Conference abstract · 12 Jun 2023
Conference abstractPublished 16 Aug 2023
Updated loss function for accurate tumor segmentation from breast MRIs
Guangzhou University, China
Abstract
Select any words in the title or abstract, or press this and choose a sentence.
We present Focal Boundary Dice, a new segmentation evaluation measure focused on boundary quality and class imbalance. We perform an extensive analysis across different error types and object sizes of imaged tumors from MRI scan and show that Focal Boundary Dice is significantly more sensitive than the standard Focal and Dice measures to boundary errors for imaged tumors from MRI scans and does not over-penalize errors on division of the boundary, including smaller imaged objects. The new quality measure displays several desirable characteristics, like higher accuracy in the selection of hard samples, prediction/ground truth pairs, and balanced responsiveness across scales, which makes it more suitable for segmentation evaluation than other classification focused measures such as combined IoU and BCE loss, Boundary BCE loss and Shape-aware Loss. Methods: Based on Boundary Dice, we update the standard evaluation protocols for tumor segmentation tasks by proposing the Focal Boundary Dice. We mainly solve the contradiction between target and background area and the contradiction between the importance and attention of boundary features. Meanwhile, a boundary attention module is introduced to further extract tumor edge features. Results: Our experiments show that the new evaluation metrics allow boundary quality improvements and image segmentation accuracy that are generally overlooked by current Mask Dice based evaluation metrics and deep learning models. The adoption of the new boundary-sensitive evaluation metrics leads to rapid progress in segmentation methods that enables the improvement of boundary quality. The optimal configuration of focal boundary dice loss is performed for the resultant segments of imaged tumors as shown in [Figure 1]. This focal boundary dice loss enables the construction of the deep learning network for good segmentation performance in all tested MRIs. The quantification results are listed in [Table 1]. Conclusion: The proposed deep learning model enables to achieve efficient discrimination between healthy and diseased tissues, and paves the way for the automatic diagnosis of breast cancer.
Subjects
Oncology & CancerAsk about this article
Answers come only from this article's title, abstract and keywords, each sentence pointing to where it comes from. Your question is sent to OpenAI to write the answer. Scholars Central does not store it.
Similar by topic
Conference abstract · 24 Aug 2022
MRI radiogenomics for intelligent diagnosis of breast tumors and accurate prediction of neoadjuvant chemotherapy responses
Research article · 29 Sep 2023
Classification and Segmentation of Breast Tumor Using Mask R-CNN on Mammograms
Research article · 2017
Multi-Scale Blood Vessel Detection and Segmentation in Breast MRIs
Short communication · 2021
Loss-Of-Function Mutationin the RB Tumor Suppressor
More from this journal
The newest in Breast Cancer: Current Research.
Editorial · 30 Nov 2024
Genetic Testing Unraveling the Future of Personalized Medicine and Disease Prevention
Editorial · 30 Nov 2024
Reconstructive Surgery Advancements Techniques and Impact on Patient Quality of Life
Editorial · 30 Nov 2024
Immunotherapy A Revolution in Cancer Treatment and Beyond
Conferences in this field
Upcoming conferences in this field.
Follow
New articles from what you follow go into your email digest, once you agree to alert emails.
- JournalBreast Cancer: Current Research
- SubjectOncology & Cancer
- BylineArticles whose byline prints “Xiao-Xia Yin”
