---
_id: '12816'
abstract:
- lang: eng
  text: Medical images need annotations with high-level semantic descriptors, so that
    domain experts can search for the desired dataset among an enormous volume of
    visual media within a Medical Data Integration Center. This article introduces
    a processing pipeline for storing and annotating DICOM and PNG imaging data by
    applying Elasticsearch, S3 and Deep Learning technologies. The proposed method
    processes both DICOM and PNG images to generate annotations. These image annotations
    are indexed in Elasticsearch with the corresponding raw data paths, where they
    can be retrieved and analyzed.
author:
- first_name: Ka Yung
  full_name: Cheng, Ka Yung
  last_name: Cheng
- first_name: Santiago
  full_name: Pazmino, Santiago
  last_name: Pazmino
- first_name: Bjoern
  full_name: Bergh, Bjoern
  last_name: Bergh
- first_name: Markus
  full_name: Lange-Hegermann, Markus
  id: '71761'
  last_name: Lange-Hegermann
- first_name: Bjorn
  full_name: Schreiweis, Bjorn
  last_name: Schreiweis
citation:
  ama: Cheng KY, Pazmino S, Bergh B, Lange-Hegermann M, Schreiweis B. <i>An Image
    Retrieval Pipeline in a Medical Data Integration Center.</i> Vol 310. IOS Press,
    Incorporated; 2024:1388-1389. doi:<a href="https://doi.org/10.3233/SHTI231208">10.3233/SHTI231208</a>
  apa: Cheng, K. Y., Pazmino, S., Bergh, B., Lange-Hegermann, M., &#38; Schreiweis,
    B. (2024). An Image Retrieval Pipeline in a Medical Data Integration Center. In
    <i>19th World Congress on Medical and Health Informatics (MEDINFO)</i> (Vol. 310,
    pp. 1388–1389). IOS Press, Incorporated. <a href="https://doi.org/10.3233/SHTI231208">https://doi.org/10.3233/SHTI231208</a>
  bjps: <b>Cheng KY <i>et al.</i></b> (2024) <i>An Image Retrieval Pipeline in a Medical
    Data Integration Center.</i> IOS Press, Incorporated.
  chicago: Cheng, Ka Yung, Santiago Pazmino, Bjoern Bergh, Markus Lange-Hegermann,
    and Bjorn Schreiweis. <i>An Image Retrieval Pipeline in a Medical Data Integration
    Center.</i> <i>19th World Congress on Medical and Health Informatics (MEDINFO)</i>.
    Vol. 310. Studies in Health Technology and Informatics. IOS Press, Incorporated,
    2024. <a href="https://doi.org/10.3233/SHTI231208">https://doi.org/10.3233/SHTI231208</a>.
  chicago-de: Cheng, Ka Yung, Santiago Pazmino, Bjoern Bergh, Markus Lange-Hegermann
    und Bjorn Schreiweis. 2024. <i>An Image Retrieval Pipeline in a Medical Data Integration
    Center.</i> <i>19th World Congress on Medical and Health Informatics (MEDINFO)</i>.
    Bd. 310. Studies in Health Technology and Informatics. IOS Press, Incorporated.
    doi:<a href="https://doi.org/10.3233/SHTI231208">10.3233/SHTI231208</a>, .
  din1505-2-1: '<span style="font-variant:small-caps;">Cheng, Ka Yung</span> ; <span
    style="font-variant:small-caps;">Pazmino, Santiago</span> ; <span style="font-variant:small-caps;">Bergh,
    Bjoern</span> ; <span style="font-variant:small-caps;">Lange-Hegermann, Markus</span>
    ; <span style="font-variant:small-caps;">Schreiweis, Bjorn</span>: <i>An Image
    Retrieval Pipeline in a Medical Data Integration Center.</i>, <i>Studies in Health
    Technology and Informatics</i>. Bd. 310 : IOS Press, Incorporated, 2024'
  havard: K.Y. Cheng, S. Pazmino, B. Bergh, M. Lange-Hegermann, B. Schreiweis, An
    Image Retrieval Pipeline in a Medical Data Integration Center., IOS Press, Incorporated,
    2024.
  ieee: 'K. Y. Cheng, S. Pazmino, B. Bergh, M. Lange-Hegermann, and B. Schreiweis,
    <i>An Image Retrieval Pipeline in a Medical Data Integration Center.</i>, vol.
    310. IOS Press, Incorporated, 2024, pp. 1388–1389. doi: <a href="https://doi.org/10.3233/SHTI231208">10.3233/SHTI231208</a>.'
  mla: Cheng, Ka Yung, et al. “An Image Retrieval Pipeline in a Medical Data Integration
    Center.” <i>19th World Congress on Medical and Health Informatics (MEDINFO)</i>,
    vol. 310, IOS Press, Incorporated, 2024, pp. 1388–89, <a href="https://doi.org/10.3233/SHTI231208">https://doi.org/10.3233/SHTI231208</a>.
  short: K.Y. Cheng, S. Pazmino, B. Bergh, M. Lange-Hegermann, B. Schreiweis, An Image
    Retrieval Pipeline in a Medical Data Integration Center., IOS Press, Incorporated,
    2024.
  ufg: '<b>Cheng, Ka Yung u. a.</b>: An Image Retrieval Pipeline in a Medical Data
    Integration Center., Bd. 310, o. O. 2024 (Studies in Health Technology and Informatics).'
  van: Cheng KY, Pazmino S, Bergh B, Lange-Hegermann M, Schreiweis B. An Image Retrieval
    Pipeline in a Medical Data Integration Center. 19th World Congress on Medical
    and Health Informatics (MEDINFO). IOS Press, Incorporated; 2024. (Studies in Health
    Technology and Informatics; vol. 310).
conference:
  end_date: 2023-08-12
  location: Sydney, AUSTRALIA
  name: 19th World Congress on Medical and Health Informatics (MEDINFO)
  start_date: 2023-08-08
date_created: 2025-04-17T08:25:27Z
date_updated: 2025-06-25T13:05:17Z
department:
- _id: DEP5023
doi: 10.3233/SHTI231208
external_id:
  pmid:
  - '38269660'
intvolume: '       310'
keyword:
- Medical image retrieval
- data lake
- DICOM
- deep learning
- elasticsearch
language:
- iso: eng
page: 1388-1389
pmid: '1'
publication: 19th World Congress on Medical and Health Informatics (MEDINFO)
publication_identifier:
  eisbn:
  - 978-1-64368-457-4
  eissn:
  - 1879-8365
  isbn:
  - 978-1-64368-456-7
  issn:
  - 0926-9630
publication_status: published
publisher: IOS Press, Incorporated
series_title: Studies in Health Technology and Informatics
status: public
title: An Image Retrieval Pipeline in a Medical Data Integration Center.
type: conference_speech
user_id: '83781'
volume: 310
year: '2024'
...
---
_id: '12822'
abstract:
- lang: eng
  text: A medical data integration center integrates a large volume of medical images
    from clinical departments, including X-rays, CT scans, and MRI scans. Ideally,
    all images should be indexed appropriately with standard clinical terms. However,
    some images have incorrect or missing annotations, which creates challenges in
    searching and integrating data centrally. To address this issue, accurate and
    meaningful descriptors are needed for indexing fields, enabling users to efficiently
    search for desired images and integrate them with international standards. This
    paper aims to provide concise annotation for missing or incorrectly indexed fields,
    incorporating essential instance -level information such as radiology modalities
    (e.g., X-rays), anatomical regions (e.g., chest), and body orientations (e.g.,
    lateral) using a Deep Learning classification model - ResNet50. To demonstrate
    the capabilities of our algorithm in generating annotations for indexing fields,
    we conducted three experiments using two opensource datasets, the ROCO dataset,
    and the IRMA dataset, along with a custom dataset featuring SNOMED CT labels.
    While the outcomes of these experiments are satisfactory (Precision of >75%) for
    less critical tasks and serve as a valuable testing ground for image retrieval,
    they also underscore the need for further exploration of potential challenges.
    This essay elaborates on the identified issues and presents well-founded recommendations
    for refining and advancing our proposed approach.
author:
- first_name: Ka Yung
  full_name: Cheng, Ka Yung
  last_name: Cheng
- first_name: Markus
  full_name: Lange-Hegermann, Markus
  id: '71761'
  last_name: Lange-Hegermann
- first_name: Jan-Bernd
  full_name: Hövener, Jan-Bernd
  last_name: Hövener
- first_name: Björn
  full_name: Schreiweis, Björn
  last_name: Schreiweis
citation:
  ama: Cheng KY, Lange-Hegermann M, Hövener JB, Schreiweis B. Instance-level medical
    image classification for text-based retrieval in a medical data integration center.
    <i>Computational and Structural Biotechnology Journal</i>. 2024;24:434-450. doi:<a
    href="https://doi.org/10.1016/j.csbj.2024.06.006">10.1016/j.csbj.2024.06.006</a>
  apa: Cheng, K. Y., Lange-Hegermann, M., Hövener, J.-B., &#38; Schreiweis, B. (2024).
    Instance-level medical image classification for text-based retrieval in a medical
    data integration center. <i>Computational and Structural Biotechnology Journal</i>,
    <i>24</i>, 434–450. <a href="https://doi.org/10.1016/j.csbj.2024.06.006">https://doi.org/10.1016/j.csbj.2024.06.006</a>
  bjps: <b>Cheng KY <i>et al.</i></b> (2024) Instance-Level Medical Image Classification
    for Text-Based Retrieval in a Medical Data Integration Center. <i>Computational
    and Structural Biotechnology Journal</i> <b>24</b>, 434–450.
  chicago: 'Cheng, Ka Yung, Markus Lange-Hegermann, Jan-Bernd Hövener, and Björn Schreiweis.
    “Instance-Level Medical Image Classification for Text-Based Retrieval in a Medical
    Data Integration Center.” <i>Computational and Structural Biotechnology Journal</i>
    24 (2024): 434–50. <a href="https://doi.org/10.1016/j.csbj.2024.06.006">https://doi.org/10.1016/j.csbj.2024.06.006</a>.'
  chicago-de: 'Cheng, Ka Yung, Markus Lange-Hegermann, Jan-Bernd Hövener und Björn
    Schreiweis. 2024. Instance-level medical image classification for text-based retrieval
    in a medical data integration center. <i>Computational and Structural Biotechnology
    Journal</i> 24: 434–450. doi:<a href="https://doi.org/10.1016/j.csbj.2024.06.006">10.1016/j.csbj.2024.06.006</a>,
    .'
  din1505-2-1: '<span style="font-variant:small-caps;">Cheng, Ka Yung</span> ; <span
    style="font-variant:small-caps;">Lange-Hegermann, Markus</span> ; <span style="font-variant:small-caps;">Hövener,
    Jan-Bernd</span> ; <span style="font-variant:small-caps;">Schreiweis, Björn</span>:
    Instance-level medical image classification for text-based retrieval in a medical
    data integration center. In: <i>Computational and Structural Biotechnology Journal</i>
    Bd. 24. Amsterdam [u.a.], Elsevier BV (2024), S. 434–450'
  havard: K.Y. Cheng, M. Lange-Hegermann, J.-B. Hövener, B. Schreiweis, Instance-level
    medical image classification for text-based retrieval in a medical data integration
    center, Computational and Structural Biotechnology Journal. 24 (2024) 434–450.
  ieee: 'K. Y. Cheng, M. Lange-Hegermann, J.-B. Hövener, and B. Schreiweis, “Instance-level
    medical image classification for text-based retrieval in a medical data integration
    center,” <i>Computational and Structural Biotechnology Journal</i>, vol. 24, pp.
    434–450, 2024, doi: <a href="https://doi.org/10.1016/j.csbj.2024.06.006">10.1016/j.csbj.2024.06.006</a>.'
  mla: Cheng, Ka Yung, et al. “Instance-Level Medical Image Classification for Text-Based
    Retrieval in a Medical Data Integration Center.” <i>Computational and Structural
    Biotechnology Journal</i>, vol. 24, 2024, pp. 434–50, <a href="https://doi.org/10.1016/j.csbj.2024.06.006">https://doi.org/10.1016/j.csbj.2024.06.006</a>.
  short: K.Y. Cheng, M. Lange-Hegermann, J.-B. Hövener, B. Schreiweis, Computational
    and Structural Biotechnology Journal 24 (2024) 434–450.
  ufg: '<b>Cheng, Ka Yung u. a.</b>: Instance-level medical image classification for
    text-based retrieval in a medical data integration center, in: <i>Computational
    and Structural Biotechnology Journal</i> 24 (2024),  S. 434–450.'
  van: Cheng KY, Lange-Hegermann M, Hövener JB, Schreiweis B. Instance-level medical
    image classification for text-based retrieval in a medical data integration center.
    Computational and Structural Biotechnology Journal. 2024;24:434–50.
date_created: 2025-04-22T13:32:38Z
date_updated: 2025-06-26T08:58:59Z
department:
- _id: DEP5023
doi: 10.1016/j.csbj.2024.06.006
external_id:
  isi:
  - '001257361300001'
  pmid:
  - '38975287'
intvolume: '        24'
isi: '1'
keyword:
- DICOM images
- Medical image captioning
- Medical image interchange
- SNOMED CT body structure
language:
- iso: eng
page: 434-450
place: Amsterdam [u.a.]
pmid: '1'
publication: Computational and Structural Biotechnology Journal
publication_identifier:
  issn:
  - 2001-0370
publication_status: published
publisher: Elsevier BV
status: public
title: Instance-level medical image classification for text-based retrieval in a medical
  data integration center
type: scientific_journal_article
user_id: '83781'
volume: 24
year: '2024'
...