▲
Email this article 
BRAIN. Broad Research in Artificial Intelligence and Neuroscience
Volume: 15 | Issue: 3 |
Classification of Breast Cancer Tumors from Histopathological Images through a Modified ResNet-50 Architecture
Published October 12, 2024
❝
Cite
Mihai Lucian Voncilă -
National University of Science and Technology Politehnica Bucharest (RO),
Nicolae Tarbă -
National University of Science and Technology Politehnica Bucharest (RO),
Ștefana Oblesniuc -
National University of Science and Technology Politehnica Bucharest (RO),
Costin Anton Boiangiu -
National University of Science and Technology Politehnica Bucharest (RO),
Valer Nimineț -
Vasile Alecsandri University of Bacau (RO),
Abstract
The diagnosis of malignant or benign breast cancer tumors from histopathological images is challenging due to human error, which may lead to the patient undergoing additional, often painful, procedures to collect new data. Utilizing a supervised, pre-trained ResNet-50 model as a second opinion for doctors can help eliminate the need for repeated procedures. One main challenge faced by doctors and machine learning models is image blurriness. Applying various data preprocessing and augmentation techniques, such as resizing, Gaussian blurring, histogram equalization, and color space conversions, can improve the model's performance. The model achieved its best results with an accuracy of 95.61%, precision of 96%, recall of 94%, and an F1-score of 95%.
Academic discipline and sub-disciplines:
Medicine; Deep Learning; Artificial Intelligence
DOI: http://dx.doi.org/10.70594/brain/15.3/15
Article Overview Video
Related articles:
-
Classification of Brain Tumor using Hybrid Deep Learning Approach
Manu SINGH , Vibhakar SHRIMALI (2 shared keywords) -
Clinical Assessment Methods for Early Autism Spectrum Disorder in Paediatrics Using Explainable Artificial Intelligence and Quantum Machine Learning
Priya Shanthini D.R , Vasu Koduri , Naveen Maddukuri , M Kalpana Chowdary , Bini Darwin , Shajin Prince (1 shared keywords) -
Application of ConvLSTM Neural Networks in Forest Fire Early Warning Systems for Vietnam
Pham Thi Lien , Nguyen Thu Huong , Nguyen The Long (1 shared keywords) -
The Relationship Between Cardiac Adipose Tissue and Anxiety in Bariatric Patients: Deep Learning Applications in Epicardial Adipose Tissue Analysis
Mihaela Toader , Ana Maria Buburuz , Madalina Maxim , Daniela Ivona Tomita , Bogdan Novac , Otilia Novac , Daniel Vasile Timofte (1 shared keywords) -
Retrospective Histopathological Aspects in the Recurrence of Bladder Tumours Following TUR-B: Insights into Progression and Regression Patterns, Computational Aspects and the Relevance of AI
Bogdan Novac , Alin Ciobica , Radu Zara , Ion Chiriac , Marcel Agachi , Otilia Novac (1 shared keywords) -
Pleomorphic Adenoma of the Parotid Gland – Histopathological, Neurological, Intraoperative and Machine Learning Insights
Cristian Niky Cumpătă , Cristina Maria Munteanu , Anca Mihaela Predescu , Ciprian Laurențiu Pătru , Alexandru Dan Popescu , Cătălina Alexandra Iacov , Cristina Jana Busuioc , Oprea Valentin Bușu , Elena Cristina Andrei , Eugen Georgescu , Marina Amărăscu , Ilona Mihaela Liliac (1 shared keywords) -
Robust Sentiment Analysis Through Bayesian Dropout-Enhanced RoBERTa-LSTM
Soufien Jaffali (1 shared keywords) -
Electroencephalography (EEG) - Based Neuromarketing: Predicting Favourable and Unfavourable Consumer Reactions Using ML Techniques
R. Sakthi Velammal , A. Leo , J. Macklin Abraham , C. Maria Fortuna , Vinoth Kumar (1 shared keywords) -
Unravelling the Power of Sentiment: How Emotions Shape Online Engagement in Public Health Discourse
Soufien Jaffali , Nesrine Khelifi (1 shared keywords) -
The Role of Artificial Intelligence in Bariatric Surgery: Perspectives and Modern Applications
Ancuta Andreea Miler , Mălina Visternicu , Viorica Rarinca , Carmen Stadoleanu , Alin Ciobica , Mădălina Maxim , Mihaela Toader , Daniel Vasile Timofte , Anton Knieling (1 shared keywords)