ABSTRACT
BACKGROUND AND PURPOSE: Autosomal dominant polycystic kidney disease (ADPKD) patients develop cysts in the kidneys, liver, spleen, pancreas, prostate and arachnoid spaces. In addition, spinal meningeal diverticula have been reported. To determine whether spinal meningeal diverticula are associated with ADPKD, we compare their prevalence in ADPKD subjects to a control cohort without ADPKD. MATERIALS AND METHODS: ADPKD subjects and age-and gender-matched controls without ADPKD undergoing abdominal MRI from mid-thorax to the pelvis from 2003 to 2023 were retrospectively evaluated for spinal meningeal diverticula by 4 blinded observers. Prevalence of spinal meningeal diverticula in ADPKD was compared to control subjects, using t-test and correlated with clinical and laboratory data, and magnetic resonance imaging (MRI) features, including cyst volumes and cyst counts. RESULTS: Identification of spinal meningeal diverticula in ADPKD (n=285, median age, 47 [37,56]; 54% female) and control (n=285, median age, 47 [37,57]; 54% female) subjects had high inter-observer agreement (Pairwise Cohen kappa=0.74). Spinal meningeal diverticula were observed in 145 of 285 (51%) ADPKD subjects compared with 66 of 285 (23%) control subjects without ADPKD (p<0.001). Spinal meningeal diverticula in ADPKD were more prevalent in women (98 of 153 [64%]) than men (47 of 132 [36%], p<0.001). The mean number of spinal meningeal diverticula per affected ADPKD subject was 3.6 + 2.9 compared to 2.4 + 1.9 in controls with cysts (p<0.001). The median volume/interquartile range (IQR, 25%/75%) of spinal meningeal diverticula was 400 mm3 (210, 740) in ADPKD compared to 250 mm3 (180, 440) in controls (p<0.001). Mean/SD spinal meningeal diverticulum diameter was greater in the sacrum (7.3 + 4.1 mm) compared to thoracic (5.4 + 1.8 mm) and lumbar spine (5.8 + 2.0 mm), p<0.001, suggesting that that hydrostatic pressure contributed to enlargement. CONCLUSIONS: ADPKD has a high prevalence of spinal meningeal diverticula, particularly in women. ABBREVIATIONS: ADPKD = Autosomal dominant polycystic kidney disease.
ABSTRACT
BACKGROUND: Pancreatic cysts in autosomal dominant polycystic kidney disease (ADPKD) correlate with PKD2 mutations, which have a different phenotype than PKD1 mutations. However, pancreatic cysts are commonly overlooked by radiologists. Here, we automate the detection of pancreatic cysts on abdominal MRI in ADPKD. METHODS: Eight nnU-Net-based segmentation models with 2D or 3D configuration and various loss functions were trained on positive-only or positive-and-negative datasets, comprising axial and coronal T2-weighted MR images from 254 scans on 146 ADPKD patients with pancreatic cysts labeled independently by two radiologists. Model performance was evaluated on test subjects unseen in training, comprising 40 internal, 40 external, and 23 test-retest reproducibility ADPKD patients. RESULTS: Two radiologists agreed on 52% of cysts labeled on training data, and 33%/25% on internal/external test datasets. The 2D model with a loss of combined dice similarity coefficient and cross-entropy trained with the dataset with both positive and negative cases produced an optimal dice score of 0.7 ± 0.5/0.8 ± 0.4 at the voxel level on internal/external validation and was thus used as the best-performing model. In the test-retest, the optimal model showed superior reproducibility (83% agreement between scan A and B) in segmenting pancreatic cysts compared to six expert observers (77% agreement). In the internal/external validation, the optimal model showed high specificity of 94%/100% but limited sensitivity of 20%/24%. CONCLUSIONS: Labeling pancreatic cysts on T2 images of the abdomen in patients with ADPKD is challenging, deep learning can help the automated detection of pancreatic cysts, and further image quality improvement is warranted.
Subject(s)
Deep Learning , Magnetic Resonance Imaging , Pancreatic Cyst , Polycystic Kidney, Autosomal Dominant , Humans , Polycystic Kidney, Autosomal Dominant/diagnostic imaging , Polycystic Kidney, Autosomal Dominant/complications , Polycystic Kidney, Autosomal Dominant/pathology , Pancreatic Cyst/diagnostic imaging , Pancreatic Cyst/pathology , Magnetic Resonance Imaging/methods , Female , Male , Middle Aged , Adult , Reproducibility of Results , Pancreas/diagnostic imaging , Pancreas/pathology , Image Interpretation, Computer-Assisted/methods , AgedABSTRACT
Mayo Imaging Classification (MIC) for predicting future kidney growth in autosomal dominant polycystic kidney disease (ADPKD) patients is calculated from a single MRI/CT scan assuming exponential kidney volume growth and height-adjusted total kidney volume at birth to be 150 mL/m. However, when multiple scans are available, how this information should be combined to improve prediction accuracy is unclear. Herein, we studied ADPKD subjects ( n = 36 ) with 8+ years imaging follow-up (mean = 11 years) to establish ground truth kidney growth trajectory. MIC annual kidney growth rate predictions were compared to ground truth as well as 1- and 2-parameter least squares fitting. The annualized mean absolute error in MIC for predicting total kidney volume growth rate was 2.1 % ± 2 % compared to 1.1 % ± 1 % ( p = 0.002 ) for a 2-parameter fit to the same exponential growth curve used for MIC when 4 measurements were available or 1.4 % ± 1 % ( p = 0.01 ) with 3 measurements averaging together with MIC. On univariate analysis, male sex ( p = 0.05 ) and PKD2 mutation ( p = 0.04 ) were associated with poorer MIC performance. In ADPKD patients with 3 or more CT/MRI scans, 2-parameter least squares fitting predicted kidney volume growth rate better than MIC, especially in males and with PKD2 mutations where MIC was less accurate.
Subject(s)
Kidney , Magnetic Resonance Imaging , Polycystic Kidney, Autosomal Dominant , Humans , Polycystic Kidney, Autosomal Dominant/diagnostic imaging , Polycystic Kidney, Autosomal Dominant/pathology , Polycystic Kidney, Autosomal Dominant/physiopathology , Male , Female , Kidney/diagnostic imaging , Kidney/pathology , Least-Squares Analysis , Adult , Organ Size , Magnetic Resonance Imaging/methods , Middle Aged , Tomography, X-Ray Computed/methodsABSTRACT
Abdominal imaging of autosomal dominant polycystic kidney disease (ADPKD) has historically focused on detecting complications such as cyst rupture, cyst infection, obstructing renal calculi, and pyelonephritis; discriminating complex cysts from renal cell carcinoma; and identifying sources of abdominal pain. Many imaging features of ADPKD are incompletely evaluated or not deemed to be clinically significant, and because of this, treatment options are limited. However, total kidney volume (TKV) measurement has become important for assessing the risk of disease progression (i.e., Mayo Imaging Classification) and predicting tolvaptan treatment's efficacy. Deep learning for segmenting the kidneys has improved these measurements' speed, accuracy, and reproducibility. Deep learning models can also segment other organs and tissues, extracting additional biomarkers to characterize the extent to which extrarenal manifestations complicate ADPKD. In this concept paper, we demonstrate how deep learning may be applied to measure the TKV and how it can be extended to measure additional features of this disease.
ABSTRACT
BACKGROUND AND PURPOSE: The objective is to demonstrate feasibility of quantitative susceptibility mapping (QSM) in autosomal dominant polycystic kidney disease (ADPKD) patients and to compare imaging findings with traditional T1/T2w magnetic resonance imaging (MRI). METHODS: Thirty-three consecutive patients (11 male, 22 female) diagnosed with ADPKD were initially selected. QSM images were reconstructed from the multiecho gradient echo data and compared to co-registered T2w, T1w, and CT images. Complex cysts were identified and classified into distinct subclasses based on their imaging features. Prevalence of each subclass was estimated. RESULTS: QSM visualized two renal calcifications measuring 9 and 10 mm and three pelvic phleboliths measuring 2 mm but missed 24 calcifications measuring 1 mm or less and 1 larger calcification at the edge of the field of view. A total of 121 complex T1 hyperintense/T2 hypointense renal cysts were detected. 52 (43%) Cysts appeared hyperintense on QSM consistent with hemorrhage; 60 (49%) cysts were isointense with respect to simple cysts and normal kidney parenchyma, while the remaining 9 (7%) were hypointense. The presentation of the latter two complex cyst subtypes is likely indicative of proteinaceous composition without hemorrhage. CONCLUSION: Our results indicate that QSM of ADPKD kidneys is possible and uniquely suited to detect large renal calculi without ionizing radiation and able to identify properties of complex cysts unattainable with traditional approaches.
Subject(s)
Hemorrhage , Kidney Calculi , Magnetic Resonance Imaging , Polycystic Kidney, Autosomal Dominant , Humans , Female , Polycystic Kidney, Autosomal Dominant/diagnostic imaging , Polycystic Kidney, Autosomal Dominant/complications , Male , Magnetic Resonance Imaging/methods , Middle Aged , Adult , Hemorrhage/diagnostic imaging , Kidney Calculi/diagnostic imaging , Tomography, X-Ray Computed/methods , Feasibility Studies , Diagnosis, Differential , Image Interpretation, Computer-Assisted/methods , AgedABSTRACT
RATIONALE AND OBJECTIVES: Following autosomal dominant polycystic kidney disease (ADPKD) progression by measuring organ volumes requires low measurement variability. The objective of this study is to reduce organ volume measurement variability on MRI of ADPKD patients by utilizing all pulse sequences to obtain multiple measurements which allows outlier analysis to find errors and averaging to reduce variability. MATERIALS AND METHODS: In order to make measurements on multiple pulse sequences practical, a 3D multi-modality multi-class segmentation model based on nnU-net was trained/validated using T1, T2, SSFP, DWI and CT from 413 subjects. Reproducibility was assessed with test-re-test methodology on ADPKD subjects (n = 19) scanned twice within a 3-week interval correcting outliers and averaging the measurements across all sequences. Absolute percent differences in organ volumes were compared to paired students t-test. RESULTS: Dice similarlity coefficient > 97%, Jaccard Index > 0.94, mean surface distance < 1 mm and mean Hausdorff Distance < 2 cm for all three organs and all five sequences were found on internal (n = 25), external (n = 37) and test-re-test reproducibility assessment (38 scans in 19 subjects). When averaging volumes measured from five MRI sequences, the model automatically segmented kidneys with test-re-test reproducibility (percent absolute difference between exam 1 and exam 2) of 1.3% which was better than all five expert observers. It reliably stratified ADPKD into Mayo Imaging Classification (area under the curve=100%) compared to radiologist. CONCLUSION: 3D deep learning measures organ volumes on five MRI sequences leveraging the power of outlier analysis and averaging to achieve 1.3% total kidney test-re-test reproducibility.
Subject(s)
Deep Learning , Polycystic Kidney, Autosomal Dominant , Humans , Polycystic Kidney, Autosomal Dominant/diagnostic imaging , Organ Size , Reproducibility of Results , Kidney/diagnostic imaging , Magnetic Resonance Imaging/methodsABSTRACT
Biomolecular condensates organize biochemistry, yet little is known about how cells control the position and scale of these structures. In cells, condensates often appear as relatively small assemblies that do not coarsen into a single droplet despite their propensity to fuse. Here, we report that ribonucleoprotein condensates of the glutamine-rich protein Whi3 interact with the endoplasmic reticulum, which prompted us to examine how membrane association controls condensate size. Reconstitution revealed that membrane recruitment promotes Whi3 condensation under physiological conditions. These assemblies rapidly arrest, resembling size distributions seen in cells. The temporal ordering of molecular interactions and the slow diffusion of membrane-bound complexes can limit condensate size. Our experiments reveal a trade-off between locally enhanced protein concentration at membranes, which favours condensation, and an accompanying reduction in diffusion, which restricts coarsening. Given that many condensates bind endomembranes, we predict that the biophysical properties of lipid bilayers are key for controlling condensate sizes throughout the cell.