Radiology domain in the diagnosis of IgG4-RD according to the 2019 American College of Rheumatology and European League Against Rheumatism classification.

OBJECTIVES: To evaluate the performance of radiology-related inclusion criteria of the 2019 ACR-EULAR classification system in the diagnosis of IgG4-related disease (IgG4-RD). METHODS: This retrospective single-institution study included patients who received a diagnosis of IgG4-RD between January 2010 and December 2020. Two abdominal radiologists independently reviewed baseline imaging studies and scored radiology findings according to the 2019 ACR-EULAR classification criteria. Additional scores were assigned based on serological, histopathological, and immunostaining features. RESULTS: Seventy-four patients (58 males and 16 females) with a mean age of 59.3 ± 13.9 years diagnosed with IgG4-RD were included. 51/74 (68.9%) were classified as having IgG4-RD according to the 2019 ACR-EULAR classification criteria. To reach a score ≥ 20 in these 51 patients, the radiology domain was sufficient in 20/51 (39.2%) and adding the serology domain was required for another 20/51 (39.2%). The remaining 11/51 patients (21.6%) required the histopathology and immunostaining domains. Radiological involvement of two or more organs at presentation was significantly associated with a score of ≥ 20 and seen in 43/51 (84.3%) compared to 5/23 (21.7%) of the non-classified group (p < 0.001). The group classified as having IgG4-RD showed a significantly higher proportion of elevated IgG4 levels (39/51, 76.5%) than the non-classified group (8/23, 34.8%) (< 0.001). CONCLUSION: The study findings support the effectiveness of the radiology-related inclusion criteria of the 2019 ACR-EULAR classification system in diagnosing IgG4-RD. Combining radiology and serology domains achieved the cut-off in 80% of IgG-RD patients, enabling non-invasive diagnosis. The classification of IgG4-RD was significantly associated with multi-organ involvement, particularly affecting the pancreas and biliary system. CRITICAL RELEVANCE STATEMENT: This study is the first to evaluate the diagnostic performance of the radiology domain in the 2019 ACR-EULAR classification criteria. The study results confirm its utility and potential to enable non-invasive diagnosis when combined with serological testing in a significant proportion of patients. KEY POINTS: • A significant proportion of patients can be diagnosed with IgG4-RD using the radiology and serology domains exclusively. • Multi-organ involvement is significantly associated with classifying patients as IgG4-RD, with the pancreas and biliary system most frequently affected. • A high level of inter-reader agreement in the scoring of the radiology domain supports its reliability.

Can absolute arterial phase hyperenhancement improve sensitivity of detection of hepatocellular carcinoma in indeterminate nodules on CT?

OBJECTIVES: To determine if quantitative assessment of relative (R) and absolute (A) arterial phase hyperenhancement (APHE) and washout (WO) applied to indeterminate nodules on CT would improve the overall sensitivity of detection of hepatocellular carcinoma (HCC). METHODS: One-hundred and fourteen patients (90 male; mean age, 65 years) with 210 treatment-naïve HCC nodules (190 HCCs, 20 benign) who underwent 4-phase CT were included in this retrospective study. Four radiologists independently assigned a qualitative LR (LI-RADS) category per nodule. LR-3/4 nodules were then quantitatively analyzed by the 4 readers, placing ROIs within nodules and adjacent liver parenchyma. A/R-APHE and WO were calculated, and per-reader sensitivity and specificity updated. Interobserver agreement and AUCs were calculated per reader. RESULTS: Qualitative readers 1-4 categorized 57, 69, 57, and 63 nodules as LR-3/4 respectively with moderate to substantial agreement in LR category (kappa 0.56-0.69, p < 0.0001); their diagnostic performances in the detection of HCC were 80%, 73.2%, 77.4%, and 77.4% sensitivity, and 100%, 95%, 70%, and 100% specificity, respectively. A threshold of ≥ 20 HU for A-APHE increased overall sensitivity of HCC detection by 0.5-3.1% without changing specificity for the subset of nodules APHE - /WO + on qualitative read, with 2, 6, 6, and 1 additional HCC detected by readers 1-4. Relative and various A-WO formulae and thresholds all increased sensitivity, but with a drop in specificity for some/all readers. CONCLUSION: Quantitatively assessed A-APHE showed potential to increase sensitivity and maintain specificity of HCC diagnosis when selectively applied to indeterminate nodules demonstrating WO without subjective APHE. Quantitatively assessed R and A-WO increased sensitivity, however reduced specificity. CLINICAL RELEVANCE STATEMENT: A workflow using selective quantification of absolute arterial enhancement is routinely employed in the CT assessment of renal and adrenal nodules. Quantitatively assessed absolute arterial enhancement is a simple tool which may be used as an adjunct to help increase sensitivity and maintain specificity of HCC diagnosis in indeterminate nodules demonstrating WO without subjective APHE. KEY POINTS: • In indeterminate nodules categorized as LI-RADS 3/4 due to absent subjective arterial phase hyperenhancement, a cut-off for absolute arterial phase hyperenhancement of ≥ 20 HU may increase the overall sensitivity of detection of HCC by 0.5-3.1% without affecting specificity. • Relative and various absolute washout formulae and cut-offs increased sensitivity of HCC detection, but with a drop in specificity for some/all readers.

Real-life use of tolvaptan in ADPKD: a retrospective analysis of a large Canadian cohort.

Tolvaptan is the first disease-modifying drug proven to slow eGFR decline in high-risk patients with ADPKD. However, barriers from the patient perspective to its use in real-life settings have not been systemically examined in a large cohort. This was a single-center, retrospective study of 523 existing or new patients with ADPKD followed at the Center for Innovative Management of PKD in Toronto, Ontario, between January 1, 2016 to December 31, 2018. All patients underwent clinical assessment including total kidney volume measurements and Mayo Clinic Imaging Class (MCIC). Those who were deemed to be at high risk were offered tolvaptan with their preference (yes or no) and reasons for their choices recorded. Overall, 315/523 (60%) patients had MCIC 1C-1E; however, only 96 (30%) of them were treated with tolvaptan at their last follow-up. Among these high-risk patients, those not treated versus treated with tolvaptan were more likely to have a higher eGFR (82 ± 26 vs. 61 ± 27 ml/min/1.73 m2), CKD stages 1-2 (79% vs. 41%), and MCIC 1C (63% vs. 31%). The most common reasons provided for not taking tolvaptan were lifestyle preference related to the aquaretic effect (51%), older age ≥ 60 (12%), and pregnancy/family planning (6%). In this real-world experience, at least 60% of patients with ADPKD considered to be at high risk for progression to ESKD by imaging were not treated with tolvaptan; most of them had early stages of CKD with well-preserved eGFR and as such, were prime targets for tolvaptan therapy to slow disease progression. Given that the most common reason for tolvaptan refusal was the concern for intolerability of the aquaretic side-effect, strategies to mitigate this may help to reduce this barrier to tolvaptan therapy.

Patterns of Relapse and Complications of Immunoglobulin G4-Related Disease.

BACKGROUND: Immunoglobulin G4-related disease (IgG4-RD) is a multisystemic fibroinflammatory condition potentially resulting in organ dysfunction. We aimed to evaluate imaging characteristics of disease relapse and complications in this cohort of patients. METHODS: This was a cohort study of IgG4-RD patients imaged between 2010 and 2020. Radiological manifestations of disease activity (remission/stability vs. relapse and complications) were correlated with clinical symptoms. Univariate analyses were performed with χ2 , Fisher exact, and Mann-Whitney U tests. Times to relapse and organ atrophy were studied with Kaplan-Meier analyses. RESULTS: A total of 69 patients had imaging surveillance over a median duration of 47 months. Radiological relapse occurred in 50.7% (35/69) with median time to relapse at 74 months (95% confidence interval, 45-122 months); 42.8% (15/35) of this cohort had different-site relapse with the following recognized primary-secondary patterns: pancreas-hepatobiliary ( p = 0.005), hepatobiliary-pancreas ( p = 0.013), and periaortitis-mesenteric ( p = 0.006). Clinical symptoms were significantly associated with imaging characteristics ( p < 0.001). Abdominal complications were detected in 52.2% (36/69) of patients, mostly solid organ atrophy (97.2% [35/36]). New-onset diabetes was more likely in pancreatic IgG4-RD (n = 51) when accompanied by gland atrophy (4/21 vs. 0/30 nonatrophy, p = 0.024). CONCLUSION: Radiological relapse of IgG4-RD is common over prolonged imaging surveillance and is significantly associated with symptomatic relapse. A multisystem review to detect new/different sites of disease and abdominal complications may help predict future organ dysfunction.

Atypical Polycystic Kidney Disease as defined by Imaging.

Using age- and height-adjusted total kidney volume, the Mayo Clinic Imaging Classification provides a validated approach to assess the risk of chronic kidney disease (CKD) progression in autosomal dominant polycystic kidney disease (ADPKD), but requires excluding patients with atypical imaging patterns, whose clinical characteristics have been poorly defined. We report an analysis of the prevalence, clinical and genetic characteristics of patients with atypical polycystic kidney disease by imaging. Patients from the extended Toronto Genetic Epidemiology Study of Polycystic Kidney Disease recruited between 2016 and 2018 completed a standardized clinical questionnaire, kidney function assessment, genetic testing, and kidney imaging by magnetic resonance or computed tomography. We compared the prevalence, clinical features, genetics, and renal prognosis of atypical versus typical polycystic kidney disease by imaging. Forty-six of the 523 (8.8%) patients displayed atypical polycystic kidney disease by imaging; they were older (55 vs. 43 years; P < 0.001), and less likely to have a family history of ADPKD (26.1% vs. 74.6%; P < 0.001), a detectable PKD1 or PKD2 mutation (9.2% vs. 80.4%; P < 0.001), or progression to CKD stage 3 or stage 5 (P < 0.001). Patients with atypical polycystic kidney disease by imaging represent a distinct prognostic group with a low likelihood of progression to CKD.

Autosomal Dominant Polycystic Kidney Disease: Role of Imaging in Diagnosis and Management.

Autosomal dominant polycystic kidney disease (ADPKD) is the most common genetic kidney disorder with progressive renal function decline, and disease severity is determined based on the type of genetic mutation. The diagnosis is usually established at imaging, primarily at US, and is based on age-dependent criteria and the number of visible cysts. ADPKD is classified into class 1 (typical) and class 2 (atypical) according to the Mayo Clinic Imaging Classification (MCIC) system. Height-adjusted total kidney volume (TKV) has emerged as a predictor of future renal function decline and renal failure in ADPKD, and several methods can be used for estimation. MCIC class 1 ADPKD is further subdivided into five types based on height-adjusted TKV (A, B, C, D, and E). Patients with a larger height-adjusted TKV (ie, MCIC 1C-E) are at high risk for progression to end-stage renal disease and will potentially benefit from vasopressin receptor antagonists, which have been shown to reduce the rate of cyst growth and slow renal function decline. Other renal complications primarily relate to hemorrhage within cysts or cyst infections. Subtraction images are key for assessment of complex cysts when malignancy is suspected, as the presence of protein and blood can limit the assessment for an enhancing component. The radiologist has a central role in establishing a diagnosis, excluding mimics, identifying complications, assessing severity, and predicting future renal failure. Interventional radiologists play a therapeutic role in management of complications by cyst drainage, sclerotherapy, or embolization. © RSNA, 2022 Online supplemental material and the slide presentation from the RSNA Annual Meeting are available for this article.

Germline BRCA2 variants in advanced pancreatic acinar cell carcinoma: A case report and review of literature.

BACKGROUND: Pancreatic acinar cell carcinoma (PACC) is a rare tumor. Up to 45% of PACCs have alterations in the DNA damage repair pathway and 23% harbor rearrangements in the BRAF or RAF1 genes. We present a PACC case with a germline BRCA2 likely pathogenic variant (LPV) to highlight the impact of genomic testing on treatment decisions and patient outcomes. In our larger case series, we provide clinic-based information on additional 10 PACC patients treated in our center. CASE SUMMARY: A 70-year-old male was diagnosed with advanced PACC. At presentation, he was cachectic with severe arthralgia despite prednisolone and a skin rash that was later confirmed to be panniculitis. He was treated with modified FOLFIRINOX (mFFX) with the knowledge of the germline BRCA2 LPV. Following 11 cycles of mFFX, a computed tomography (CT) scan demonstrated significant tumor response in the pancreatic primary and hepatic metastases, totaling 70% from baseline as per Response Evaluation Criteria in Solid Tumors. Resolution of the skin panniculitis was also noted. We identified two additional PACCs with druggable targets in our case series. Our data contribute to practical evidence for the value of germline and somatic profiling in the management of rare diseases like PACC. CONCLUSION: This patient and others in our larger case series highlight the importance of genomic testing in PACC with potential utility in personalized treatment.

Leiomyosarcoma: Current Clinical Management and Future Horizons.

Leiomyosarcomas are soft tissue tumors that are derived from smooth muscle mainly in the pelvis and retroperitoneum. Percutaneous biopsy is paramount to confirm diagnosis. Imaging is necessary to complete clinical staging. Multimodal treatment should be directed by expert sarcoma multidisciplinary teams that see a critical volume of these rare tumors. Surgery is the mainstay of curative intent treatment; however due to its high metastatic progression, there may be a benefit for neoadjuvant systemic treatment. Adjuvant systemic treatment has no proven disease-free survival, and its main role is in the palliative setting to potentially prolong overall survival.

Total Kidney Volume Measurements in ADPKD by 3D and Ellipsoid Ultrasound in Comparison with Magnetic Resonance Imaging.

BACKGROUND AND OBJECTIVES: Total kidney volume is a validated prognostic biomarker for autosomal dominant polycystic kidney disease. Total kidney volume by magnetic resonance imaging (MRI) and manual segmentation is considered the "reference standard," but it is time consuming and not readily accessible. By contrast, three-dimensional (3D) ultrasound provides a promising technology for total kidney volume measurements with unknown potential. Here, we report a comparative study of total kidney volume measurements by 3D ultrasound versus the conventional methods by ultrasound ellipsoid and MRI ellipsoid. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: This single-center prospective study included 142 patients who completed a standardized 3D ultrasound and MRI. Total kidney volumes by 3D ultrasound and ultrasound ellipsoid were compared with those by MRI. We assessed the agreement of total kidney volume measurements by Bland-Altman plots and misclassification of the Mayo Clinic imaging classes between the different imaging methods, and we assessed prediction of Mayo Clinic imaging classes 1C-1E by average ultrasound kidney length >16.5 cm. RESULTS: Compared with MRI manual segmentation, MRI ellipsoid, 3D ultrasound, and ultrasound ellipsoid underestimated total kidney volume (mean difference: -3%, -9%, and -11%, respectively), with Mayo Clinic imaging classes misclassified in 11%, 21%, and 22% of patients, respectively; most misclassified cases by MRI ellipsoid (11 of 16), 3D ultrasound (23 of 30), and ultrasound ellipsoid (26 of 31) were placed into a lower Mayo Clinic imaging class. Predictions of the high-risk Mayo Clinic imaging classes (1C-1E) by MRI ellipsoid, 3D ultrasound, and ultrasound ellipsoid all yielded high positive predictive value (96%, 95%, and 98%, respectively) and specificity (96%, 96%, and 99%, respectively). However, both negative predictive value (90%, 88%, and 95%, respectively) and sensitivity (88%, 85%, and 94%, respectively) were lower for 3D ultrasound and ultrasound ellipsoid compared with MRI ellipsoid. An average ultrasound kidney length >16.5 cm was highly predictive of Mayo Clinic imaging classes 1C-1E only in patients aged ≤45 years. CONCLUSIONS: Total kidney volume measurements in autosomal dominant polycystic kidney disease by 3D ultrasound and ultrasound ellipsoid displayed similar bias and variability and are less accurate than MRI ellipsoid. Prediction of high-risk Mayo Clinic imaging classes (1C-1E) by all three methods provides high positive predictive value, but ultrasound ellipsoid is simpler to use and more readily available.

Contrast-enhanced US of the Liver and Kidney: A Problem-solving Modality.

Contrast-enhanced US (CEUS) has an important role as a supplement to CT or MRI in clinical practice. The main established utilizations are in the liver and the kidney. The primary advantages of CEUS compared with contrast-enhanced CT or MRI relate to its superior contrast resolution, real-time continuous scanning, pure intravascular nature, portability, and safety-especially in patients with renal impairment or CT or MRI contrast agent allergy. This article focuses on the use of CEUS in the liver and kidney.

Autologous Hematopoietic Stem Cell Transplantation for Liver Transplant Recipients With Recurrent Primary Sclerosing Cholangitis: A Pilot Study.

BACKGROUND: Primary sclerosing cholangitis (PSC) is an indication for liver transplantation, but recurrence after liver transplantation is associated with poor outcomes often requiring repeat transplantation. We investigated whether autologous hematopoietic stem cell transplantation (aHSCT) could be used to stop progression of recurrent PSC and promote operational tolerance. METHODS: Twelve patients with recurrent PSC were fully evaluated and 5 were selected for aHSCT. Autologous hematopoietic stem cells were collected, purified by CD34 immunomagnetic selection, and cryopreserved. Immunoablation using busulfan, cyclophosphamide, and rabbit antithymocyte globulin was followed by aHSCT. The primary endpoint of the study was the establishment of operational tolerance defined as lack of biochemical, histologic, and clinical evidence of rejection while off immunosuppression at 2 y post-aHSCT. RESULTS: Two of the 5 patients achieved operational tolerance with no clinical or histologic evidence of PSC progression or allorejection. A third patient developed sinusoidal obstruction syndrome following aHSCT requiring repeat liver transplantation but has no evidence of PSC recurrence while on sirolimus monotherapy now >3 y after aHSCT. A fourth patient was weaned off immunosuppression but died 212 d after aHSCT from pericardial constriction. A fifth patient died from multiorgan failure. Immunosuppression-free allograft acceptance was associated with deletion of T-cell clones, loss of autoantibodies, and increases in regulatory T cells, transitional B cells, and programmed cell death protein-1 expressing CD8+ T cells in the 2 long-term survivors. CONCLUSIONS: Although operational tolerance occurred following aHSCT, the high morbidity and mortality observed render this specific protocol unsuitable for clinical adoption.

Combination of FIB-4 with ultrasound surface nodularity or elastography as predictors of histologic advanced liver fibrosis in chronic liver disease.

Reliable and available non-invasive methods for hepatic fibrosis assessment are important in chronic liver disease (CLD). Our aim was to compare stepwise algorithms combining standard ultrasound with serum markers and transient elastography (TE) for detecting advanced fibrosis (F3-4) and cirrhosis. Retrospective single center study between 2012 and 2018 of CLD patients with biopsy, TE, blood tests, and liver ultrasound parameters of surface nodularity (SN), lobar redistribution, and hepatic vein nodularity. Our cohort included 157 patients (51.6% males), mean age 47.6 years, predominantly non-alcoholic fatty liver disease and viral hepatitis (61%), with F3-4 prevalence of 60.5%. Area under the curve for F3-4 was 0.89 for TE ≥ 9.6 kPa and 0.80 for FIB-4 > 3.25. In multivariate modeling, TE ≥ 9.6 kPa (OR 21.78) and SN (OR 3.81) had independent association with F3-4; SN (OR 5.89) and TE ≥ 10.2 kPa (OR 15.73) were independently associated with cirrhosis. Two stepwise approaches included FIB-4 followed by SN or TE; sensitivity and specificity of stepwise SN were 0.65 and 1.00, and 0.89 and 0.33 for TE ≥ 9.6 kPa, respectively. Ultrasound SN and TE were independently predictive of F3-4 and cirrhosis in our cohort. FIB-4 followed by SN had high specificity for F3-4.

The Renal Vasculature: What the Radiologist Needs to Know.

The physiologic role of the kidneys is dependent on the normal structure and functioning of the renal vasculature. Knowledge and understanding of the embryologic basis of the renal vasculature are necessary for the radiologist. Common anatomic variants involving the renal artery (supernumerary arteries and prehilar branching) and renal vein (supernumerary veins, delayed venous confluence, retroaortic or circumaortic vein) may affect procedures like renal transplantation, percutaneous biopsy, and aortic aneurysm repair. Venous compression syndromes (anterior and posterior nutcracker syndrome) can be symptomatic and can be diagnosed with a combination of radiologic features. Renal artery stenosis is commonly atherosclerotic and is diagnosed with Doppler US, CT angiography, or MR angiography. Fibromuscular dysplasia, the second most common cause of renal artery narrowing, has a characteristic string-of-beads appearance resulting from multifocal stenoses and dilatations. Manifestations of renal vasculitis differ depending on whether the affected vessels are large, medium, or small. Renal vascular injury is graded according to the American Association for the Surgery of Trauma (AAST) renal injury scale, which defines vascular injury and active bleeding in renal injuries. Both renal arteries and veins are affected by primary neoplasms or secondarily by neoplasms from adjacent structures. Differentiation between bland thrombus and tumor thrombus and the extent of involvement dictate management in malignancies, especially renal cell carcinoma. Aneurysms, pseudoaneurysms, arteriovenous malformations, and arteriovenous fistulas can affect renal vessels and can be diagnosed with specific imaging features. The radiologist has a critical role in identification of specific imaging characteristics and establishing the diagnosis in the varied pathologic conditions affecting the renal vasculature, which is critical for directing management. Thus, the renal vasculature should be an integral part of radiologists' checklist. ©RSNA, 2021.

The added value of contrast-enhanced ultrasound in evaluation of indeterminate small solid renal masses and risk stratification of cystic renal lesions.

OBJECTIVES: To investigate accuracy of contrast-enhanced ultrasound (CEUS) to characterize indeterminate small solid renal masses (sSRMs), excluding lipid-rich AMLs, and cystic renal masses (CRMs) according to the proposed Bosniak Classification 2019 MATERIALS AND METHODS: CEUS of pathology-proven CRMs and sSRMs (without definite enhancement or macroscopic fat on CT/MRI), and CRMs with ≥18 months follow-up were retrospectively reviewed. Two radiologists blindly categorized CRMs according to new Bosniak Classification on CT/MRI. On CEUS, two other radiologists evaluated arterial-phase enhancement of sSRMs relative to renal cortex and categorized CRMs following new Bosniak Classification. Fisher's exact/chi-squared test was used to compare categorical variables, and Cohen κ statistics for inter-observer agreement RESULTS: A total of 237 patients had 241 lesions: 161 pathology-proven sSRMs (122 malignant and 39 benign), 29 pathology-proven CRMs, 51 CRMs with adequate follow-up. Arterial-phase enhancement < renal cortex predicted malignancy with specificity of 97.4% (38/39) (CI 85.6-99.9%), and positive predictive value (PPV) of 98.2% (54/55) (CI 90.4-99.9%). Inter-observer kappa was 0.95. In pathology-proven CRMS, sensitivity of CEUS vs CT/MRI was 100% (15/15) (CI 79.6-100%) vs 60% (9/15) (CI 35.8-80.1%) (p value = .002) and negative predictive value (NPV) 100% (2/2) (CI 17.8-100%) vs 25% (2/8 ) (CI 4.4-59.1%) (p value < 0.0001), with similar specificity (50%) and PPV- 88.2% (15/17) (CI 65.7-97.9%) vs 81.8% (9/11) (CI 52.3-96.8%) ( p value = 0.586). Bosniak Classification inter-observer kappa was 0.92 for CEUS vs 0.68 for CT/MRI (p value = 0.009). CONCLUSION: In our cohort, CEUS had high specificity and PPV to diagnose RCC in sSRMs excluding lipid-rich AML. CEUS had significantly higher sensitivity/NPV to diagnose malignancy in CRMs as compared to CT/MRI. KEY POINTS: • Once lipid-rich AML is excluded by the other modalities, sSRM arterial phase hypo-enhancement relative to renal cortex on CEUS yielded high specificity (97.4%) and PPV (98.2%) to diagnose RCC. • When applying the proposed Bosniak Classification 2019, CEUS showed higher sensitivity compared to CT/MRI (100% vs 60%), p value=.0024, in the stratification of cystic renal masses to diagnose malignancy. • CEUS may reduce the number of CT/MRI Bosniak IIF lesions by assigning them to either II or III/IV categories.

Patients with Protein-Truncating PKD1 Mutations and Mild ADPKD.

BACKGROUND AND OBJECTIVES: Progression of autosomal dominant polycystic kidney disease (ADPKD) is highly variable. On average, protein-truncating PKD1 mutations are associated with the most severe kidney disease among all mutation classes. Here, we report that patients with protein-truncating PKD1 mutations may also have mild kidney disease, a finding not previously well recognized. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: From the extended Toronto Genetic Epidemiologic Study of Polycystic Kidney Disease, 487 patients had PKD1 and PKD2 sequencing and typical ADPKD imaging patterns by magnetic resonance imaging or computed tomography. Mayo Clinic Imaging Classification on the basis of age- and height-adjusted total kidney volume was used to assess their cystic disease severity; classes 1A or 1B were used as a proxy to define mild disease. Multivariable linear regression was performed to test the effects of age, sex, and mutation classes on log-transformed height-adjusted total kidney volume and eGFR. RESULTS: Among 174 study patients with typical imaging patterns and protein-truncating PKD1 mutations, 32 (18%) were found to have mild disease on the basis of imaging results (i.e., Mayo Clinic Imaging class 1A-1B), with their mutations spanning the entire gene. By multivariable analyses of age, sex, and mutation class, they displayed mild disease similar to patients with PKD2 mutations and Mayo Clinic Imaging class 1A-1B. Most of these mildly affected patients with protein-truncating PKD1 mutations reported a positive family history of ADPKD in preceding generations and displayed significant intrafamilial disease variability. CONCLUSIONS: Despite having the most severe mutation class, 18% of patients with protein-truncating PKD1 mutations had mild disease on the basis of clinical and imaging assessment. PODCAST: This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2021_02_18_CJN11100720_final.mp3.

Convolutional neural networks versus radiologists in characterization of small hypoattenuating hepatic nodules on CT: a critical diagnostic challenge in staging of colorectal carcinoma.

Our objective was to compare the diagnostic performance and diagnostic confidence of convolutional neural networks (CNN) to radiologists in characterizing small hypoattenuating hepatic nodules (SHHN) in colorectal carcinoma (CRC) on CT scans. Retrospective review of CRC CT scans over 6-years yielded 199 patients (550 SHHN) defined as < 1 cm in diameter. The reference standard was established through 1-year stability/MRI for benign or nodule evolution for malignant nodules. Five CNNs underwent supervised training on 150 patients (412 SHHN). The remaining 49 patients (138 SHHN) were used as testing-set to compare performance of 3 radiologists to CNN, measured through ROC AUC analysis of confidence rating assigned to each nodule by the radiologists. Multivariable modeling was used to compensate for radiologist bias from visible findings other than SHHN. In characterizing SHHN as benign or malignant, the radiologists' mean AUC ROC (0.96) was significantly higher than CNN (0.84, p = 0.0004) but equivalent to CNN adjusted through multivariable modeling for presence of synchronous ≥ 1 cm liver metastases (0.95, p = 0.9). The diagnostic confidence of radiologists and CNN were analyzed. There were significantly lower number of nodules rated with low confidence by CNN (19.6%) and CNN with liver metastatic status (18.1%) than two (38.4%, 44.2%, p < 0.0001) but not a third radiologist (11.1%, p = 0.09). We conclude that in CRC, CNN in combination with liver metastatic status equaled expert radiologists in characterizing SHHN but with better diagnostic confidence.