Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings

Shiradkar, Rakesh; Ghose, Soumya; Jambor, Ivan; Taimen, Pekka; Ettala, Otto; Purysko, Andrei S.; Madabhushi, Anant

doi:10.1002/jmri.26178

Cited by 110 publications

(73 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When compared with traditional Cox regression analysis, the three ML algorithms had superior prediction performance. Tissue morphometric data , imaging radiomic features , and tissue genomic profiling were also used to predict patient outcomes. These studies showed that AI algorithms trained with clinicopathological data, imaging radiomic features and genomic profiling outperformed the prediction accuracy of D'Amico risk stratification, single clinicopathological features, or multiple discriminant analysis, a type of conventional multivariate statistics .…”

Section: Application Of Ai In Urologymentioning

confidence: 99%

Current status of artificial intelligence applications in urology and their potential to influence clinical practice

et al. 2019

View full text Add to dashboard Cite

Objective To investigate the applications of artificial intelligence (AI) in diagnosis, treatment and outcome predictionin urologic diseases and evaluate its advantages over traditional models and methods. Materials and methods A literature search was performed after PROSPERO registration (CRD42018103701) and in compliance with Preferred Reported Items for Systematic Reviews and Meta‐Analyses (PRISMA) methods. Articles between 1994 and 2018 using the search terms “urology”, “artificial intelligence”, “machine learning” were included and categorized by the application of AI in urology. Review articles, editorial comments, articles with no full‐text access, and nonurologic studies were excluded. Results Initial search yielded 231 articles, but after excluding duplicates and following full‐text review and examination of article references, only 111 articles were included in the final analysis. AI applications in urology include: utilizing radiomic imaging or ultrasonic echo data to improve or automate cancer detection or outcome prediction, utilizing digitized tissue specimen images to automate detection of cancer on pathology slides, and combining patient clinical data, biomarkers, or gene expression to assist disease diagnosis or outcome prediction. Some studies employed AI to plan brachytherapy and radiation treatments while others used video based or robotic automated performance metrics to objectively evaluate surgical skill. Compared to conventional statistical analysis, 71.8% of studies concluded that AI is superior in diagnosis and outcome prediction. Conclusion AI has been widely adopted in urology. Compared to conventional statistics AI approaches are more accurate in prediction and more explorative for analyzing large data cohorts. With an increasing library of patient data accessible to clinicians, AI may help facilitate evidence‐based and individualized patient care.

show abstract

Section: Application Of Ai In Urologymentioning

confidence: 99%

Current status of artificial intelligence applications in urology and their potential to influence clinical practice

et al. 2019

View full text Add to dashboard Cite

show abstract

“…For example, statistical descriptors can be particularly sensitive to the intensity of the image. Texture features of DWI, among other radiomic features, have already demonstrated some promise for PCa detection and management (e.g., Shiradkar et al and Algohary et al). However, a large variation in radiomics performance has been observed in multi‐institutional studies .…”

Section: Discussionmentioning

confidence: 99%

“…Aggressiveness of PCa is histologically determined by Gleason score that is classified into Gleason grade group (GGG) . Various radiomics and ML methods have already been developed for PCa detection and characterization (e.g., Shiradkar et al and Algohary et al). However, radiomics and ML methods have not been evaluated in terms of their repeatability, which contributes to reservations of making imaging applications that would use prostate MRI more extensively coupled with machine learning in routine clinical practice.…”

Section: Introductionmentioning

confidence: 99%

Repeatability of radiomics and machine learning for DWI: Short‐term repeatability study of 112 patients with prostate cancer

Merisaari

Taimen

Shiradkar

et al. 2019

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Purpose To evaluate repeatability of prostate DWI‐derived radiomics and machine learning methods for prostate cancer (PCa) characterization. Methods A total of 112 patients with diagnosed PCa underwent 2 prostate MRI examinations (Scan1 and Scan2) performed on the same day. DWI was performed using 12 b‐values (0–2000 s/mm2), post‐processed using kurtosis function, and PCa areas were annotated using whole mount prostatectomy sections. A total of 1694 radiomic features including Sobel, Kirch, Gradient, Zernike Moments, Gabor, Haralick, CoLIAGe, Haar wavelet coefficients, 3D analogue to Laws features, 2D contours, and corner detectors were calculated. Radiomics and 4 feature pruning methods (area under the receiver operator characteristic curve, maximum relevance minimum redundancy, Spearman’s ρ, Wilcoxon rank‐sum) were evaluated in terms of Scan1‐Scan2 repeatability using intraclass correlation coefficient (ICC)(3,1). Classification performance for clinically significant and insignificant PCa with Gleason grade groups 1 versus >1 was evaluated by area under the receiver operator characteristic curve in unseen random 30% data split. Results The ICC(3,1) values for conventional radiomics and feature pruning methods were in the range of 0.28–0.90. The machine learning classifications varied between Scan1 and Scan2 with % of same class labels between Scan1 and Scan2 in the range of 61–81%. Surface‐to‐volume ratio and corner detector‐based features were among the most represented features with high repeatability, ICC(3,1) >0.75, consistently high ranking using all 4 feature pruning methods, and classification performance with area under the receiver operator characteristic curve >0.70. Conclusion Surface‐to‐volume ratio and corner detectors for prostate DWI led to good classification of unseen data and performed similarly in Scan1 and Scan2 in contrast to multiple conventional radiomic features.

show abstract

“…Multiple sequences can provide considerable advantages in presenting the different components of tumors. A radiomics model, which is based on a large number of imaging features, has been regarded as a powerful prognostic biomarker for cancer recurrence . Thio et al recently developed different machine‐learning models for predicting the 5‐year survival rates of CS patients; however, further validation is needed .…”

mentioning

confidence: 99%

Can clinical radiomics nomogram based on 3D multiparametric MRI features and clinical characteristics estimate early recurrence of pelvic chondrosarcoma?

Yin

Mao

Liu

et al. 2019

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Background Chondrosarcoma (CS) is the second most common primary malignant bone tumor, with a relatively high recurrence rate. However, an effective method that estimates whether pelvic CS will recur after surgery, which influences the formulation of a clinical treatment plan, remains lacking. Purpose To develop and validate a clinical radiomics nomograms based on 3D multiparametric magnetic resonance imaging (mpMRI) features and clinical characteristics that could estimate early recurrence (ER) (≤1 year) of pelvic CS. Study Type Retrospective. Population In all, 103 patients (ER = 41, non‐ER = 62) with histologically proven CS were retrospectively analyzed and divided into a training set (n = 72) and a validation set (n = 31). Field Strength/Sequence 3.0T axial T1‐weighted (T1‐w), T2‐weighted (T2‐w), diffusion weighted imaging (DWI), contrast‐enhanced T1‐weighted (CET1‐w). Assessment Risk factors (sex, age, type, grade, resection margins, etc.) associated with ER were evaluated. Five individual models based on T1‐w, T2‐w, DWI, CET1‐w, and clinical data were built. Then we compared the performance of models based on T1‐w, T2‐w, CET1‐w and their combination. Lastly, two nomograms based on the best model + clinical data and DWI + clinical data were built. Statistical Tests The area under the receiver operating characteristic curve (AUC) and accuracy (ACC) were used to evaluate different models. Results Grade was the most important univariate clinical predictor of ER of pelvic CS patients (odds ratio [OR]1 = 4.616, OR2 = 8.939, P < 0.05). T1‐w + T2‐w + CET1‐w had a significantly higher performance than CET1‐w in the training set (P = 0.01). Radiomics features are more important than clinical characteristics in clinical radiomics nomograms, especially for multisequence combined features (OR = 3.208, P < 0.01). Clinical radiomics nomogram based on combined features (T1‐w + T2‐w + CET1‐w) + clinical data achieved an AUC of 0.891 and ACC of 0.857, followed by DWI + clinical data (AUC = 0.882, ACC = 0.760) in the validation set. Data Conclusion The clinical radiomics nomogram had good performance in estimating ER of pelvic CS patients, which would be helpful in clinical decision‐making. Level of Evidence: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2020;51:435–445.

show abstract

Radiomic features from pretreatment biparametric MRI predict prostate cancer biochemical recurrence: Preliminary findings

Abstract: 4 Technical Efficacy: Stage 5 J. Magn. Reson. Imaging 2018;48:1626-1636.

Cited by 110 publications

References 35 publications

Current status of artificial intelligence applications in urology and their potential to influence clinical practice

Current status of artificial intelligence applications in urology and their potential to influence clinical practice

Repeatability of radiomics and machine learning for DWI: Short‐term repeatability study of 112 patients with prostate cancer

Can clinical radiomics nomogram based on 3D multiparametric MRI features and clinical characteristics estimate early recurrence of pelvic chondrosarcoma?

Contact Info

Product

Resources

About