Breast cancer Diagnosis by AI New Technology Research Papers

Breast Cancer Diagnosis by AI Deep Learning Model  Research Papers

You must read these papers if you are doing research in AI for Cancer Diagnosis

Breast cancer remains a significant focus in medical research Specifically the Diagnosis area focuses a lot because when we can diagnose early we can prevent it easily  Let me share with you some key points.


  • It is the leading cause of cancer-related mortality among women.
  • In India, breast cancer accounts for 28.2% of all female cancers, making it the most common cancer among women.
  • In 2022, 2.3 million women were diagnosed with breast cancer worldwide, resulting in 670,000 deaths.
  • Breast cancer can occur in women of any age after puberty, with higher incidence rates in older age groups.
  • Advances in breast cancer screening have enabled earlier diagnosis.
  • Early diagnosis significantly improves the likelihood of curing breast cancer.
  • Various treatments are available to extend life even when breast cancer is not curable.


I am Sharing with you some of the papers that are very  for your research in AI Models for Breast Cancer


Deep Learning Based Methods for Breast Cancer Diagnosis: A Systematic Review and Future Direction

  • This research presents a Systematic Literature Review (SLR) on deep learning-based breast cancer diagnosis methods involving genetic sequencing or histopathological imaging.
  • The SLR follows the PRISMA approach.
  • The review focuses on the applicability of various deep learning techniques for breast cancer detection.
  • After searching and screening for eligibility and quality, 95 articles were identified.
  • Convolutional Neural Network (CNN) is found to be the most accurate and widely used model for breast cancer detection.
  • Accuracy metrics are the most popular method for evaluating performance.
  • The review explores datasets used for breast cancer diagnosis and the performance of different algorithms.
  • Challenges and future research directions are discussed to provide deeper insights for researchers and practitioners.
  • The widespread use of CNN algorithms on MRI images and gene expression data is highlighted as a significant breakthrough.
  • Comparing CNN models with other algorithms often yields positive results.
  • Further research is suggested, especially in applying more hybrid algorithms with CNN. Read More

Total References : 134


Breast Cancer Detection and Prevention Using Machine Learning

Six different categorization models were applied for breast cancer diagnosis in this paper:

    • Random Forest (RF)
    • Decision Tree (DT)
    • k-Nearest Neighbors (KNN)
    • Logistic Regression (LR)
    • Support Vector Classifier (SVC)
    • Linear Support Vector Classifier (linear SVC)

Total References : 34                Read More


A Review Paper on Breast Cancer Detection Using Deep Learning

  • Machine learning generally yields better results on linear data.
  • Previous research indicates that machine learning techniques often fail when applied to image data.
  • To address this issue, deep learning, a recently developed and frequently used technique in data science, is employed.
  • For classifying breast cancer image data, the deep learning technique Convolutional Neural Network (CNN) is used.
  • CNN is particularly effective on image datasets.
  • Previous research also concludes that CNN provides better results compared to traditional machine learning techniques.


Total References : 42     Read More


Breast Cancer Detection Based on Simplified Deep Learning Technique With Histopathological Image Using BreaKHis Database


  • The research study aimed to evaluate the ability of deep learning (DL) models to extract discriminative features for breast cancer detection from histopathological images.
  • A series of experiments were conducted using recent and precise Convolutional Neural Network (CNN) models trained on the ImageNet dataset.
  • These models were fine-tuned and trained using the BreaKHis database.
  • Due to the lack of training images and the complexity of medical images, transfer learning was applied, proving to be an effective solution.
  • Experimental results demonstrated that the investigated models performed exceptionally well compared to traditional machine learning models for detecting breast cancer in histopathological images.
  • The study showed that different image resolutions yielded different results, with DL models struggling with low resolution and noisy images.
  • The work was conducted on 2D histopathological images, which have inherent limitations in the amount of information they can provide.

Total References : 45     Read More


Deep Learning to Improve Breast Cancer Detection on Screening Mammography

  • This study demonstrates that accurate classification of screening mammograms can be achieved with a deep learning model trained end-to-end, using clinical Region of Interest (ROI) annotations only in the initial stage.
  • Once the whole image classifier is built, it can be fine-tuned using additional datasets that lack ROI annotations, even if there are differences in pixel intensity distributions from heterogeneous mammography platforms.
  • The commercial Computer-Aided Detection (CAD) system used Convolutional Neural Networks (CNNs) trained with lesion annotations from 9,000 cancerous mammograms to generate patch-level scores, which were combined into an examination-level score.
  • The commercial CAD system cannot be easily fine-tuned on different mammography datasets without lesion annotations.
  • The approach presented in this study requires only image-level labels for fine-tuning after the whole image classifier is built, facilitating scaling to larger datasets and adaptation to new mammography systems.

Total References : 46     Read More


Development of an Artificial Intelligence-Based Breast Cancer Detection Model by Combining Mammograms and Medical Health Records

  • This paper proposed a combined deep learning and machine learning model to detect breast cancer, achieving significantly improved performance compared to using a single model.
  • The study demonstrated that integrating mammography images with clinical data is beneficial.
  • Four different deep learning classifiers were used to learn features directly from mammography images.
  • Multiple machine learning classifiers were employed using various clinical variables.
  • A combination model was created by integrating the best two models from the single classifiers, resulting in acceptable overall performance.
  • The study suggests that incorporating both image data and clinical data can further enhance the performance of ML-DL models.
  • The results are promising for developing new detection models that successfully apply medical imaging to estimate the probability of breast cancer.

Total References : 55    Read More


Breast Cancer Detection and Prediction using Image Processing and ML

  • This study compared Support Vector Machine (SVM) and Convolutional Neural Network (CNN) architectures for breast cancer detection using a dataset of 1,693 microscopic images of breast tumor tissue from 82 patients (547 benign, 1,147 malignant; 700 x 460 pixels, 3-channel RGB, 8-bit depth in each channel, PNG format).
  • The proposed system, employing Model 2 (CNN), achieved a 96% accuracy rate, compared to Model 1 (SVM) with a 93% accuracy rate.
  • The main goal is to aid healthcare professionals and oncologists in accurately diagnosing cancer early and reducing human errors in the diagnostic phase.
  • The future implication is the increased use of AI and ML for efficient diagnosis to minimize human errors and support early cancer detection and treatment.

Total References : 12   Read More



A Precise Detection of Breast Cancer Using Machine Learning Model

  • The machine learning models achieved high classification accuracy, showing promising results for early breast cancer detection, potentially leading to improved patient outcomes.
  • Specifically, the MLP (Multi-Layer Perceptron) algorithm performed exceptionally well, achieving an accuracy of 99%, indicating its value in assisting medical professionals with accurate diagnoses.
  • While this research has made significant strides, further validation on larger and more diverse datasets from multiple medical institutions is necessary to ensure the robustness and reliability of the proposed approach.
  • Exploring deep learning architectures, such as Convolutional Neural Networks (CNNs), for breast cancer detection from medical imaging is suggested. CNNs have shown impressive results in image recognition tasks and may provide more detailed insights into tumor characteristics.

Total References : 10   Read More


Breast Cancer Detection and Classification Empowered With Transfer Learning

  • This study examined the use of transfer learning, specifically the AlexNet architecture, for breast cancer classification and detection.
  • Deep learning and transfer learning approaches were tailored to the specific characteristics of each dataset.
  • The proposed model utilized a customized AlexNet technique on three datasets: A, B, C, and A2, where A2 is a modified version of dataset A with two classes.
  • The model, empowered with transfer learning, achieved the best results using the customized AlexNet architecture.
  • Dataset A attained a maximum accuracy of 99.4%, dataset B reached a maximum accuracy of 96.70%, dataset C achieved a maximum accuracy of 99.10%, and dataset A2 had a maximum accuracy of 100%.
  • Future work will involve applying fusion techniques on these datasets to optimize results. Additionally, other CNN algorithms and machine learning models will be explored and applied to these datasets.


Total References : 10   Read More




Note: We provide ease of access to accurate information in less time Instead of searching in Google we can help you to see what is in the research to save your time we ieearc  and the team are not the author of this publication .

Credit and Source: nature, NCBI, frontiers etc

No responses yet

Leave a Reply

Your email address will not be published. Required fields are marked *