Automatically Detecting Pancreatic Cysts in Autosomal Dominant Polycystic Kidney Disease on MRI Using Deep Learning.

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.

A Primer for Utilizing Deep Learning and Abdominal MRI Imaging Features to Monitor Autosomal Dominant Polycystic Kidney Disease Progression.

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.

An exploration of optimal time and safety of 595-nm pulsed dye laser for the treatment of early superficial infantile hemangioma.

Infantile hemangioma (IH) is the most common benign vascular tumor that occurs in infants and young children. Studies have shown laser therapy to reduce the proliferation of superficial IH and promote its regression, but the optimal timing for treatment has not been determined. Our study explores the timing and safety of 595-nm pulsed dye laser (PDL) treatment for early superficial IH. We retrospectively analyzed 180 cases of superficial IH treated with 595-nm PDL. Data was organized according to patient age at the first visit. Six months after the initial treatment, patients were evaluated using a grade IV classification method, and the clinical curative effect of each group was calculated. The number of laser treatments and the occurrence of adverse reactions were recorded simultaneously. The overall effective and cure rates were 98.3% and 84.4%, respectively, with no significant difference in rates between groups (p > 0.05). There was a statistically significant difference in the number of laser treatments among the age groups (p < 0.05). The average laser frequency: "0-2 months group" < "2-4 months group" < "4-6 months group." The overall incidence of adverse reactions was 11.1%, and 12 (6.7%) cases had short-term adverse reactions, with no statistically significant differences between groups (p > 0.05). Eight cases had long-term adverse reactions. This difference between groups was statistically significant (p < 0.05). Younger children (≤2 months of age) receiving 595-nm PDL treatment for IH require relatively fewer treatment times than other children (>2 months of age), have a shorter course of disease, experience better curative effect, and have fewer sequelae reactions.

DNA Marker Transmission and Linkage Analysis in Populations Derived from a Sugarcane (Saccharum spp.) x Erianthus arundinaceus Hybrid.

Introgression of Erianthus arundinaceus has been the focus of several sugarcane breeding programs in the world, because the species has desirable traits such as high biomass production, vigour, ratooning ability and good resistance to environmental stresses and disease. In this study four genetic maps were constructed for two intergeneric populations. The first population (BC1) was generated from a cross between an Erianthus/Saccharum hybrid YC96-40 and a commercial sugarcane variety CP84-1198. The second population (BC2) was generated from a cross between YCE01-116, a progeny of the BC1 cross and NJ57-416, a commercial sugarcane cultivar. Markers across both populations were generated using 35 AFLP and 23 SSR primer pairs. A total of 756 and 728 polymorphic markers were scored in the BC1 and BC2 populations, respectively. In the BC1 population, a higher proportion of markers was derived from the Erianthus ancestor than those from the Saccharum ancestor Badila. In the BC2 population, both the number and proportion of markers derived from Erianthus were approximately half of those in the BC1 population. Linkage analysis led to the construction of 38, 57, 36 and 47 linkage groups (LGs) for YC96-40, CP84-1198, YCE01-116, and NJ57-416, encompassing 116, 174, 97 and 159 markers (including single dose, double dose and bi-parental markers), respectively. These LGs could be further placed into four, five, five and six homology groups (HGs), respectively, based on information from multi-allelic SSR markers and repulsion phase linkages detected between LGs. Analysis of repulsion phase linkage indicated that Erianthus behaved like a true autopolyploid.