MDCC-Net: Multiscale double-channel convolution U-Net framework for colorectal tumor segmentation

Zheng, Suichang; Lin, Xue; Zhang, Weifeng; He, Baochun; Jia, Shuangfu; Wang, Ping; Jiang, Huijie; Shi, Jingjing; Jia, Fucang

doi:10.1016/j.compbiomed.2020.104183

Cited by 26 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…U-Net is extensively used in image analysis tasks and shows promising results. − However, at each downsampling step, U-Net usually suffers from a high-dimensional feature loss. Although skip connections are added, the features before the connections are not screened.…”

Section: Methodsmentioning

confidence: 99%

Pixel-Level Classification of Five Histologic Patterns of Lung Adenocarcinoma

Shao

Xue-yu

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

Lung adenocarcinoma is the most common histologic type of lung cancer. The pixel-level labeling of histologic patterns of lung adenocarcinoma can assist pathologists in determining tumor grading with more details than normal classification. We manually annotated a dataset containing a total of 1000 patches (200 patches for each pattern) of 512 × 512 pixels and 420 patches (contains test sets) of 1024 × 1024 pixels according to the morphological features of the five histologic patterns of lung adenocarcinoma (lepidic, acinar, papillary, micropapillary, and solid). To generate an even large amount of data patches, we developed a data stitching strategy as a data augmentation for classification in model training. Stitched patches improve the Dice similarity coefficient (DSC) scores by 24.06% on the whole-slide image (WSI) with the solid pattern. We propose a WSI analysis framework for lung adenocarcinoma pathology, intelligently labeling lung adenocarcinoma histologic patterns at the pixel level. Our framework contains five branches of deep neural networks for segmenting each histologic pattern. We test our framework with 200 unclassified patches. The DSC scores of our results outpace comparing networks (U-Net, LinkNet, and FPN) by up to 10.78%. We also perform results on four WSIs with an overall accuracy of 99.6%, demonstrating that our network framework exhibits better accuracy and robustness in most cases.

show abstract

Section: Methodsmentioning

confidence: 99%

Pixel-Level Classification of Five Histologic Patterns of Lung Adenocarcinoma

Shao

Xue-yu

et al. 2023

Anal. Chem.

View full text Add to dashboard Cite

show abstract

“…The ResNet50 team separately constructed a ResNet50 building block with "Shortcut Connection" and a down-sampling ResNet50 building block. A 1×1 convolution operation is added to the main branch of the regional down-sampling building block [31].…”

Section: Deep Learning Methodsmentioning

confidence: 99%

EBHI:A New Enteroscope Biopsy Histopathological H&E Image Dataset for Image Classification Evaluation

Hu¹,

Li²,

Li³

et al. 2022

Preprint

View full text Add to dashboard Cite

Background and purpose: Colorectal cancer has become the third most common cancer worldwide, accounting for approximately 10% of cancer patients. Early detection of the disease is important for the treatment of colorectal cancer patients. Histopathological examination is the gold standard for screening colorectal cancer. However, the current lack of histopathological image datasets of colorectal cancer, especially enteroscope biopsies, hinders the accurate evaluation of computer-aided diagnosis techniques. Methods: A new publicly available Enteroscope Biopsy Histopathological H&E Image Dataset (EBHI) is published in this paper. To demonstrate the effectiveness of the EBHI dataset, we have utilized several machine learning, convolutional neural networks and novel transformer-based classifiers for experimentation and evaluation, using an image with a magnification of 200×. Results: Experimental results show that the deep learning method performs well on the EBHI dataset. Traditional machine learning methods achieve maximum accuracy of 76.02% and deep learning method achieves a maximum accuracy of 95.37%. Conclusion: To the best of our knowledge, EBHI is the first publicly available colorectal histopathology enteroscope biopsy dataset with four magnifications and five types of images of tumor differentiation stages, totaling 5532 images. We believe that EBHI could attract researchers to explore new classification algorithms for the automated diagnosis of colorectal cancer, which could help physicians and patients in clinical settings.

show abstract

“…Therefore, sufficient information may not be learned. To overcome these two problems, they proposed a multi-scale dual-channel evolutionary U-Net model [14].…”

Section: Related Workmentioning

confidence: 99%

Kidney Tumor Segmentation Using Two-Stage Bottleneck Block Architecture

Turk¹,

Lüy²,

Barışçı³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Cases of kidney cancer have shown a rapid increase in recent years. Advanced technology has allowed bettering the existing treatment methods. Research on the subject is still continuing. Medical segmentation is also of increasing importance. In particular, deep learning-based studies are of great importance for accurate segmentation. Tumor detection is a relatively difficult procedure for soft tissue organs such as kidneys and the prostate. Kidney tumors, specifically, are a type of cancer with a higher incidence in older people. As age progresses, the importance of having diagnostic tests increases. In some cases, patients with kidney tumors may not show any serious symptoms until the last stage. Therefore, early diagnosis of the tumor is important. This study aimed to develop support systems that could help physicians in the segmentation of kidney tumors. In the study, improvements were made on the encoder and decoder phases of the V-Net model. With the double-stage bottleneck block structure, the architecture was transformed into a unique one, which achieved an 86.9% kidney tumor Dice similarity coefficient. The results show that the model gives applicable and accurate results for kidney tumor segmentation.

show abstract

MDCC-Net: Multiscale double-channel convolution U-Net framework for colorectal tumor segmentation

Cited by 26 publications

References 21 publications

Pixel-Level Classification of Five Histologic Patterns of Lung Adenocarcinoma

Pixel-Level Classification of Five Histologic Patterns of Lung Adenocarcinoma

EBHI:A New Enteroscope Biopsy Histopathological H&E Image Dataset for Image Classification Evaluation

Kidney Tumor Segmentation Using Two-Stage Bottleneck Block Architecture

Contact Info

Product

Resources

About