A radiomic approach to histologically proven prostate pathology scored by PIRADSv2

Congress:

ECR 2019

Poster Number:

C-3388

Type:

Scientific Exhibit

Keywords:

Tissue characterisation, Neoplasia, Cancer, Segmentation, Computer Applications-Detection, diagnosis, Computer Applications-3D, MR-Diffusion/Perfusion, MR, Image manipulation / Reconstruction, Pelvis, Genital / Reproductive system male, Computer applications

Authors:

D. grimaldi¹, S. Monti², C. Cavaliere², V. Brancato¹, L. Palumbo¹, M. Aiello², G. Di Costanzo¹, M. Salvatore¹, A. Ragozzino¹; ¹Napoli/IT, ²Naples/IT

DOI:

10.26044/ecr2019/C-3388

DOI-Link:

https://dx.doi.org/10.26044/ecr2019/C-3388

Table 1: Multiparametric RM acquisition parameters

Fig. 2: Distribution of the PIRADS v2 scores assigned by the two radiologists in...

Fig. 1: Selection of the study population

Fig. 3: MR image processing: lesion segmentation and feature extraction

Aims and objectives

Prostate cancer (PCa) is one of the most common malignant neoplasms and is the second leading cause of cancer-related death among older males in Western countries (1). The early detection and grading of the PCa are fundamental in patient management and in the evaluation of long-term survival. In 2015, the Prostate Imaging and Reporting and Data System version 2 (PI-RADS v2) was described to promote standardized reporting criteria for the interpretation of mp-MRI scans in the assessment of PCa, including clinical indications for prostate mp-MRI,...

Methods and materials

Partecipants This retrospective analysis was performed in a cohort of men with a clinical indication for prostate biopsy based on prostate-specific antigen elevation and clinical examination or participation in an active surveillance program. 650 patients examined from January 2014 until October 2018 were consecutively imaged with a dedicated prostate mutiparametric MR protocol using an endorectal coil (median age, 67 years; IQR, 50–81 years). Inclusion criteria were (a) imaging performed on our main institutional 1.5-T MRI system and (b) extended systematic and targeted MRI transrectal US...

Results

100 patients were enrolled in our study. Imaging findings were scored according the PIRADSv2 by two radiologists in consensus, blinded to the results of biopsy performed following the imaging session. 20 patients were scored as PIRADS 2, 40 as PIRADS 3, 14 as PIRADS 4, and 26 as PIRADS 5 (Fig2); 4 patients scored as PIRADS 2 resulted positive to the following biopsy with a Gleason score of 3+3; conversely, 2 patients with an imaging score of PIRADS 5 resulted negative for cancer at biopsy,...

Conclusion

In conclusion, quantitative assessment of the ADC was more accurate than qualitative PI-RADS assessment in classifying clinical relevance of a lesion forprostate cancer. Radiomics provided additional data than qualitative biparametric approach (including ADC and T2w). T2W and ADC-based radiomics models showed high diagnostic efficacy in subcategorise PIRADS 3 in two groups with low or high likelihood of PCa. Radiomics features outperformed the PI-RADS v2 scores in distinguishing cancerous vs. noncancerous prostate tissue.

Personal information

D. Grimaldi, MD PO SM delle Grazie Pozzuoli (Na) ASL NA2 NORD Phone: +393347060548 e-mail: [email protected] C. Cavaliere, MD IRCCS SDN, Naples Italy Phone: +393387484984 e-mail: [email protected]

References

Torre LA, et al. Global cancer statistic, 2012. CA Can- cer J Clin 2015;65:87–108. Park SY, Oh YT, Jung DC, et al. Prediction of biochemical recurrence after radical prostatectomy with PI-RADS version 2 in prostate cancers: Initial results. Eur Radiol 2016;26:2502–2509. Park SY, Shin SJ, Jung DC, et al. PI-RADS version 2: Preoperative role in the detection of normal-sized pelvic lymph node metastasis in prostate cancer. Eur J Radiol 2017;91:22. Zhao C, Gao G, Fang D, et al. The efficiency of multiparametric magnetic resonance imaging...