Computer-aided diagnosis of prostate cancer with MRI

Fei, Baowei

doi:10.1016/j.cobme.2017.09.009

Cited by 29 publications

(16 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radiologists still need extensive experience to correctly discriminate CS from non-CS tumors [11,12], with the additional issue that some lesions are not visible on mpMRI [13,14]. Computer-aided diagnosis (CAD) aimed to increase correct diagnosis; however, due to the use of a small group of handcrafted features, its success is dependent on expert knowledge [15]. Therefore, there is a need for new technology that improves CS PCa detection on mpMRI without expert knowledge dependency.…”

Section: Introductionmentioning

confidence: 99%

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer

et al. 2019

View full text Add to dashboard Cite

Objectives To create a radiomics approach based on multiparametric magnetic resonance imaging (mpMRI) features extracted from an auto-fixed volume of interest (VOI) that quantifies the phenotype of clinically significant (CS) peripheral zone (PZ) prostate cancer (PCa). Methods This study included 206 patients with 262 prospectively called mpMRI prostate imaging reporting and data system 3-5 PZ lesions. Gleason scores > 6 were defined as CS PCa. Features were extracted with an auto-fixed 12-mm spherical VOI placed around a pin point in each lesion. The value of dynamic contrast-enhanced imaging(DCE), multivariate feature selection and extreme gradient boosting (XGB) vs. univariate feature selection and random forest (RF), expert-based feature pre-selection, and the addition of image filters was investigated using the training (171 lesions) and test (91 lesions) datasets. Results The best model with features from T2-weighted (T2-w) + diffusion-weighted imaging (DWI) + DCE had an area under the curve (AUC) of 0.870 (95% CI 0.980-0.754). Removal of DCE features decreased AUC to 0.816 (95% CI 0.920-0.710), although not significantly (p = 0.119). Multivariate and XGB outperformed univariate and RF (p = 0.028). Expert-based feature pre-selection and image filters had no significant contribution. Conclusions The phenotype of CS PZ PCa lesions can be quantified using a radiomics approach based on features extracted from T2-w + DWI using an auto-fixed VOI. Although DCE features improve diagnostic performance, this is not statistically significant. Multivariate feature selection and XGB should be preferred over univariate feature selection and RF. The developed model may be a valuable addition to traditional visual assessment in diagnosing CS PZ PCa. Key Points • T2-weighted and diffusion-weighted imaging features are essential components of a radiomics model for clinically significant prostate cancer; addition of dynamic contrast-enhanced imaging does not significantly improve diagnostic performance. • Multivariate feature selection and extreme gradient outperform univariate feature selection and random forest. • The developed radiomics model that extracts multiparametric MRI features with an auto-fixed volume of interest may be a valuable addition to visual assessment in diagnosing clinically significant prostate cancer.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer

et al. 2019

View full text Add to dashboard Cite

show abstract

“…6 Quantitative DCE imaging in a 71-year-old man undergoing pre-biopsy mpMRI for a left mid PZ cancer (Gleason score 3 + 3 on pathology after radical prostatectomy), showing restricted diffusion on the ADC map (a) and hypointensity on T2-weighted imaging (b) (arrows). DCE parametric maps obtained using the extended Tofts model showed markedly increased K trans (arrowhead in c) and K ep (arrowhead in d) compared to the surrounding PZ (see Table 4 for details) [49]. Of note, CAD is of particular help to less experienced readers [48] and can increase inter-reader agreement [50].…”

Section: Less Variability From Human Readersmentioning

confidence: 99%

“…From a practical point of view, CAD has the task to prompt image markers where csPCa is likely to be present (Fig. 5) [3,49].…”

Section: Less Variability From Human Readersmentioning

confidence: 99%

“…CAD also helped less experienced readers to diagnose more TZ cancers, and reduced reading time. Whether the increase in sensitivity affects specificity is a matter of debate, with works reporting it as unaltered, improved, or decreased [48,49]. Controversial results also exist about the accuracy for TZ cancers [48], and the capability to act as a stand-alone reader Fig.…”

Section: Less Variability From Human Readersmentioning

confidence: 99%

“…Importantly, one can ask whether CAD impacts on prostate MRI protocol composition (e.g., bpMRI versus mpMRI). As a matter of fact, CAD includes a variety of technologies, each with its unique approach and reference sequences to analyse (e.g., T2WI alone, DCE alone, T2WI and DWI, T2WI and DCE) [49]. It is difficult to establish whether prostate MRI protocols should be tailored to the available CAD model and concept, or, in contrast, CAD should be modelled on a standard protocol.…”

Section: Less Variability From Human Readersmentioning

confidence: 99%

See 2 more Smart Citations

Evolution of prostate MRI: from multiparametric standard to less-is-better and different-is better strategies

et al. 2019

View full text Add to dashboard Cite

Multiparametric magnetic resonance imaging (mpMRI) has become the standard of care to achieve accurate and reproducible diagnosis of prostate cancer. However, mpMRI is quite demanding in terms of technical rigour, patient's tolerability and safety, expertise in interpretation, and costs. This paper reviews the main technical strategies proposed as less-is-better solutions for clinical practice (non-contrast biparametric MRI, reduction of acquisition time, abbreviated protocols, computer-aided diagnosis systems), discussing them in the light of the available evidence and of the concurrent evolution of Prostate Imaging Reporting and Data System (PI-RADS). We also summarised research results on those advanced techniques representing an alternative different-is-better line of the still ongoing evolution of prostate MRI (quantitative diffusion-weighted imaging, quantitative dynamic contrast enhancement, intravoxel incoherent motion, diffusion tensor imaging, diffusional kurtosis imaging, restriction spectrum imaging, radiomics analysis, hybrid positron emission tomography/MRI).

show abstract

On the potential use of dynamic contrast‐enhanced (DCE) MRI parameters as radiomic features of cervical cancer

Lu¹,

Peng²,

Song³

et al. 2019

Medical Physics

View full text Add to dashboard Cite

Purpose: To evaluate whether the analysis of high-temporal resolution DCE-MRI by various tracer kinetic models could yield useful radiomic features in discriminating cervix carcinoma and normal cervix tissue. Methods: Forty-three patients (median age 51 yr; range 26-78 yr) diagnosed with cervical cancer based on postoperative pathology were enrolled in this study with informed consent. DCE-MRI data with temporal resolution of 2 s were acquired and analyzed using the Tofts (TOFTS), extended Tofts (EXTOFTS), conventional two-compartment (CC), adiabatic tissue homogeneity (ATH), and distributed parameter (DP) models. Ability of all kinetic parameters in distinguishing tumor from normal tissue was assessed using Mann-Whitney U test and receiver operating characteristic (ROC) curves. Repeatability of parameter estimates due to sampling of arterial input functions (AIFs) was also studied using intraclass correlation (ICC) analysis. Results: Fractional extravascular, extracellular volume (Ve) of all models were significantly smaller in cervix carcinoma than normal cervix tissue, and were associated with large values of area under ROC curve (AUC 0.884-0.961). Capillary permeability PS derived from the ATH, CC, and DP models also yielded large AUC values (0.730, 0.860, and 0.797). Transfer constant Ktrans derived from TOFTS and EXTOFTS models yielded smaller AUC (0.587 and 0.701). Repeatability of parameters derived from all models was robust to AIF sampling, with ICC coefficients typically larger than 0.80. Conclusions: With the use of high-temporal resolution DCE-MRI, all tracer kinetic models could reflect pathophysiological differences between cervix carcinoma and normal tissue (with significant differences in Ve and PS) and potentially yield radiomic features with diagnostic value.

show abstract

Computer-aided diagnosis of prostate cancer with MRI

Cited by 29 publications

References 51 publications

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer

Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral zone prostate cancer

Evolution of prostate MRI: from multiparametric standard to less-is-better and different-is better strategies

On the potential use of dynamic contrast‐enhanced (DCE) MRI parameters as radiomic features of cervical cancer

Contact Info

Product

Resources

About