EUVIMEDEUVIMED entdecken
Crossref

CNN1D-LSTM with SMOTE for breast cancer classification: performance and statistical insights

Kamini G Panchbhai, Lalchand B Patle, Madhusudan G Lanjewar

Physical and Engineering Sciences in Medicine · 2026-06 · 49 (2) · 747-758

DOI: 10.1007/s13246-026-01724-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Physical and Engineering Sciences in Medicine, online erschienen am 24.03.2026. Verfasst von Kamini G Panchbhai und 2 weiteren Autor:innen. Beteiligte Einrichtung: Goa College of Pharmacy, Panaji, Goa, 403001, India. Hauptthemen laut MEDLINE: Breast Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer is a significant global health issue, demanding early identification to provide appropriate therapy and satisfactory survival results. This work used two independent imbalanced datasets (EIS-BT and WBCD). CNN1D with Long Short-Term Memory (LSTM) was integrated to acquire features from these datasets to identify breast cancer. Three scenarios for breast cancer detection were investigated based on CNN1D-LSTM derived characteristics from Dataset-1, Dataset-2, and their combination. The Synthetic Minority Over-sampling Technique (SMOTE) was used to balance the collected features in all three scenarios. The suggested CNN1D-LSTM-SMOTE approach, in conjunction with Support Vector Classification (SVC), yields impressive results with a Matthews Correlation Coefficient (MCC) of 97.2 % on Dataset-1 and 100.0% on Dataset-2. Random Forest Classifiers (RFC) perform better, achieving an MCC of 98.4% on the combined features. The K-fold approach was used, yielding average MCCs of 91.7%, 74.1%, and 96.9% on Dataset-1, Dataset-2, and the combined features, respectively. Statistical analysis revealed a p-value of 0.01, signifying the significance of the findings, and a standard error of 0.006 for the combined features. Bootstrapping was employed to calculate confidence intervals, resulting in Lower Confidence Intervals (LCI) of 95.6% and Higher Confidence Intervals (HCI) of 97.9% for the combined features. These findings highlight the model's potential clinical application in supporting oncologists with early, real-time, reliable, and automated breast cancer diagnosis, leading to improved diagnostic procedures and patient outcomes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsHumansFemaleClassification AlgorithmsLong Short Term MemoryConvolutional Neural NetworksRandom ForestSupport Vector Machine

Stichwörter der Autor:innen

BenignBreast cancerBreast tissueCNN1DLSTMMalignantSMOTE

Autor:innen und Institutionen

  • Goa College of Pharmacy, Panaji, Goa, 403001, India.
  • Department of Electronics, MGSM's DDSGP College Chopda, KBCNMU Jalgaon, Jalgaon, 425107, India. lbpatle@mgsmasc.ac.in.
  • School of Physical and Applied Sciences, Goa University, Taleigao Plateau, Goa, 403206, India. madhusudan@unigoa.ac.in.

Zitieren

APA

Panchbhai, K. G., Patle, L. B., & Lanjewar, M. G. (2026). CNN1D-LSTM with SMOTE for breast cancer classification: performance and statistical insights. Physical and Engineering Sciences in Medicine, 49(2), 747-758. https://doi.org/10.1007/s13246-026-01724-4

Vancouver

Panchbhai KG, Patle LB, Lanjewar MG. CNN1D-LSTM with SMOTE for breast cancer classification: performance and statistical insights. Physical and Engineering Sciences in Medicine. 2026;49(2):747-758. doi:10.1007/s13246-026-01724-4

BibTeX
@article{Panchbhai2026,
  author = {Panchbhai, Kamini G and Patle, Lalchand B and Lanjewar, Madhusudan G},
  title = {CNN1D-LSTM with SMOTE for breast cancer classification: performance and statistical insights},
  journal = {Physical and Engineering Sciences in Medicine},
  year = {2026},
  volume = {49},
  number = {2},
  pages = {747--758},
  doi = {10.1007/s13246-026-01724-4}
}
Kostenlos starten →