Volume-awareness and outlier-suppression co-training for weakly-supervised MRI breast mass segmentation with partial annotations

Meng, Xianqi; Fan, Jingfan; Yu, Hongwei; Mu, Jinrong; Li, Zongyu; Yang, Aocai; Liu, Bing; Lv, Kuan; Ai, Danni; Lin, Yucong; Song, Hong; Fu, Tianyu; Xiao, Deqiang; Ma, Guolin; Yang, Jian; Gu, Ying

doi:10.1016/j.knosys.2022.109988

Cited by 7 publications

(3 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maicas et al [55] combined globally optimal inference in a continuous space with deep learning. Other efforts in this direction can be found in the works of Meng et al [56] and Parekh et al [4].…”

Section: Key Gaps and Current Challenges A Well-annotated Big Datamentioning

confidence: 99%

“…Breast MRIs may significantly vary in shape, size, position, image appearance due to diverse imaging protocols, and patient characteristics, such as breast morphology, race, ethnicity, and disease features [56]. Consequently, there is a demand for robust deep learning models trained on large diverse datasets to handle such variabilities.…”

Section: B Inter/intra Variationsmentioning

confidence: 99%

See 1 more Smart Citation

Breast MRI Segmentation by Deep Learning: Key Gaps and Challenges

Askaripour,

Zak

2023

IEEE Access

View full text Add to dashboard Cite

Breast MRI segmentation plays a vital role in early diagnosis and treatment planning of breast anomalies. Convolutional neural networks with deep learning have indicated promise in automating this process, but significant gaps and challenges remain to address. This PubMed-based review provides a comprehensive literature overview of the latest deep learning models used for breast segmentation. The article categorizes the literature on deep learning based on input modalities, use of labeled/unlabeled data during training, and different architectures. Additionally, it describes more complex frameworks structured using hierarchical, ensemble, or fused learning. Then, MRI processing approaches, key aspects of convolutional neural networks, and key gaps and challenges are focused. The need for large breast MRI datasets with accurate annotations and the generalization of the proposed structures to diverse and comprehensive datasets are among the gaps. INDEX TERMS Breast cancer, computer-aided diagnosis, CNNs, MRI processing, review.

show abstract

Section: Key Gaps and Current Challenges A Well-annotated Big Datamentioning

confidence: 99%

Section: B Inter/intra Variationsmentioning

confidence: 99%

Breast MRI Segmentation by Deep Learning: Key Gaps and Challenges

Askaripour,

Zak

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…However, researchers in both academia and the healthcare industry are faced with the significant challenge of automated medical image processing [5]. Due to the complex contrast in lung nodule images and the patient-specific nature of lung nodules that may lead to differences in lesion characteristics (size, texture, location, shadows, etc), the direct processing of raw CT scan images using only deep learning techniques does not do a good job, and these issues are presents a formidable challenge for radiologists [6]. Within traditional approaches to lung nodule segmentation, the nodule boundary region is the major point that distinguishes the nodule from the surrounding background pixels.…”

Section: Introductionmentioning

confidence: 99%

BiCFormer: Swin Transformer based model for classification of benign and malignant pulmonary nodules

Zhao,

Xu,

Lin

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Pulmonary cancer is one of the most common and deadliest cancers worldwide, and the detection of benign and malignant nodules in the lungs can be an important aid in the early diagnosis of lung cancer. Existing convolutional neural networks (CNNs) inherit their limitations by extracting global contextual information, and in most cases prove to be less efficient in obtaining satisfactory results. Transformer-based deep learning methods have obtained good performance in different computer vision tasks, and this study attempts to introduce them into the task of CT image classification of lung nodules. However, the problems of sample scarcity and difficulty of local feature extraction in this field. To this end, we are inspired by Swin Transformer to propose a model named BiCFormer for the task of classifying and diagnosing CT scan images of lung nodules. Specifically, first we introduce a Multi-layer Discriminator GAN (MDG) module for data augmentation to assist the model in extracting features more accurately. Second, unlike the encoder of traditional Transformer, we divide the encoder part of BiCFormer into two parts: Bi-level Coordinate (BiC) and Fast-partial-window (FPW).The BiC module has a part similar to the traditional channel attention mechanism is able to enhance the performance of the model, and is more able to enhance the representation of attention object features by aggregating features along two spatial directions. The BiC module also has a dynamic sparse attention mechanism that filters out irrelevant key-value pairs in rough regions, allowing the model to focus more on features of interest.The FPW module is mainly used to reduce computational redundancy and minimize feature loss. We conducted extensive experiments on the LIDC-IDRI dataset. The experimental results show that our model achieves an accuracy of 97.4% compared to other studies using this dataset for lung nodule classification, making it an effective and competitive method.

show abstract

SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI

Zhong,

Wang

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Volume-awareness and outlier-suppression co-training for weakly-supervised MRI breast mass segmentation with partial annotations

Cited by 7 publications

References 43 publications

Breast MRI Segmentation by Deep Learning: Key Gaps and Challenges

Breast MRI Segmentation by Deep Learning: Key Gaps and Challenges

BiCFormer: Swin Transformer based model for classification of benign and malignant pulmonary nodules

SimPLe: Similarity-Aware Propagation Learning for Weakly-Supervised Breast Cancer Segmentation in DCE-MRI

Contact Info

Product

Resources

About