PI-QUAL version 2: an update of a standardised scoring system for the assessment of image quality of prostate MRI.

Multiparametric MRI is the optimal primary investigation when prostate cancer is suspected, and its ability to rule in and rule out clinically significant disease relies on high-quality anatomical and functional images. Avenues for achieving consistent high-quality acquisitions include meticulous patient preparation, scanner setup, optimised pulse sequences, personnel training, and artificial intelligence systems. The impact of these interventions on the final images needs to be quantified. The prostate imaging quality (PI-QUAL) scoring system was the first standardised quantification method that demonstrated the potential for clinical benefit by relating image quality to cancer detection ability by MRI. We present the updated version of PI-QUAL (PI-QUAL v2) which applies to prostate MRI performed with or without intravenous contrast medium using a simplified 3-point scale focused on critical technical and qualitative image parameters. CLINICAL RELEVANCE STATEMENT: High image quality is crucial for prostate MRI, and the updated version of the PI-QUAL score (PI-QUAL v2) aims to address the limitations of version 1. It is now applicable to both multiparametric MRI and MRI without intravenous contrast medium. KEY POINTS: High-quality images are essential for prostate cancer diagnosis and management using MRI. PI-QUAL v2 simplifies image assessment and expands its applicability to prostate MRI without contrast medium. PI-QUAL v2 focuses on critical technical and qualitative image parameters and emphasises T2-WI and DWI.

MRI-guided Minimally Invasive Focal Therapies for Prostate Cancer.

Two cases involving patients diagnosed with localized prostate cancer and treated with MRI-guided focal therapies are presented. Patient selection procedures, techniques, outcomes, challenges, and future directions of MRI-guided focal therapies, as well as their role in the treatment of low- to intermediate-risk localized prostate cancer, are summarized.

Predicting the recurrence risk of renal cell carcinoma after nephrectomy: potential role of CT-radiomics for adjuvant treatment decisions.

OBJECTIVES: Previous trial results suggest that only a small number of patients with non-metastatic renal cell carcinoma (RCC) benefit from adjuvant therapy. We assessed whether the addition of CT-based radiomics to established clinico-pathological biomarkers improves recurrence risk prediction for adjuvant treatment decisions. METHODS: This retrospective study included 453 patients with non-metastatic RCC undergoing nephrectomy. Cox models were trained to predict disease-free survival (DFS) using post-operative biomarkers (age, stage, tumor size and grade) with and without radiomics selected on pre-operative CT. Models were assessed using C-statistic, calibration, and decision curve analyses (repeated tenfold cross-validation). RESULTS: At multivariable analysis, one of four selected radiomic features (wavelet-HHL_glcm_ClusterShade) was prognostic for DFS with an adjusted hazard ratio (HR) of 0.44 (p = 0.02), along with American Joint Committee on Cancer (AJCC) stage group (III versus I, HR 2.90; p = 0.002), grade 4 (versus grade 1, HR 8.90; p = 0.001), age (per 10 years HR 1.29; p = 0.03), and tumor size (per cm HR 1.13; p = 0.003). The discriminatory ability of the combined clinical-radiomic model (C = 0.80) was superior to that of the clinical model (C = 0.78; p < 0.001). Decision curve analysis revealed a net benefit of the combined model when used for adjuvant treatment decisions. At an exemplary threshold probability of ≥ 25% for disease recurrence within 5 years, using the combined versus the clinical model was equivalent to treating 9 additional patients (per 1000 assessed) who would recur without treatment (i.e., true-positive predictions) with no increase in false-positive predictions. CONCLUSION: Adding CT-based radiomic features to established prognostic biomarkers improved post-operative recurrence risk assessment in our internal validation study and may help guide decisions regarding adjuvant therapy. KEY POINTS: In patients with non-metastatic renal cell carcinoma undergoing nephrectomy, CT-based radiomics combined with established clinical and pathological biomarkers improved recurrence risk assessment. Compared to a clinical base model, the combined risk model enabled superior clinical utility if used to guide decisions on adjuvant treatment.

Development of a Radiomics-Based Model to Predict Graft Fibrosis in Liver Transplant Recipients: A Pilot Study.

Liver Transplantation is complicated by recurrent fibrosis in 40% of recipients. We evaluated the ability of clinical and radiomic features to flag patients at risk of developing future graft fibrosis. CT scans of 254 patients at 3-6 months post-liver transplant were retrospectively analyzed. Volumetric radiomic features were extracted from the portal phase using an Artificial Intelligence-based tool (PyRadiomics). The primary endpoint was clinically significant (≥F2) graft fibrosis. A 10-fold cross-validated LASSO model using clinical and radiomic features was developed. In total, 75 patients (29.5%) developed ≥F2 fibrosis by a median of 19 (4.3-121.8) months. The maximum liver attenuation at the venous phase (a radiomic feature reflecting venous perfusion), primary etiology, donor/recipient age, recurrence of disease, brain-dead donor, tacrolimus use at 3 months, and APRI score at 3 months were predictive of ≥F2 fibrosis. The combination of radiomics and the clinical features increased the AUC to 0.811 from 0.793 for the clinical-only model (p = 0.008) and from 0.664 for the radiomics-only model (p < 0.001) to predict future ≥F2 fibrosis. This pilot study exploring the role of radiomics demonstrates that the addition of radiomic features in a clinical model increased the model's performance. Further studies are required to investigate the generalizability of this experimental tool.

Comparison of Micro-US and Multiparametric MRI for Prostate Cancer Detection in Biopsy-Naive Men.

Background Multiparametric MRI has led to increased detection of clinically significant prostate cancer (csPCa). Micro-US is being investigated for csPCa detection. Purpose To compare multiparametric MRI and micro-US in detecting csPCa (grade group ≥2) and to determine the proportion of MRI nodules visible at micro-US for real-time targeted biopsy. Materials and methods This prospective, single-center trial enrolled biopsy-naive men with suspected prostate cancer (PCa) between May 2019 and September 2020. All patients underwent multiparametric MRI followed by micro-US; findings at both were interpreted in a blinded fashion, followed by targeted biopsy and nontargeted systematic biopsy using micro-US. Proportions were compared using the exact McNemar test. The differences in proportions were calculated. Results Ninety-four men (median age, 61 years; IQR, 57-68 years) were included. MRI- and micro-US-targeted biopsy depicted csPCa in 37 (39%) and 33 (35%) of the 94 men, respectively (P = .22); clinically insignificant PCa in 14 (15%) and 15 (16%) (P > .99); and cribriform and/or intraductal PCa in 14 (15%) and 13 (14%) (P > .99). The MRI- plus micro-US-targeted biopsy pathway depicted csPCa in 38 of the 94 (40%) men. The addition of nontargeted systematic biopsy to MRI- plus micro-US-targeted biopsy did not enable identification of any additional men with csPCa but did help identify nine additional men with clinically insignificant PCa (P = .04). Biopsy was avoided in 32 of the 94 men (34%) with MRI and nine of the 94 men (10%) with micro-US (P < .001). Among 93 MRI targets, 62 (67%) were prospectively visible at micro-US. Conclusion MRI and micro-US showed similar rates of prostate cancer detection, but more biopsies were avoided with the MRI pathway than with micro-US, with no benefit of adding nontargeted systematic biopsy to the MRI- plus micro-US-targeted biopsy pathway. Most MRI lesions were prospectively visible at micro-US, allowing real-time targeted biopsy. ClinicalTrials.gov registration no.: NCT03938376 © RSNA, 2022 Online supplemental material is available for this article.

Balancing the benefits and harms of MRI-directed biopsy pathways.

KEY POINTS: • Before a prostate biopsy, the likely benefits and the harms emanating from true and false test MRI results need to be balanced. Prioritizing patients' preferences and their tolerance to potential harms are essential to assess.• The decision curve analysis method is an analytical framework where the net clinical benefit is plotted against a range of risk thresholds of having important cancers, helping patients and their physicians to decide between cancer averse (important cancers being detected) and biopsy averse (biopsies avoided) strategies.• The decision curve analysis method showed that the incorporation of clinical risk factors with MRI findings optimizes biopsy outcomes over a range of clinically relevant risk thresholds, compared to other biopsy strategies.

Prostate biopsy in the era of MRI-targeting: towards a judicious use of additional systematic biopsy.

OBJECTIVES: We aimed to develop and compare strategies that help optimize current prostate biopsy practice by identifying patients who may forgo concurrent systematic biopsy (SBx) in favor of MRI-targeted (TBx) alone. METHODS: Retrospective study on 745 patients who underwent combined MRI-TBx plus SBx. Primary outcome was the upgrade to clinically significant prostate cancer (csPCa; grade group ≥ 2) on SBx versus MRI-TBx. Variables (age, previous biopsy status, Prostate Imaging Reporting and Data System (PI-RADS) score, index lesion size/location, number of lesions, PSA, PSA density, prostate volume) associated with the primary outcome were identified by logistic regression and used for biopsy strategies. Clinical utility was assessed by decision curve analysis (DCA). RESULTS: SBx detected 47 (6%) additional men with csPCa. The risk of detecting csPCa uniquely on SBx was significantly lower in men with PI-RADS 5 (versus PI-RADS 3: OR 0.30, p = 0.03; versus PI-RADS 4: OR 0.33, p = 0.01), and previous negative biopsy (versus previous positive biopsy: OR 0.40, p = 0.007), and increased with age (per 10 years: OR 1.64, p = 0.016). No significant association was observed for other variables. DCA identified the following strategies as most useful: (a) avoid SBx in men with PI-RADS 5 and (b) additionally in those with previous negative biopsy, resulting in avoiding SBx in 201 (27%) and 429 (58%), while missing csPCa in 5 (1%) and 15 (2%) patients, respectively. CONCLUSION: Not all men benefit equally from the combination of SBx and MRI-TBx. SBx avoidance in men with PI-RADS 5 and/or previous negative biopsy may reduce the risk of excess biopsies with a low risk of missing csPCa. KEY POINTS: • In men undergoing MRI-targeted biopsy, the risk of detecting clinically significant prostate cancer (csPCa) only on additional systematic biopsy (SBx) decreased in men with PI-RADS 5, previous negative biopsy, and younger age. • Using these variables may help select men who could avoid the risk of excess SBx. • If missing csPCa in 5% was acceptable, forgoing SBx in men with PI-RADS 5 and/or previous negative biopsy enabled the highest net reduction in SBx.

Correlation of transcriptional subtypes with a validated CT radiomics score in resectable pancreatic ductal adenocarcinoma.

OBJECTIVES: Transcriptional classifiers (Bailey, Moffitt and Collison) are key prognostic factors of pancreatic ductal adenocarcinoma (PDAC). Among these classifiers, the squamous, basal-like, and quasimesenchymal subtypes overlap and have inferior survival. Currently, only an invasive biopsy can determine these subtypes, possibly resulting in treatment delay. This study aimed to investigate the association between transcriptional subtypes and an externally validated preoperative CT-based radiomic prognostic score (Rad-score). METHODS: We retrospectively evaluated 122 patients who underwent resection for PDAC. All treatment decisions were determined at multidisciplinary tumor boards. Tumor Rad-score values from preoperative CT were dichotomized into high or llow categories. The primary endpoint was the correlation between the transcriptional subtypes and the Rad-score using multivariable linear regression, adjusting for clinical and histopathological variables (i.e., tumor size). Prediction of overall survival (OS) was secondary endpoint. RESULTS: The Bailey transcriptional classifier significantly associated with the Rad-score (coefficient = 0.31, 95% confidence interval [CI]: 0.13-0.44, p = 0.001). Squamous subtype was associated with high Rad-scores while non-squamous subtype was associated with low Rad-scores (adjusted p = 0.03). Squamous subtype and high Rad-score were both prognostic for OS at multivariable analysis with hazard ratios (HR) of 2.79 (95% CI: 1.12-6.92, p = 0.03) and 4.03 (95% CI: 1.42-11.39, p = 0.01), respectively. CONCLUSIONS: In patients with resectable PDAC, an externally validated prognostic radiomic model derived from preoperative CT is associated with the Bailey transcriptional classifier. Higher Rad-scores were correlated with the squamous subtype, while lower Rad-scores were associated with the less lethal subtypes (immunogenic, ADEX, pancreatic progenitor). KEY POINTS: • The transcriptional subtypes of PDAC have been shown to have prognostic importance but they require invasive biopsy to be assessed. • The Rad-score radiomic biomarker, which is obtained non-invasively from preoperative CT, correlates with the Bailey squamous transcriptional subtype and both are negative prognostic biomarkers. • The Rad-score is a promising non-invasive imaging biomarker for personalizing neoadjuvant approaches in patients undergoing resection for PDAC, although additional validation studies are required.

Pre-operative radiomics model for prognostication in resectable pancreatic adenocarcinoma with external validation.

OBJECTIVES: In resectable pancreatic ductal adenocarcinoma (PDAC), few pre-operative prognostic biomarkers are available. Radiomics has demonstrated potential but lacks external validation. We aimed to develop and externally validate a pre-operative clinical-radiomic prognostic model. METHODS: Retrospective international, multi-center study in resectable PDAC. The training cohort included 352 patients (pre-operative CTs from five Canadian hospitals). Cox models incorporated (a) pre-operative clinical variables (clinical), (b) clinical plus CT-radiomics, and (c) post-operative TNM model, which served as the reference. Outcomes were overall (OS)/disease-free survival (DFS). Models were assessed in the validation cohort from Ireland (n = 215, CTs from 34 hospitals), using C-statistic, calibration, and decision curve analyses. RESULTS: The radiomic signature was predictive of OS/DFS in the validation cohort, with adjusted hazard ratios (HR) 2.87 (95% CI: 1.40-5.87, p < 0.001)/5.28 (95% CI 2.35-11.86, p < 0.001), respectively, along with age 1.02 (1.01-1.04, p = 0.01)/1.02 (1.00-1.04, p = 0.03). In the validation cohort, median OS was 22.9/37 months (p = 0.0092) and DFS 14.2/29.8 (p = 0.0023) for high-/low-risk groups and calibration was moderate (mean absolute errors 7%/13% for OS at 3/5 years). The clinical-radiomic model discrimination (C = 0.545, 95%: 0.543-0.546) was higher than the clinical model alone (C = 0.497, 95% CI 0.496-0.499, p < 0.001) or TNM (C = 0.525, 95% CI: 0.524-0.526, p < 0.001). Despite superior net benefit compared to the clinical model, the clinical-radiomic model was not clinically useful for most threshold probabilities. CONCLUSION: A multi-institutional pre-operative clinical-radiomic model for resectable PDAC prognostication demonstrated superior net benefit compared to a clinical model but limited clinical utility at external validation. This reflects inherent limitations of radiomics for PDAC prognostication, when deployed in real-world settings. KEY POINTS: • At external validation, a pre-operative clinical-radiomics prognostic model for pancreatic ductal adenocarcinoma (PDAC) outperformed pre-operative clinical variables alone or pathological TNM staging. • Discrimination and clinical utility of the clinical-radiomic model for treatment decisions remained low, likely due to heterogeneity of CT acquisition parameters. • Despite small improvements, prognosis in PDAC using state-of-the-art radiomics methodology remains challenging, mostly owing to its low discriminative ability. Future research should focus on standardization of CT protocols and acquisition parameters.

Artificial Intelligence for Automated Cancer Detection on Prostate MRI: Opportunities and Ongoing Challenges, From the AJR Special Series on AI Applications.

Use of prostate MRI has increased greatly in the past decade, primarily in directing targeted prostate biopsy. However, prostate MRI interpretation remains prone to interreader variation. Artificial intelligence (AI) has the potential to standardize detection of lesions on MRI that are suspicious for prostate cancer (PCa). The purpose of this review is to explore the current status of AI for the automated detection of PCa on MRI. Recent literature describing promising results regarding AI models for PCa detection on MRI is highlighted. Numerous limitations of the existing literature are also described, including biases in model validation, heterogeneity in reporting of performance metrics, and lack of sufficient evidence of clinical translation. Challenges related to AI ethics and data governance are also discussed. An outlook is provided for AI in lesion detection on prostate MRI in the coming years, emphasizing current research needs. Future investigations, incorporating large-scale diverse multiinstitutional training and testing datasets, are anticipated to enable the development of more robust AI models for PCa detection on MRI, though prospective clinical trials will ultimately be required to establish benefit of AI in patient management.

Radiomics in Abdominopelvic Solid-Organ Oncologic Imaging: Current Status.

Radiomics is the process of extraction of high-throughput quantitative imaging features from medical images. These features represent noninvasive quantitative biomarkers that go beyond the traditional imaging features visible to the human eye. This article first reviews the steps of the radiomics pipeline, including image acquisition, ROI selection and image segmentation, image preprocessing, feature extraction, feature selection, and model development and application. Current evidence for the application of radiomics in abdominopelvic solid-organ cancers is then reviewed. Applications including diagnosis, subtype determination, treatment response assessment, and outcome prediction are explored within the context of hepatobiliary and pancreatic cancer, renal cell carcinoma, prostate cancer, gynecologic cancer, and adrenal masses. This literature review focuses on the strongest available evidence, including systematic reviews, meta-analyses, and large multicenter studies. Limitations of the available literature are highlighted, including marked heterogeneity in radiomics methodology, frequent use of small sample sizes with high risk of overfitting, and lack of prospective design, external validation, and standardized radiomics workflow. Thus, although studies have laid a foundation that supports continued investigation into radiomics models, stronger evidence is needed before clinical adoption.

Exploring the value of using patient-oriented MRI reports in clinical practice - a pilot study.

PURPOSE: Standard radiology reports (SRR) are designed to communicate information between doctors. With many patients having instantaneous access to SRRs on patient portals, interpretation without guidance from doctors can cause anxiety and panic. In this pilot study, we designed a patient-centred prostate MRI template report (PACERR) to address some of these challenges and tested whether PACERRs improve patient knowledge and experience. MATERIALS AND METHODS: Patients booked for clinical prostate MRI were randomly assigned to SRR or SRR + PACERR. Questionnaires included multiple-choice that targeted 4 domains (understanding, usefulness, next steps, emotional experience) hypothesized to improve with patient-centred reports and short answer questions, testing knowledge regarding MRI results. Clinical encounters were observed and recorded to explore whether adding PACERR improved communication. Likert scaled-responses and short-answer questions were compared using Mann-Whitney U test and Kruskal-Wallis test. RESULTS: Of the 40 participants, the majority were MRI naïve (70%). Patients receiving a PACERR had higher scores in the categories of patient understanding (mean: 4.17 vs. 3.39, p=0.006), usefulness (mean: 4.58 vs. 3.07, p<0.001), and identifying next steps (mean: 1.89 vs. 3.03, p=0.003) but not emotional experience (mean: 4.18 vs. 3.79, p=0.22). PACERR participants found the layout and design more patient friendly (mean: 4.47 vs. 2.61, p<0.001) and easier to understand (mean: 4.37 vs. 2.38, p<0.001). In the knowledge section, overall, the PACERR arm scored better (87% vs. 56%, p=0.004). CONCLUSION: With the addition of prostate MRI PACERR, participants had better understanding of their results and felt more prepared to involve themselves in discussions with their doctor.

Canadian Association of Radiologists Prostate MRI White Paper.

Prostate cancer is the most common malignancy and the third most common cause of death in Canadian men. In light of evolving diagnostic pathways for prostate cancer and the increased use of MRI, which now includes its use in men prior to biopsy, the Canadian Association of Radiologists established a Prostate MRI Working Group to produce a white paper to provide recommendations on establishing and maintaining a Prostate MRI Programme in the context of the Canadian healthcare system. The recommendations, which are based on available scientific evidence and/or expert consensus, are intended to maintain quality in image acquisition, interpretation, reporting and targeted biopsy to ensure optimal patient care. The paper covers technique, reporting, quality assurance and targeted biopsy considerations and includes appendices detailing suggested reporting templates, quality assessment tools and sample image acquisition protocols relevant to the Canadian healthcare context.

Avoiding Unnecessary Biopsy: MRI-based Risk Models versus a PI-RADS and PSA Density Strategy for Clinically Significant Prostate Cancer.

Background In validation studies, risk models for clinically significant prostate cancer (csPCa; Gleason score ≥3+4) combining multiparametric MRI and clinical factors have demonstrated poor calibration (over- and underprediction) and limited use in avoiding unnecessary prostate biopsies. Purpose MRI-based risk models following local recalibration were compared with a strategy that combined Prostate Imaging Data and Reporting System (PI-RADS; version 2) and prostate-specific antigen density (PSAd) to assess the potential reduction of unnecessary prostate biopsies. Materials and Methods This retrospective study included 385 patients without prostate cancer diagnosis who underwent multipara-metric MRI (PI-RADS category ≥3) and MRI-targeted biopsy between 2015 and 2019. Recalibration and selection of the best-performing MRI model (MRI-European Randomized Study of Screening for Prostate Cancer [ERSPC], van Leeuwen, Radtke, and Mehralivand models) were undertaken in cohort C1 (n = 242; 2015-2017). The impact on biopsy decisions was compared with an alternative strategy (no biopsy for PI-RADS category 3 plus PSAd < 0.1 ng/mL per milliliter) in cohort C2 (n = 143; 2018-2019). Discrimination, calibration, and clinical utility were assessed by using the area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis, respectively. Results The prevalence of csPCa was 38% (93 of 242 patients) and 45% (64 of 143 patients) in cohorts C1 and C2, respectively. Decision curve analysis demonstrated the highest net benefit for the van Leeuwen and Mehralivand models in C1. Used for biopsy decisions in C2, van Leeuwen (AUC, 0.84; 95% CI: 0.77, 0.9) and Mehralivand (AUC, 0.79; 95% CI: 0.72, 0.86) enabled no net benefit at a risk threshold of 10%. Up to a risk threshold of 15%, net benefit remained inferior to the PI-RADS plus PSAd strategy, which avoided biopsy in 63 per 1000 men, without missing csPCa. Without prior recalibration in C1, three of four models (MRIERSPC, Radtke, Mehralivand) were poorly calibrated and not clinically useful in C2. Conclusion The number of unnecessary prostate biopsies in men with positive MRI may be safely reduced by using a prostate-specific antigen density-based strategy. In a risk-averse scenario, this strategy enabled better biopsy decisions compared with MRI-based risk models. ©RSNA, 2021 Online supplemental material is available for this article.

MRI-guided Focused Ultrasound Ablation for Localized Intermediate-Risk Prostate Cancer: Early Results of a Phase II Trial.

Background To reduce adverse effects of whole-gland therapy, participants with localized clinically significant prostate cancer can undergo MRI-guided focal therapy. Purpose To explore safety and early oncologic and functional outcomes of targeted focal high-intensity focused ultrasound performed under MRI-guided focused ultrasound for intermediate-risk clinically significant prostate cancer. Materials and Methods In this prospective phase II trial, between February 2016 and July 2019, men with unifocal clinically significant prostate cancer visible at MRI were treated with transrectal MRI-guided focused ultrasound. The primary end point was the 5-month biopsy (last recorded in December 2019) with continuation to the 24-month follow-up projected to December 2021. Real-time ablation monitoring was performed with MR thermography. Nonperfused volume was measured at treatment completion. Periprocedural complications were recorded. Follow-up included International Prostate Symptom Score (IPSS) and International Index of Erectile Function-15 (IIEF-15) score at 6 weeks and 5 months, and multiparametric MRI and targeted biopsy of the treated area at 5 months. The generalized estimating equation model was used for statistical analysis, and the Holm method was used to adjust P value. Results Treatment was successfully completed in all 44 men, 36 with grade group (GG) 2 and eight with GG 3 disease (median age, 67 years; interquartile range [IQR], 62-70 years). No major treatment-related adverse events occurred. Forty-one of 44 participants (93%; 95% CI: 82, 98) were free of clinically significant prostate cancer (≥6 mm GG 1 disease or any volume ≥GG 2 disease) at the treatment site at 5-month biopsy (median, seven cores). Median IIEF-15 and IPSS scores were similar at baseline and at 5 months (IIEF-15 score at baseline, 61 [IQR, 34-67] and at 5 months, 53 [IQR, 24-65.5], P = .18; IPSS score at baseline, 3.5 [IQR, 1.8-7] and at 5 months, 6 [IQR, 2-7.3], P = .43). Larger ablations (≥15 cm3) compared with smaller ones were associated with a decline in IIEF-15 scores at 6 weeks (adjusted P < .01) and at 5 months (adjusted P = .07). Conclusion Targeted focal therapy of intermediate-risk prostate cancer performed with MRI-guided focused ultrasound ablation was safe and had encouraging early oncologic and functional outcomes. © RSNA, 2021 Online supplemental material is available for this article See also the editorial by Tempany-Afdhal in this issue.

Can machine learning radiomics provide pre-operative differentiation of combined hepatocellular cholangiocarcinoma from hepatocellular carcinoma and cholangiocarcinoma to inform optimal treatment planning?

OBJECTIVE: To differentiate combined hepatocellular cholangiocarcinoma (cHCC-CC) from cholangiocarcinoma (CC) and hepatocellular carcinoma (HCC) using machine learning on MRI and CT radiomics features. METHODS: This retrospective study included 85 patients aged 32 to 86 years with 86 histopathology-proven liver cancers: 24 cHCC-CC, 24 CC, and 38 HCC who had MRI and CT between 2004 and 2018. Initial CT reports and morphological evaluation of MRI features were used to assess the performance of radiologists read. Following tumor segmentation, 1419 radiomics features were extracted using PyRadiomics library and reduced to 20 principle components by principal component analysis. Support vector machine classifier was utilized to evaluate MRI and CT radiomics features for the prediction of cHCC-CC vs. non-cHCC-CC and HCC vs. non-HCC. Histopathology was the reference standard for all tumors. RESULTS: Radiomics MRI features demonstrated the best performance for differentiation of cHCC-CC from non-cHCC-CC with the highest AUC of 0.77 (SD 0.19) while CT was of limited value. Contrast-enhanced MRI phases and pre-contrast and portal-phase CT showed excellent performance for the differentiation of HCC from non-HCC (AUC of 0.79 (SD 0.07) to 0.81 (SD 0.13) for MRI and AUC of 0.81 (SD 0.06) and 0.71 (SD 0.15) for CT phases, respectively). The misdiagnosis of cHCC-CC as HCC or CC using radiologists read was 69% for CT and 58% for MRI. CONCLUSIONS: Our results demonstrate promising predictive performance of MRI and CT radiomics features using machine learning analysis for differentiation of cHCC-CC from HCC and CC with potential implications for treatment decisions. KEY POINTS: • Retrospective study demonstrated promising predictive performance of MRI radiomics features in the differentiation of cHCC-CC from HCC and CC and of CT radiomics features in the differentiation of HCC from cHCC-CC and CC. • With future validation, radiomics analysis has the potential to inform current clinical practice for the pre-operative diagnosis of cHCC-CC and to enable optimal treatment decisions regards liver resection and transplantation.

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.

Prognostic value of early changes in CT-measured body composition in patients receiving chemotherapy for unresectable pancreatic cancer.

OBJECTIVES: Skeletal muscle mass is a prognostic factor in pancreatic ductal adenocarcinoma (PDAC). However, it remains unclear whether changes in body composition provide an incremental prognostic value to established risk factors, especially the Response Evaluation Criteria in Solid Tumors version 1.1 (RECISTv1.1). The aim of this study was to determine the prognostic value of CT-quantified body composition changes in patients with unresectable PDAC starting chemotherapy. METHODS: We retrospectively evaluated 105 patients with unresectable (locally advanced or metastatic) PDAC treated with FOLFIRINOX (n = 64) or gemcitabine-based (n = 41) first-line chemotherapy within a multicenter prospective trial. Changes (Δ) in skeletal muscle index (SMI), subcutaneous (SATI), and visceral adipose tissue index (VATI) between pre-chemotherapy and first follow-up CT were assessed. Cox regression models and covariate-adjusted survival curves were used to identify predictors of overall survival (OS). RESULTS: At multivariable analysis, adjusting for RECISTv1.1-response at first follow-up, ΔSMI was prognostic for OS with a hazard ratio (HR) of 1.2 (95% CI: 1.08-1.33, p = 0.001). No significant association with OS was observed for ΔSATI (HR: 1, 95% CI: 0.97-1.04, p = 0.88) and ΔVATI (HR: 1.01, 95% CI: 0.99-1.04, p = 0.33). At an optimal cutoff of 2.8 cm2/m2 per 30 days, the median survival of patients with high versus low ΔSMI was 143 versus 233 days (p < 0.001). CONCLUSIONS: Patients with a lower rate of skeletal muscle loss at first follow-up demonstrated improved survival for unresectable PDAC, regardless of their RECISTv1.1-category. Assessing ΔSMI at the first follow-up CT may be useful for prognostication, in addition to routine radiological assessment. KEY POINTS: • In patients with unresectable pancreatic ductal adenocarcinoma, change of skeletal muscle index (ΔSMI) in the early phase of chemotherapy is prognostic for overall survival, even after adjusting for Response Evaluation Criteria in Solid Tumors version 1.1 (RECISTv1.1) assessment at first follow-up. • Changes in adipose tissue compartments at first follow-up demonstrated no significant association with overall survival. • Integrating ΔSMI into routine radiological assessment may improve prognostic stratification and impact treatment decision-making at the first follow-up.

PI-RADS Committee Position on MRI Without Contrast Medium in Biopsy-Naive Men With Suspected Prostate Cancer: Narrative Review.

The steadily increasing demand for diagnostic prostate MRI has led to concerns regarding the lack of access to and the availability of qualified MRI scanners and sufficiently experienced radiologists, radiographers, and technologists to meet the demand. Solutions must enhance operational benefits without compromising diagnostic performance, quality, and delivery of service. Solutions should also mitigate risks such as decreased reader confidence and referrer engagement. One approach may be the implementation of MRI without the use gadolinium-based contrast medium (bipara-metric MRI), but only if certain prerequisites such as high-quality imaging, expert interpretation quality, and availability of patient recall or on-table monitoring are mandated. Alternatively, or in combination, a clinical risk-based approach could be used for protocol selection, specifically, which biopsy-naive men need MRI with contrast medium (multiparametric MRI). There is a need for prospective studies in which biopsy decisions are made according to MRI without contrast enhancement. Such studies must define clinical and operational benefits and identify which patient groups can be scanned successfully without contrast enhancement. These higher-quality data are needed before the Prostate Imaging Reporting and Data System (PI-RADS) Committee can make evidence-based recommendations about MRI without contrast enhancement as an initial diagnostic approach for prostate cancer workup.

A Comprehensive Study of Data Augmentation Strategies for Prostate Cancer Detection in Diffusion-Weighted MRI Using Convolutional Neural Networks.

Data augmentation refers to a group of techniques whose goal is to battle limited amount of available data to improve model generalization and push sample distribution toward the true distribution. While different augmentation strategies and their combinations have been investigated for various computer vision tasks in the context of deep learning, a specific work in the domain of medical imaging is rare and to the best of our knowledge, there has been no dedicated work on exploring the effects of various augmentation methods on the performance of deep learning models in prostate cancer detection. In this work, we have statically applied five most frequently used augmentation techniques (random rotation, horizontal flip, vertical flip, random crop, and translation) to prostate diffusion-weighted magnetic resonance imaging training dataset of 217 patients separately and evaluated the effect of each method on the accuracy of prostate cancer detection. The augmentation algorithms were applied independently to each data channel and a shallow as well as a deep convolutional neural network (CNN) was trained on the five augmented sets separately. We used area under receiver operating characteristic (ROC) curve (AUC) to evaluate the performance of the trained CNNs on a separate test set of 95 patients, using a validation set of 102 patients for finetuning. The shallow network outperformed the deep network with the best 2D slice-based AUC of 0.85 obtained by the rotation method.