Experts' cognition-driven safe noisy labels learning for precise
segmentation of residual tumor in breast cancer
- URL: http://arxiv.org/abs/2304.07295v1
- Date: Thu, 13 Apr 2023 03:46:40 GMT
- Title: Experts' cognition-driven safe noisy labels learning for precise
segmentation of residual tumor in breast cancer
- Authors: Yongquan Yang, Jie Chen, Yani Wei, Mohammad Alobaidi and Hong Bu
- Abstract summary: We propose an experts' cognition-driven safe noisy labels learning (ECDSNLL) approach.
ECDSNLL is constructed by integrating the experts' cognition about identifying residual tumor in breast cancer and the artificial intelligence experts' cognition about data modeling.
We show the advantages of the proposed ECDSNLL approach and its promising potentials in addressing PSRTBC.
- Score: 5.445090025094291
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Precise segmentation of residual tumor in breast cancer (PSRTBC) after
neoadjuvant chemotherapy is a fundamental key technique in the treatment
process of breast cancer. However, achieving PSRTBC is still a challenge, since
the breast cancer tissue and tumor cells commonly have complex and varied
morphological changes after neoadjuvant chemotherapy, which inevitably
increases the difficulty to produce a predictive model that has good
generalization with machine learning. To alleviate this situation, in this
paper, we propose an experts' cognition-driven safe noisy labels learning
(ECDSNLL) approach. In the concept of safe noisy labels learning, which is a
typical type of safe weakly supervised learning, ECDSNLL is constructed by
integrating the pathology experts' cognition about identifying residual tumor
in breast cancer and the artificial intelligence experts' cognition about data
modeling with provided data basis. We show the advantages of the proposed
ECDSNLL approach and its promising potentials in addressing PSRTBC. We also
release a better predictive model for achieving PSRTBC, which can be leveraged
to promote the development of related application software.
Related papers
- MAST-Pro: Dynamic Mixture-of-Experts for Adaptive Segmentation of Pan-Tumors with Knowledge-Driven Prompts [54.915060471994686]
We propose MAST-Pro, a novel framework that integrates dynamic Mixture-of-Experts (D-MoE) and knowledge-driven prompts for pan-tumor segmentation.
Specifically, text and anatomical prompts provide domain-specific priors guiding tumor representation learning, while D-MoE dynamically selects experts to balance generic and tumor-specific feature learning.
Experiments on multi-anatomical tumor datasets demonstrate that MAST-Pro outperforms state-of-the-art approaches, achieving up to a 5.20% improvement in average improvement while reducing trainable parameters by 91.04%, without compromising accuracy.
arXiv Detail & Related papers (2025-03-18T15:39:44Z) - Multimodal AI-driven Biomarker for Early Detection of Cancer Cachexia [14.27396467108753]
Cancer cachexia is a multifactorial syndrome characterized by progressive muscle wasting, metabolic dysfunction, and systemic inflammation.
There is no single definitive biomarker for cachexia.
This study proposes a multimodal AI-based biomarker for early cancer cachexia detection.
arXiv Detail & Related papers (2025-03-09T22:32:37Z) - A Holistic Weakly Supervised Approach for Liver Tumor Segmentation with Clinical Knowledge-Informed Label Smoothing [17.798774864007505]
Liver cancer is a leading cause of mortality worldwide.
Deep learning has shown promise for automated liver segmentation.
We present a novel holistic weakly supervised framework to address these challenges.
arXiv Detail & Related papers (2024-10-13T20:52:25Z) - Radiomics-guided Multimodal Self-attention Network for Predicting Pathological Complete Response in Breast MRI [3.6852491526879687]
This study presents a model that predicts pCR in breast cancer patients using dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) and apparent diffusion coefficient (ADC) maps.
Our approach extracts features from both DCE MRI and ADC using an encoder with a self-attention mechanism, leveraging radiomics to guide feature extraction from tumor-related regions.
arXiv Detail & Related papers (2024-06-05T04:49:55Z) - Using Multiparametric MRI with Optimized Synthetic Correlated Diffusion Imaging to Enhance Breast Cancer Pathologic Complete Response Prediction [71.91773485443125]
Neoadjuvant chemotherapy has recently gained popularity as a promising treatment strategy for breast cancer.
The current process to recommend neoadjuvant chemotherapy relies on the subjective evaluation of medical experts.
This research investigates the application of optimized CDI$s$ to enhance breast cancer pathologic complete response prediction.
arXiv Detail & Related papers (2024-05-13T15:40:56Z) - BreastRegNet: A Deep Learning Framework for Registration of Breast
Faxitron and Histopathology Images [0.05454343470301196]
This study introduces a deep learning-based image registration approach trained on mono-modal synthetic image pairs.
The models were trained using data from 50 women who received neoadjuvant chemotherapy and underwent surgery.
arXiv Detail & Related papers (2024-01-18T08:23:29Z) - Intelligent Breast Cancer Diagnosis with Heuristic-assisted
Trans-Res-U-Net and Multiscale DenseNet using Mammogram Images [0.0]
Breast cancer (BC) significantly contributes to cancer-related mortality in women.
accurately distinguishing malignant mass lesions remains challenging.
We propose a novel deep learning approach for BC screening utilizing mammography images.
arXiv Detail & Related papers (2023-10-30T10:22:14Z) - Post-Hoc Explainability of BI-RADS Descriptors in a Multi-task Framework
for Breast Cancer Detection and Segmentation [48.08423125835335]
MT-BI-RADS is a novel explainable deep learning approach for tumor detection in Breast Ultrasound (BUS) images.
It offers three levels of explanations to enable radiologists to comprehend the decision-making process in predicting tumor malignancy.
arXiv Detail & Related papers (2023-08-27T22:07:42Z) - Cancer-Net BCa-S: Breast Cancer Grade Prediction using Volumetric Deep
Radiomic Features from Synthetic Correlated Diffusion Imaging [82.74877848011798]
The prevalence of breast cancer continues to grow, affecting about 300,000 females in the United States in 2023.
The gold-standard Scarff-Bloom-Richardson (SBR) grade has been shown to consistently indicate a patient's response to chemotherapy.
In this paper, we study the efficacy of deep learning for breast cancer grading based on synthetic correlated diffusion (CDI$s$) imaging.
arXiv Detail & Related papers (2023-04-12T15:08:34Z) - A Multi-Institutional Open-Source Benchmark Dataset for Breast Cancer
Clinical Decision Support using Synthetic Correlated Diffusion Imaging Data [82.74877848011798]
Cancer-Net BCa is a multi-institutional open-source benchmark dataset of volumetric CDI$s$ imaging data of breast cancer patients.
Cancer-Net BCa is publicly available as a part of a global open-source initiative dedicated to accelerating advancement in machine learning to aid clinicians in the fight against cancer.
arXiv Detail & Related papers (2023-04-12T05:41:44Z) - Pre-screening breast cancer with machine learning and deep learning [0.0]
Deep learning can be used for pre-screening cancer by analyzing demographic and anthropometric information of patients.
Deep learning model with an input-layer architecture that is fine-tuned using feature selection can effectively distinguish between patients with and without cancer.
These findings suggest that deep learning algorithms applied to cancer pre-screening offer a radiation-free, non-invasive, and affordable complement to screening methods based on imagery.
arXiv Detail & Related papers (2023-02-05T15:27:50Z) - Enhancing Clinical Support for Breast Cancer with Deep Learning Models
using Synthetic Correlated Diffusion Imaging [66.63200823918429]
We investigate enhancing clinical support for breast cancer with deep learning models.
We leverage a volumetric convolutional neural network to learn deep radiomic features from a pre-treatment cohort.
We find that the proposed approach can achieve better performance for both grade and post-treatment response prediction.
arXiv Detail & Related papers (2022-11-10T03:02:12Z) - Exploiting segmentation labels and representation learning to forecast
therapy response of PDAC patients [60.78505216352878]
We propose a hybrid deep neural network pipeline to predict tumour response to initial chemotherapy.
We leverage a combination of representation transfer from segmentation to classification, as well as localisation and representation learning.
Our approach yields a remarkably data-efficient method able to predict treatment response with a ROC-AUC of 63.7% using only 477 datasets in total.
arXiv Detail & Related papers (2022-11-08T11:50:31Z) - Improved Pancreatic Tumor Detection by Utilizing Clinically-Relevant
Secondary Features [6.132193527180974]
Pancreatic cancer is one of the global leading causes of cancer-related deaths.
We propose a method for detecting pancreatic tumor that utilizes clinically-relevant features in the surrounding anatomical structures.
arXiv Detail & Related papers (2022-08-06T20:38:25Z) - Open-Set Recognition of Breast Cancer Treatments [91.3247063132127]
Open-set recognition generalizes a classification task by classifying test samples as one of the known classes from training or "unknown"
We apply a recent existing Gaussian mixture variational autoencoder model, which achieves state-of-the-art results for image datasets, to breast cancer patient data.
Not only do we obtain more accurate and robust classification results, with a 24.5% average F1 increase compared to a recent method, but we also reexamine open-set recognition in terms of deployability to a clinical setting.
arXiv Detail & Related papers (2022-01-09T04:35:55Z) - Stan: Small tumor-aware network for breast ultrasound image segmentation [68.8204255655161]
We propose a novel deep learning architecture called Small Tumor-Aware Network (STAN) to improve the performance of segmenting tumors with different size.
The proposed approach outperformed the state-of-the-art approaches in segmenting small breast tumors.
arXiv Detail & Related papers (2020-02-03T22:25:01Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.