download PDF (1212K)
  • Kazuki UEHARA, Hidenori SAKANASHI
    2021 Volume 39 Issue 3 Pages 105-109
    Published: May 25, 2021
    Released: June 26, 2021
    JOURNALS RESTRICTED ACCESS

    With the recent advance of deep learning technology, research of artificial intelligence (AI) applications for the medical domain has been growing. However, a lack of interpretability (or explainability) of the basis of AI decisions is a major problem for practical use of AI. Since physicians are responsible for the diagnosis, it is desirable to be able to confirm the reliability of the decisions made by AI. We developed an XAI technique to realize an AI platform, which allows co-evolve both humans and AI via interaction between them and applied it to pathological image analysis.

    Download PDF (3818K)
  • Hironobu FUJIYOSHI, Takayoshi YAMASHITA, Tsubasa HIRAKAWA
    2021 Volume 39 Issue 3 Pages 110-116
    Published: May 25, 2021
    Released: June 26, 2021
    JOURNALS RESTRICTED ACCESS

    In the field of image recognition, deep learning has achieved high recognition performance. However, it is difficult for people to interpret the network for the decisions. Visual explanations can visualize the regions that the network gazed at during the inference by using attention maps. By visualizing the attention map, we can understand the basis of the AIʼs decision. The attention map used for visual explanation can be applied to the inference process using the attention mechanism to improve the recognition performance. Furthermore, the attention map can be manually adjusted and trained to introduce human knowledge into the network. This paper presents a brief survey of a visual explanation of deep learning and our research on visualization of the attention map by the attention mechanism.

    Download PDF (5109K)
  • Hirokatsu KATAOKA, Ryosuke YAMADA, Asato MATSUMOTO
    2021 Volume 39 Issue 3 Pages 117-123
    Published: May 25, 2021
    Released: June 26, 2021
    JOURNALS RESTRICTED ACCESS

    The paper introduces a framework for Formula-Driven Supervised Learning (FDSL) which automatically generates image patterns and their image labels for creating a large-scale image dataset. We mainly focus on Fractal DataBase (FractalDB) which consists of fractal geometry existing around our real world. That is, one of the important natural principle enables to train convolutional neural networks without any natural images taken by a camera and human-annotated labels in a pre-training phase.

    Download PDF (1425K)
Tutorial
Activity of JAMIT
Editors’ Note
feedback
Top