Deep learning with a convolutional neural network model to differentiate renal parenchymal tumors: a preliminary study

Zheng, Yao; Wang, Shuai; Chen, Yan; Du, Huiqian

doi:10.1007/s00261-021-02981-5

Cited by 15 publications

(7 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the view of the comprehensive performance of all metrics and the statistical significance in AUC, the EfficientNet-B4 could be considered the best among three models for both of malignant and benign multi-class classification task, which revealed the advantage of EfficientNet-B4 and the certain consistency between two multi-class classification task. Besides, the previously reported studies about renal tumor diagnosis were mainly based on MRI or CT images and covered less subtypes compared with our study [27,29,33,35,39]. In the clinical practice, more renal tumor subtypes are desired to be diagnosed and the diagnosis process are expected to be as efficient as possible.…”

Section: Performance Of the Multi-class Classification Modelsmentioning

confidence: 69%

“…Tanaka et al used CNN-based Inception-v3 architecture to identify the small renal mass on multiphase contrastenhanced CT and performed multivariate logistic regression analysis, which drawn the conclusions that deep CNN model make it possible differentiating the small solid renal masses in dynamic CT images [32]. Zheng et al built a novel CNN model to identify the four subtypes of the renal parenchymal tumors in T2-weighted fat saturation sequence magnetic resonance images [33]. With an aim to identify two subtypes of benign renal masses and three subtypes of malignant renal masses, Oberai et al applied CNN-based deep learning method to multiphase contrast enhanced CT images [34].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognizing pathology of renal tumor from macroscopic cross-section image by deep learning

Lin

Yang

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

Objectives: This study aims to develop and evaluate the deep learning-based classification model for recognizing the pathology of renal tumor from macroscopic cross-section image. Methods: A total of 467 pathology-confirmed patients who received radical nephrectomy or partial nephrectomy were retrospectively enrolled. The experiment of distinguishing malignant and benign renal tumor are conducted followed by performing the multi-subtypes classification models for recognizing four subtypes of benign tumor and four subtypes of malignant tumorsrespectively. The classification models used the same backbone networks which are based on the convolutional neural network (CNN), including EfficientNet-B4, ResNet-18 and VGG-16. The performance of the classification models was evaluated by area under the receiver operating characteristic curve (AUC),sensitivity, specificity and accuracy. Besides, we performed the quantitative comparison among these CNN models. Results: For the model to differentiate the malignant tumor from the benign tumor, three CNN models all obtained relatively satisfactory performance and the highest AUC was achieved by the ResNet-18 model (AUC=0.9226). There is not statistically significance between EfficientNet-B4 and ResNet-18 architectures and both of them are significantly statistically better than the VGG-16 model. The micro-averaged AUC, macro-averaged sensitivity, macro-averaged specificity and micro-averaged accuracy for the VGG-16 model to distinguish the malignant tumor subtypes achieved 0.9398, 0.5774, 0.8660 and 0.7917 respectively. The performance of the EfficientNet-B4 is not better than that of VGG-16 in terms of micro-averaged AUC except for other metrics. For the models to recognize the benign tumor subtypes, the EfficientNet-B4 ranked the best performance but had not significantly statistical difference with other two models with respect to micro-averaged AUC. Conclusions: The classification results were relatively satisfactory, which showed the potential for clinical application when analyzing the renal tumor macroscopic cross-section images. Automatically distinguishing the malignant tumor from benign tumor and identifying the subtypes pathology of renal tumor could make the patient-management process more efficient.

show abstract

Section: Performance Of the Multi-class Classification Modelsmentioning

confidence: 69%

Section: Introductionmentioning

confidence: 99%

Recognizing pathology of renal tumor from macroscopic cross-section image by deep learning

Lin

Yang

Zhang

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The baseline CNN architecture of this study, ResNet‐18, is widely used in medical image classification, including the classification of thyroid US images, 32 renal parenchymal tumors classification, 15 COVID‐19 diagnosis, 33 and so on. The research of Boehm 34 used ResNet‐18 as a histopathological tissue‐type classifier for risk stratification of high‐grade serous ovarian cancer.…”

Section: Methodsmentioning

confidence: 99%

“…Sun et al 14 reported that the deep features extracted by CNNs could improve diagnostic accuracy for thyroid nodules by fusing with hand-crafted features. And Zheng et al 15 first investigated the performance of ResNet-18 in distinguishing the subtypes of renal tumors on MR images and reported higher performance than experienced radiologists.…”

Section: Introductionmentioning

confidence: 99%

Attention feature fusion methodology with additional constraint for ovarian lesion diagnosis on magnetic resonance images

Wang

et al. 2022

Medical Physics

Self Cite

View full text Add to dashboard Cite

It is challenging for radiologists and gynecologists to identify the type of ovarian lesions by reading magnetic resonance (MR) images. Recently developed convolutional neural networks (CNNs) have made great progress in computer vision, but their architectures still need modification if they are used in processing medical images. This study aims to improve the feature extraction capability of CNNs, thus promoting the diagnostic performance in discriminating between benign and malignant ovarian lesions. Methods: We introduce a feature fusion architecture and insert the attention models in the neural network.The features extracted from different middle layers are integrated with reoptimized spatial and channel weights. We add a loss function to constrain the additional probability vector generated from the integrated features, thus guiding the middle layers to emphasize useful information. We analyzed 159 lesions imaged by dynamic contrast-enhanced MR imaging (DCE-MRI), including 73 benign lesions and 86 malignant lesions. Senior radiologists selected and labeled the tumor regions based on the pathology reports. Then, the tumor regions were cropped into 7494 nonoverlapping image patches for training and testing. The type of a single tumor was determined by the average probability scores of the image patches belonging to it. Results: We implemented fivefold cross-validation to characterize our proposed method, and the distribution of performance matrics was reported. For all the test image patches, the average accuracy of our method is 70.5% with an average area under the curve (AUC) of 0.785, while the baseline is 69.4% and 0.773, and for the diagnosis of single tumors, our model achieved an average accuracy of 82.4% and average AUC of 0.916, which were better than the baseline (81.8% and 0.899). Moreover, we evaluated the performance of our proposed method utilizing different CNN backbones and different attention mechanisms. Conclusions:The texture features extracted from different middle layers are crucial for ovarian lesion diagnosis. Our proposed method can enhance the feature extraction capabilities of different layers of the network, thereby improving diagnostic performance.

show abstract

“…It affects 65,000 new patients a year [2]. There are 3 major RCC subtypes, 1 3 including clear cell (ccRCC), chromophobe (chRCC) and papillary (pRCC) [3][4][5].…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Approaches Applied to Image Classification of Renal Tumors: A Systematic Review

Amador,

Beuschlein,

Chauhan

et al. 2023

Arch Computat Methods Eng

View full text Add to dashboard Cite

Renal cancer is one of the ten most common cancers in the population that affects 65,000 new patients a year. Nowadays, to predict pathologies or classify tumors, deep learning (DL) methods are effective in addition to extracting high-performance features and dealing with segmentation tasks. This review has focused on the different studies related to the application of DL techniques for the detection or segmentation of renal tumors in patients. From the bibliographic search carried out, a total of 33 records were identified in Scopus, PubMed and Web of Science. The results derived from the systematic review give a detailed description of the research objectives, the types of images used for analysis, the data sets used, whether the database used is public or private, and the number of patients involved in the studies. The first paper where DL is applied compared to other types of tumors was in 2019 which is relatively recent. Public collection and sharing of data sets are of utmost importance to increase research in this field as many studies use private databases. We can conclude that future research will identify many benefits, such as unnecessary incisions for patients and more accurate diagnoses. As research in this field grows, the amount of open data is expected to increase.

show abstract

Deep learning with a convolutional neural network model to differentiate renal parenchymal tumors: a preliminary study

Cited by 15 publications

References 40 publications

Recognizing pathology of renal tumor from macroscopic cross-section image by deep learning

Recognizing pathology of renal tumor from macroscopic cross-section image by deep learning

Attention feature fusion methodology with additional constraint for ovarian lesion diagnosis on magnetic resonance images

Deep Learning Approaches Applied to Image Classification of Renal Tumors: A Systematic Review

Contact Info

Product

Resources

About