Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology

Lung squamous cell carcinoma in situ (SCIS) is the preinvasive precursor lesion of lung squamous cell carcinoma (SCC). Only around two-thirds of these lesions progress to invasive cancer, while one-third undergo spontaneous regression, which presents a significant clinical challenge due to the risk...

Full description

Saved in:
Bibliographic Details
Main Authors: Alon Vigdorovits, Gheorghe-Emilian Olteanu, Ovidiu Tica, Andrei Pascalau, Monica Boros, Ovidiu Pop
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Bioengineering
Subjects:
Online Access:https://www.mdpi.com/2306-5354/12/4/377
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712519341408256
author Alon Vigdorovits
Gheorghe-Emilian Olteanu
Ovidiu Tica
Andrei Pascalau
Monica Boros
Ovidiu Pop
author_facet Alon Vigdorovits
Gheorghe-Emilian Olteanu
Ovidiu Tica
Andrei Pascalau
Monica Boros
Ovidiu Pop
author_sort Alon Vigdorovits
collection DOAJ
description Lung squamous cell carcinoma in situ (SCIS) is the preinvasive precursor lesion of lung squamous cell carcinoma (SCC). Only around two-thirds of these lesions progress to invasive cancer, while one-third undergo spontaneous regression, which presents a significant clinical challenge due to the risk of overtreatment. The ability to predict the evolution of SCIS lesions can significantly impact patient management. Our study explores the use of computational pathology in predicting the evolution of SCIS. We used a dataset consisting of 112 H&E-stained whole slide images (WSIs) that were obtained from the Image Data Resource public repository. The dataset corresponded to tumors of patients who underwent biopsies of SCIS lesions and were subsequently followed up by bronchoscopy and CT scans to monitor for progression to SCC. We used this dataset to train two models: a pathomics-based ridge classifier trained on 80 principal components derived from almost 2000 extracted features and a deep convolutional neural network with a modified ResNet18 architecture. The performance of both approaches in predicting progression was assessed. The pathomics-based ridge classifier model obtained an F1-score of 0.77, precision of 0.80, and recall of 0.77. The deep learning model performance was similar, with a WSI-level F1-score of 0.80, precision of 0.71, and recall of 0.90. These findings highlight the potential of computational pathology approaches in providing insights into the evolution of SCIS. Larger datasets will be required in order to train highly accurate models. In the future, computational pathology could be used in predicting outcomes in other preinvasive lesions.
format Article
id doaj-art-dbf680ed23e44a02b5c450e5c8fc3236
institution DOAJ
issn 2306-5354
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Bioengineering
spelling doaj-art-dbf680ed23e44a02b5c450e5c8fc32362025-08-20T03:14:14ZengMDPI AGBioengineering2306-53542025-04-0112437710.3390/bioengineering12040377Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational PathologyAlon Vigdorovits0Gheorghe-Emilian Olteanu1Ovidiu Tica2Andrei Pascalau3Monica Boros4Ovidiu Pop5Department of Pathology, Bihor County Clinical Emergency Hospital, 410169 Oradea, RomaniaDepartment of Pathology, British Columbia Cancer Agency, Vancouver, BC V5Z 4E6, CanadaDepartment of Pathology, Bihor County Clinical Emergency Hospital, 410169 Oradea, RomaniaDepartment of Pathology, Bihor County Clinical Emergency Hospital, 410169 Oradea, RomaniaDepartment of Pathology, Bihor County Clinical Emergency Hospital, 410169 Oradea, RomaniaDepartment of Pathology, Bihor County Clinical Emergency Hospital, 410169 Oradea, RomaniaLung squamous cell carcinoma in situ (SCIS) is the preinvasive precursor lesion of lung squamous cell carcinoma (SCC). Only around two-thirds of these lesions progress to invasive cancer, while one-third undergo spontaneous regression, which presents a significant clinical challenge due to the risk of overtreatment. The ability to predict the evolution of SCIS lesions can significantly impact patient management. Our study explores the use of computational pathology in predicting the evolution of SCIS. We used a dataset consisting of 112 H&E-stained whole slide images (WSIs) that were obtained from the Image Data Resource public repository. The dataset corresponded to tumors of patients who underwent biopsies of SCIS lesions and were subsequently followed up by bronchoscopy and CT scans to monitor for progression to SCC. We used this dataset to train two models: a pathomics-based ridge classifier trained on 80 principal components derived from almost 2000 extracted features and a deep convolutional neural network with a modified ResNet18 architecture. The performance of both approaches in predicting progression was assessed. The pathomics-based ridge classifier model obtained an F1-score of 0.77, precision of 0.80, and recall of 0.77. The deep learning model performance was similar, with a WSI-level F1-score of 0.80, precision of 0.71, and recall of 0.90. These findings highlight the potential of computational pathology approaches in providing insights into the evolution of SCIS. Larger datasets will be required in order to train highly accurate models. In the future, computational pathology could be used in predicting outcomes in other preinvasive lesions.https://www.mdpi.com/2306-5354/12/4/377computational pathologydeep learningsquamous cell carcinoma in situ
spellingShingle Alon Vigdorovits
Gheorghe-Emilian Olteanu
Ovidiu Tica
Andrei Pascalau
Monica Boros
Ovidiu Pop
Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology
Bioengineering
computational pathology
deep learning
squamous cell carcinoma in situ
title Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology
title_full Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology
title_fullStr Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology
title_full_unstemmed Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology
title_short Predicting the Evolution of Lung Squamous Cell Carcinoma In Situ Using Computational Pathology
title_sort predicting the evolution of lung squamous cell carcinoma in situ using computational pathology
topic computational pathology
deep learning
squamous cell carcinoma in situ
url https://www.mdpi.com/2306-5354/12/4/377
work_keys_str_mv AT alonvigdorovits predictingtheevolutionoflungsquamouscellcarcinomainsituusingcomputationalpathology
AT gheorgheemilianolteanu predictingtheevolutionoflungsquamouscellcarcinomainsituusingcomputationalpathology
AT ovidiutica predictingtheevolutionoflungsquamouscellcarcinomainsituusingcomputationalpathology
AT andreipascalau predictingtheevolutionoflungsquamouscellcarcinomainsituusingcomputationalpathology
AT monicaboros predictingtheevolutionoflungsquamouscellcarcinomainsituusingcomputationalpathology
AT ovidiupop predictingtheevolutionoflungsquamouscellcarcinomainsituusingcomputationalpathology