Deep learning segmentation of glomeruli on kidney donor frozen sections.

Purpose: Recent advances in computational image analysis offer the opportunity to develop automatic quantification of histologic parameters as aid tools for practicing pathologists. We aim to develop deep learning (DL) models to quantify nonsclerotic and sclerotic glomeruli on frozen sections from donor kidney biopsies. Approach: A total of 258 whole slide images (WSI) from cadaveric donor kidney biopsies performed at our institution ( n = 123 ) and at external institutions ( n = 135 ) were used in this study. WSIs from our institution were divided at the patient level into training and validation datasets (ratio: 0.8:0.2), and external WSIs were used as an independent testing dataset. Nonsclerotic ( n = 22767 ) and sclerotic ( n = 1366 ) glomeruli were manually annotated by study pathologists on all WSIs. A nine-layer convolutional neural network based on the common U-Net architecture was developed and tested for the segmentation of nonsclerotic and sclerotic glomeruli. DL-derived, manual segmentation, and reported glomerular count (standard of care) were compared. Results: The average Dice similarity coefficient testing was 0.90 and 0.83. And the F 1 , recall, and precision scores were 0.93, 0.96, and 0.90, and 0.87, 0.93, and 0.81, for nonsclerotic and sclerotic glomeruli, respectively. DL-derived and manual segmentation-derived glomerular counts were comparable, but statistically different from reported glomerular count. Conclusions: DL segmentation is a feasible and robust approach for automatic quantification of glomeruli. We represent the first step toward new protocols for the evaluation of donor kidney biopsies.

Pulmonary artery intimal sarcoma mimicking pulmonary thromboembolism: A case report.

RATIONALE: Pulmonary artery intimal sarcoma is a rare tumor with exceptionally high mortality and easily misdiagnosed as pulmonary thromboembolism pulmonary thromboembolism (PTE) due to the nonspecific clinical presentation and symptom. Misdiagnosis or untimely diagnosis makes the disease progress to an advanced stage and eventually leads to a poor prognosis. PATIENT CONCERNS: A 37-year-old Chinese female presented with chest tightness and dyspnea for 3 months. Echocardiography and chest computed tomography revealed an intraluminal obstruction of the pulmonary arteries. Tests of serum tumor makers showed slight elevation for carbohydrate antigen-125, and α-fetoprotein. PTE was suspected according to the radiological and laboratory findings. DIAGNOSIS: Microscopic findings of the presumed thrombus showed prominent myxoid and edematous background with atypical spindled cells and curvilinear vascularity. Immunohistochemical staining demonstrated that the atypical spindled cells were positive for vimentin but negative for CK, S100, SMA, desmin, CD68, STAT6, CD34, ß-catenin, ALK-p80, p53, and MDM2. According to the radiological and pathological findings, the diagnosis of fibrosarcoma of pulmonary artery was made. INTERVENTIONS: The patient underwent surgical resection and the mass was excised as completely as possible. OUTCOME: Follow-up information showed no evidence of recurrence or metastasis after 3 months postresection. LESSONS: Because of the low incidence rate, nonspecific clinical symptoms, and radiological findings, primary fibrosarcoma of the pulmonary artery is commonly misdiagnosed as PTE. Pathological examination is necessary to confirm the diagnosis.