Development and validation of a deep learning system for ascites cytopathology interpretation
- 1 November 2020
- journal article
- research article
- Published by Springer Science and Business Media LLC in Gastric Cancer
- Vol. 23 (6), 1041-1050
- https://doi.org/10.1007/s10120-020-01093-1
Abstract
Background Early diagnosis of Peritoneal metastasis (PM) is clinically significant regarding optimal treatment selection and avoidance of unnecessary surgical procedures. Cytopathology plays an important role in early screening of PM. We aimed to develop a deep learning (DL) system to achieve intelligent cytopathology interpretation, especially in ascites cytopathology. Methods The original ascites cytopathology image dataset consists of 139 patients' original hematoxylin-eosin (HE) and Papanicolaou (PAP) Staining images. DL system was developed using transfer learning (TL) to achieve cell detection and classification. Pre-trained alexnet, vgg16, goolenet, resnet18 and resnet50 models were studied. Cell detection dataset consists of 176 cropped images with 6573 annotated cell bounding boxes. Cell classification data set consists of 487 cropped images with 18,558 and 6089 annotated malignant and benign cells in total, respectively. Results We established a novel ascites cytopathology image dataset and achieved automatically cell detection and classification. DetectionNet based on Faster R-CNN using pre-trained resnet18 achieved cell detection with 87.22% of cells' Intersection of Union (IoU) bigger than the threshold of 0.5. The mean average precision (mAP) was 0.8316. The ClassificationNet based on resnet50 achieved the greatest performance in cell classification with AUC = 0.8851, Precision = 96.80%, FNR = 4.73%. The DL system integrating the separately trained DetectionNet and Classificationnet showed great performance in the cytopathology image interpretation. Conclusions We demonstrate that the integration of DL can improve the efficiency of healthcare. The DL system we developed using TL techniques achieved accurate cytopathology interpretation, and had great potential to be integrated into clinician workflow.Funding Information
- National Key Research and Development Program of China (2017YFA0700904)
- National Natural Science Foundation of China (61620106010)
- Capital’s Funds for Health Improvement and Research (2018-2Z-1026)
This publication has 37 references indexed in Scilit:
- Amplify scientific discovery with artificial intelligenceScience, 2014
- Clinical Significance of Cytological Status of Peritoneal Lavage Fluid During Intraperitoneal Chemotherapy for Gastric Cancer with Overt Peritoneal DisseminationAnnals of Surgical Oncology, 2014
- Guidelines for pancreaticobiliary cytology from the Papanicolaou Society of Cytopathology: A reviewCancer Cytopathology, 2014
- Digital Whole Slide Imaging in CytologyArchives of Pathology & Laboratory Medicine, 2014
- Digital Slide Imaging in Cervicovaginal Cytology: A Pilot StudyArchives of Pathology & Laboratory Medicine, 2012
- Prognostic significance of peritoneal washing cytology in patients with gastric cancerBritish Journal of Surgery, 2011
- From critical values to critical diagnosesCancer Cytopathology, 2011
- Quantitative prognostic indicators of peritoneal dissemination of gastric cancerEuropean Journal of Surgical Oncology, 2006
- Comparison of CT and 18F-FDG PET for Detecting Peritoneal Metastasis on the Preoperative Evaluation for Gastric CarcinomaKorean Journal of Radiology, 2006
- Endoscopic Ultrasound-Guided Fine-Needle Aspiration Biopsy of Liver Lesions: Histological and Cytological AssessmentEndoscopy, 2003