Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: discriminating malignant parotid tumors in MRI

Matsuo, Hiroo; Nishio, Motohiro; Kanda, Tomonori; Kojita, Yasuyuki; Kono, Atsushi K.; Hori, Masatoshi; Teshima, Masanori; Otsuki, Naoki; Nibu, Ken‐ichi; Murakami, Takamichi

doi:10.1038/s41598-020-76389-4

Cited by 39 publications

(28 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There have also been several reports on characterizing PGTs using deep learning. For example, Matsuo et al [ 22 ] reported that the deep learning method could discriminate benign and malignant PGTs in MRI images, with an AUC of 0.86. Gabelloni et al [ 24 ] used magnetic resonance radiomics to discriminate PGTs, with results showing that radiomics analysis had a high diagnostic performance in pleomorphic adenomas and malignant tumors (sensitivity, specificity, and diagnostic accuracy of 0.66, 0.87, and 0.80, respectively).…”

Section: Discussionmentioning

confidence: 99%

The Diagnostic Value of Ultrasound-Based Deep Learning in Differentiating Parotid Gland Tumors

Wang

Xie

Huang

et al. 2022

Journal of Oncology

View full text Add to dashboard Cite

Objectives. Evidence suggests that about 80% of all salivary gland tumors involve the parotid glands, with approximately 20% of parotid gland tumors (PGTs) being malignant. Discriminating benign and malignant parotid gland lesions preoperatively is vital for selecting the appropriate treatment strategy. This study explored the diagnostic performance of deep learning system for discriminating benign and malignant PGTs in ultrasonography images and compared it with radiologists. Methods. A total of 251 consecutive patients with surgical resection and proven parotid gland malignant or benign tumors who underwent preoperative ultrasound examinations were enrolled in this study between January 2014 and November 2020. Next, we compared the diagnostic accuracy of deep learning methods (ViT-B\16, EfficientNetB3, DenseNet121, and ResNet50) and radiologists in parotid gland tumor. In addition, the area under the curve (AUC), specificity, sensitivity, positive predictive value, and negative predictive value were calculated. Results. Among the 251 patients, 176/251 were the training set, whereas 75/251 were the validation set. Results showed that 74/251 patients had malignant tumor. Deep learning models achieved good performance in differentiating benign from malignant tumors, with the diagnostic accuracy and AUCs of ViT-B\16, EfficientNetB3, DenseNet121, and ResNet50 model being 81% and 0.81, 80% and 0.82, 77% and 0.81, and 79% and 0.80, respectively. On the other hand, the diagnostic accuracy and AUCs of radiologists were 77%-81% and 0.68-0.75, respectively. It was evident that the diagnostic accuracy of deep learning methods was higher than that of inexperienced radiologists, but there was no significant difference between deep learning methods and experienced radiologists. Conclusions. This study shows that the deep learning system can be used for diagnosing parotid tumors. The findings also suggest that the deep learning system may improve the diagnosis performance of inexperienced radiologists.

show abstract

Section: Discussionmentioning

confidence: 99%

The Diagnostic Value of Ultrasound-Based Deep Learning in Differentiating Parotid Gland Tumors

Wang

Xie

Huang

et al. 2022

Journal of Oncology

View full text Add to dashboard Cite

show abstract

“…It was observed that intra/inter-tumoral heterogeneity and overlap of ADC values between BT and MT could be overcome by making a whole-tumor analysis ( 30 , 31 , 43 ). Previously, Ma et al.…”

Section: Discussionmentioning

confidence: 99%

Apparent Diffusion Coefficient Map–Based Radiomics Features for Differential Diagnosis of Pleomorphic Adenomas and Warthin Tumors From Malignant Tumors

Wen

Zhang²,

Zhu³

et al. 2022

Front. Oncol.

View full text Add to dashboard Cite

PurposeThe magnetic resonance imaging (MRI) findings may overlap due to the complex content of parotid gland tumors and the differentiation level of malignant tumor (MT); consequently, patients may undergo diagnostic lobectomy. This study assessed whether radiomics features could noninvasively stratify parotid gland tumors accurately based on apparent diffusion coefficient (ADC) maps.MethodsThis study examined diffusion-weighted imaging (DWI) obtained with echo planar imaging sequences. Eighty-eight benign tumors (BTs) [54 pleomorphic adenomas (PAs) and 34 Warthin tumors (WTs)] and 42 MTs of the parotid gland were enrolled. Each case was randomly divided into training and testing cohorts at a ratio of 7:3 and then was compared with each other, respectively. ADC maps were digitally transferred to ITK SNAP (www.itksnap.org). The region of interest (ROI) was manually drawn around the whole tumor margin on each slice of ADC maps. After feature extraction, the Synthetic Minority Oversampling TEchnique (SMOTE) was used to remove the unbalance of the training dataset. Then, we applied the normalization process to the feature matrix. To reduce the similarity of each feature pair, we calculated the Pearson correlation coefficient (PCC) value of each feature pair and eliminated one of them if the PCC value was larger than 0.95. Then, recursive feature elimination (RFE) was used to process feature selection. After that, we used linear discriminant analysis (LDA) as the classifier. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of the ADC.ResultsThe LDA model based on 13, 8, 3, and 1 features can get the highest area under the ROC curve (AUC) in differentiating BT from MT, PA from WT, PA from MT, and WT from MT on the validation dataset, respectively. Accordingly, the AUC and the accuracy of the model on the testing set achieve 0.7637 and 73.17%, 0.925 and 92.31%, 0.8077 and 75.86%, and 0.5923 and 65.22%, respectively.ConclusionThe ADC-based radiomics features may be used to assist clinicians for differential diagnosis of PA and WT from MTs.

show abstract

“…Therefore, we experimented with two different preprocessing methods to convert the MRI images to eligible CNN input format, to take full advantage of the pre‐trained networks. To briefly sum, the MRI images were resized to 224 × 224 according to the input requirement of Resnet‐18, then converted to RGB format in one of the two following methods. In the single‐modal paradigm, the same MRI sequence served as reiterated input of RGB channels. In the multi‐modal paradigm, compatible modalities were combined, such as T1, T2 and CE‐T1, so that each MRI sequence served as the channel input of individual RGB channels 17 …”

Section: Methodsmentioning

confidence: 99%

A Deep Learning Model for Classification of Parotid Neoplasms Based on Multimodal Magnetic Resonance Image Sequences

et al. 2022

View full text Add to dashboard Cite

Objective: To design a deep learning model based on multimodal magnetic resonance image (MRI) sequences for automatic parotid neoplasm classification, and to improve the diagnostic decision-making in clinical settings.Methods: First, multimodal MRI sequences were collected from 266 patients with parotid neoplasms, and an artificial intelligence (AI)-based deep learning model was designed from scratch, combining the image classification network of Resnet and the Transformer network of Natural language processing. Second, the effectiveness of the deep learning model was improved through the multi-modality fusion of MRI sequences, and the fusion strategy of various MRI sequences was optimized. In addition, we compared the effectiveness of the model in the parotid neoplasm classification with experienced radiologists.Results: The deep learning model delivered reliable outcomes in differentiating benign and malignant parotid neoplasms. The model, which was trained by the fusion of T2-weighted, postcontrast T1-weighted, and diffusion-weighted imaging (b = 1000 s/mm 2 ), produced the best result, with an accuracy score of 0.85, an area under the receiver operator characteristic (ROC) curve of 0.96, a sensitivity score of 0.90, and a specificity score of 0.84. In addition, the multi-modal paradigm exhibited reliable outcomes in diagnosing the pleomorphic adenoma and the Warthin tumor, but not in the identification of the basal cell adenoma.Conclusion: An accurate and efficient AI based classification model was produced to classify parotid neoplasms, resulting from the fusion of multimodal MRI sequences. The effectiveness certainly outperformed the model with single MRI images or single MRI sequences as input, and potentially, experienced radiologists.

show abstract

Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: discriminating malignant parotid tumors in MRI

Cited by 39 publications

References 19 publications

The Diagnostic Value of Ultrasound-Based Deep Learning in Differentiating Parotid Gland Tumors

The Diagnostic Value of Ultrasound-Based Deep Learning in Differentiating Parotid Gland Tumors

Apparent Diffusion Coefficient Map–Based Radiomics Features for Differential Diagnosis of Pleomorphic Adenomas and Warthin Tumors From Malignant Tumors

A Deep Learning Model for Classification of Parotid Neoplasms Based on Multimodal Magnetic Resonance Image Sequences

Contact Info

Product

Resources

About