Characterization of Texture Features of Bladder Carcinoma and the Bladder Wall on MRI: Initial Experience

doi:10.1016/j.acra.2013.03.011

Academic Radiology

Volume 20, Issue 8, August 2013, Pages 930-938

https://doi.org/10.1016/j.acra.2013.03.011 Get rights and content

Rationale and Objectives

The purpose of this study was to determine textural features that show a significant difference between carcinomatous tissue and the bladder wall on magnetic resonance imaging (MRI) and explore the feasibility of using them to differentiate malignancy from the normal bladder wall as an initial step for establishing MRI as a screening modality for the noninvasive diagnosis of bladder cancer.

Materials and Methods

Regions of interest (ROIs) were manually placed on foci of bladder cancer and uninvolved bladder wall in 22 patients and on the normal bladder wall of 23 volunteers to calculate 40 known textural features. Statistical analysis was applied to determine the difference in these features in bladder cancer versus uninvolved bladder wall versus normal bladder wall of volunteers. The significantly different features were then analyzed using a support vector machine (SVM) classifier to determine their accuracy in differentiating malignancy from the bladder wall.

Results

Thirty-three of 40 features show significant differences between bladder cancer and the bladder wall. Nine of 40 features were significantly different in uninvolved bladder wall of patients versus normal bladder wall of volunteers. Further study indicates that seven of these 33 features were significantly different between uninvolved bladder wall of patients with early cancer and that of volunteers, whereas 15 of 33 features were different between that of patients with advanced cancer and normal wall. With the testing dataset consisting of ROIs acquired from patients, the classification accuracy using 33 textural features fed into the SVM classifier was 86.97%.

Conclusion

The initial experience demonstrates that texture features are sensitive to reveal the differences between bladder cancer and the bladder wall on MRI. The different features can be used to develop a computer-aided system for the evaluation of the entire bladder wall.

Section snippets

Subjects

Twenty-two consecutive male patients in whom findings from routine cystoscopy were positive for tumors were referred from the urology department, Tangdu Hospital, Xi′an, China, between March 2008 and May 2010. All the patients were confirmed of having urothelial carcinoma by postoperative pathological biopsy. Twenty-three male volunteers were also recruited simultaneously as the control group; they had no known history of bladder diseases, no bladder mass observed during the ultrasound

Results

Table 2 shows the age distribution, histological subtypes, and staging of all patients. The age of volunteers ranges from 28 to 64, with mean and standard deviation of 46.55 ± 13.19. There was no significant difference in age between the two groups.

Among 22 patients enrolled, all tumors were polypoidal shaped and the size of bladder tumors ranged from 0.5 to 6 cm in diameter. Because the smallest one was too small to be encircled, it was not included in group A. In addition, the bladder wall of

Discussion

In the past few years, CAD/CADx for breast cancer, pulmonary nodules, and colon polyps has been a very active research topic, aiming to assist physicians to detect and distinguish nodules and polyps from benign to malignant. The achievement is still moderate possibly because the primary consideration of the outside characteristics on the surface of nodules or polyps. It was gradually recognized that different image textural patterns may reflect different types of tissues and can be used to

Acknowledgments

This work was partially supported by the National Nature Science Foundation of China under grants 81230035 and 81071220. Zhengrong Liang was partially supported by National Institute of Health grant #CA082402.

References (23)

Z. Kirkali et al.
Bladder cancer: epidemiology, staging and grading, and diagnosis
Urology
(2005)
H.S. Sheshadri et al.
Experimental investigation on breast tissue classification based on statistical feature extraction of mammograms
Comp Med Imaging Graphics
(2007)
B. Ganeshan et al.
Texture analysis in non-contrast enhanced CT: impact of malignancy on texture in apparently disease-free areas of the liver
Eur J Radiol
(2009)
W.-J. Wu et al.
Ultrasound breast tumor image computer-aided diagnosis with texture and morphological features
Acad Radiol
(2008)
R.W. Conners et al.
Segmentation of a high-resolution urban scene using texture operators
Comp Vision Graphics Image Pro
(1984)
A. Scher et al.
“Probability transforms” of digital pictures
Pattern Recognit
(1980)
American Cancer Society
Cancer facts & figures 2012
(2012)
Bladder Cancer Clinical Guideline Update Panel
Bladder cancer: guideline for the management of nonmuscle invasive bladder cancer: (stages Ta, T1, and Tis): 2007 update
(2007)
Committee of Chinese diagnosis and treatment guidelines in urology surgery
Chinese diagnosis and treatment guidelines in urology surgery
(2007)
The top ten malignancy mortality rates of China (man) [EB/OL]. Available at:...

B.L. Jacobs et al.

Bladder cancer in 2010: how far have we come?

CA Cancer J Clin

(2010)

Cited by (35)

Exploring Texture Analysis to Optimize Bladder Preservation in Muscle Invasive Bladder Cancer
2023, Clinical Genitourinary Cancer
Citation Excerpt :
Previously reported finding by Shi et al on MRI texture features comparing bladder cancer and uninvolved bladder wall (opposite the tumour location) found 33 of 40 features (mean, sd, mpp, kurtosis, skewness and second order features like GLCM) significantly different between the two types of tissues (P < .01). They also reported 9/40 features to be significantly different between uninvolved bladder wall of patients and normal bladder wall of volunteers (P < .05 15. The ability of texture analysis to differentiate between normal and cancerous bladder mucosa can be potentially utilized for a number of clinical applications in bladder cancer radiotherapy like characterization of suspicious areas on planning CT images for dose escalation, deciding the need for resection to bladder tumour before radiotherapy, prediction of response to neoadjuvant chemotherapy, avoiding biopsy of lesions on cystoscopic follow up.
To explore if texture analysis of Muscle Invasive Bladder Cancer (MIBC) can aid in better patient selection for bladder preservation.
Pretreatment noncontrast CT images of 41 patients of MIBC treated with bladder preservation were included. The visible tumor was contoured on all slices by a single observer. The primary endpoint was to identify texture parameters associated with disease recurrence posttreatment. The secondary endpoints included intra and interobserver variability, single and multislice analysis, and differentiating the texture features of normal bladder and tumor. For interobserver variability of bladder tumor texture features, 3 observers contoured the visible tumor on all slices independently. Observer 1 contoured again at an interval of 1 month for intraobserver variability.
The median follow-up was 30 months with 12 patients having a recurrence. In the primary endpoint analysis, the mean of the pixels at Spatial Scaling Filter (SSF) 2 for the no recurrence group and recurrence group was 6.44 v 13.73 respectively (P = .031) and the same at SSF-3 was 11.95 and 22.32 respectively (P = .034). The texture features that could significantly differentiate tumor and normal bladder were mean, standard deviation and kurtosis of the pixels at SSF-2 and entropy and kurtosis of the pixels at SSF-3. Overall, there was an excellent intra and interobserver concordance in texture features. Only multislice analysis and not single-slice could differentiate recurrence and no recurrence posttreatment.
Texture analysis can be explored as a modality for patient selection for bladder preservation along with the established clinical parameters to improve outcomes.
MRI Radiomic Analysis of IMRT-Induced Bladder Wall Changes in Prostate Cancer Patients: A Relationship with Radiation Dose and Toxicity
2019, Journal of Medical Imaging and Radiation Sciences
Citation Excerpt :
In this study, we used MRI for radiomic analysis because it has excellent soft tissue resolution and multiplanar capabilities, which has made it an important modality for bladder abnormalities detection and diagnosis. There have been some investigations into the feasibility of bladder MR feature analysis for cancer detection [28] and CT features for improving radiotherapy planning [29]. There are several radiomic features that can be extracted from medical images and evaluated as an imaging biomarker.
The main purpose of this study was to assess the structural changes in the bladder wall of prostate cancer patients treated with intensity-modulated radiation therapy using magnetic resonance imaging texture features analysis and to correlate image texture changes with radiation dose and urinary toxicity.
Ethical clearance was granted to enroll 33 patients into this study who were treated with intensity-modulated radiation therapy for prostate cancer. All patients underwent two magnetic resonance imagings before and after radiation therapy (RT). A total of 274 radiomic features were extracted from MR-T2W–weighted images. Wilcoxon singed rank-test was performed to assess significance of the change in mean radiomic features post-RT relative to pre-RT values. The relationship between radiation dose and feature changes was assessed and depicted. Cystitis was recorded as urinary toxicity. Area under receiver operating characteristic curve of a logistic regression–based classifier was used to find correlation between radiomic features with significant changes and radiation toxicity.
Thirty-three bladder walls were analyzed, with 11 patients developing grade ≥2 urinary toxicity. We showed that radiomic features may predict radiation toxicity and features including S5.0SumVarnc, S2.2SumVarnc, S1.0AngScMom, S0.4SumAverg, and S5. _5InvDfMom with area under receiver operating characteristic curve 0.75, 0.69, 0.65, 0.63, and 0.62 had highest correlation with toxicity, respectively. The results showed that most of the radiomic features were changed with radiation dose.
Feature changes have a good correlation with radiation dose and radiation-induced urinary toxicity. These radiomic features can be identified as being potentially important imaging biomarkers and also assessing mechanisms of radiation-induced bladder injuries.
Le but premier de cette étude était d’évaluer les changements structurels dans la paroi de la vessie chez les patients atteints d'un cancer de la prostate (PCa) traités par radiothérapie avec modulation d'intensité (IMRT) en utilisant l'analyse des caractéristiques de texture par imagerie par résonance magnétique (IRM) et d’établir une corrélation entre les changements de texture dans les images, la dose de rayonnement et la toxicité urinaire.
Le comité d’éthique de la recherche a donné son accord pour inscrire à cette étude 33 patients traités pour PCa par IMRT. Tous les patients ont eu deux IRM, avant et après la radiothérapie. Au total, 274 caractéristiques radiomiques ont été extraites des images pondérées MR-T2W. Un test Wilcoxon Signed Rank a été fait pour évaluer la signification du changement dans les caractéristiques radiomiques moyennes après la RT par rapport aux valeurs avant la RT. La relation entre la dose de rayonnement et les changements dans les caractéristiques a été évaluée et illustrée. La cystite a été utilisée comme toxicité urinaire. L'aire sous la courbe de fonction d'efficacité du récepteur d'un classificateur (AUC) basé sur une régression logistique a été utilisée pour déterminer la corrélation entre les caractéristiques radiomiques présentant des changements significatifs et la toxicité du rayonnement.
Trente-trois parois de vessies ont été analysées, et 11 patients ont développé une toxicité urinaire de grade ≥2. Nous avons démontré que les caractéristiques radiomiques pouvaient permettre de prédire la toxicité et les caractéristiques du rayonnement, incluant S5.0SumVarnc, S2.2SumVarnc, S1.0AngScMom, S0.4SumAverg et S5. _5InvDfMom avec AUC 0,75, 0,69, 0,65, 0,63 et 0,62 présentaient respectivement la plus forte corrélation avec la toxicité. Les résultats démontrent que la plupart des caractéristiques radiomiques ont été modifiées avec la dose de rayonnement.
Les changements dans les caractéristiques présentent une bonne corrélation avec la dose de rayonnement et la toxicité urinaire induite par le rayonnement. Ces caractéristiques radiomiques peuvent être identifiées comme biomarqueurs d'imagerie potentiellement importants et comme mécanismes d’évaluation des blessures à la vessie induites par le rayonnement.
Evaluation of radiomic texture feature error due to MRI acquisition and reconstruction: A simulation study utilizing ground truth
2018, Physica Medica
Citation Excerpt :
As a radiomics tool, texture analysis (TA) is increasingly being applied to diverse imaging modalities to provide anatomical segmentation, cancerous lesion delineation, and prediction of response of normal and pathologic tissue to radiation therapy [2–6]. TA of magnetic resonance (MR) images has been applied to diverse clinical sites in the context of radiation treatment (RT), for example: brain [7,8], head and neck [9,10], breast [11], kidney [12], bladder [13], prostate [14–17], and extremities [18]. The results of those studies, as well as those of ongoing clinical research, indicate great potential for the incorporation of information gleaned from quantitative texture features into initial RT planning as well as adaptive RT of cancer patients.
The purpose of this study was to examine the dependence of image texture features on MR acquisition parameters and reconstruction using a digital MR imaging phantom. MR signal was simulated in a parallel imaging radiofrequency coil setting as well as a single element volume coil setting, with varying levels of acquisition noise, three acceleration factors, and four image reconstruction algorithms. Twenty-six texture features were measured on the simulated images, ground truth images, and clinical brain images. Subtle algorithm-dependent errors were observed on reconstructed phantom images, even in the absence of added noise. Sources of image error include Gibbs ringing at image edge gradients (tissue interfaces) and well-known artifacts due to high acceleration; two of the iterative reconstruction algorithms studied were able to mitigate these image errors. The difference of the texture features from ground truth, and their variance over reconstruction algorithm and parallel imaging acceleration factor, were compared to the clinical “effect size”, i.e., the feature difference between high- and low-grade tumors on T1- and T2-weighted brain MR images of twenty glioma patients. The measured feature error (difference from ground truth) was small for some features, but substantial for others. The feature variance due to reconstruction algorithm and acceleration factor were generally smaller than the clinical effect size. Certain texture features may be preserved by MR imaging, but adequate precautions need to be taken regarding their validity and reliability. We present a general simulation framework for assessing the robustness and accuracy of radiomic textural features under various MR acquisition/reconstruction scenarios.
Contrast enhanced magnetic resonance imaging as a diagnostic tool to assess bladder permeability and associated colon cross talk: Preclinical studies in a rat model
2015, Journal of Urology
Interstitial cystitis/painful bladder syndrome is a devastating disease associated with multiple symptoms. It is usually diagnosed based on pain, urgency and frequency in the absence of other known causes. To our knowledge there is no diagnostic test to date.
In a model of rats intravesically exposed to protamine sulfate we performed in vivo diagnostic contrast enhanced magnetic resonance imaging with intravesical administration of Gd-diethylenetriamine pentaacetic acid contrast medium via a catheter to visualize increased bladder urothelium permeability. Gd-diethylenetriamine pentaacetic acid was administered intravenously to visualize secondary tissue effects in the colon.
Bladder urothelium and colon mucosa were assessed 24 hours after bladder protamine sulfate exposure. Enhanced contrast magnetic resonance imaging established bladder urothelium leakage of Gd-diethylenetriamine pentaacetic acid according to the change in magnetic resonance imaging signal intensity in rats exposed to protamine sulfate vs controls (mean ± SD 399.7% ± 68.7% vs 39.2% ± 12.2%, p <0.0001) as well as colon related uptake of contrast agent (mean 65.2% ± 17.1% vs 20.8% ± 9.8%, p <0.01) after bladder protamine sulfate exposure. The kinetics of Gd-diethylenetriamine pentaacetic acid uptake and excretion were also assessed during 20 minutes of bladder and 30 minutes of colon exposure with increased signal intensity at 7 and 12 minutes, respectively.
These preliminary studies indicate that contrast enhanced magnetic resonance imaging can be used to monitor primary bladder urothelium loss of permeability and secondary enhanced contrast medium in the colon mucosa. It can be considered a potential clinical diagnostic method for interstitial cystitis/painful bladder syndrome that involves loss of the permeability barrier. It can also be used to assess visceral organ cross talk.
Multiparametric MRI in Era of Artificial Intelligence for Bladder Cancer Therapies
2023, Cancers
Prediction of myometrial invasion of bladder cancer based on texture analysis of the bladder wall at tumor base
2023, Chinese Journal of Ultrasonography

View all citing articles on Scopus

: Z.S. and Z.Y. are co-first authors.

View full text

Original InvestigationCharacterization of Texture Features of Bladder Carcinoma and the Bladder Wall on MRI: Initial Experience

Rationale and Objectives

Materials and Methods

Results

Conclusion

Section snippets

Subjects

Results

Discussion

Acknowledgments

Urology

Comp Med Imaging Graphics

Eur J Radiol

Acad Radiol

Comp Vision Graphics Image Pro

Pattern Recognit

Cancer facts & figures 2012

Bladder cancer: guideline for the management of nonmuscle invasive bladder cancer: (stages Ta, T1, and Tis): 2007 update

Chinese diagnosis and treatment guidelines in urology surgery

Bladder cancer in 2010: how far have we come?

CA Cancer J Clin

Original Investigation
Characterization of Texture Features of Bladder Carcinoma and the Bladder Wall on MRI: Initial Experience