Rapid screening using pathomorphological interpretation to detect BRAFV600E mutation and microsatellite instability in colorectal cancer

Morphological basis of the lung adenocarcinoma subtypes

Lung adenocarcinoma (LUAD), which accounts for a large proportion of lung cancers, is divided into five major subtypes based on histologic characteristics. The clinical characteristics, prognosis, and responses to treatments vary among subtypes. Here, we demonstrate that the variations of cell-cell contact energy result in the LUAD subtype-specific morphogenesis. We reproduced the morphologies of the papillary LUAD subtypes with the cellular Potts Model (CPM). Simulations and experimental validations revealed modifications of cell-cell contact energy changed the morphology from a papillary-like structure to micropapillary or solid subtype-like structures. Remarkably, differential gene expression analysis revealed subtype-specific expressions of genes relating to cell adhesion. Knockdown experiments of the micropapillary upregulated ITGA11 gene resulted in the morphological changes of the spheroids produced from an LUAD cell line PC9. This work shows the consequences of gene mutations and gene expressions on patient prognosis through differences in tissue composing physical forces among LUAD subtypes.

Digital pathology-based artificial intelligence models for differential diagnosis and prognosis of sporadic odontogenic keratocysts

Odontogenic keratocyst (OKC) is a common jaw cyst with a high recurrence rate. OKC combined with basal cell carcinoma as well as skeletal and other developmental abnormalities is thought to be associated with Gorlin syndrome. Moreover, OKC needs to be differentiated from orthokeratinized odontogenic cyst and other jaw cysts. Because of the different prognosis, differential diagnosis of several cysts can contribute to clinical management. We collected 519 cases, comprising a total of 2 157 hematoxylin and eosin-stained images, to develop digital pathology-based artificial intelligence (AI) models for the diagnosis and prognosis of OKC. The Inception_v3 neural network was utilized to train and test models developed from patch-level images. Finally, whole slide image-level AI models were developed by integrating deep learning-generated pathology features with several machine learning algorithms. The AI models showed great performance in the diagnosis (AUC = 0.935, 95% CI: 0.898-0.973) and prognosis (AUC = 0.840, 95%CI: 0.751-0.930) of OKC. The advantages of multiple slides model for integrating of histopathological information are demonstrated through a comparison with the single slide model. Furthermore, the study investigates the correlation between AI features generated by deep learning and pathological findings, highlighting the interpretative potential of AI models in the pathology. Here, we have developed the robust diagnostic and prognostic models for OKC. The AI model that is based on digital pathology shows promise potential for applications in odontogenic diseases of the jaw.

Detecting microsatellite instability in colorectal cancer using Transformer-based colonoscopy image classification and retrieval

Colorectal cancer (CRC) is a major global health concern, with microsatellite instability-high (MSI-H) being a defining characteristic of hereditary nonpolyposis colorectal cancer syndrome and affecting 15% of sporadic CRCs. Tumors with MSI-H have unique features and better prognosis compared to MSI-L and microsatellite stable (MSS) tumors. This study proposed establishing a MSI prediction model using more available and low-cost colonoscopy images instead of histopathology. The experiment utilized a database of 427 MSI-H and 1590 MSS colonoscopy images and vision Transformer (ViT) with different feature training approaches to establish the MSI prediction model. The accuracy of combining pre-trained ViT features was 84% with an area under the receiver operating characteristic curve of 0.86, which was better than that of DenseNet201 (80%, 0.80) in the experiment with support vector machine. The content-based image retrieval (CBIR) approach showed that ViT features can obtain a mean average precision of 0.81 compared to 0.79 of DenseNet201. ViT reduced the issues that occur in convolutional neural networks, including limited receptive field and gradient disappearance, and may be better at interpreting diagnostic information around tumors and surrounding tissues. By using CBIR, the presentation of similar images with the same MSI status would provide more convincing deep learning suggestions for clinical use.

Development of a Pathomics-Based Model for the Prediction of Malignant Transformation in Oral Leukoplakia

Accurate prognostic stratification of oral leukoplakia (OLK) with risk of malignant transformation into oral squamous cell carcinoma is crucial. We developed an objective and powerful pathomics-based model for the prediction of malignant transformation in OLK using hematoxylin and eosin (H&E)-stained images. In total, 759 H&E-stained images from multicenter cohorts were included. A training set (n = 489), validation set (n = 196), and testing set (n = 74) were used for model development. Four deep learning methods were used to train and validate the model constructed using H&E-stained images. Pathomics features generated through deep learning combined with machine learning algorithms were used to develop a pathomics-based model. Immunohistochemical staining of Ki67, p53, and PD-L1 was used to interpret the black box of the model. Pathomics-based models predicted the malignant transformation of OLK (validation set area under curve [AUC], 0.899; testing set AUC, 0.813) and significantly identified high-risk and low-risk populations. The prediction performance of malignant transformation from dysplasia grading (validation set AUC, 0.743) was lower than that of the pathomics-based model. The expressions of Ki67, p53, and PD-L1 were correlated with various pathomics features. The pathomics-based model accurately predicted the malignant transformation of OLK and may be useful for the objective and rapid assessment of the prognosis of patients with OLK.

O3C Glass-Class: A Machine-Learning Framework for Prognostic Prediction of Ovarian Clear-Cell Carcinoma

Ovarian clear cell carcinoma (OCCC), one of the histopathological types of ovarian cancer, has a poor prognosis when it recurs; however, it is difficult to precisely predict the risk of recurrence. Here, we analyzed pathological images of OCCC to elucidate the relationship between pathological findings and recurrence, and using machine learning, we established a classifier to predict the recurrence and several other prognosis indicators of this disease. In total, 110 patients with OCCC treated with primary surgery at a single institution were enrolled in this study. We used the deep-learning neural networks to process the whole slide images of OCCC obtained by digitally scanning the original hematoxylin and eosin-stained glass slides. The images were preprocessed and used as input to the machine learning pipeline. We fine-tuned its parameters to predict the recurrence, progression-free survival, and the overall survival days of all patients. We predicted the recurrence of OCCC with an overall accuracy of 93%, area under the receiver operating characteristic curve of 0.98, and sensitivity/specificity above 0.92 using Resnet 34. Furthermore, we predicted progression-free survival/overall survival of the patients with ~90% accuracy. In conclusion, our study demonstrates the feasibility of using a machine learning system to predict different features of OCCC samples using histopathological images as input. This novel application provides accurate prognosis information and aids in the development of personalized treatment strategies.