2019
DOI: 10.1016/j.tranon.2018.10.012
|View full text |Cite
|
Sign up to set email alerts
|

A Deep Learning-Based Radiomics Model for Differentiating Benign and Malignant Renal Tumors

Abstract: OBJECTIVES: To investigate the effect of transfer learning on computed tomography (CT) images for the benign and malignant classification on renal tumors and to attempt to improve the classification accuracy by building patient-level models. METHODS: One hundred ninety-two cases of renal tumors were collected and identified by pathologic diagnosis within 15 days after enhanced CT examination (66% male, 70% malignant renal tumors, average age of 62.27 ± 12.26 years). The InceptionV3 model pretrained by the Imag… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
88
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
4

Relationship

1
8

Authors

Journals

citations
Cited by 129 publications
(89 citation statements)
references
References 35 publications
0
88
0
1
Order By: Relevance
“…Precision ( Pre ): It indicates the proportion of processed samples that are correctly divided into positive samples [ 25 ]. where N TP represents the number of satellite cloud pictures that should be correctly classified; N FP represents the number of true correct classification after passing through the typhoon satellite cloud picture prediction model.…”
Section: Methodsmentioning
confidence: 99%
“…Precision ( Pre ): It indicates the proportion of processed samples that are correctly divided into positive samples [ 25 ]. where N TP represents the number of satellite cloud pictures that should be correctly classified; N FP represents the number of true correct classification after passing through the typhoon satellite cloud picture prediction model.…”
Section: Methodsmentioning
confidence: 99%
“…We used our multichannel image representation described in a previous study [24] that could capture both the anatomical and metabolic characteristics of the lesion in a single three-channel image. The three-channel image representation naturally fit the input architecture of the CNNs.…”
Section: ) Three-channel Representationmentioning
confidence: 99%
“…This approach was chosen on account of the small size of the dataset. We used our subset by partitioning as previously described in [24] to prevent contamination of the training, validation and testing sets with images of the same patient. The results were reported in terms of accuracy (ACC), sensitivity (SEN), specificity (SPE), Matthews correlation coefficient (MCC) and AUC.…”
Section: F Performance Evaluationmentioning
confidence: 99%
“…Besides this, the visual geometry group (VGG) network [ 5 ] is utilized to identity papillary thyroid carcinomas in cytological images [ 6 ] and discover COVID-19 cases based on X-ray images [ 7 ]. In addition, the Inception-V3 [ 8 ] is trained for distinguishing skin cancer images from normal ones [ 9 ], and differentiating benign and malignant renal tumors based on CT images [ 10 ]. Moreover, the residual network (ResNet) [ 11 ] is applied to HEp-2 cell classification [ 12 ] and the quality assessment of retinal OCT images [ 13 ].…”
Section: Introductionmentioning
confidence: 99%