AI Article Synopsis

  • A predictive model using weakly supervised deep learning techniques is developed to forecast major pathological response (MPR) in patients with resectable non-small cell lung cancer (NSCLC) undergoing neoadjuvant chemoimmunotherapy (NICT) by analyzing whole slide images (WSIs).
  • The study involved 186 NSCLC patients and employed advanced deep learning architectures like DenseNet121, ResNet50, and Inception V3 to assess WSIs through various data augmentation and normalization methods.
  • Results indicated that histology was a significant prognostic factor for MPR, with DenseNet121 performing best among the models, while integrating clinical data with pathomics features enhanced model accuracy and yielded promising AUC scores in validation and testing

Article Abstract

Objective: Develop a predictive model utilizing weakly supervised deep learning techniques to accurately forecast major pathological response (MPR) in patients with resectable non-small cell lung cancer (NSCLC) undergoing neoadjuvant chemoimmunotherapy (NICT), by leveraging whole slide images (WSIs).

Methods: This retrospective study examined pre-treatment WSIs from 186 patients with non-small cell lung cancer (NSCLC), using a weakly supervised learning framework. We employed advanced deep learning architectures, including DenseNet121, ResNet50, and Inception V3, to analyze WSIs on both micro (patch) and macro (slide) levels. The training process incorporated innovative data augmentation and normalization techniques to bolster the robustness of the models. We evaluated the performance of these models against traditional clinical predictors and integrated them with a novel pathomics signature, which was developed using multi-instance learning algorithms that facilitate feature aggregation from patch-level probability distributions.

Results: Univariate and multivariable analyses confirmed histology as a statistically significant prognostic factor for MPR (-value< 0.05). In patch model evaluations, DenseNet121 led in the validation set with an area under the curve (AUC) of 0.656, surpassing ResNet50 (AUC = 0.626) and Inception V3 (AUC = 0.654), and showed strong generalization in external testing (AUC = 0.611). Further evaluation through visual inspection of patch-level data integration into WSIs revealed XGBoost's superior class differentiation and generalization, achieving the highest AUCs of 0.998 in training and robust scores of 0.818 in validation and 0.805 in testing. Integrating pathomics features with clinical data into a nomogram yielded AUC of 0.819 in validation and 0.820 in testing, enhancing discriminative accuracy. Gradient-weighted Class Activation Mapping (Grad-CAM) and feature aggregation methods notably boosted the model's interpretability and feature modeling.

Conclusion: The application of weakly supervised deep learning to WSIs offers a powerful tool for predicting MPR in NSCLC patients treated with NICT.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11449764PMC
http://dx.doi.org/10.3389/fimmu.2024.1453232DOI Listing

Publication Analysis

Top Keywords

weakly supervised
16
deep learning
16
supervised deep
12
non-small cell
12
cell lung
12
lung cancer
12
major pathological
8
pathological response
8
neoadjuvant chemoimmunotherapy
8
cancer nsclc
8

Similar Publications

Immune checkpoint inhibitors (ICI) have become integral to treatment of non-small cell lung cancer (NSCLC). However, reliable biomarkers predictive of immunotherapy efficacy are limited. Here, we introduce HistoTME, a novel weakly supervised deep learning approach to infer the tumor microenvironment (TME) composition directly from histopathology images of NSCLC patients.

View Article and Find Full Text PDF

Background: Patient-reported outcome measures (PROMs) have become crucial in assessing cataract surgery, especially with increasing patient expectations. The RayPro database offers a platform for tracking PROMs after surgery. The purpose of this study is to investigate determinants of patient satisfaction following cataract surgery by analysing PROMs.

View Article and Find Full Text PDF

Purpose: Training machine learning models to segment tumors and other anomalies in medical images is an important step for developing diagnostic tools but generally requires manually annotated ground truth segmentations, which necessitates significant time and resources. We aim to develop a pipeline that can be trained using readily accessible binary image-level classification labels, to effectively segment regions of interest without requiring ground truth annotations.

Methods: This work proposes the use of a deep superpixel generation model and a deep superpixel clustering model trained simultaneously to output weakly supervised brain tumor segmentations.

View Article and Find Full Text PDF

The United Nations sustainable development agenda emphasizes the importance of forests. China's forests cover 5% of the world's forest area, significantly influencing global climate and ecology. In recent decades, China's forests have undergone notable changes.

View Article and Find Full Text PDF

Proximity adjusted centroid mapping for accurate detection of nuclei in dense 3D cell systems.

Comput Biol Med

December 2024

Laboratory of Cell Biology and Histology, University of Antwerp, 2610, Antwerpen, Belgium; IMARK, University of Antwerp, Belgium; Antwerp Centre for Advanced Microscopy, University of Antwerp, 2610, Antwerpen, Belgium; μNeuro Research Centre of Excellence, University of Antwerp, 2610, Antwerpen, Belgium. Electronic address:

In the past decade, deep learning algorithms have surpassed the performance of many conventional image segmentation pipelines. Powerful models are now available for segmenting cells and nuclei in diverse 2D image types, but segmentation in 3D cell systems remains challenging due to the high cell density, the heterogenous resolution and contrast across the image volume, and the difficulty in generating reliable and sufficient ground truth data for model training. Reasoning that most image processing applications rely on nuclear segmentation but do not necessarily require an accurate delineation of their shapes, we implemented Proximity Adjusted Centroid MAPping (PAC-MAP), a 3D U-net based method that predicts the position of nuclear centroids and their proximity to other nuclei.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!