Quantitative analysis of diffusion-weighted magnetic resonance images: differentiation between prostate cancer and normal tissue based on a computer-aided diagnosis system

Gao, Ge; Wang, Chengyan; Zhang, Xiaodong; Hu, Juan; Yang, Xuedong; Wang, He; Zhang, Jue; Wang, Xiaoying

doi:10.1007/s11427-016-0389-9

Cited by 16 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The radiomics‐based models with T 2 WI, ADC, or T 2 WI&ADC features outperformed the PI‐RADS scores for PCa differentiation and aggressiveness evaluation, which is consistent with previous studies. Gao et al extracted several texture features from DWI and compared the computer‐aided diagnosis model with DWI scores from PI‐RADS v2; the CAD‐predicted AUCs were higher than the AUCs of the DWI scores. Wang et al also indicated that a radiomics‐based machine‐learning approach can help to improve the predictive performance of PI‐RADS scores.…”

Section: Discussionmentioning

confidence: 99%

“…A number of studies have used radiomics analysis to automate PCa diagnosis and risk stratification . Gao et al utilized an artificial neural network (ANN) classifier to detect PCa using quantitative features extracted from DWI. The diagnostic prediction reached high accuracies (89.7% for the peripheral zone [PZ] and 91% for the transition zone [TZ]) and specificity (94.8% for the PZ and 94.1% for the TZ) while maintaining acceptable sensitivity (80.4% for the PZ and 82.7% for the TZ).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Prostate Cancer Differentiation and Aggressiveness: Assessment With a Radiomic‐Based Model vs. PI‐RADS v2

Chen

et al. 2018

Magnetic Resonance Imaging

102

106

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Prostate Cancer Differentiation and Aggressiveness: Assessment With a Radiomic‐Based Model vs. PI‐RADS v2

Chen

et al. 2018

Magnetic Resonance Imaging

102

106

View full text Add to dashboard Cite

show abstract

“…34 Another study presented a CAD system to identify the PCa from healthy tissues while using 13 quantitative features from diffusion MRI with an artificial neural network method and achieved an accuracy of 89.50% for PZ and 91% for TZ. 35 However, most of the existing methods for classification of PCa have used the GS as a reference standard, or were restricted to two-class classification only. Also, as presented by Lemaître et al in a comprehensive review of CAD systems for PCa, it was observed that most of the CAD models use typical feature extraction algorithms based on filtering and convolution that are computationally expensive.…”

Section: Discussionmentioning

confidence: 99%

Characterisation of prostate cancer using texture analysis for diagnostic and prognostic monitoring

et al. 2021

View full text Add to dashboard Cite

Automated classification of significant prostate cancer (PCa) using MRI plays a potential role in assisting in clinical decision-making. Multiparametric MRI using a machine-aided approach is a better step to improve the overall accuracy of diagnosis of PCa. The objective of this study was to develop and validate a framework for differentiating Prostate Imaging-Reporting and Data System version 2 (PI-RADS v2) grades (grade 2 to grade 5) of PCa using texture features and machine learning (ML) methods with diffusionweighted imaging (DWI) and apparent diffusion coefficient (ADC). The study cohort included an MRI dataset of 59 patients with clinically proven PCa. Regions of interest (ROIs) for a total of 435 lesions were delineated from the segmented peripheral zones of DWI and ADC. Six texture methods comprising 98 texture features in total (49 each of DWI and ADC) were extracted from lesion ROIs. Random forest (RF) and correlationbased feature selection methods were applied on feature vectors to select the best features for classification. Two ML classifiers, support vector machine (SVM) and K-nearest neighbour, were used and validated by 10-fold cross-validation. The proposed framework achieved high diagnostic performance with a sensitivity of 85.25% ± 3.84%, specificity of 95.71% ± 1.96%, accuracy of 84.90% ± 3.37% and area under the receiver-operating characteristic curve of 0.98 for PI-RADS v2 grades (2 to 5) classification using the RF feature selection method and Gaussian SVM classifier with combined features of DWI + ADC. The proposed computer-assisted framework can distinguish between PCa lesions with different aggressiveness based on PI-RADS v2 standards using texture analysis to improve the efficiency of PCa diagnostic performance.apparent diffusion coefficient, diffusion-weighted imaging, machine learning, prostate cancer, Prostate Imaging-Reporting and Data System version 2, texture analysis | INTRODUCTIONEarly diagnosis and grading of prostate cancer (PCa) are essential for the clinical management of patients, and can directly impact planning management strategy and clinical outcomes. One challenge in the diagnosis of PCa is to correctly identify patients with moderate and high-risk

show abstract

“…For example, contrast of the gray‐level co‐occurrence matrix is quite important to detect cancer in PZ, yet not important for cancer detection in TZ. Thus, it is necessary to segment PZ and TZ simultaneously for CAD especially on T 2 ‐weighted images (T 2 WIs). In fact, T 2 WI is an essential sequence used in the diagnosis of PCa.…”

mentioning

confidence: 99%

Fully automatic segmentation on prostate MR images based on cascaded fully convolution network

Zhu

Wei

Gao

et al. 2018

Magnetic Resonance Imaging

Self Cite

View full text Add to dashboard Cite

Background: Computer-aided diagnosis (CAD) can aid radiologists in quantifying prostate cancer, and MRI segmentation plays an essential role in CAD applications. Clinical experience shows that prostate cancer occurs predominantly in the peripheral zone (PZ) and there exist different evaluation criteria for different regions in the Prostate Imaging Reporting and Data System (PI-RADS). Purpose: To develop a fully automatic approach to segmenting the prostate outer contour and the PZ contour with high efficacy.Population: In all, 163 subjects, including 61 healthy subjects and 102 prostate cancer patients. For each subject, all slices that contained prostate gland in diffusion-weighted images (DWIs) and T 2 -weighted images (T 2 WIs) were selected as the datasets. Field Strength: T 2 -weighted, DWI at 3.0T. Assessment: The computer-generated segmentation results were compared with the manual outlining results that were depicted by two experts with more than 5 years' experience. Dice similarity coefficient (DSC), false-positive rate (FPR), and false-negative rate (FNR) were used to compared the algorithm and manual segmentation results. Statistical Tests: A paired t-test was adopted for comparison between our method and classical U-Net segmentation methods. Results: The mean DSC was 92.7 ± 4.2% for the total whole prostate gland and 79.3 ± 10.4% for the total peripheral zone. Compared with classical U-Net segmentation methods, our segmentation precision was significantly higher (P < 0.001). Data Conclusion: By cropping the region of interest and cascading the two networks, our method balances the positive and negative sample gradually, and results in higher segmentation accuracy. This fully automatic strategy could provide satisfactory performance in prostate DWIs and T 2 WIs-based image segmentation. Level of Evidence: 2 Technical Efficacy: Stage 1

show abstract

Quantitative analysis of diffusion-weighted magnetic resonance images: differentiation between prostate cancer and normal tissue based on a computer-aided diagnosis system

Cited by 16 publications

References 25 publications

Prostate Cancer Differentiation and Aggressiveness: Assessment With a Radiomic‐Based Model vs. PI‐RADS v2

Prostate Cancer Differentiation and Aggressiveness: Assessment With a Radiomic‐Based Model vs. PI‐RADS v2

Characterisation of prostate cancer using texture analysis for diagnostic and prognostic monitoring

Fully automatic segmentation on prostate MR images based on cascaded fully convolution network

Contact Info

Product

Resources

About