Dataset Information

Deep learning for predicting major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer: A multicentre study.

ABSTRACT:

Background

This study, based on multicentre cohorts, aims to utilize computed tomography (CT) images to construct a deep learning model for predicting major pathological response (MPR) to neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC) and further explore the biological basis under its prediction.

Methods

274 patients undergoing curative surgery after neoadjuvant chemoimmunotherapy for NSCLC at 4 centres from January 2019 to December 2021 were included and divided into a training cohort, an internal validation cohort, and an external validation cohort. ShuffleNetV2x05-based features of the primary tumour on the CT scans within the 2 weeks preceding neoadjuvant administration were employed to develop a deep learning score for distinguishing MPR and non-MPR. To reveal the underlying biological basis of the deep learning score, a genetic analysis was conducted based on 25 patients with RNA-sequencing data.

Findings

MPR was achieved in 54.0% (n = 148) patients. The area under the curve (AUC) of the deep learning score to predict MPR was 0.73 (95% confidence interval [CI]: 0.58-0.86) and 0.72 (95% CI: 0.58-0.85) in the internal validation and external validation cohorts, respectively. After integrating the clinical characteristic into the deep learning score, the combined model achieved satisfactory performance in the internal validation (AUC: 0.77, 95% CI: 0.64-0.89) and external validation cohorts (AUC: 0.75, 95% CI: 0.62-0.87). In the biological basis exploration for the deep learning score, a high deep learning score was associated with the downregulation of pathways mediating tumour proliferation and the promotion of antitumour immune cell infiltration in the microenvironment.

Interpretation

The proposed deep learning model could effectively predict MPR in NSCLC patients treated with neoadjuvant chemoimmunotherapy.

Funding

This study was supported by National Key Research and Development Program of China, China (2017YFA0205200); National Natural Science Foundation of China, China (91959126, 82022036, 91959130, 81971776, 81771924, 6202790004, 81930053, 9195910169, 62176013, 8210071009); Beijing Natural Science Foundation, China (L182061); Strategic Priority Research Program of Chinese Academy of Sciences, China (XDB38040200); Chinese Academy of Sciences, China (GJJSTD20170004, QYZDJ-SSW-JSC005); Shanghai Hospital Development Center, China (SHDC2020CR3047B); and Science and Technology Commission of Shanghai Municipality, China (21YF1438200).

SUBMITTER: She Y

PROVIDER: S-EPMC9672965 | biostudies-literature | 2022 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning for predicting major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer: A multicentre study.

She Yunlang Y He Bingxi B Wang Fang F Zhong Yifan Y Wang Tingting T Liu Zhenchuan Z Yang Minglei M Yu Bentong B Deng Jiajun J Sun Xiwen X Wu Chunyan C Hou Likun L Zhu Yuming Y Yang Yang Y Hu Hongjie H Dong Di D Chen Chang C Tian Jie J

EBioMedicine 20221114

<h4>Background</h4>This study, based on multicentre cohorts, aims to utilize computed tomography (CT) images to construct a deep learning model for predicting major pathological response (MPR) to neoadjuvant chemoimmunotherapy in non-small cell lung cancer (NSCLC) and further explore the biological basis under its prediction.<h4>Methods</h4>274 patients undergoing curative surgery after neoadjuvant chemoimmunotherapy for NSCLC at 4 centres from January 2019 to December 2021 were included and div ...[more]

PMID: 36395737

Similar Datasets

Project description:ObjectiveDevelop 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).MethodsThis 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.ResultsUnivariate and multivariable analyses confirmed histology as a statistically significant prognostic factor for MPR (P-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.ConclusionThe application of weakly supervised deep learning to WSIs offers a powerful tool for predicting MPR in NSCLC patients treated with NICT.

Project description:BackgroundIn patients with non-small cell lung cancer (NSCLC) receiving neoadjuvant chemoimmunotherapy (NCIT), inconsistent pathological responses between the tumor and lymph nodes (LNs) are often observed. There has been limited evidence comparing the different responses of tumors and LNs in those patients. This retrospective real-world analysis intended to evaluate the clinical and pathological response of primary tumors and LNs, and the long-term outcomes in NSCLC patients after NCIT.MethodsWe included resectable NSCLC patients who had received neoadjuvant therapy and had available clinicopathological records. The progression-free survival (PFS) and overall survival (OS) outcomes were analyzed using survival analysis.ResultsIn total, 204 patients were included in the final analysis. Patients were predominantly male (85.8%) and ever-smokers (66.2%), with a median age of 63 years. No significant difference was observed in intraoperative bleeding (P=0.51 and P=0.54) and operation time (P=0.57 and P=0.58) between the major pathologic response (MPR) and pathological complete response (pCR) group, respectively. Patients who were male (pCR, P=0.01; MPR, P=0.004), with squamous cell carcinoma (SCC) (pCR, P=0.02; MPR, P=0.001), and overall response rate (ORR) (pCR, P<0.001; MPR, P<0.001) demonstrated significantly higher rates of pCR and MPR. The median follow-up time for all patients in this study was 23 months. Patients with MPR (P=0.004) and pCR (P=0.02) experienced prolonged PFS, but not OS (MPR, P=0.08; pCR, P=0.15). In terms of yield pathological tumor MPR (ypTMPR) and yield pathological LNs stage (ypN), Kaplan-Meier analyses demonstrated that there was a better PFS for the ypTMPR(+)/ypN(0) group, followed by ypTMPR(-)/ypN(0), ypTMPR(+)/ypN(0), and ypTMPR(-)/ypN(1+2) (P=0.01). The average PFS time was 35.7, 31.7, 29.4, and 28.7 months, respectively. After achieving MPR, the probability of local recurrence or distant metastasis was 7.3%, 25%, 23.5%, and 23.7%, respectively.ConclusionsIn this real-world study, the combination of tumor and LNs responses was significantly associated with prognosis, and we demonstrated that ypTMPR(+)/ypN(0) group had a better prognosis, followed by ypTMPR(-)/ypN(0), ypTMPR(+)/ypN(0), and ypTMPR(-)/ypN(1+2). We advocate for ypTMPR(+)/ypN(0) status as a better surrogate of PFS in resectable NSCLC patients after NCIT.

Project description:ObjectivesIn radiomics, high-throughput algorithms extract objective quantitative features from medical images. In this study, we evaluated CT-based radiomics features, clinical features, in-depth learning features, and a combination of features for predicting a good pathological response (GPR) in non-small cell lung cancer (NSCLC) patients receiving immunotherapy-based neoadjuvant therapy (NAT).Materials and methodsWe reviewed 62 patients with NSCLC who received surgery after immunotherapy-based NAT and collected clinicopathological data and CT images before and after immunotherapy-based NAT. A series of image preprocessing was carried out on CT scanning images: tumor segmentation, conventional radiomics feature extraction, deep learning feature extraction, and normalization. Spearman correlation coefficient, principal component analysis (PCA), and least absolute shrinkage and selection operator (LASSO) were used to screen features. The pretreatment traditional radiomics combined with clinical characteristics (before_rad_cil) model and pretreatment deep learning characteristics (before_dl) model were constructed according to the data collected before treatment. The data collected after NAT created the after_rad_cil model and after_dl model. The entire model was jointly constructed by all clinical features, conventional radiomics features, and deep learning features before and after neoadjuvant treatment. Finally, according to the data obtained before and after treatment, the before_nomogram and after_nomogram were constructed.ResultsIn the before_rad_cil model, four traditional radiomics features ("original_shape_flatness," "wavelet hhl_firer_skewness," "wavelet hlh_firer_skewness," and "wavelet lll_glcm_correlation") and two clinical features ("gender" and "N stage") were screened out to predict a GPR. The average prediction accuracy (ACC) after modeling with k-nearest neighbor (KNN) was 0.707. In the after_rad_cil model, nine features predictive of GPR were obtained after feature screening, among which seven were traditional radiomics features: "exponential_firer_skewness," "exponential_glrlm_runentropy," "log- sigma-5-0-mm-3d_firer_kurtosis," "logarithm_skewness," "original_shape_elongation," "original_shape_brilliance," and "wavelet llh_glcm_clustershade"; two were clinical features: "after_CRP" and "after lymphocyte percentage." The ACC after modeling with support vector machine (SVM) was 0.682. The before_dl model and after_dl model were modeled by SVM, and the ACC was 0.629 and 0.603, respectively. After feature screening, the entire model was constructed by multilayer perceptron (MLP), and the ACC of the GPR was the highest, 0.805. The calibration curve showed that the predictions of the GPR by the before_nomogram and after_nomogram were in consensus with the actual GPR.ConclusionCT-based radiomics has a good predictive ability for a GPR in NSCLC patients receiving immunotherapy-based NAT. Among the radiomics features combined with the clinicopathological information model, deep learning feature model, and the entire model, the entire model had the highest prediction accuracy.

Project description:BackgroundInvasive breast cancer patients are increasingly being treated with neoadjuvant chemotherapy; however, only a fraction of the patients respond to it completely. To prevent overtreatment, there is an urgent need for biomarkers to predict treatment response before administering the therapy.MethodsIn this retrospective study, we developed hypothesis-driven interpretable biomarkers based on deep learning, to predict the pathological complete response (pCR, i.e., the absence of tumor cells in the surgical resection specimens) to neoadjuvant chemotherapy solely using digital pathology H&E images of pre-treatment breast biopsies. Our approach consists of two steps: First, we use deep learning to characterize aspects of the tumor micro-environment by detecting mitoses and segmenting tissue into several morphology compartments including tumor, lymphocytes and stroma. Second, we derive computational biomarkers from the segmentation and detection output to encode slide-level relationships of components of the tumor microenvironment, such as tumor and mitoses, stroma, and tumor infiltrating lymphocytes (TILs).ResultsWe developed and evaluated our method on slides from n = 721 patients from three European medical centers with triple-negative and Luminal B breast cancers and performed external independent validation on n = 126 patients from a public dataset. We report the predictive value of the investigated biomarkers for predicting pCR with areas under the receiver operating characteristic curve between 0.66 and 0.88 across the tested cohorts.ConclusionThe proposed computational biomarkers predict pCR, but will require more evaluation and finetuning for clinical application. Our results further corroborate the potential role of deep learning to automate TILs quantification, and their predictive value in breast cancer neoadjuvant treatment planning, along with automated mitoses quantification. We made our method publicly available to extract segmentation-based biomarkers for research purposes.

Project description:BackgroundSleeve lobectomy has been reported to be a safe procedure after neoadjuvant chemotherapy. We aim to evaluate the oncological and surgical outcomes of neoadjuvant chemoimmunotherapy (IO+C) for local advanced non-small cell lung cancer (NSCLC) patients who underwent sleeve lobectomy.MethodsNSCLC patients that underwent sleeve lobectomy between December 2016 and December 2019 were retrospectively included. Patients were divided into two groups: neoadjuvant IO+C and chemotherapy. Oncological, intraoperative and postoperative variables were compared.ResultsIn total, 20 patients underwent sleeve lobectomy after neoadjuvant IO+C (n=10) or chemotherapy (n=10). In the neoadjuvant IO+C group, 8/10 (80%) patients achieved a partial response (PR), 1/10 (10%) patients had a complete pathological response (CPR), and 5/10 (50%) patients achieved a major pathological response (MPR). In the neoadjuvant chemotherapy group, only 3/10 (30%) patients had PR, and 3/10 (30%) patients achieved MPR. No complications were found in the neoadjuvant IO+C group, 1 chylothorax occurred in the neoadjuvant chemotherapy group. Other peri- and postoperative outcomes were similar: bleeding volume (365.00 vs. 347.50 mL; P=0.267), operation time (291.88 vs. 287.50 min; P=0.886), chest tube duration (5.40 vs. 5.00 day; P=0.829), total drainage volume (815.50 vs. 842.50 mL; P=0.931) and the length of hospital-stay (7.00 vs. 6.56 day; P=0.915). In addition, less N1 (average number 4.70 vs. 7.40) and N2 (average number 9.80 vs. 20.10) lymph nodes were acquired in the neoadjuvant IO+C group than the neoadjuvant chemotherapy group. The number of lymph nodes positive for tumor cells was also less in the neoadjuvant IO+C group than the neoadjuvant chemotherapy group, both in N1 (0.40 vs. 1.60) and N2 (0.10 vs. 1.30). The positive lymph node ratio (LNR) was lower in the neoadjuvant IO+C group, both in N1 (0.05 vs. 0.15) and N2 (0.01 vs. 0.09). A greater destruction on elastic fiber of the blood vessels, vascular wall degeneration, fibrinoid necrosis and fibrosis, and greater pulmonary interstitial exudation were found in neoadjuvant IO+C patients compared to the neoadjuvant chemotherapy patients.ConclusionsSleeve lobectomy for advanced NSCLC following IO+C is feasible, although the operations become more complex, neoadjuvant IO+C did not delay postoperative recovery.

Dataset Information

Deep learning for predicting major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer: A multicentre study.

Background

Methods

Findings

Interpretation

Funding

Publications

Deep learning for predicting major pathological response to neoadjuvant chemoimmunotherapy in non-small cell lung cancer: A multicentre study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets