Biology subjects

Okoshi, E. N.

Publications and source records attributed to Okoshi, E. N..

2 recordsLinked to original sources

bioRxiv2026

SortIT - A Tool For Assessing Observer Variability And Creating Ground Truth Image Classification Datasets

Interobserver variability in pathological assessments is a well-recognized challenge that impacts diagnostic reliability and disease understanding. This variability exists across many subspecialties due to the subjective nature of evaluations. Artificial intelligence (AI) applied to whole slide images has potential to standardize procedures and reduce variability in pathology, but transitioning to these technologies does not guarantee improvement. Establishing reliable ground truth datasets with consensus annotations is crucial for developing robust AI solutions. We introduce SortIT, an open-source web application that facilitates systematic creation and evaluation of ground truth image tile annotations. SortIT enables multiple annotators to independently label tiles, with flexible user permission controls. Annotated data can be exported for statistical analysis of observer variation and for creating ground truth datasets from consensus tiles. We outline protocols using SortIT for several use cases: (1) mitosis segmentation in tumor regions, (2) evaluating AI solutions for prostate cancer grading by comparing to expert consensus, and (3) granuloma classification by annotating discriminative tile-level features. Key strengths of SortIT lies in its ease of deployment, making it accessible and usable for a wide range of users. Overall, SortIT provides a valuable tool to establish high-quality ground truth datasets and comprehensively assess observer variability. Critical evaluation of ground truth quality using systematic annotation methodologies is crucial for developing accurate and generalizable diagnostic AI tools. Its open-source nature facilitates community adoption and further development.

pathology↗

bioRxiv2022

Collaborative workflow between pathologists and deep learning for evaluation of tumor cellularity in lung adenocarcinoma

Owing to the high demand for molecular testing, the reporting of tumor cellularity in cancer samples has become a mandatory task for pathologists. However, the pathological estimation of tumor cellularity is often inaccurate. We developed a collaborative workflow between pathologists and artificial intelligence (AI) models to evaluate tumor cellularity in lung cancer samples and prospectively applied it to routine practice. We also developed a quantitative model that we validated and tested on retrospectively analyzed cases and ran the model prospectively in a collaborative workflow where pathologists could access the AI results and apply adjustments (Adjusted-Score). The Adjusted-Scores were validated by comparing them with the ground truth established by manual annotation of hematoxylin-eosin slides with reference to immunostains with thyroid transcription factor-1 and napsin A. For training, validation, retrospective testing, and prospective application of the model, we used 40, 10, 50, and 151 whole slide images, respectively. The sensitivity and specificity of tumor segmentation were 97% and 87%, and the accuracy of nuclei recognition was 99%. Pathologists altered the initial scores in 87% of the cases after referring to the AI results and found that the scores became more precise after collaborating with AI. For validation of Adjusted-Score, we found the Adjusted-Score was significantly closer to the ground truth than non-AI-aided estimates (p<0.05). Thus, an AI-based model was successfully implemented into the routine practice of pathological investigations. The proposed model for tumor cell counting efficiently supported the pathologists to improve the prediction of tumor cellularity for genetic tests.

pathology↗