Dataset Information

Enabling large-scale screening of Barrett's esophagus using weakly supervised deep learning in histopathology.

ABSTRACT: Timely detection of Barrett's esophagus, the pre-malignant condition of esophageal adenocarcinoma, can improve patient survival rates. The Cytosponge-TFF3 test, a non-endoscopic minimally invasive procedure, has been used for diagnosing intestinal metaplasia in Barrett's. However, it depends on pathologist's assessment of two slides stained with H&E and the immunohistochemical biomarker TFF3. This resource-intensive clinical workflow limits large-scale screening in the at-risk population. To improve screening capacity, we propose a deep learning approach for detecting Barrett's from routinely stained H&E slides. The approach solely relies on diagnostic labels, eliminating the need for expensive localized expert annotations. We train and independently validate our approach on two clinical trial datasets, totaling 1866 patients. We achieve 91.4% and 87.3% AUROCs on discovery and external test datasets for the H&E model, comparable to the TFF3 model. Our proposed semi-automated clinical workflow can reduce pathologists' workload to 48% without sacrificing diagnostic performance, enabling pathologists to prioritize high risk cases.

SUBMITTER: Bouzid K

PROVIDER: S-EPMC10928093 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Enabling large-scale screening of Barrett's esophagus using weakly supervised deep learning in histopathology.

Bouzid Kenza K Sharma Harshita H Killcoyne Sarah S Castro Daniel C DC Schwaighofer Anton A Ilse Max M Salvatelli Valentina V Oktay Ozan O Murthy Sumanth S Bordeaux Lucas L Moore Luiza L O'Donovan Maria M Thieme Anja A Nori Aditya A Gehrung Marcel M Alvarez-Valle Javier J

Nature communications 20240311 1

Timely detection of Barrett's esophagus, the pre-malignant condition of esophageal adenocarcinoma, can improve patient survival rates. The Cytosponge-TFF3 test, a non-endoscopic minimally invasive procedure, has been used for diagnosing intestinal metaplasia in Barrett's. However, it depends on pathologist's assessment of two slides stained with H&E and the immunohistochemical biomarker TFF3. This resource-intensive clinical workflow limits large-scale screening in the at-risk population. To imp ...[more]

PMID: 38467600

Similar Datasets

Project description:BackgroundPancreatic ductal carcinoma patients have a really poor prognosis given its difficult early detection and the lack of early symptoms. Digital pathology is routinely used by pathologists to diagnose the disease. However, visually inspecting the tissue is a time-consuming task, which slows down the diagnostic procedure. With the advances occurred in the area of artificial intelligence, specifically with deep learning models, and the growing availability of public histology data, clinical decision support systems are being created. However, the generalization capabilities of these systems are not always tested, nor the integration of publicly available datasets for pancreatic ductal carcinoma detection (PDAC).MethodsIn this work, we explored the performace of two weakly-supervised deep learning models using the two more widely available datasets with pancreatic ductal carcinoma histology images, The Cancer Genome Atlas Project (TCGA) and the Clinical Proteomic Tumor Analysis Consortium (CPTAC). In order to have sufficient training data, the TCGA dataset was integrated with the Genotype-Tissue Expression (GTEx) project dataset, which contains healthy pancreatic samples.ResultsWe showed how the model trained on CPTAC generalizes better than the one trained on the integrated dataset, obtaining an inter-dataset accuracy of 90.62% ± 2.32 and an outer-dataset accuracy of 92.17% when evaluated on TCGA + GTEx. Furthermore, we tested the performance on another dataset formed by tissue micro-arrays, obtaining an accuracy of 98.59%. We showed how the features learned in an integrated dataset do not differentiate between the classes, but between the datasets, noticing that a stronger normalization might be needed when creating clinical decision support systems with datasets obtained from different sources. To mitigate this effect, we proposed to train on the three available datasets, improving the detection performance and generalization capabilities of a model trained only on TCGA + GTEx and achieving a similar performance to the model trained only on CPTAC.ConclusionsThe integration of datasets where both classes are present can mitigate the batch effect present when integrating datasets, improving the classification performance, and accurately detecting PDAC across different datasets.

Project description:(1) Background: The Fuhrman grading (FG) system is widely used in the management of clear cell renal cell carcinoma (ccRCC). However, it is affected by observer variability and irreproducibility in clinical practice. We aimed to use a deep learning multi-class model called SSL-CLAM to assist in diagnosing the FG status of ccRCC patients using digitized whole slide images (WSIs). (2) Methods: We recruited 504 eligible ccRCC patients from The Cancer Genome Atlas (TCGA) cohort and obtained 708 hematoxylin and eosin-stained WSIs for the development and internal validation of the SSL-CLAM model. Additionally, we obtained 445 WSIs from 188 ccRCC eligible patients in the Clinical Proteomic Tumor Analysis Consortium (CPTAC) cohort as an independent external validation set. A human-machine fusion approach was used to validate the added value of the SSL-CLAM model for pathologists. (3) Results: The SSL-CLAM model successfully diagnosed the five FG statuses (Grade-0, 1, 2, 3, and 4) of ccRCC, and achieved AUCs of 0.917 and 0.887 on the internal and external validation sets, respectively, outperforming a junior pathologist. For the normal/tumor classification (Grade-0, Grade-1/2/3/4) task, the SSL-CLAM model yielded AUCs close to 1 on both the internal and external validation sets. The SSL-CLAM model achieved a better performance for the two-tiered FG (Grade-0, Grade-1/2, and Grade-3/4) task, with AUCs of 0.936 and 0.915 on the internal and external validation sets, respectively. The human-machine diagnostic performance was superior to that of the SSL-CLAM model, showing promising prospects. In addition, the high-attention regions of the SSL-CLAM model showed that with an increasing FG status, the cell nuclei in the tumor region become larger, with irregular contours and increased cellular pleomorphism. (4) Conclusions: Our findings support the feasibility of using deep learning and human-machine fusion methods for FG classification on WSIs from ccRCC patients, which may assist pathologists in making diagnostic decisions.

Dataset Information

Enabling large-scale screening of Barrett's esophagus using weakly supervised deep learning in histopathology.

Publications

Enabling large-scale screening of Barrett's esophagus using weakly supervised deep learning in histopathology.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets