ESUR/ESUI position paper: developing artificial intelligence for precision diagnosis of prostate cancer using magnetic resonance imaging.

Artificial intelligence developments are essential to the successful deployment of community-wide, MRI-driven prostate cancer diagnosis. AI systems should ensure that the main benefits of biopsy avoidance are delivered while maintaining consistent high specificities, at a range of disease prevalences. Since all current artificial intelligence / computer-aided detection systems for prostate cancer detection are experimental, multiple developmental efforts are still needed to bring the vision to fruition. Initial work needs to focus on developing systems as diagnostic supporting aids so their results can be integrated into the radiologists' workflow including gland and target outlining tasks for fusion biopsies. Developing AI systems as clinical decision-making tools will require greater efforts. The latter encompass larger multicentric, multivendor datasets where the different needs of patients stratified by diagnostic settings, disease prevalence, patient preference, and clinical setting are considered. AI-based, robust, standard operating procedures will increase the confidence of patients and payers, thus enabling the wider adoption of the MRI-directed approach for prostate cancer diagnosis. KEY POINTS: • AI systems need to ensure that the benefits of biopsy avoidance are delivered with consistent high specificities, at a range of disease prevalence. • Initial work has focused on developing systems as diagnostic supporting aids for outlining tasks, so they can be integrated into the radiologists' workflow to support MRI-directed biopsies. • Decision support tools require a larger body of work including multicentric, multivendor studies where the clinical needs, disease prevalence, patient preferences, and clinical setting are additionally defined.

Comparison of four MRI protocols for detection of extrahepatic colorectal cancer metastases.

PURPOSE: To compare three magnetic resonance imaging (MRI) protocols containing diffusion-weighted imaging with background suppression (DWIBS) and one traditional protocol for detecting extrahepatic colorectal cancer metastases. MATERIALS AND METHODS: Thirty patients with extrahepatic colorectal cancer metastases were scanned in three stations from the skull base to the upper thighs using a 1.5T MRI system with six different MRI sequences; transverse and coronal T2 -weighted (T2 W) turbo spin-echo (TSE), coronal short tau inversion recovery (STIR), 3D T1 W TSE, DWIBS, and a contrast-enhanced T1 W 3D gradient echo (GRE) sequence. The six sequences were used to build four hypothetical MRI interpretive sets which were read by two readers in consensus, blinded to prior imaging. Lesions were categorized into 13 anatomic regions. Fluorodeoxyglucose / positron emission tomography / computed tomography (FDG-PET/CT) read with full access to prior imaging and clinical records was used as the reference standard. Sensitivity, specificity, and false discovery rate (FDR) were calculated as appropriate and receiver operating characteristic (ROC) curves were constructed. RESULTS: In all, 177 malignant lesions were detected by FDG-PET/CT and distributed in 92 out of 390 scanned anatomic regions. The sensitivity was statistically higher in two out of three sets incorporating DWIBS on a per-lesion basis (66.7%, 63.3%, and 66.7% vs. 57.6%) (P = 0.01, P = 0.11, and P = 0.01, respectively) and in all sets incorporating DWIBS on a per-region basis (75.0%, 75.0%, and 77.2 vs. 66.3%) (P = 0.04, P = 0.04, and P = 0.01, respectively). There was no difference in specificity, FDR, or AUCROC . There was no difference between sets containing DWIBS irrespective of the use of a contrast-enhanced sequence. CONCLUSION: MRI sets containing DWIBS had superior sensitivity. This sensitivity was retained when omitting a contrast-enhanced sequence. LEVEL OF EVIDENCE: 1 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2017;46:1619-1630.

Diagnostic accuracy of MR colonography with fecal tagging.

BACKGROUND: MR colonography (MRC) is a non-invasive method of examining the colon, but it is still only used in a few specialized centers on a daily basis. The purpose of this study was to evaluate the performance of MRC with improved fecal tagging vs. conventional colonoscopy (CC). METHODS: Between March 2006 and February 2007, consecutive patients who received first-time referrals to CC were asked to participate in the study. Two days prior to MRC, a new contrast mixture (barium/ferumoxsil) was ingested together with four meals each day. Standard bowel cleansing was performed before CC. MRC was evaluated by two blinded observers. MRC results were compared with CC. RESULTS: A total of 56 patients were included. The per-polyp sensitivity was 85.7% for polyps 6-10 mm and 81.3% for polyps >10 mm. The per-patient sensitivity/specificity was 100%/80% for polyps >6 mm and 100%/91.4% for polyps >10 mm. CONCLUSION: MRC showed acceptable per-patient sensitivities, but the per-polyp sensitivities are still compromised by the fecal tagging. MRC may be implemented, but at the present time MRC with fecal tagging is not ready for widespread use, although it remains a very promising diagnostic tool.

MR colonography with fecal tagging: barium vs. barium ferumoxsil.

RATIONALE AND OBJECTIVES: Both magnetic resonance (MR) and computed tomographic (CT) colonography are useful for colon examination. With sensitivities close to those for conventional colonoscopy (CC) for polyps, colonography has been proposed as an alternative to diagnostic CC. MR colonography (MRC) with fecal tagging may be a method of gaining further patient acceptance and widespread use, but the method has to be optimized. The aim of our study was to evaluate the quality of a new contrast agent mixture and to validate a new method for evaluating the tagging efficiency of contrast agents. MATERIALS AND METHODS: Twenty patients referred to CC underwent dark lumen MRC prior to the colonoscopy. Two groups of patients received two different oral contrast agents (barium sulfate and barium sulfate/ferumoxsil) as a laxative-free fecal tagging prior to the MRC. After MRC, the contrast agent was rated qualitatively (with the standard method using contrast-to-wall ratio) and subjectively (using a visual analog scale [VAS]) by three different blinded observers. RESULTS: Evaluated both qualitatively and subjectively, the tagging efficiency of barium sulfate/ferumoxsil was significantly better (P < .05) than barium sulfate alone. The VAS method for evaluating the tagging efficiency of contrast agents showed a high correlation (observer II, r = 0.91) to the standard method using contrast-to-wall ratio and also a high interclass correlation (observer II and III = 0.89/0.85). MRC found 1 of 22 (5%) polyps <6 mm, 2 of 3 (67%) polyps 6-10 mm, and 2 of 2 (100%) polyps >10 mm. CONCLUSION: MRC with fecal tagging using barium sulfate/ferumoxsil as contrast agent will give better overall assessment of the colon wall compared to barium sulfate alone. Furthermore, the VAS method of evaluating fecal tagging efficiency correlated with the standard method of calculating the contrast-to-wall ratio.

Diagnostic accuracy of three different MRI protocols in patients with inflammatory bowel disease.

BACKGROUND: Magnetic resonance imaging (MRI) is used for workup and control of inflammatory bowel disease (IBD); however, disagreement remains as to how the MRI should be performed. PURPOSE: To compare prospectively the diagnostic accuracy of MRI with neither oral nor intravenous contrast medium (plain MRI), magnetic resonance follow-through (MRFT) and MR enteroclysis (MRE) using MRE as the reference standard in patients with inflammatory bowel disease. MATERIAL AND METHODS: Plain MRI and MRE were carried out in addition to MRFT. All patients underwent both plain MR and MRFT on the same day and MRE within seven days. For the evaluation, the bowel was divided into nine segments. One radiologist, blinded to clinical findings, evaluated bowel wall thickness, diffusion weighted imaging (DWI), mural hyperenhancement, and other inflammatory changes in each bowel segment. RESULTS: Twenty patients (6 men, 14 women; median age, 43.5 years; age range, 26-76 years) underwent all three examinations; 10 with Crohn's disease (CD), three with ulcerative colitis (UC), and seven with IBD unclassified (IBD-U). Sensitivity, specificity, and accuracy were in the range of 0-75%, 81-96%, and 75-95% for wall thickening, and 0-37%, 59-89%, and 50-86% for DWI in plain MRI, respectively. Sensitivity, specificity, and accuracy were in the range of 0-50%, 96-100%, and 90-100% for wall thickening, 0-50%, 84-97%, and 82-95% for DWI, and 0-71%, 94-100%, and 85-100% for mural hyperenhancement in MRFT, respectively. CONCLUSION: The use of oral and intravenous contrast agent improves detection of bowel lesions resulting in MRFT remaining the superior choice over plain MRI for diagnostic workup in patients with IBD.

[Use of magnetic resonance imaging]. / Anvendelse af MR-skanning.

Magnetic resonance imaging (MRI) is one of the four imaging modalities used in radiology. In contrast to computed tomography (CT), it does not use radiation. MRI is still developing and the diagnostic capabilities are growing. There are many indications for MRI and in some fields it has replaced CT. With few exceptions MRI is used mainly for elective examinations, and because of the new techniques like diffusion and perfusion MRI in cancer imaging the use is increasing both with regard to work-up and follow-up. For non-malignant lesions MRI is increasingly used thanks to its great soft-tissue contrast capabilities.

[Magnetic resonance colonography: a new diagnostic tool]. / Magnetisk resonans-kolografi: et nyt diagnostisk vaerktøj.

Magnetic resonance colonography (MR colonography) is a three-dimensional imaging of the colon. Data postprocessing also allows for virtual colonoscopy, depicting the intraluminal morphology. Acquisition and postprocessing of high-resolution images require a state-of the-art modern MR scanner and a workstation. Regarding patient preparation, a bowel cleansing is necessary. The results of cancer screening have shown MR colonography to be superior to the traditional double-contrast barium enema. In inflammatory bowel disease, MR colonography can be used to assess disease activity, including spreading.