Biology subjects

Fukuoka, J.

Publications and source records attributed to Fukuoka, J..

5 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

Deep learning for histopathological subtyping and grading of lung adenocarcinoma

The histopathological distinction of lung adenocarcinoma (LADC) subtypes is subject to high inter-observer variability, which can compromise the optimal assessment of the patient prognosis. Therefore, this study developed convolutional neural networks (CNNs) capable of distinguishing LADC subtypes and predicting disease-specific survival, according to the LADC tumour grades established recently by the International Association for the Study of Lung Cancer pathology committee. Consensus LADC ground truth histopathological images were obtained from seventeen expert pulmonary pathologists and one pathologist in training. Two deep learning models (AI-1 and AI-2) were trained with EfficientNet b3 architecture to predict eight different LADC classes (lepidic, acinar, papillary, micropapillary, solid, invasive mucinous adenocarcinoma, other carcinoma types, and no carcinoma cells). Furthermore, the trained models were tested on an independent cohort of 133 patients. The models achieved high precision, recall, and F1-scores exceeding 0.90 for most of the LADC classes. Clear stratification of the three LADC grades was reached in predicting the disease-specific survival by the two models. Moreover, the grading prediction of one of the trained models was more accurate than those of 14 out of 15 pulmonary pathologists involved in the study (p=0.0003). Both trained models showed high stability in the segmentation of each pair of predicted grades with low variation in the hazard ratio across 200 bootstrapped samples. These findings indicate that the trained CNNs improve the diagnostic accuracy of the pathologist, standardise LADC subtype recognition, and refine LADC grade assessment. Thus, the trained models are promising tools that may assist in the routine evaluation of LADC subtypes and grades in clinical practice.

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↗

bioRxiv2020

Resolving the spatial and cellular architecture of lung adenocarcinoma by multi-region single-cell sequencing

Little is known of the geospatial architecture of individual cell populations in lung adenocarcinoma (LUAD) evolution. Here, we perform single-cell RNA sequencing of 186,916 cells from 5 early-stage LUADs and 14 multi-region normal lung tissues of defined spatial proximities from the tumors. We show that cellular lineages, states, and transcriptomic features geospatially evolve across normal regions to LUADs. LUADs also exhibit pronounced intratumor cell heterogeneity within single sites and transcriptional lineage-plasticity programs. T regulatory cell phenotypes are increased in normal tissues with proximity to LUAD, in contrast to diminished signatures and fractions of cytotoxic CD8+ T cells, antigen-presenting macrophages and inflammatory dendritic cells. We further find that the LUAD ligand-receptor interactome harbors increased expression of epithelial CD24 which mediates pro-tumor phenotypes. These data provide a spatial atlas of LUAD evolution, and a resource for identification of targets for its treatment. Statement of significanceThe geospatial ecosystem of the peripheral lung and early-stage LUAD is not known. Our multi-region single-cell sequencing analyses unravel cell populations, states, and phenotypes in the spatial and ecological evolution of LUAD from the lung that comprise high-potential targets for early interception.

cancer biology↗

bioRxiv2020

Genomic and TCR Repertoire Intratumor Heterogeneity of Small-cell Lung Cancer and its Impact on Survival

Small-cell lung cancer (SCLC) is speculated to harbor complex genomic intratumor heterogeneity (ITH) associated with high recurrence rate and suboptimal response to immunotherapy. Here, we revealed a rather homogeneous mutational landscape but extremely suppressed and heterogeneous T cell receptor (TCR) repertoire in SCLCs. Higher mutational burden, lower chromosomal copy number aberration (CNA) burden, less CNA ITH and less TCR ITH were associated with longer overall survival of SCLC patients. Compared to non-small cell lung cancers (NSCLCs), SCLCs had similar predicted neoantigen burden and mutational ITH, but significantly more suppressed and heterogeneous TCR repertoire that may be associated with higher CNA burden and CNA ITH in SCLC. Novel therapeutic strategies targeting CNA could potentially improve the tumor immune microenvironment and response to immunotherapy in SCLC.

genomics↗