T1 and T2 MR fingerprinting measurements of prostate cancer and prostatitis correlate with deep learning–derived estimates of epithelium, lumen, and stromal composition on corresponding whole mount histopathology

Shiradkar, Rakesh; Panda, Ananya; Leo, Patrick; Janowczyk, Andrew; Farré, Xavier; Janaki, Nafiseh; Li, Lin; Pahwa, Shivani; Mahran, Amr; Buzzy, Christina; Fu, Pingfu; Elliott, Robin; MacLennan, Gregory T.; Ponsky, Lee; Gulani, Vikas; Madabhushi, Anant

doi:10.1007/s00330-020-07214-9

Cited by 29 publications

(26 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous studies have reported good to excellent repeatability and reproducibility of MRF in vivo even across MRI platforms of different field strengths (8)(9)(10)(11)(12)(13). Recent studies have demonstrated the application of MRF in the brain (4,8,9,(13)(14)(15)(16), and preliminary investigations in other body parts, including breast, liver, kidney, prostate and ovaries (2,5,10,(17)(18)(19)(20)(21)(22)(23). Furthermore, MRF has shown the potential ability in differentiating cancers from normal tissues and distinguishing primary tumours from metastases (15,20,21).…”

Section: Introductionmentioning

confidence: 99%

Repeatability of MR fingerprinting in normal cervix and utility in cervical carcinoma

Wang¹,

Perucho²,

Cao³

et al. 2021

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: Magnetic resonance fingerprinting (MRF) is a fast-imaging acquisition technique that generates quantitative and co-registered parametric maps. The aim of this feasibility study was to evaluate the agreement between MRF and phantom reference values, scan-rescan repeatability of MRF in normal cervix, and its ability to distinguish cervical carcinoma (CC) from normal cervical tissues. Methods: An International Society of Magnetic Resonance in Medicine/National Institute of Standards and Technology (ISMRM/NIST) phantom was scanned using MRF 15 times over 65 days. Agreement between MRF and phantom reference T1 and T2 values was assessed by linear regression. Healthy volunteers and patients with suspected CC were prospectively recruited. MRF was repeated twice for healthy volunteers (MRF1 and MRF2). Volumes of interest of normal cervical tissues and CC were delineated on T1 and T2 maps. MRF scan-rescan repeatability was evaluated by Bland-Altman plots, within-subject coefficients of variation (wCV), and intraclass correlation coefficients (ICC). T1 and T2 values were compared between CC and normal cervical tissues using Mann-Whitney U test. Receiver operating characteristic (ROC) analysis was performed to evaluate diagnostic efficiency. Results: Strong correlations were observed between MRF and phantom (R 2 =0.999 for T1, 0.981 for T2). Twelve healthy volunteers (28.7±5.1 years) and 28 patients with CC (54.6±15.2 years) were recruited for the in-vivo experiments. Repeatability of MRF parameters were wCV <3% for T1, <5% for T2 and ICC ≥0.92 for T1, ≥0.94 for T2. T1 value of CC (1,529±112 msec) was higher than normal mucosa [MRF1: 1,430± 129 msec, MRF2: 1,440±130 msec; P=0.031, area under the curve (AUC) ≥0.717] and normal stroma (MRF1: 1,258±101 msec, MRF2: 1,276±105 msec; P<0.001, AUC ≥0.946). T2 value of CC (69±9 msec) was lower than normal mucosa (MRF1: 88±16 msec, MRF2: 87±13 msec; P<0.001, AUC ≥0.854), but was not different from normal stroma (P=0.919).

show abstract

Section: Introductionmentioning

confidence: 99%

Repeatability of MR fingerprinting in normal cervix and utility in cervical carcinoma

Wang¹,

Perucho²,

Cao³

et al. 2021

Quant Imaging Med Surg

View full text Add to dashboard Cite

show abstract

“…Several studies have shown meaningful results of MRF in providing objective parameters to differentiate prostate cancer from normal prostate tissue [ 10 11 12 13 ]. The MRF protocol used in previous studies can take approximately 7–8 minutes to acquire images from the entire prostate gland.…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, the phantom study proved the reliability of the MRF results. We believe that MRF would also be reliable in a clinical study, since the same MRF protocols were used in both the phantom and clinical studies [ 10 11 12 13 ].…”

Section: Discussionmentioning

confidence: 99%

“…In this study, we used a new 3D MRF technique that can obtain images in less than 4 minutes. The advantages of the new MRF technique, along with the short acquisition time, include higher spatial resolution (0.6 × 0.6 mm) and smaller thickness (3 mm) than the previously used MRF technique (1 × 1 × 5 mm) [ 10 11 12 13 ]. The margin of the focal lesion was well-defined on high-resolution images.…”

Section: Discussionmentioning

confidence: 99%

“…Additionally, T1 and T2 MRF correlate well with the histological aggressiveness of prostate cancer in both the peripheral and transition zones [ 10 11 12 ]. In a recent study, significant associations were found between MRF-based parameters and the tissue compartment ratio (epithelium, stroma, and lumen) based on histopathology [ 13 ]. MRF appears to have great potential as a quantitative parameter in prostate imaging.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Feasibility of Novel Three-Dimensional Magnetic Resonance Fingerprinting of the Prostate Gland: Phantom and Clinical Studies

Han¹,

Choi

Lee

et al. 2021

Korean J Radiol

View full text Add to dashboard Cite

Objective To evaluate the feasibility of a new three-dimensional (3D) MR fingerprinting (MRF) technique for the prostate gland by conducting phantom and clinical studies. Materials and Methods The new 3D MRF technique used in this study enables quick data acquisition and has a high resolution. For the phantom study, the MRF T1 and T2 values in an in-house phantom were compared with those of gold-standard mapping methods using linear regression analysis. For the clinical study, we evaluated 90 patients who underwent prostate imaging with MRF for suspected prostate cancer between September 2019 and February 2020. The mean T1 and T2 values were compared in the peripheral zone, transition zone, and focal lesions using paired t tests. The differences in the T1 and T2 values according to cancer aggressiveness were evaluated using one-way analysis of variance. Results In the phantom study, the MRF T1 and T2 values showed a perfect correlation with the gold-standard T1 and T2 values (R > 0.99). In the clinical study, the T1 and T2 values in the peripheral zone were significantly higher than those in the transitional zone ( p < 0.001, both). The T1 and T2 values in prostate cancer were significantly lower than those in the peripheral and transitional zones. The higher the grade of cancer, the lower the T2 values. Conclusion The T1 and T2 values obtained from the 3D MRF showed a perfect correlation with the gold standard values in the phantom study. Differences in the T1 and T2 values among the different zones of the prostate gland were identified using 3D MRF in patients.

show abstract

Artificial intelligence in multiparametric magnetic resonance imaging: A review

Liu

et al. 2022

Medical Physics

View full text Add to dashboard Cite

Multiparametric magnetic resonance imaging (mpMRI) is an indispensable tool in the clinical workflow for the diagnosis and treatment planning of various diseases. Machine learning-based artificial intelligence (AI) methods, especially those adopting the deep learning technique, have been extensively employed to perform mpMRI image classification, segmentation, registration, detection, reconstruction, and super-resolution. The current availabilities of increasing computational power and fast-improving AI algorithms have empowered numerous computer-based systems for applying mpMRI to disease diagnosis, imaging-guided radiotherapy, patient risk and overall survival time prediction, and the development of advanced quantitative imaging technology for magnetic resonance fingerprinting.However,the wide application of these developed systems in the clinic is still limited by a number of factors, including robustness, reliability, and interpretability. This survey aims to provide an overview for new researchers in the field as well as radiologists with the hope that they can understand the general concepts, main application scenarios, and remaining challenges of AI in mpMRI.

show abstract

T1 and T2 MR fingerprinting measurements of prostate cancer and prostatitis correlate with deep learning–derived estimates of epithelium, lumen, and stromal composition on corresponding whole mount histopathology

Cited by 29 publications

References 34 publications

Repeatability of MR fingerprinting in normal cervix and utility in cervical carcinoma

Repeatability of MR fingerprinting in normal cervix and utility in cervical carcinoma

Feasibility of Novel Three-Dimensional Magnetic Resonance Fingerprinting of the Prostate Gland: Phantom and Clinical Studies

Artificial intelligence in multiparametric magnetic resonance imaging: A review

Contact Info

Product

Resources

About