Pathological Image Classification Based on Hard Example Guided CNN

Wang, Ying; Peng, Ting; Duan, Jiajia; Zhu, Chuang; Liu, Jun; Ye, Jiandong; Jin, Mulan

doi:10.1109/access.2020.3003070

Cited by 13 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The CNN's immersive design enables the extraction of a collection of distinct characteristics at multiple levels of abstraction without the need for operator intervention [28]. The CNN approach directly relates to the picture used to create the relationship mapping feature [29].…”

Section: Proposed Methodsmentioning

confidence: 99%

DeepSkin: Robust Skin Cancer Classification Using Convolutional Neural Network Algorithm

2022

ijicom

View full text Add to dashboard Cite

Classification of skin cancer is a growing research topic with significant challenges in the image processing. Learning algorithms for classifying a kind of skin cancer have been presented in recent articles to accelerate the diagnosis process with a rapid and accurate diagnosis. However, effective detection of skin cancer requires extensive graphical data. Inspired by deep learning successful results in computer vision, A Convolutional Neural Network (CNN) is proposed in this study to build a skin cancer classification model. We conduct this experiment by collecting massive skin cancer datasets, conducting pre-processing, training models, and evaluating the performance. Based on the experiment result, the benign and malignant classification model can obtain a good accuracy with a slight loss. Therefore, the results obtained reached an accuracy of 54%.

show abstract

Section: Proposed Methodsmentioning

confidence: 99%

DeepSkin: Robust Skin Cancer Classification Using Convolutional Neural Network Algorithm

2022

ijicom

View full text Add to dashboard Cite

show abstract

“…Talo [49] demonstrated that pre-trained ResNet [43] and DenseNet [42] to achieve better accuracy than traditional methods in the literature for classifying grayscale and color histopathological images. Similarly, Wang et al [50] proposed a DCNN-based method based on GoogleNet [44] to locate tumors in breast and colon images using complex example-guided training for WSI analysis. Among other DCNN works, Meng et al [29] compared several architectures for classification and segmentation problems on a cervical histopathology dataset.…”

Section: Deep Learning For Computational Pathologymentioning

confidence: 99%

Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offs

Kanwal,

Khoraminia,

Kiraz

et al. 2024

Preprint

View full text Add to dashboard Cite

Background: Histopathology is a gold standard for cancer diagnosis. It involves extracting tissue specimens from suspicious areas to prepare a glass slide for a microscopic examination. However, histological tissue processing procedures result in the introduction of artifacts, which are ultimately transferred to the digitized version of glass slides, known as whole slide images (WSIs). Artifacts are diagnostically irrelevant areas and may result in wrong predictions from deep learning (DL) algorithms. Therefore, detecting and excluding artifacts in the computational pathology (CPATH) system is essential for reliable automated diagnosis. Methods: In this paper, we propose a mixture of experts (MoE) scheme for detecting five notable artifacts, including damaged tissue, blur, folded tissue, air bubbles, and histologically irrelevant blood from WSIs. First, we train independent binary DL models as experts to capture particular artifact morphology. Then, we ensemble their predictions using a fusion mechanism. We apply probabilistic thresholding over the final probability distribution to improve the sensitivity of the MoE. We developed four DL pipelines to evaluate computational and performance trade-offs. These include two MoEs and two multiclass models of state-of-the-art deep convolutional neural networks (DCNNs) and vision transformers (ViTs). These DL pipelines are quantitatively and qualitatively evaluated on external and out-of-distribution (OoD) data to assess generalizability and robustness for artifact detection application. Results: We extensively evaluated the proposed MoE and multiclass models. DCNNs-based MoE and ViTs-based MoE schemes outperformed simpler multiclass models and were tested on datasets from different hospitals and cancer types, where MoE using (MobiletNet) DCNNs yielded the best results. The proposed MoE yields 86.15% F1 and 97.93% sensitivity scores on unseen data, retaining less computational cost for inference than MoE using ViTs. This best performance of MoEs comes with relatively higher computational trade-offs than multiclass models. Furthermore, we apply post-processing to create an artifact segmentation mask, a potential artifact-free RoI map, a quality report, and an artifact-refined WSI for further computational analysis. During the qualitative evaluation, pathologists assessed the predictive performance of MoEs over OoD WSIs. They rated artifact detection and artifact-free area preservation, where the highest agreement translated to a Cohen kappa of 0.82, indicating substantial agreement for the overall diagnostic usability of the DCNN-based MoE scheme. Conclusion: The proposed artifact detection pipeline will not only ensure reliable CPATH predictions but may also provide quality control. In this work, the best-performing pipeline for artifact detection is MoE with DCNNs. Our detailed experiments show that there is always a trade-off between performance and computational complexity, and no straightforward DL solution equally suits all types of data and applications. The code and dataset for training and development can be found online at Github and Zenodo, respectively.

show abstract

“…Detection of gastric cancer primarily relied on endoscopy images and pathological images. Wang et al [21] developed a Convolutional Neural Network (CNN) model to recognize biopsy tissue from Hematoxylin and Eosin (H&E) stained images and identify diseases. The lesions detected helped assess the malignancy in digestive system-related problems.…”

Section: Literature Reviewmentioning

confidence: 99%

Bottleneck Feature-Based U-Net for Automated Detection and Segmentation of Gastrointestinal Tract Tumors from CT Scans

Gandikota,

Abirami,

Kumar

2023

View full text Add to dashboard Cite

In today's medical landscape, an array of diagnostic techniques for cancer, leveraging imaging data, have become increasingly prevalent. This has posed a unique challenge for radiologists in the detection of Digestive System Cancer (DSC). This paper introduces the Bottleneck Feature-based U-Net, an innovative method designed for the automated detection and segmentation of the digestive system utilizing endoscopy. The U-Net design, previously proven successful for image segmentation tasks, is harnessed to its full potential in our proposed method. We have enhanced its performance by integrating a bottleneck feature extraction technique. The encoding U-Net is initially trained prior to the training of the BS U-Net, facilitating the procurement of encodings from label maps containing crucial anatomical information, such as shape and location. A Bottleneck Supervised (BS) U-Net is thus formed by pairing an encoding U-Net with a segmentation U-Net. Our proposed bottleneck feature in the U-Network enables the model to compress input data, an essential learning component. This compressed view of data retains vital information used for either reconstructing the input image or carrying out the segmentation process. In the current study, we put forth a bottleneck-based U-Net model tailored to perform gastrointestinal tract tumor segmentation. To train and test our method, we employed the comprehensive Kvasir dataset, which encompasses a wide range of digestive system images. We further tested the robustness and generalizability of our model through a thorough quantitative and qualitative analysis. The results underscore the versatility of the bottleneck U-Net and its potential as a reliable tool for radiologists in clinical practice. Our proposed model demonstrated rapid and effective cancer diagnosis capabilities, thus reducing diagnosis time. The model exhibited an impressive accuracy rate of 98.64% and a specificity score of 99.71%, outperforming both LSTM-ANN and GA Algorithms. This not only attests to the efficacy of our model but also underscores its potential in advancing diagnostic methodologies in clinical settings.

show abstract

Pathological Image Classification Based on Hard Example Guided CNN

Cited by 13 publications

References 22 publications

DeepSkin: Robust Skin Cancer Classification Using Convolutional Neural Network Algorithm

DeepSkin: Robust Skin Cancer Classification Using Convolutional Neural Network Algorithm

Equipping Computational Pathology Systems with Artifact Processing Pipelines: A Showcase for Computation and Performance Trade-offs

Bottleneck Feature-Based U-Net for Automated Detection and Segmentation of Gastrointestinal Tract Tumors from CT Scans

Contact Info

Product

Resources

About