Deep learning based digital cell profiles for risk stratification of urine cytology images

• Published in: Cytometry. Part A Vol. 99; no. 7; pp. 732 - 742
• Main Authors: Awan, Ruqayya, Benes, Ksenija, Azam, Ayesha, Song, Tzu‐Hsi, Shaban, Muhammad, Verrill, Clare, Tsang, Yee Wah, Snead, David, Minhas, Fayyaz, Rajpoot, Nasir
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.07.2021; Wiley Subscription Services, Inc
• Subjects: Annotations; Bladder; cell classification; cell detection; cell segmentation; Cellular biology; Cytodiagnosis; Cytology; Deep Learning; Depth profiling; Diagnosis; Digital imaging; digital risk; Histopathology; Machine learning; Malignancy; Medical imaging; Morphology; oversampling; Risk; Risk Assessment; ROC Curve; The Paris System; Urine; urine cytology; The Paris System; deep learning; urine cytology; cell classification; cell segmentation; cell detection; digital risk; oversampling
• ISSN: 1552-4922; 1552-4930; 1552-4930
• DOI: 10.1002/cyto.a.24313

Urine cytology is a test for the detection of high‐grade bladder cancer. In clinical practice, the pathologist would manually scan the sample under the microscope to locate atypical and malignant cells. They would assess the morphology of these cells to make a diagnosis. Accurate identification of atypical and malignant cells in urine cytology is a challenging task and is an essential part of identifying different diagnosis with low‐risk and high‐risk malignancy. Computer‐assisted identification of malignancy in urine cytology can be complementary to the clinicians for treatment management and in providing advice for carrying out further tests. In this study, we presented a method for identifying atypical and malignant cells followed by their profiling to predict the risk of diagnosis automatically. For cell detection and classification, we employed two different deep learning‐based approaches. Based on the best performing network predictions at the cell level, we identified low‐risk and high‐risk cases using the count of atypical cells and the total count of atypical and malignant cells. The area under the receiver operating characteristic (ROC) curve shows that a total count of atypical and malignant cells is comparably better at diagnosis as compared to the count of malignant cells only. We obtained area under the ROC curve with the count of malignant cells and the total count of atypical and malignant cells as 0.81 and 0.83, respectively. Our experiments also demonstrate that the digital risk could be a better predictor of the final histopathology‐based diagnosis. We also analyzed the variability in annotations at both cell and whole slide image level and also explored the possible inherent rationales behind this variability.