This report describes the process of radiomics, its challenges, and its potential power to facilitate better clinical decision making, particularly in the care of patients with cancer.
These results suggest that a 3D MRSI examination added to a clinical MR imaging examination may help define the presence and spatial extent of prostate cancer.
The major goal for prostate cancer imaging in the next decade is more accurate disease characterization through the synthesis of anatomic, functional, and molecular imaging information. No consensus exists regarding the use of imaging for evaluating primary prostate cancers. Ultrasonography is mainly used for biopsy guidance and brachytherapy seed placement. Endorectal magnetic resonance (MR) imaging is helpful for evaluating local tumor extent, and MR spectroscopic imaging can improve this evaluation while providing information about tumor aggressiveness. MR imaging with superparamagnetic nanoparticles has high sensitivity and specificity in depicting lymph node metastases, but guidelines have not yet been developed for its use, which remains restricted to the research setting. Computed tomography (CT) is reserved for the evaluation of advanced disease. The use of combined positron emission tomography/CT is limited in the assessment of primary disease but is gaining acceptance in prostate cancer treatment follow-up. Evidence-based guidelines for the use of imaging in assessing the risk of distant spread of prostate cancer are available. Radionuclide bone scanning and CT supplement clinical and biochemical evaluation (prostate-specific antigen [PSA], prostatic acid phosphate) for suspected metastasis to bones and lymph nodes. Guidelines for the use of bone scanning (in patients with PSA level > 10 ng/mL) and CT (in patients with PSA level > 20 ng/mL) have been published and are in clinical use. Nevertheless, changes in practice patterns have been slow. This review presents a multidisciplinary perspective on the optimal role of modern imaging in prostate cancer detection, staging, treatment planning, and follow-up.
The addition of 3D MR spectroscopic imaging to MR imaging provides better detection and localization of prostate cancer in a sextant of the prostate than does use of MR imaging alone.
Noninvasive, radiological image-based detection and stratification of Gleason patterns can impact clinical outcomes, treatment selection, and the determination of disease status at diagnosis without subjecting patients to surgical biopsies. We present machine learning-based automatic classification of prostate cancer aggressiveness by combining apparent diffusion coefficient (ADC) and T2-weighted (T2-w) MRI-based texture features. Our approach achieved reasonably accurate classification of Gleason scores (GS) 6(3 + 3) vs. ≥7 and 7(3 + 4) vs. 7(4 + 3) despite the presence of highly unbalanced samples by using two different sample augmentation techniques followed by feature selection-based classification. Our method distinguished between GS 6(3 + 3) and ≥7 cancers with 93% accuracy for cancers occurring in both peripheral (PZ) and transition (TZ) zones and 92% for cancers occurring in the PZ alone. Our approach distinguished the GS 7(3 + 4) from GS 7(4 + 3) with 92% accuracy for cancers occurring in both the PZ and TZ and with 93% for cancers occurring in the PZ alone. In comparison, a classifier using only the ADC mean achieved a top accuracy of 58% for distinguishing GS 6(3 + 3) vs. GS ≥7 for cancers occurring in PZ and TZ and 63% for cancers occurring in PZ alone. The same classifier achieved an accuracy of 59% for distinguishing GS 7(3 + 4) from GS 7(4 + 3) occurring in the PZ and TZ and 60% for cancers occurring in PZ alone. Separate analysis of the cancers occurring in TZ alone was not performed owing to the limited number of samples. Our results suggest that texture features derived from ADC and T2-w MRI together with sample augmentation can help to obtain reasonably accurate classification of Gleason patterns.
Purpose:To assess the incremental value of diffusion-weighted (DW) magnetic resonance (MR) imaging over T2-weighted MR imaging at 3 T for prostate cancer detection and to investigate the use of the apparent diffusion coeffi cient (ADC) to characterize tumor aggressiveness, with wholemount step-section pathologic analysis as the reference standard.
Materials and Methods:The Internal Review Board approved this HIPAA-compliant retrospective study and waived informed consent. [ n = 20] or 0 and 1000 sec/mm 2 [ n = 31]) followed by prostatectomy. The prostate was divided into 12 regions; two readers provided a score for each region according to their level of suspicion for the presence of cancer on a fi ve-point scale, fi rst using T2-weighted MR imaging alone and then using T2-weighted MR imaging and the ADC map in conjunction. Areas under the receiver operating characteristic curve (AUCs) were estimated to evaluate performance. Generalized estimating equations were used to test the ADC difference between benign and malignant prostate regions and the association between ADCs and tumor Gleason scores.
Results:For tumor detection, the AUCs for readers 1 and 2 were 0.79 and 0.76, respectively, for T2-weighted MR imaging and 0.79 and 0.78, respectively, for T2-weighted MR imaging plus the ADC map. Mean ADCs for both cancerous and healthy prostatic regions were lower when DW MR imaging was performed with a b value of 1000 sec/mm 2 rather than 700 sec/mm 2 . Regardless of the b value used, there was a signifi cant difference in the mean ADC between malignant and benign prostate regions. A lower mean ADC was signifi cantly associated with a higher tumor Gleason score (mean ADCs of [1.21, 1.10, 0.87, and 0.69] 3 10 2 3 mm 2 /sec were associated with Gleason score of 3 + 3, 3 + 4, 4 + 3, and 8 or higher, respectively; P = .017).
Conclusion:Combined DW and T2-weighted MR imaging had similar performance to T2-weighted MR imaging alone for tumor detection; however, DW MR imaging provided additional quantitative information that signifi cantly correlated with prostate cancer aggressiveness.q RSNA, 2011
MR spectroscopic imaging measurement of prostate tumor (Cho + Cr)/Cit and tumor volume correlate with pathologic Gleason score. There is overlap between MR spectroscopic imaging parameters at various Gleason score levels, which may reflect methodologic and physiologic variations. MR spectroscopic imaging has potential in noninvasive assessment of prostate cancer aggressiveness.
Objectives
To investigate Haralick texture analysis of prostate MRI for cancer detection and differentiating Gleason Scores (GS).
Methods
One hundred and forty-seven patients underwent T2- weighted (T2WI) and diffusion-weighted prostate MRI. Cancers ≥0.5ml and non-cancerous peripheral (PZ) and transition zone (TZ) tissue were identified on T2WI and apparent diffusion coefficient (ADC) maps, using whole-mount pathology as reference. Texture features (Energy, Entropy, Correlation, Homogeneity, Inertia) were extracted and analyzed using generalized estimating equations.
Results
PZ cancers (n=143) showed higher Entropy and Inertia and lower Energy, Correlation and Homogeneity compared to non-cancerous tissue on T2WI and ADC maps (p-values: <.0001–0.008). In TZ cancers (n=43), we observed significant differences for all five texture features on the ADC map (all p-values: <.0001) and for Correlation (p=0.041) and Inertia (p=0.001) on T2WI. On ADC maps, GS was associated with higher Entropy (GS 6 vs 7: p=0.0225; 6 vs >7: p=0.0069) and lower Energy (GS 6 vs 7: p=0.0116, 6 vs >7: p=0.0039). ADC map Energy (p=0.0102) and Entropy (p=0.0019) were significantly different in GS ≤3+4 vs. ≥4+3 cancers; ADC map Entropy remained significant after controlling for the median ADC (p=0.0291).
Conclusion
Several Haralick based texture features appear useful for prostate cancer detection and GS assessment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.