Breast Cancer Lesion Detection and Segmentation Based On Mask R-CNN

Soltani, Hama; Amroune, Mohamed; Bendib, Issam; Haouam, Mohamed Yassine

doi:10.1109/icrami52622.2021.9585913

Cited by 11 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The model is compiled using the Adam optimizer as in equation ( 4) and binary cross-entropy loss function as in equation (5).…”

Section: Optimization Techniques Employedmentioning

confidence: 99%

See 1 more Smart Citation

Transformative Breast Cancer Diagnosis using CNNs with Optimized ReduceLROnPlateau and Early Stopping Enhancements

Thakur,

Gupta

et al. 2024

Int J Comput Intell Syst

View full text Add to dashboard Cite

Breast cancer stands as a paramount public health concern worldwide, underscoring an imperative necessity within the research sphere for precision-driven and efficacious methodologies facilitating accurate detection. The existing diagnostic approaches in breast cancer often suffer from limitations in accuracy and efficiency, leading to delayed detection and subsequent challenges in personalized treatment planning. The primary focus of this research is to overcome these shortcomings by harnessing the power of advanced deep learning techniques, thereby revolutionizing the precision and reliability of breast cancer classification. This research addresses the critical need for improved breast cancer diagnostics by introducing a novel Convolutional Neural Network (CNN) model integrated with an Early Stopping callback and ReduceLROnPlateau callback. By enhancing the precision and reliability of breast cancer classification, the study aims to overcome the limitations of existing diagnostic methods, ultimately leading to better patient outcomes and reduced mortality rates. The comprehensive methodology includes diverse datasets, meticulous image preprocessing, robust model training, and validation strategies, emphasizing the model's adaptability and reliability in varied clinical contexts. The findings showcase the CNN model's exceptional performance, achieving a 95.2% accuracy rate in distinguishing cancerous and non-cancerous breast tissue in the integrated dataset, thereby demonstrating its potential for enhancing clinical decision-making and fostering the development of AI-driven diagnostic solutions.

show abstract

“…The model is compiled using the Adam optimizer as in equation ( 4) and binary cross-entropy loss function as in equation (5).…”

Section: Optimization Techniques Employedmentioning

confidence: 99%

“…With an emphasis on advanced Convolutional Neural Networks (CNNs), a deep learning technique that leverages the potential of computational biology, this research study focuses on the realm of breast cancer diagnosis [5].…”

Section: Introductionmentioning

confidence: 99%

Transformative Breast Cancer Diagnosis using CNNs with Optimized ReduceLROnPlateau and Early Stopping Enhancements

Thakur,

Gupta

et al. 2024

Int J Comput Intell Syst

View full text Add to dashboard Cite

show abstract

“…Among the abnormality types, masses are reportedly major contributors to breast cancer [16]. Therefore, in this paper, we aim to address the identification of masses that generally has two forms: mass detection [17][18][19][20] and mass segmentation [21][22][23][24][25]. Mass segmentation provides more comprehensive information, including border information; hence, in this paper, the main task is mass segmentation.…”

Section: Introductionmentioning

confidence: 99%

Improved Loss Function for Mass Segmentation in Mammography Images Using Density and Mass Size

Aliniya,

Nicolescu,

Nicolescu

et al. 2024

J. Imaging

View full text Add to dashboard Cite

Mass segmentation is one of the fundamental tasks used when identifying breast cancer due to the comprehensive information it provides, including the location, size, and border of the masses. Despite significant improvement in the performance of the task, certain properties of the data, such as pixel class imbalance and the diverse appearance and sizes of masses, remain challenging. Recently, there has been a surge in articles proposing to address pixel class imbalance through the formulation of the loss function. While demonstrating an enhancement in performance, they mostly fail to address the problem comprehensively. In this paper, we propose a new perspective on the calculation of the loss that enables the binary segmentation loss to incorporate the sample-level information and region-level losses in a hybrid loss setting. We propose two variations of the loss to include mass size and density in the loss calculation. Also, we introduce a single loss variant using the idea of utilizing mass size and density to enhance focal loss. We tested the proposed method on benchmark datasets: CBIS-DDSM and INbreast. Our approach outperformed the baseline and state-of-the-art methods on both datasets.

show abstract

Application of Faster-RCNN with Detectron2 for Effective Breast Tumor Detection in Mammography

Soltani,

Amroune,

Bendib

et al. 2024

13th International Conference on Information Systems and Advanced Technologies “ICISAT 2023”

View full text Add to dashboard Cite

Breast Cancer Lesion Detection and Segmentation Based On Mask R-CNN

Cited by 11 publications

References 20 publications

Transformative Breast Cancer Diagnosis using CNNs with Optimized ReduceLROnPlateau and Early Stopping Enhancements

Transformative Breast Cancer Diagnosis using CNNs with Optimized ReduceLROnPlateau and Early Stopping Enhancements

Improved Loss Function for Mass Segmentation in Mammography Images Using Density and Mass Size

Application of Faster-RCNN with Detectron2 for Effective Breast Tumor Detection in Mammography

Contact Info

Product

Resources

About