Automatic analysis of nuclear features reveals a non-tumoral predictor of tumor grade in bladder cancer.

BACKGROUND & OBJECTIVES: Tumor grade determines prognosis in urothelial carcinoma. The classification of low and high grade is based on nuclear morphological features that include nuclear size, hyperchromasia and pleomorphism. These features are subjectively assessed by the pathologists and are not numerically measured, which leads to high rates of interobserver variability. The purpose of this study is to assess the value of a computer-based image analysis tool for identifying predictors of tumor grade in bladder cancer. METHODS: Four hundred images of urothelial tumors were graded by five pathologists and two expert genitourinary pathologists using a scale of 1 (lowest grade) to 5 (highest grade). A computer algorithm was used to automatically segment the nuclei and to provide morphometric parameters for each nucleus, which were used to establish the grading algorithm. Grading algorithm was compared to pathologists' agreement. RESULTS: Comparison of the grading scores of the five pathologists with the expert genitourinary pathologists score showed agreement rates between 88.5% and 97.5%.The agreement rate between the two expert genitourinary pathologists was 99.5%. The quantified algorithm based conventional parameters that determine the grade (nuclear size, pleomorphism and hyperchromasia) showed > 85% agreement with the expert genitourinary pathologists. Surprisingly, the parameter that was most associated with tumor grade was the 10th percentile of the nuclear area, and high grade was associated with lower 10th percentile nuclei, caused by the presence of more inflammatory cells in the high-grade tumors. CONCLUSION: Quantitative nuclear features could be applied to determine urothelial carcinoma grade and explore new biologically explainable parameters with better correlation to grade than those currently used.

Detection of Muscularis propria Invasion in Urothelial Carcinoma Using Artificial Intelligence.

Background & Objective: Assessment of muscularis propria invasion is a crucial step in the management of urothelial carcinoma since it necessitates aggressive treatment. The diagnosis of muscle invasion is a challenging process for pathologists. Artificial intelligence is developing rapidly and being implemented in various fields of pathology. The purpose of this study was to develop an algorithm for the detection of muscularis propria invasion in urothelial carcinoma. Methods: The Training cohort consisted of 925 images from 50 specimens of urothelial carcinoma. Ninety-seven images from 10 new specimens were used as a validation cohort. Clinical validation used 127 whole specimens with a total of 617 slides. The algorithm determined areas where tumor and muscularis propria events were in nearest proximity, and presented these areas to the pathologist. Results: Analytical evaluation showed a sensitivity of 72% for muscularis propria and 65% for tumor, and a specificity of 46% and 77% for muscularis propria and tumor detection, respectively. The incorporation of the spatial proximity factor between muscularis propria and tumor in the clinical validation significantly improved the detection of muscularis propria invasion, as the algorithm managed to identify all except for one case with muscle invasive bladder cancer in the clinical validation cohort. The case missed by the algorithm was nested urothelial carcinoma, a rare subtype with unusual morphologic features. The pathologist managed to identify muscle invasion based on the images provided by the algorithm in a short time, with an average of approximately 5 s. Conclusion: The algorithm we developed may greatly aid in accurate identification of muscularis propria invasion by imitating the thought process of the pathologist.