EUVIMEDEUVIMED entdecken
LeserbriefKommentarOpen Access

Letter to the Editor: Potential pitfalls in deep learning-based imaging for spontaneous intracerebral hemorrhage

Sachin D Balutkar, Sachin S Bhavthankar, Basavraj S Nagoba

World Journal of Radiology · 28.07.2026 · 18 (7)

DOI: 10.4329/wjr.120076 ↗

Kurz gefasst

Leserbrief in der Zeitschrift World Journal of Radiology, online erschienen am 28.07.2026. Verfasst von Sachin D Balutkar und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Maharashtra Institute of Medical Sciences and Research (Medical College), Latur 413512, Maharashtra, India. Die Arbeit nennt 16 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The study by Yang and Li in the World Journal of Radiology reports strong predictive performance for hematoma enlargement, perihematomal edema (PHE) and hospital mortality using hand crafted quantitative radiomics and deep learning models in patients with spontaneous intracerebral haemorrhage (ICH). While the authors report strong predictive performance using quantitative radiomics and deep learning features, several methodological concerns warrant discussion. By letting the deep learning models based on pretrained Convolutional Neural Network (CNN) to detect the density range of 50-400 Hounsfield units, may falsely detect age related and pathological basal ganglionic calcifications as heterogeneity within the ICH. This may lead to increased false positive rates in the prediction of hematoma enlargement. Similarly, by not restricting the density range between 25-35 Hounsfield units for pretrained CNN to detect PHE, may also add bias by falsely detecting age related micro ischaemic areas and chronic lacunar infarcts in basal ganglionic region as PHE. Further, hand crafted quantitative radiomics by trained clinical radiologists will calculate volume of ICH and PHE more accurately as compared to the CNN models using only three consecutive axial slices centered on the maximum haematomal cross-sectional area, as reported in the original study. Hence, an integrated model consisting of hand crafted quantitative radiomics by trained clinical radiologist with deep learning models based on pre trained CNN with the above-mentioned enhancements and a human touch by a trained clinical radiologist to remove the mentioned confounding factors is highly recommended for better outcomes.

Schlagwörter

Stichwörter der Autor:innen

Basal ganglionic calcificationsConvolutional nurolon networksDeep learningHaematoma enlargementIntra-cerebral haematomaPeri haematomal oedema

Autor:innen und Institutionen

  • Department of Radiology, Maharashtra Institute of Medical Sciences and Research (Medical College), Latur 413512, Maharashtra, India.
  • Department of Biochemistry, Maharashtra Institute of Medical Sciences and Research, Latur 413512, Maharashtra, India.
  • Department of Microbiology, Maharashtra Institute of Medical Sciences and Research (Medical College), Latur 413531, Maharashtra, India. basavraj.nagoba@mimsr.edu.in.

Zitieren

APA

Balutkar, S. D., Bhavthankar, S. S., & Nagoba, B. S. (2026). Letter to the Editor: Potential pitfalls in deep learning-based imaging for spontaneous intracerebral hemorrhage. World Journal of Radiology, 18(7). https://doi.org/10.4329/wjr.120076

Vancouver

Balutkar SD, Bhavthankar SS, Nagoba BS. Letter to the Editor: Potential pitfalls in deep learning-based imaging for spontaneous intracerebral hemorrhage. World Journal of Radiology. 2026;18(7). doi:10.4329/wjr.120076

BibTeX
@article{Balutkar2026,
  author = {Balutkar, Sachin D and Bhavthankar, Sachin S and Nagoba, Basavraj S},
  title = {Letter to the Editor: Potential pitfalls in deep learning-based imaging for spontaneous intracerebral hemorrhage},
  journal = {World Journal of Radiology},
  year = {2026},
  volume = {18},
  number = {7},
  doi = {10.4329/wjr.120076}
}
Kostenlos starten →