Chinese Journal of Cancer Research

Deep learning-based multi-task prediction of response to neoadjuvant chemotherapy using multiscale whole slide images in breast cancer: A multicenter study

doi: 10.21147/j.issn.1000-9604.2025.01.03

ObjectiveEarly predicting response before neoadjuvant chemotherapy (NAC) is crucial for personalized treatment plans for locally advanced breast cancer patients. We aim to develop a multi-task model using multiscale whole slide images (WSIs) features to predict the response to breast cancer NAC more finely.MethodsThis work collected 1,670 whole slide images for training and validation sets, internal testing sets, external testing sets, and prospective testing sets of the weakly-supervised deep learning-based multi-task model (DLMM) in predicting treatment response and pCR to NAC. Our approach models two-by-two feature interactions across scales by employing concatenate fusion of single-scale feature representations, and controls the expressiveness of each representation via a gating-based attention mechanism.ResultsIn the retrospective analysis, DLMM exhibited excellent predictive performance for the prediction of treatment response, with area under the receiver operating characteristic curves (AUCs) of 0.869 [95% confidence interval (95% CI): 0.806−0.933] in the internal testing set and 0.841 (95% CI: 0.814−0.867) in the external testing sets. For the pCR prediction task, DLMM reached AUCs of 0.865 (95% CI: 0.763−0.964) in the internal testing and 0.821 (95% CI: 0.763−0.878) in the pooled external testing set. In the prospective testing study, DLMM also demonstrated favorable predictive performance, with AUCs of 0.829 (95% CI: 0.754−0.903) and 0.821 (95% CI: 0.692−0.949) in treatment response and pCR prediction, respectively. DLMM significantly outperformed the baseline models in all testing sets (P<0.05). Heatmaps were employed to interpret the decision-making basis of the model. Furthermore, it was discovered that high DLMM scores were associated with immune-related pathways and cells in the microenvironment during biological basis exploration.ConclusionsThe DLMM represents a valuable tool that aids clinicians in selecting personalized treatment strategies for breast cancer patients.

关键词: Artificial intelligence, breast cancer, digital pathology, whole slide images

Deep learning-based differentiation of benign and malignant thyroid follicular neoplasms on multiscale intraoperative frozen pathological images: A multicenter diagnostic study

doi: 10.21147/j.issn.1000-9604.2025.03.02

ObjectiveThis study aims to develop a deep multiscale image learning system (DMILS) to differentiate malignant from benign thyroid follicular neoplasms on multiscale whole-slide images (WSIs) of intraoperative frozen pathological images.MethodsA total of 1,213 patients were divided into training and validation sets, an internal test set, a pooled external test set, and a pooled prospective test set at three centers. DMILS was constructed using a deep learning-based weakly supervised method based on multiscale WSIs at 10×, 20×, and 40× magnifications. The performance of the DMILS was compared with that of a single magnification and validated in two pathologist-unidentified subsets.ResultsThe DMILS yielded good performance, with areas under the receiver operating characteristic curves (AUCs) of 0.848, 0.857, 0.810, and 0.787 in the training and validation sets, internal test set, pooled external test set, and pooled prospective test set, respectively. The AUC of the DMILS was higher than that of a single magnification, with 0.788 of 10×, 0.824 of 20×, and 0.775 of 40× in the internal test set. Moreover, DMILS yielded satisfactory performance on the two pathologist-unidentified subsets. Furthermore, the most indicative region predicted by DMILS is the follicular epithelium.ConclusionsDMILS has good performance in differentiating thyroid follicular neoplasms on multiscale WSIs of intraoperative frozen pathological images.

关键词: Deep learning, intraoperative frozen pathological image, pathological diagnosis, thyroid follicular neoplasm

Deep learning-based automatic pipeline system for predicting lateral cervical lymph node metastasis in patients with papillary thyroid carcinoma using computed tomography: A multi-center study

doi: 10.21147/j.issn.1000-9604.2024.05.07

ObjectiveThe assessment of lateral lymph node metastasis (LLNM) in patients with papillary thyroid carcinoma (PTC) holds great significance. This study aims to develop and evaluate a deep learning-based automatic pipeline system (DLAPS) for diagnosing LLNM in PTC using computed tomography (CT).MethodsA total of 1,266 lateral lymph nodes (LLNs) from 519 PTC patients who underwent CT examinations from January 2019 to November 2022 were included and divided into training and validation set, internal test set, pooled external test set, and prospective test set. The DLAPS consists of an auto-segmentation network based on RefineNet model and a classification network based on ensemble model (ResNet, Xception, and DenseNet). The performance of the DLAPS was compared with that of manually segmented DL models, the clinical model, and Node Reporting and Data System (Node-RADS). The improvement of radiologists’ diagnostic performance under the DLAPS-assisted strategy was explored. In addition, bulk RNA-sequencing was conducted based on 12 LLNs to reveal the underlying biological basis of the DLAPS.ResultsThe DLAPS yielded good performance with area under the receiver operating characteristic curve (AUC) of 0.872, 0.910, and 0.822 in the internal, pooled external, and prospective test sets, respectively. The DLAPS significantly outperformed clinical models (AUC 0.731, P<0.001) and Node-RADS (AUC 0.602, P<0.001) in the internal test set. Moreover, the performance of the DLAPS was comparable to that of the manually segmented deep learning (DL) model with AUCs ranging 0.814−0.901 in three test sets. Furthermore, the DLAPS-assisted strategy improved the performance of radiologists and enhanced inter-observer consistency. In clinical situations, the rate of unnecessary LLN dissection decreased from 33.33% to 7.32%. Furthermore, the DLAPS was associated with the cell-cell conjunction in the microenvironment.ConclusionsUsing CT images from PTC patients, the DLAPS could effectively segment and classify LLNs non-invasively, and this system had a good generalization ability and clinical applicability.

关键词: Bulk RNA sequencing, convolutional neural networks, deep learning, thyroid tumor, lateral lymph node metastasis

Unveiling clinical significance and tumor immune landscape of CXCL12 in bladder cancer: Insights from multiple omics analysis

doi: 10.21147/j.issn.1000-9604.2023.06.12

ObjectiveThe interplay between chemokine C-X-C motif ligand 12 (CXCL12) and its specific receptors is known to trigger various signaling pathways, contributing to tumor proliferation and metastasis. Consequently, targeting this signaling axis has emerged as a potential strategy in cancer therapy. However, the precise role of CXCL12 in clinical therapy, especially in immunotherapy for bladder cancer (BCa), remains poorly elucidated.MethodsWe gathered multiple omics data from public databases to unveil the clinical relevance and tumor immune landscape associated with CXCL12 in BCa patients. Univariate and multivariate Cox regression analyses were employed to assess the independent prognostic significance of CXCL12 expression and formulate a nomogram. The expression of CXCL12 in BCa cell lines and clinical tissue samples was validated using enzyme-linked immunosorbent assays (ELISA) and immunohistochemistry (IHC).ResultsWhile transcriptional expression of CXCL12 exhibited a decrease in nearly all tumor tissues, CXCL12 methylation expression was notably increased in BCa tissues. Single-cell RNA analysis highlighted tissue stem cells and endothelial cells as the primary sources expressing CXCL12. Abnormal CXCL12 expression, based on transcriptional and methylation levels, correlated with various clinical characteristics in BCa patients. Functional analysis indicated enrichment of CXCL12 and its co-expression genes in immune regulation and cell adhesion. The immune landscape analysis unveiled a significant association between CXCL12 expression and M2 macrophages (CD163⁺ cells) in BCa tissues. Notably, CXCL12 expression emerged as a potential predictor of immunotherapy response and chemotherapy drug sensitivity in BCa patients.ConclusionsTaken together, these findings suggest aberrant production of CXCL12 in BCa tissues, potentially influencing the treatment responses of affected individuals.

关键词: C-X-C motif ligand 12, bladder cancer, tumor immune landscape, clinical significance

主管单位：	中国科学院
主办单位：	中国电子学会

版权所有：
通讯地址：
工作邮箱：
办公电话：	020-37627489

Chinese Journal of Cancer Research

高级检索