Risk and Prognostics of Second Primary Cancer After Prostate Radiation Therapy.

INTRODUCTION: As overall survival in prostate cancer increases due to advances in early detection and management, there is a growing need to understand the long-term morbidity associated with treatment, including secondary tumors. The significance of developing radiation-associated secondary cancers in an elderly population remains unknown. METHODS: Patients diagnosed with prostate cancer between 1975 and 2016 in one of 9 Surveillance, Epidemiology, and End Results registries were included in this study. Risk of second primary pelvic malignancies (SPPMs) were assessed with death as a competing risk using the Fine-Gray model. Time-varying Cox proportional hazard models were employed to analyze risk to overall mortality based on secondary tumor status. RESULTS: A total of 569,167 primary prostate cancers were included in analysis with an average follow-up of 89 months. Among all prostate cancer patients, 4956 SPPMs were identified. After controlling for differences in age, year of diagnosis, and surgery at time of prostate cancer treatment, radiation receipt was associated with a significantly higher incidence of SPPMs (1.1% vs 1.8% at 25 years). Among those who received radiation during initial prostate cancer treatment (n = 195,415), developing an SPPM is significantly associated with worse survival (adjusted hazard ratio = 1.76), especially among younger patients (under age 63, adjusted hazard ratio = 2.36). CONCLUSIONS: While developing a secondary malignancy carries a detrimental effect on overall survival, the absolute risk of developing such tumors is exceedingly low regardless of radiation treatment.

A Tool to Integrate Electrophysiological Mapping for Cardiac Radioablation of Ventricular Tachycardia.

Purpose: Cardiac radioablation is an emerging therapy for recurrent ventricular tachycardia. Electrophysiology (EP) data, including electroanatomic maps (EAM) and electrocardiographic imaging (ECGI), provide crucial information for defining the arrhythmogenic target volume. The absence of standardized workflows and software tools to integrate the EP maps into a radiation planning system limits their use. This study developed a comprehensive software tool to enable efficient utilization of the mapping for cardiac radioablation treatment planning. Methods and Materials: The tool, HeaRTmap, is a Python-scripted plug-in module on the open-source 3D Slicer software platform. HeaRTmap is able to import EAM and ECGI data and visualize the maps in 3D Slicer. The EAM is translated into a 3D space by registration with cardiac magnetic resonance images (MRI) or computed tomography (CT). After the scar area is outlined on the mapping surface, the tool extracts and extends the annotated patch into a closed surface and converts it into a structure set associated with the anatomic images. The tool then exports the structure set and the images as The Digital Imaging and Communications in Medicine Standard in Radiotherapy for a radiation treatment planning system to import. Overlapping the scar structure on simulation CT, a transmural target volume is delineated for treatment planning. Results: The tool has been used to transfer Ensite NavX EAM data into the Varian Eclipse treatment planning system in radioablation on 2 patients with ventricular tachycardia. The ECGI data from CardioInsight was retrospectively evaluated using the tool to derive the target volume for a patient with left ventricular assist device, showing volumetric matching with the clinically used target with a Dice coefficient of 0.71. Conclusions: HeaRTmap smoothly fuses EP information from different mapping systems with simulation CT for accurate definition of radiation target volume. The efficient integration of EP data into treatment planning potentially facilitates the study and adoption of the technique.

Contrast-enhanced digital breast tomosythesis and breast MRI to monitor response to neoadjuvant chemotherapy: patient tolerance and preference.

OBJECTIVE: Contrast-enhanced digital breast tomosynthesis (CE-DBT) is a novel imaging technique, combining contrast-enhanced spectral mammography and tomosynthesis. This may offer an alternative imaging technique to breast MRI for monitoring of response to neoadjuvant chemotherapy. This paper addresses patient experience and preference regarding the two techniques. METHODS: Conducted as part of a prospective pilot study; patients were asked to complete questionnaires pertaining to their experience of CE-DBT and MRI following pre-treatment and end-of-treatment imaging. Questionnaires consisted of eight questions answered on a categorical scale, two using a visual analogue scale (VAS), and a question to indicate preference of imaging technique. Statistical analysis was performed with Wilcoxon signed rank test and McNemar test for related samples using SPSS v. 25. RESULTS: 18 patients were enrolled in the pilot study. Matched CE-DBT and MRI questionnaires were completed after 22 patient episodes. Patient preference was indicated after 31 patient episodes. Overall, on 77% of occasions patients preferred CE-DBT with no difference between pre-treatment and end-of-treatment imaging. Overall experience (p = 0.008), non-breast pain (p = 0.046), anxiety measured using VAS (p = 0.003), and feeling of being put at ease by staff (p = 0.023) was better for CE-DBT. However, more breast pain was experienced during CE-DBT when measured on both VAS (p = 0.011) and categorical scale (p = 0.021). CONCLUSION: Our paper suggests that patients prefer CE-DBT to MRI, adding further evidence in favour of contrast-enhanced mammographic techniques. ADVANCES IN KNOWLEDGE: Contrast mammographic techniques offer an alternative, more accessible imaging technique to breast MRI. Whilst other studies have addressed patient experience of contrast-enhanced spectral mammography, this is the first study to directly explore patient preference for CE-DBT over MRI in the setting of neoadjuvant chemotherapy, finding that overall, patients preferred CE-DBT despite the relatively long breast compression.

Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge.

Artificial intelligence (AI) has shown promise for diagnosing prostate cancer in biopsies. However, results have been limited to individual studies, lacking validation in multinational settings. Competitions have been shown to be accelerators for medical imaging innovations, but their impact is hindered by lack of reproducibility and independent validation. With this in mind, we organized the PANDA challenge-the largest histopathology competition to date, joined by 1,290 developers-to catalyze development of reproducible AI algorithms for Gleason grading using 10,616 digitized prostate biopsies. We validated that a diverse set of submitted algorithms reached pathologist-level performance on independent cross-continental cohorts, fully blinded to the algorithm developers. On United States and European external validation sets, the algorithms achieved agreements of 0.862 (quadratically weighted κ, 95% confidence interval (CI), 0.840-0.884) and 0.868 (95% CI, 0.835-0.900) with expert uropathologists. Successful generalization across different patient populations, laboratories and reference standards, achieved by a variety of algorithmic approaches, warrants evaluating AI-based Gleason grading in prospective clinical trials.

Validating Whole Slide Imaging Systems for Diagnostic Purposes in Pathology.

CONTEXT.­: The original guideline, "Validating Whole Slide Imaging for Diagnostic Purposes in Pathology," was published in 2013 and included 12 guideline statements. The College of American Pathologists convened an expert panel to update the guideline following standards established by the National Academies of Medicine for developing trustworthy clinical practice guidelines. OBJECTIVE.­: To assess evidence published since the release of the original guideline and provide updated recommendations for validating whole slide imaging (WSI) systems used for diagnostic purposes. DESIGN.­: An expert panel performed a systematic review of the literature. Frozen sections, anatomic pathology specimens (biopsies, curettings, and resections), and hematopathology cases were included. Cytology cases were excluded. Using the Grading of Recommendations Assessment, Development, and Evaluation approach, the panel reassessed and updated the original guideline recommendations. RESULTS.­: Three strong recommendations and 9 good practice statements are offered to assist laboratories with validating WSI digital pathology systems. CONCLUSIONS.­: Systematic review of literature following release of the 2013 guideline reaffirms the use of a validation set of at least 60 cases, establishing intraobserver diagnostic concordance between WSI and glass slides and the use of a 2-week washout period between modalities. Although all discordances between WSI and glass slide diagnoses discovered during validation need to be reconciled, laboratories should be particularly concerned if their overall WSI-glass slide concordance is less than 95%.

ISUP Consensus Definition of Cribriform Pattern Prostate Cancer.

The presence of a cribriform pattern is now recognized as a clinically important, independent adverse prognostic indicator for prostate cancer. For this reason the International Society of Urological Pathology (ISUP) recently recommended its inclusion in standard reporting. In order to improve interobserver agreement as to the diagnosis of cribriform patterns, the ISUP assembled an international panel of 12 expert urogenital pathologists for the purpose of drafting a consensus definition of cribriform pattern in prostate cancer, and provide their opinions on a set of 32 images and on potential diagnostic criteria. These images were selected by the 2 nonvoting convenors of the study and included the main categories where disagreement was anticipated. The Delphi method was applied to promote consensus among the 12 panelists in their review of the images during 2 initial rounds of the study. Following a virtual meeting, convened to discuss selected images and diagnostic criteria, the following definition for cribriform pattern in prostate cancer was approved: "A confluent sheet of contiguous malignant epithelial cells with multiple glandular lumina that are easily visible at low power (objective magnification ×10). There should be no intervening stroma or mucin separating individual or fused glandular structures" together with a set of explanatory notes. We believe this consensus definition to be practical and that it will facilitate reproducible recognition and reporting of this clinically important pattern commonly seen in prostate cancer. The images and the results of the final Delphi round are available at the ISUP website as an educational slide set (https://isupweb.org/isup/blog/slideshow/cribriform-slide-deck/).

Cribriform prostate cancer: Morphologic criteria enabling a diagnosis, based on survey of experts.

Among four sub-patterns of Gleason grade 4 prostate cancer, voluminous evidence supports that the cribriform pattern holds an unfavorable prognostic impact, as compared with poorly-formed, fused, or glomeruloid. The International Society of Urological Pathology (ISUP) recommends specifying whether invasive grade 4 cancer is cribriform. Recently, ISUP experts published a consensus definition of cribriform pattern highlighting criteria that distinguish it from mimickers. The current study aimed to analyze morphologic features separately to identify those that define the essence of the cribriform pattern. Thirty-two selected photomicrographs were classified by 12 urologic pathologists as: definitely cribriform cancer, probably cribriform, unsure, probably not cribriform, or definitely not cribriform. Consensus was defined as 9/12 agree or disagree, with ≤1 strongly supporting the opposite choice. Final consensus was achieved in 21 of 32 cases. Generalized estimating equation (GEE) model with logit link was fitted to estimate effect of multiple morphologic predictors. Fisher exact test was used for categorical findings. Presence of intervening stroma precluded calling cribriform cancer (p = 0.006). Mucin presence detracted (p = 0.003) from willingness to call cribriform cancer (only 3 cases had mucin). Lumen number was associated with cribriform consensus (p = 0.0006), and all consensus cases had ≥9 lumens. Predominant papillary pattern or an irregular outer boundary detracted (p = NS). Invasive cribriform carcinoma should have absence of intervening stroma, and usually neither papillary pattern, irregular outer boundary, nor very few lumens. Setting the criteria for cribriform will help prevent over- or undercalling this important finding.

Digital breast tomosynthesis: sensitivity for cancer in younger symptomatic women.

OBJECTIVE: Full-field digital mammography (FFDM) has limited sensitivity for cancer in younger women with denser breasts. Digital breast tomosynthesis (DBT) can reduce the risk of cancer being obscured by overlying tissue. The primary study aim was to compare the sensitivity of FFDM, DBT and FFDM-plus-DBT in women under 60 years old with clinical suspicion of breast cancer. METHODS: This multicentre study recruited 446 patients from UK breast clinics. Participants underwent both standard FFDM and DBT. A blinded retrospective multireader study involving 12 readers and 300 mammograms (152 malignant and 148 benign cases) was conducted. RESULTS: Sensitivity for cancer was 86.6% with FFDM [95% CI (85.2-88.0%)], 89.1% with DBT [95% CI (88.2-90%)], and 91.7% with FFDM+DBT [95% CI (90.7-92.6%)]. In the densest breasts, the maximum sensitivity increment with FFDM +DBT over FFDM alone was 10.3%, varying by density measurement method. Overall specificity was 81.4% with FFDM [95% CI (80.5-82.3%)], 84.6% with DBT [95% CI (83.9-85.3%)], and 79.6% with FFDM +DBT [95% CI (79.0-80.2%)]. No differences were detected in accuracy of tumour measurement in unifocal cases. CONCLUSIONS: Where available, DBT merits first-line use in the under 60 age group in symptomatic breast clinics, particularly in women known to have very dense breasts. ADVANCES IN KNOWLEDGE: This study is one of very few to address the accuracy of DBT in symptomatic rather than screening patients. It quantifies the diagnostic gains of DBT in direct comparison with standard digital mammography, supporting informed decisions on appropriate use of DBT in this population.

Investigating Urinary Circular RNA Biomarkers for Improved Detection of Renal Cell Carcinoma.

Renal cell carcinomas (RCC) are usually asymptomatic until late stages, posing several challenges for early detection of malignant disease. Non-invasive liquid biopsy biomarkers are emerging as an important diagnostic tool which could aid with routine screening of RCCs. Circular RNAs (circRNAs) are novel non-coding RNAs that play diverse roles in carcinogenesis. They are promising biomarkers due to their stability and ease of detection in small quantities from non-invasive sources such as urine. In this study, we analyzed the expression of various circRNAs that were previously identified in RCC tumors (circEGLN3, circABCB10, circSOD2 and circACAD11) in urinary sediment samples from non-neoplastic controls, patients with benign renal tumors, and clear cell RCC (ccRCC) patients. We observed significantly reduced levels of circEGLN3 and circSOD2 in urine from ccRCC patients compared to healthy controls. We also assessed the linear variant of EGLN3 and found differential expression between patients with benign tumors compared to ccRCC patients. These findings highlight the potential of circRNA markers as non-invasive diagnostic tools to detect malignant RCC.

Early-onset renal cell carcinoma in PTEN harmatoma tumour syndrome.

Individuals with PTEN hamartoma tumour syndrome (PHTS), including Cowden syndrome (CS), are susceptible to multiple benign hamartomas and an increased risk of cancer, particularly breast, endometrial, and thyroid. As a result, individuals undergo enhanced surveillance for early detection of these cancers. However, less commonly occurring cancers, such as colorectal and kidney, have insufficient guidelines for early detection. Currently, screening for kidney cancer via renal ultrasound begins at 40 years of age, because there were only rare cases of elevated risk in prospective series under 40. There have, however, been accumulating reports of kidney cancer in individuals with CS in their 30s, illustrating a need to lower the age of surveillance. We present additional evidence of renal cell carcinoma in two individuals with CS in their early twenties, and propose a reassessment of the abdominal surveillance in patients with PHTS. We propose biannual screening for kidney cancer beginning at 20 years of age.

Unsupervised Resolution of Histomorphologic Heterogeneity in Renal Cell Carcinoma Using a Brain Tumor-Educated Neural Network.

PURPOSE: Applications of deep learning to histopathology have proven capable of expert-level performance, but approaches have largely focused on supervised classification tasks requiring context-specific training and deployment. More generalizable workflows that can be easily shared across subspecialties could help accelerate and broaden adoption. Here, we hypothesized that histology-optimized feature representations, generated by a convolutional neural network (CNN) during supervised learning, are transferable and can resolve meaningful differences in large-scale, discovery-type unsupervised analyses. METHODS: We used a CNN, previously trained to recognize brain tumor histomorphologies, to extract 512 feature representations from > 550 digital whole-slide images (WSIs) of renal cell carcinomas (RCCs) from The Cancer Genome Atlas and other previously unencountered tumors. We use these extracted feature vectors to conduct unsupervised image-set clustering and analyze the clinical and biologic relevance of the intra- and interpatient subgroups generated. RESULTS: Within individual WSIs, feature-based clustering could reliably segment tumor regions and other relevant histopathologic subpatterns (eg, adenosquamous and poorly differentiated regions). Across the larger RCC cohorts, clustering extracted features generated subgroups enriched for clinically relevant subtypes (eg, papillary RCC) and outcomes (eg, survival). Importantly, individual feature activation mapping highlighted salient subtype-specific patterns and features of malignancies (eg, nuclear grade, sarcomatous change) contributing to subgroupings. Moreover, some proposed clusters were enriched for recurring, human-based RCC-subtype misclassifications. CONCLUSION: Our data support that CNNs, pretrained on large histologic datasets, can extend learned representations to novel scenarios and resolve clinically relevant intra- and interpatient tissue-pattern differences without explicit instruction or additional optimization. Repositioning of existing histology-educated networks could provide scalable approaches for image classification, quality assurance, and discovery of unappreciated patterns and subgroups of disease.

Small Renal Mass Surveillance: Histology-specific Growth Rates in a Biopsy-characterized Cohort.

BACKGROUND: Most reports of active surveillance (AS) of small renal masses (SRMs) lack biopsy confirmation, and therefore include benign tumors and different subtypes of renal cell carcinoma (RCC). OBJECTIVE: We compared the growth rates and progression of different histologic subtypes of RCC SRMs (SRMRCC) in the largest cohort of patients with biopsy-characterized SRMs on AS. DESIGN, SETTING, AND PARTICIPANTS: Data from patients in a multicenter Canadian trial and a Princess Margaret cohort were combined to include 136 biopsy-proven SRMRCC lesions managed by AS, with treatment deferred until progression or patient/surgeon decision. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: Growth curves were estimated from serial tumor size measures. Tumor progression was defined by sustained size ≥4 cm or volume doubling within 1 yr. RESULTS AND LIMITATIONS: Median follow-up for patients who remained on AS was 5.8 yr (interquartile range 3.4-7.5 yr). Clear cell RCC SRMs (SRMccRCC) grew faster than papillary type 1 SRMs (0.25 and 0.02 cm/yr on average, respectively, p = 0.0003). Overall, 60 SRMRCC lesions progressed: 49 (82%) by rapid growth (volume doubling), seven (12%) increasing to ≥4 cm, and four (6.7%) by both criteria. Six patients developed metastases, and all were of clear cell RCC histology. Limitations include the use of different imaging modalities and a lack of central imaging review. CONCLUSIONS: Tumor growth varies between histologic subtypes of SRMRCC and among SRMccRCC, which likely reflects individual host and tumor biology. Without validated biomarkers that predict this variation, initial follow-up of histologically characterized SRMs can inform personalized treatment for patients on AS. PATIENT SUMMARY: Many small kidney cancers are suitable for surveillance and can be monitored over time for change. We demonstrate that different types of kidney cancers grow at different rates and are at different risks of progression. These results may guide better personalized treatment.

Development and Validation of a Deep Learning Algorithm for Gleason Grading of Prostate Cancer From Biopsy Specimens.

Importance: For prostate cancer, Gleason grading of the biopsy specimen plays a pivotal role in determining case management. However, Gleason grading is associated with substantial interobserver variability, resulting in a need for decision support tools to improve the reproducibility of Gleason grading in routine clinical practice. Objective: To evaluate the ability of a deep learning system (DLS) to grade diagnostic prostate biopsy specimens. Design, Setting, and Participants: The DLS was evaluated using 752 deidentified digitized images of formalin-fixed paraffin-embedded prostate needle core biopsy specimens obtained from 3 institutions in the United States, including 1 institution not used for DLS development. To obtain the Gleason grade group (GG), each specimen was first reviewed by 2 expert urologic subspecialists from a multi-institutional panel of 6 individuals (years of experience: mean, 25 years; range, 18-34 years). A third subspecialist reviewed discordant cases to arrive at a majority opinion. To reduce diagnostic uncertainty, all subspecialists had access to an immunohistochemical-stained section and 3 histologic sections for every biopsied specimen. Their review was conducted from December 2018 to June 2019. Main Outcomes and Measures: The frequency of the exact agreement of the DLS with the majority opinion of the subspecialists in categorizing each tumor-containing specimen as 1 of 5 categories: nontumor, GG1, GG2, GG3, or GG4-5. For comparison, the rate of agreement of 19 general pathologists' opinions with the subspecialists' majority opinions was also evaluated. Results: For grading tumor-containing biopsy specimens in the validation set (n = 498), the rate of agreement with subspecialists was significantly higher for the DLS (71.7%; 95% CI, 67.9%-75.3%) than for general pathologists (58.0%; 95% CI, 54.5%-61.4%) (P < .001). In subanalyses of biopsy specimens from an external validation set (n = 322), the Gleason grading performance of the DLS remained similar. For distinguishing nontumor from tumor-containing biopsy specimens (n = 752), the rate of agreement with subspecialists was 94.3% (95% CI, 92.4%-95.9%) for the DLS and similar at 94.7% (95% CI, 92.8%-96.3%) for general pathologists (P = .58). Conclusions and Relevance: In this study, the DLS showed higher proficiency than general pathologists at Gleason grading prostate needle core biopsy specimens and generalized to an independent institution. Future research is necessary to evaluate the potential utility of using the DLS as a decision support tool in clinical workflows and to improve the quality of prostate cancer grading for therapy decisions.

Does the Visibility of Grade Group 1 Prostate Cancer on Baseline Multiparametric Magnetic Resonance Imaging Impact Clinical Outcomes?

PURPOSE: We assessed whether the visibility of Grade Group (GG) 1 prostate cancer on baseline multiparametric magnetic resonance imaging affects clinical outcomes. MATERIALS AND METHODS: We evaluated 454 men who underwent multiparametric magnetic resonance imaging between 2006 and 2018 with maximum GG1 prostate cancer inclusive of magnetic resonance imaging targeted biopsy. Multiparametric magnetic resonance imaging was graded as negative, equivocal or positive. Assessed outcomes were treatment-free survival, biopsy upgrade-free survival and unfavorable disease at radical prostatectomy (pT 3 or greater and/or GG3 or greater). Kaplan-Meier and multivariable Cox proportional hazard analyses were used to estimate the impact of multiparametric magnetic resonance imaging and clinicopathological variables (age, year, prostate specific antigen density and measures of tumor volume on biopsy) on outcomes. RESULTS: During followup (median 45.2 months) 61 men had disease upgraded on followup biopsy and 139 underwent definitive treatment. In men with negative, equivocal and positive baseline multiparametric magnetic resonance imaging at 5 years, treatment-free survival was 79%, 73% and 49% (p <0.0001), treatment-free survival was 89%, 82% and 70% (p=0.002), and survival without unfavorable disease at radical prostatectomy was 98%, 98% and 86% (p=0.007), respectively. At multivariable analysis positive (HR 1.93, 95% CI 1.21-3.09, p=0.006) and equivocal multiparametric magnetic resonance imaging (HR 2.02, 95% CI 1.11-3.68, p=0.02) were associated with shorter treatment-free survival, and positive multiparametric magnetic resonance imaging was a significant prognostic factor for upgrade-free survival (HR 2.03, 95% CI 1.06-3.86, p=0.03) and unfavorable disease at radical prostatectomy (HR 4.45, 95% CI 1.39-18.17, p=0.01). CONCLUSIONS: Men with positive multiparametric magnetic resonance imaging and GG1 prostate cancer on magnetic resonance imaging targeted biopsy are at increased risk for intervention, upgrading and unfavorable disease at radical prostatectomy compared to those with multiparametric magnetic resonance imaging invisible GG1 prostate cancer.

Identification of areas of grading difficulties in prostate cancer and comparison with artificial intelligence assisted grading.

The International Society of Urological Pathology (ISUP) hosts a reference image database supervised by experts with the purpose of establishing an international standard in prostate cancer grading. Here, we aimed to identify areas of grading difficulties and compare the results with those obtained from an artificial intelligence system trained in grading. In a series of 87 needle biopsies of cancers selected to include problematic cases, experts failed to reach a 2/3 consensus in 41.4% (36/87). Among consensus and non-consensus cases, the weighted kappa was 0.77 (range 0.68-0.84) and 0.50 (range 0.40-0.57), respectively. Among the non-consensus cases, four main causes of disagreement were identified: the distinction between Gleason score 3 + 3 with tangential cutting artifacts vs. Gleason score 3 + 4 with poorly formed or fused glands (13 cases), Gleason score 3 + 4 vs. 4 + 3 (7 cases), Gleason score 4 + 3 vs. 4 + 4 (8 cases) and the identification of a small component of Gleason pattern 5 (6 cases). The AI system obtained a weighted kappa value of 0.53 among the non-consensus cases, placing it as the observer with the sixth best reproducibility out of a total of 24. AI may serve as a decision support and decrease inter-observer variability by its ability to make consistent decisions. The grading of these cancer patterns that best predicts outcome and guides treatment warrants further clinical and genetic studies. Results of such investigations should be used to improve calibration of AI systems.

The 2019 International Society of Urological Pathology (ISUP) Consensus Conference on Grading of Prostatic Carcinoma.

Five years after the last prostatic carcinoma grading consensus conference of the International Society of Urological Pathology (ISUP), accrual of new data and modification of clinical practice require an update of current pathologic grading guidelines. This manuscript summarizes the proceedings of the ISUP consensus meeting for grading of prostatic carcinoma held in September 2019, in Nice, France. Topics brought to consensus included the following: (1) approaches to reporting of Gleason patterns 4 and 5 quantities, and minor/tertiary patterns, (2) an agreement to report the presence of invasive cribriform carcinoma, (3) an agreement to incorporate intraductal carcinoma into grading, and (4) individual versus aggregate grading of systematic and multiparametric magnetic resonance imaging-targeted biopsies. Finally, developments in the field of artificial intelligence in the grading of prostatic carcinoma and future research perspectives were discussed.

Predictive Value of In Vivo MR Spectroscopy With Semilocalization by Adiabatic Selective Refocusing in Differentiating Clear Cell Renal Cell Carcinoma From Other Subtypes.

OBJECTIVE. The purpose of this study is to evaluate the diagnostic value of in vivo MR spectroscopy (MRS) with semilocalization by adiabatic selective refocusing (semi-LASER MRS) in differentiating clear cell renal cell carcinoma (RCC) from the non-clear cell subtype. SUBJECTS AND METHODS. Sixteen patients with biopsy-proven RCC or masses highly suspicious for RCC were prospectively recruited to participate in the study. Single-voxel 1H spectra were acquired using a 3-T MRI system, with a semi-LASER sequence acquired for renal tumors in 14 patients and for healthy renal tissue (control tissue) in 12 patients. Offline processing of the MR spectra was performed. MRI and spectra analysis were performed independently by radiologists who were blinded to the reference histopathologic findings. RESULTS. Semi-LASER MRS was diagnostic for nine of 11 patients (82%) with histopathologically proven clear cell RCC, showing a strong lipid peak in seven patients and a weaker lipid resonance in two others, whereas control spectra showed weakly positive findings in only one patient. MRS findings were negative for lipid resonance in two of three patients (67%) with non-clear cell tumors and were weakly positive in another patient. Semi-LASER MRS had a high sensitivity and positive predictive value of 82% and 90%, respectively, in addition to a specificity of 67%, a negative predictive value of 50%, and overall accuracy of 79% for the detection of clear cell RCC. Lipid resonance was detected by MRS for four of six clear cell RCCs with no intravoxel fat on chemical-shift MRI. CONCLUSION. The preliminary results of the present study show that semi-LASER MRS is promising for the noninvasive discrimination of clear cell RCC from non-clear cell RCC on the basis of detection of lipid resonance and that it provides an incremental yield compared with chemical-shift MRI.

Artificial intelligence for diagnosis and grading of prostate cancer in biopsies: a population-based, diagnostic study.

BACKGROUND: An increasing volume of prostate biopsies and a worldwide shortage of urological pathologists puts a strain on pathology departments. Additionally, the high intra-observer and inter-observer variability in grading can result in overtreatment and undertreatment of prostate cancer. To alleviate these problems, we aimed to develop an artificial intelligence (AI) system with clinically acceptable accuracy for prostate cancer detection, localisation, and Gleason grading. METHODS: We digitised 6682 slides from needle core biopsies from 976 randomly selected participants aged 50-69 in the Swedish prospective and population-based STHLM3 diagnostic study done between May 28, 2012, and Dec 30, 2014 (ISRCTN84445406), and another 271 from 93 men from outside the study. The resulting images were used to train deep neural networks for assessment of prostate biopsies. The networks were evaluated by predicting the presence, extent, and Gleason grade of malignant tissue for an independent test dataset comprising 1631 biopsies from 246 men from STHLM3 and an external validation dataset of 330 biopsies from 73 men. We also evaluated grading performance on 87 biopsies individually graded by 23 experienced urological pathologists from the International Society of Urological Pathology. We assessed discriminatory performance by receiver operating characteristics and tumour extent predictions by correlating predicted cancer length against measurements by the reporting pathologist. We quantified the concordance between grades assigned by the AI system and the expert urological pathologists using Cohen's kappa. FINDINGS: The AI achieved an area under the receiver operating characteristics curve of 0·997 (95% CI 0·994-0·999) for distinguishing between benign (n=910) and malignant (n=721) biopsy cores on the independent test dataset and 0·986 (0·972-0·996) on the external validation dataset (benign n=108, malignant n=222). The correlation between cancer length predicted by the AI and assigned by the reporting pathologist was 0·96 (95% CI 0·95-0·97) for the independent test dataset and 0·87 (0·84-0·90) for the external validation dataset. For assigning Gleason grades, the AI achieved a mean pairwise kappa of 0·62, which was within the range of the corresponding values for the expert pathologists (0·60-0·73). INTERPRETATION: An AI system can be trained to detect and grade cancer in prostate needle biopsy samples at a ranking comparable to that of international experts in prostate pathology. Clinical application could reduce pathology workload by reducing the assessment of benign biopsies and by automating the task of measuring cancer length in positive biopsy cores. An AI system with expert-level grading performance might contribute a second opinion, aid in standardising grading, and provide pathology expertise in parts of the world where it does not exist. FUNDING: Swedish Research Council, Swedish Cancer Society, Swedish eScience Research Center, EIT Health.