A machine learning model for separating epithelial and stromal regions in oral cavity squamous cell carcinomas using H&E-stained histology images: A multi-center, retrospective study

Oral squamous cell carcinoma detection using EfficientNet on histopathological images

Introduction

Oral Squamous Cell Carcinoma (OSCC) poses a significant challenge in oncology due to the absence of precise diagnostic tools, leading to delays in identifying the condition. Current diagnostic methods for OSCC have limitations in accuracy and efficiency, highlighting the need for more reliable approaches. This study aims to explore the discriminative potential of histopathological images of oral epithelium and OSCC. By utilizing a database containing 1224 images from 230 patients, captured at varying magnifications and publicly available, a customized deep learning model based on EfficientNetB3 was developed. The model's objective was to differentiate between normal epithelium and OSCC tissues by employing advanced techniques such as data augmentation, regularization, and optimization.

Methods

The research utilized a histopathological imaging database for Oral Cancer analysis, incorporating 1224 images from 230 patients. These images, taken at various magnifications, formed the basis for training a specialized deep learning model built upon the EfficientNetB3 architecture. The model underwent training to distinguish between normal epithelium and OSCC tissues, employing sophisticated methodologies including data augmentation, regularization techniques, and optimization strategies.

Results

The customized deep learning model achieved significant success, showcasing a remarkable 99% accuracy when tested on the dataset. This high accuracy underscores the model's efficacy in effectively discerning between normal epithelium and OSCC tissues. Furthermore, the model exhibited impressive precision, recall, and F1-score metrics, reinforcing its potential as a robust diagnostic tool for OSCC.

Discussion

This research demonstrates the promising potential of employing deep learning models to address the diagnostic challenges associated with OSCC. The model's ability to achieve a 99% accuracy rate on the test dataset signifies a considerable leap forward in earlier and more accurate detection of OSCC. Leveraging advanced techniques in machine learning, such as data augmentation and optimization, has shown promising results in improving patient outcomes through timely and precise identification of OSCC.

Computational pathology identifies immune-mediated collagen disruption to predict clinical outcomes in gynecologic malignancies

BACKGROUND

The role of immune cells in collagen degradation within the tumor microenvironment (TME) is unclear. Immune cells, particularly tumor-infiltrating lymphocytes (TILs), are known to alter the extracellular matrix, affecting cancer progression and patient survival. However, the quantitative evaluation of the immune modulatory impact on collagen architecture within the TME remains limited.

METHODS

We introduce CollaTIL, a computational pathology method that quantitatively characterizes the immune-collagen relationship within the TME of gynecologic cancers, including high-grade serous ovarian (HGSOC), cervical squamous cell carcinoma (CSCC), and endometrial carcinomas. CollaTIL aims to investigate immune modulatory impact on collagen architecture within the TME, aiming to uncover the interplay between the immune system and tumor progression.

RESULTS

We observe that an increased immune infiltrate is associated with chaotic collagen architecture and higher entropy, while immune sparse TME exhibits ordered collagen and lower entropy. Importantly, CollaTIL-associated features that stratify disease risk are linked with gene signatures corresponding to TCA-Cycle in CSCC, and amino acid metabolism, and macrophages in HGSOC.

CONCLUSIONS

CollaTIL uncovers a relationship between immune infiltration and collagen structure in the TME of gynecologic cancers. Integrating CollaTIL with genomic analysis offers promising opportunities for future therapeutic strategies and enhanced prognostic assessments in gynecologic oncology.

Computational Image and Molecular Analysis Reveal Unique Prognostic Features of Immune Architecture in African Versus European American Women with Endometrial Cancer

Endometrial cancer (EC) disproportionately affects African American (AA) women in terms of progression and death. In our study, we sought to employ computerized image and bioinformatic analysis to tease out morphologic and molecular differences in EC between AA and European-American (EA) populations. We identified the differences in immune cell spatial patterns between AA and EA populations with markers of tumor biology, including histologic and molecular subtypes. The models performed best when they were trained and validated using data from the same population. Unsupervised clustering revealed a distinct association between immune cell features and known molecular subtypes of endometrial cancer that varied between AA and EA populations. Our genomic analysis revealed two distinct and novel gene sets with mutations associated with improved prognosis in AA and EA patients. Our study findings suggest the need for population-specific risk prediction models for women with endometrial cancer.

OralNet: Fused Optimal Deep Features Framework for Oral Squamous Cell Carcinoma Detection

Humankind is witnessing a gradual increase in cancer incidence, emphasizing the importance of early diagnosis and treatment, and follow-up clinical protocols. Oral or mouth cancer, categorized under head and neck cancers, requires effective screening for timely detection. This study proposes a framework, OralNet, for oral cancer detection using histopathology images. The research encompasses four stages: (i) Image collection and preprocessing, gathering and preparing histopathology images for analysis; (ii) feature extraction using deep and handcrafted scheme, extracting relevant features from images using deep learning techniques and traditional methods; (iii) feature reduction artificial hummingbird algorithm (AHA) and concatenation: Reducing feature dimensionality using AHA and concatenating them serially and (iv) binary classification and performance validation with three-fold cross-validation: Classifying images as healthy or oral squamous cell carcinoma and evaluating the framework's performance using three-fold cross-validation. The current study examined whole slide biopsy images at 100× and 400× magnifications. To establish OralNet's validity, 3000 cropped and resized images were reviewed, comprising 1500 healthy and 1500 oral squamous cell carcinoma images. Experimental results using OralNet achieved an oral cancer detection accuracy exceeding 99.5%. These findings confirm the clinical significance of the proposed technique in detecting oral cancer presence in histology slides.