EUVIMEDEUVIMED entdecken
Vergleichsstudie

Comparative Evaluation of Transfer Learning Models for Detecting Malignant Cells in Urinary Cytology

Pranab Dey iD, Chandrasekaran Muralidaran

Cytopathology · 2026-05 · 37 (3) · 232-239

DOI: 10.1111/cyt.70061 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Cytopathology, online erschienen am 23.02.2026. Verfasst von Pranab Dey und 1 weiteren Autor:innen. Beteiligte Einrichtung: Oncopathology, Homi Bhabha Cancer Hospital and Research Centre (Tata Memorial Center), New Chandigarh, India. Hauptthemen laut MEDLINE: Cytodiagnosis, Urinary Bladder Neoplasms, Urine. Die Arbeit nennt 19 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Aims and Objectives In the present paper, we compared the efficiency of six transfer learning models to detect malignant cells in urine cytology. We also applied an ensemble learning with weighted soft voting to assess its importance in the diagnostic accuracy in urine cytology. Materials and Methods The voided urine samples of total 104 cases of urothelial cell carcinoma (UCC) and 86 cases with no malignancy (benign) were selected. All the 104 cases of UCC were histopathology proven high grade urothelial cell carcinoma (UCC). Urine with negative cytology reports were followed up clinically. There were 446 images of benign samples and 1369 images from malignant samples on 100 x objective. We applied six transfer learning models (DenseNet121, inception_v3, ResNet50, MobileNetV2, VGG16 and Xception) to detect malignant cells in urine. To compare the performance of different models, dynamic training optimization was done and each model was auto stopped after their maximum performance. In addition, an ensemble learning with soft voting was used including the top three models to enhance the diagnostic accuracy.

Result

Xception transfer model showed the highest sensitivity ( 88.57 %), accuracy ( 86.55 %), precision (80.52%) and FI score (84.35%). It was the best performing model. The other two top performing models were InceptionV3 and ResNet50. The area under curve of receiver operating characteristic (AUCROC) was ≤ 90 in all the transfer learning models. The accuracy, sensitivity, specificity, precision, F1‐Score and AUCROC of the ensemble transfer learning model were as follows: 92.10%, 95.41%, 85.51%, 91.23%, 93.24% and 0.977 respectively.

Conclusions

First time, we evaluated a large number of transfer learning models in urine cytology to detect malignant cells. All the models showed high sensitivity, specificity and accuracy. In addition, the ensemble learning technique with soft voting showed remarkable superior performance than individual top three transfer learning models. The techniques transfer learning and ensemble models have high potential to use in routine screening of urine.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CytodiagnosisUrinary Bladder NeoplasmsUrineHumansTransfer Machine LearningFemaleMaleConvolutional Neural NetworksSensitivity and SpecificityUrotheliumROC Curve

Stichwörter der Autor:innen

convolutional neural networkcytologydeep learningtransfer learningurine

Autor:innen und Institutionen

  • Oncopathology, Homi Bhabha Cancer Hospital and Research Centre (Tata Memorial Center), New Chandigarh, India.
  • Department of Pathology, Postgraduate Institute of Medical Education and Research, Chandigarh, India.

ORCID-Profile: Pranab Dey

Zitieren

APA

Dey, P., & Muralidaran, C. (2026). Comparative Evaluation of Transfer Learning Models for Detecting Malignant Cells in Urinary Cytology. Cytopathology, 37(3), 232-239. https://doi.org/10.1111/cyt.70061

Vancouver

Dey P, Muralidaran C. Comparative Evaluation of Transfer Learning Models for Detecting Malignant Cells in Urinary Cytology. Cytopathology. 2026;37(3):232-239. doi:10.1111/cyt.70061

BibTeX
@article{Dey2026,
  author = {Dey, Pranab and Muralidaran, Chandrasekaran},
  title = {Comparative Evaluation of Transfer Learning Models for Detecting Malignant Cells in Urinary Cytology},
  journal = {Cytopathology},
  year = {2026},
  volume = {37},
  number = {3},
  pages = {232--239},
  doi = {10.1111/cyt.70061}
}
Kostenlos starten →