ASSIST-U: A system for segmentation and image style transfer for ureteroscopy.

Kidney stones require surgical removal when they grow too large to be broken up externally or to pass on their own. Upper tract urothelial carcinoma is also sometimes treated endoscopically in a similar procedure. These surgeries are difficult, particularly for trainees who often miss tumours, stones or stone fragments, requiring re-operation. Furthermore, there are no patient-specific simulators to facilitate training or standardized visualization tools for ureteroscopy despite its high prevalence. Here a system ASSIST-U is proposed to create realistic ureteroscopy images and videos solely using preoperative computerized tomography (CT) images to address these unmet needs. A 3D UNet model is trained to automatically segment CT images and construct 3D surfaces. These surfaces are then skeletonized for rendering. Finally, a style transfer model is trained using contrastive unpaired translation (CUT) to synthesize realistic ureteroscopy images. Cross validation on the CT segmentation model achieved a Dice score of 0.853 ± 0.084. CUT style transfer produced visually plausible images; the kernel inception distance to real ureteroscopy images was reduced from 0.198 (rendered) to 0.089 (synthesized). The entire pipeline from CT to synthesized ureteroscopy is also qualitatively demonstrated. The proposed ASSIST-U system shows promise for aiding surgeons in the visualization of kidney ureteroscopy.

Towards navigation in endoscopic kidney surgery based on preoperative imaging.

Endoscopic renal surgeries have high re-operation rates, particularly for lower volume surgeons. Due to the limited field and depth of view of current endoscopes, mentally mapping preoperative computed tomography (CT) images of patient anatomy to the surgical field is challenging. The inability to completely navigate the intrarenal collecting system leads to missed kidney stones and tumors, subsequently raising recurrence rates. A guidance system is proposed to estimate the endoscope positions within the CT to reduce re-operation rates. A Structure from Motion algorithm is used to reconstruct the kidney collecting system from the endoscope videos. In addition, the kidney collecting system is segmented from CT scans using 3D U-Net to create a 3D model. The two collecting system representations can then be registered to provide information on the relative endoscope position. Correct reconstruction and localization of intrarenal anatomy and endoscope position is demonstrated. Furthermore, a 3D map is created supported by the RGB endoscope images to reduce the burden of mental mapping during surgery. The proposed reconstruction pipeline has been validated for guidance. It can reduce the mental burden for surgeons and is a step towards the long-term goal of reducing re-operation rates in kidney stone surgery.

Automated Upper Tract Urothelial Carcinoma Tumor Segmentation During Ureteroscopy Using Computer Vision Techniques.

INTRODUCTION: Endoscopic tumor ablation of upper tract urothelial carcinoma (UTUC) allows for tumor control with the benefit of renal preservation but is impacted by intraoperative visibility. We sought to develop a computer vision model for real-time, automated segmentation of UTUC tumors to augment visualization during treatment. MATERIALS AND METHODS: We collected twenty videos of endoscopic treatment of UTUC from two institutions. Frames from each video (N=3387) were extracted and manually annotated to identify tumors and areas of ablated tumor. Three established computer vision models (U-Net, U-Net++ and UNext) were trained using these annotated frames and compared. Eighty percent of the data was used to train the models while 10% was used for both validation and testing. We evaluated the highest performing model for tumor and ablated tissue segmentation using a pixel-based analysis. The model and a video overlay depicting tumor segmentation were further evaluated intraoperatively. RESULTS: All twenty videos (mean 36 seconds ± 58s) demonstrated tumor identification and 12 depicted areas of ablated tumor. The U-Net model demonstrated the best performance for segmentation of both tumors (AUC-ROC of 0.96) and areas of ablated tumor (AUC-ROC of 0.90). Additionally, we implemented a working system to process real-time video feeds and overlay model predictions intraoperatively. The model was able to annotate new videos at 15 fps. CONCLUSIONS: Computer vision models demonstrate excellent real-time performance for automated upper tract urothelial tumor segmentation during ureteroscopy.

Heat stress reduces brown adipose tissue activity by exacerbating mitochondrial damage in type 2 diabetic mice.

Epidemiological evidence shows that diabetic patients are susceptible to high temperature weather, and brown adipose tissue (BAT) activity is closely related to type 2 diabetes (T2DM). Activation of BAT under cold stress helps improve T2DM. However, the impact of high temperature on the activity of BAT is still unclear. The study aimed to investigate the impact of heat stress on glucose and lipid metabolism in T2DM mice by influencing BAT activity. High-fat feeding and injecting streptozotocin (STZ) induced model of T2DM mice. All mice were randomly divided into three groups: a normal(N) group, a diabetes (DM) group and a heat stress diabetes (DMHS) group. The DMHS group received heat stress intervention for 3 days. Fasting blood glucose, fasting serum insulin and blood lipids were measured in all three groups. The activity of BAT was assessed by using quantitative real-time PCR (qRT-PCR), electron microscopy, and PET CT. Furthermore, the UHPLC-Q-TOF MS technique was employed to perform metabolomics analysis of BAT on both DM group and DMHS group. The results of this study indicated that heat stress aggravated the dysregulation of glucose and lipid metabolism, exacerbated mitochondrial dysfunction in BAT and reduced the activity of BAT in T2DM mice. This may be related to the abnormal accumulation of branched-chain amino acids (BCAAs) in the mitochondria of BAT.

Computer Vision Enabled Segmentation of Kidney Stones During Ureteroscopy and Laser Lithotripsy.

Objective: To evaluate the performance of computer vision models for automated kidney stone segmentation during flexible ureteroscopy and laser lithotripsy. Materials and Methods: We collected 20 ureteroscopy videos of intrarenal kidney stone treatment and extracted frames (N = 578) from these videos. We manually annotated kidney stones on each frame. Eighty percent of the data were used to train three standard computer vision models (U-Net, U-Net++, and DenseNet) for automatic stone segmentation during flexible ureteroscopy. The remaining data (20%) were used to compare performance of the three models after optimization through Dice coefficients and binary cross entropy. We identified the highest performing model and evaluated automatic segmentation performance during ureteroscopy for both stone localization and treatment using a separate set of endoscopic videos. We evaluated performance of the pixel-based analysis using area under the receiver operating characteristic curve (AUC-ROC), accuracy, sensitivity, and positive predictive value both in previously recorded videos and in real time. Results: A computer vision model (U-Net++) was evaluated, trained, and optimized for kidney stone segmentation during ureteroscopy using 20 surgical videos (mean video duration of 22 seconds, standard deviation ±13 seconds). The model showed good performance for stone localization with both digital ureteroscopes (AUC-ROC: 0.98) and fiberoptic ureteroscopes (AUC-ROC: 0.93). Furthermore, the model was able to accurately segment stones and stone fragments <270 µm in diameter during laser fragmentation (AUC-ROC: 0.87) and dusting (AUC-ROC: 0.77). The model automatically annotated videos intraoperatively in three cases and could do so in real time at 30 frames per second (FPS). Conclusion: Computer vision models demonstrate strong performance for automatic stone segmentation during ureteroscopy. Automatically annotating new videos at 30 FPS demonstrate the feasibility of real-time application during surgery, which could facilitate tracking tools for stone treatment.

Establishment and validation of a model to determine the progression risk of low grade intraepithelial neoplasia.

OBJECTIVE: To establish and validate a model to determine the progression risk of gastric low-grade intraepithelial neoplasia (LGIN). METHODS: A total of 705 patients with gastric LGIN at the endoscopy center of Jiangsu Provincial People's Hospital during January 2010 and August 2017 were retrospectively reviewed. Basic clinical and pathological information were recorded. According to the time sequence of the initial examination, the first 605 patients were enrolled in the derivation group, and the remaining 100 patients were used in the validation group. SPSS 19 software was used as statistical analysis to determine independent risk factors for progression of LGIN of the stomach and to establish a risk model. The ROC was used to verify the application value of the predictive model. RESULTS: Univariate and multivariate analysis suggested that sex, multiple location, congestion, ulceration and form were independent risk factors for prolonged or advanced progression in patients with LGIN. Based on this, a predictive model is constructed: P = ex/(1 + ex) X = - 10.399 + 0.922 × Sex + 1.934 × Multiple Location + 1.382 × Congestion + 0.797 × Ulceration + 0.525 × Form. The higher of the P value means the higher risk of progression. The AUC of the derivation group and validation group were 0.784 and 0.766, respectively. CONCLUSION: Sex, multi-site, hyperemia, ulcer and morphology are independent risk factors for the prolongation or progression of patients with gastric LGIN. These factors are objective and easy to obtain data. Based on this, a predictive model is constructed, which can be used in management of patients. The model can be used to identify high-risk groups in patients with LGIN that may progress to gastric cancer. Strengthening follow-up or endoscopic treatment to improve the detection rate of early cancer or reduce the incidence of gastric cancer can provide a reliable basis for the treatment of LGIN.

UCP2 Overexpression Redirects Glucose into Anabolic Metabolic Pathways.

Uncoupling protein 2 (UCP2) is often upregulated in cancer cells. The UCP2 upregulation is positively correlated with enhanced proliferation, tumorigenesis, and metabolic alterations, thus suggesting that UCP2 upregulation can play a key role in sensing metabolic changes to promote tumorigenesis. To determine the global metabolic impact of UCP2 upregulation, 13 C6 glucose as a source molecule is used to "trace" the metabolic fate of carbon atoms derived from glucose. UCP2 overexpression in skin epidermal cells enhances the incorporation of 13 C label to pyruvate, tricarboxylic acid cycle intermediates, nucleotides, and amino acids, suggesting that UCP2 upregulation reprograms cellular metabolism toward macromolecule synthesis. To the best of our knowledge, this is the first study to bring to light the overall metabolic differences caused by UCP2 upregulation.