Non-Invasive Measurement Using Deep Learning Algorithm Based on Multi-Source Features Fusion to Predict PD-L1 Expression and Survival in NSCLC

Frontiers in Immunology, Journal Year: 2022, Volume and Issue: 13

Published: April 7, 2022

Programmed death-ligand 1 (PD-L1) assessment of lung cancer in immunohistochemical assays was only approved diagnostic biomarker for immunotherapy. But the tumor proportion score (TPS) PD-L1 challenging owing to invasive sampling and intertumoral heterogeneity. There a strong demand development an artificial intelligence (AI) system measure expression signature (ES) non-invasively.

Language: Английский

---

Predicting EGFR and PD-L1 Status in NSCLC Patients Using Multitask AI System Based on CT Images

Frontiers in Immunology, Journal Year: 2022, Volume and Issue: 13

Published: Feb. 18, 2022

Epidermal growth factor receptor (EGFR) genotyping and programmed death ligand-1 (PD-L1) expressions are of paramount importance for treatment guidelines such as the use tyrosine kinase inhibitors (TKIs) immune checkpoint (ICIs) in lung cancer. Conventional identification EGFR or PD-L1 status requires surgical biopsied tumor specimens, which obtained through invasive procedures associated with risk morbidities may be unavailable to access tissue samples. Here, we developed an artificial intelligence (AI) system that can predict using non-invasive computed tomography (CT) images.

Language: Английский

---

Facts and Hopes on the Use of Artificial Intelligence for Predictive Immunotherapy Biomarkers in Cancer

Clinical Cancer Research, Journal Year: 2022, Volume and Issue: 29(2), P. 316 - 323

Published: Sept. 9, 2022

Immunotherapy by immune checkpoint inhibitors has become a standard treatment strategy for many types of solid tumors. However, the majority patients with cancer will not respond, and predicting response to this therapy is still challenge. Artificial intelligence (AI) methods can extract meaningful information from complex data, such as image data. In clinical routine, radiology or histopathology images are ubiquitously available. AI been used predict immunotherapy images, either directly indirectly via surrogate markers. While none these currently in academic commercial developments pointing toward potential adoption near future. Here, we summarize state art AI-based biomarkers based on images. We point out limitations, caveats, pitfalls, including biases, generalizability, explainability, which relevant researchers health care providers alike, outline key use cases new class predictive biomarkers.

Language: Английский

---

Biology-guided deep learning predicts prognosis and cancer immunotherapy response

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: Aug. 23, 2023

Substantial progress has been made in using deep learning for cancer detection and diagnosis medical images. Yet, there is limited success on prediction of treatment response outcomes, which important implications personalized strategies. A significant hurdle clinical translation current data-driven models lack interpretability, often attributable to a disconnect from the underlying pathobiology. Here, we present biology-guided approach that enables simultaneous tumor immune stromal microenvironment status as well outcomes We validate model predicting prognosis gastric benefit adjuvant chemotherapy multi-center international study. Further, predicts checkpoint inhibitors complements clinically approved biomarkers. Importantly, our identifies subset mismatch repair-deficient tumors are non-responsive immunotherapy may inform selection patients combination treatments.

Language: Английский

---

Artificial intelligence-assisted selection and efficacy prediction of antineoplastic strategies for precision cancer therapy

Seminars in Cancer Biology, Journal Year: 2023, Volume and Issue: 90, P. 57 - 72

Published: Feb. 14, 2023

Language: Английский

---

Radiomics models based on multisequence MRI for predicting PD-1/PD-L1 expression in hepatocellular carcinoma

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: May 12, 2023

Abstract The purpose of this study was to explore the effectiveness radiomics based on multisequence MRI in predicting expression PD-1/PD-L1 hepatocellular carcinoma (HCC). One hundred and eight patients with HCC who underwent contrast-enhanced 2 weeks before surgical resection were enrolled retrospective study. Corresponding paraffin sections collected for immunohistochemistry detect PD-1 PD-L1. All randomly divided into a training cohort validation at ratio 7:3. Univariate multivariate analyses used select potential clinical characteristics related PD-L1 expression. Radiomics features extracted from axial fat-suppression T2-weighted imaging (FS-T2WI) images arterial phase portal venous dynamic MRI, corresponding feature sets generated. least absolute shrinkage selection operator (LASSO) optimal analysis. Logistic regression analysis performed construct single-sequence radiomic-clinical models. predictive performance judged by area under receiver operating characteristic curve (AUC) cohorts. In whole cohort, positive 43 patients, 34 patients. presence satellite nodules served as an independent predictor AUC values FS-T2WI, phase, models 0.696, 0.843, 0.863, 0.946 group 0.669, 0.792, 0.800 0.815 group, respectively. 0.731, 0.800, 0.831 0.898 0.621, 0.743, 0.771, 0.810 0.779 combined showed better performance. results suggest that model has predict preoperative HCC, which could become biomarker immune checkpoint inhibitor (ICI)-based treatment.

Language: Английский

---

Artificial Intelligence-Based Treatment Decisions: A New Era for NSCLC

Cancers, Journal Year: 2024, Volume and Issue: 16(4), P. 831 - 831

Published: Feb. 19, 2024

Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related mortality among women and men, in developed countries, despite public health interventions including tobacco-free campaigns, screening early detection methods, recent therapeutic advances, ongoing intense research on novel antineoplastic modalities. Targeting oncogenic driver mutations immune checkpoint inhibition has indeed revolutionized NSCLC treatment, yet there still remains unmet need for robust standardized predictive biomarkers to accurately inform clinical decisions. Artificial intelligence (AI) represents computer-based science concerned with large datasets complex problem-solving. Its concept brought a paradigm shift oncology considering its immense potential improved diagnosis, treatment guidance, prognosis. In this review, we present current state AI-driven applications management, particular focus radiomics pathomics, critically discuss both existing limitations future directions field. The thoracic community should not be discouraged by likely long road AI implementation into daily practice, as transformative impact personalized approaches undeniable.

Language: Английский

---

Integration of deep learning and habitat radiomics for predicting the response to immunotherapy in NSCLC patients

Cancer Immunology Immunotherapy, Journal Year: 2024, Volume and Issue: 73(8)

Published: June 4, 2024

Abstract Background The non-invasive biomarkers for predicting immunotherapy response are urgently needed to prevent both premature cessation of treatment and ineffective extension. This study aimed construct a model response, based on the integration deep learning habitat radiomics in patients with advanced non-small cell lung cancer (NSCLC). Methods Independent patient cohorts from three medical centers were enrolled training ( n = 164) test 82). Habitat imaging features derived sub-regions clustered individual’s tumor by K-means method. extracted 3D ResNet algorithm. Pearson correlation coefficient, T least absolute shrinkage selection operator regression used select features. Support vector machine was applied implement radiomics, respectively. Then, combination developed integrating sources data. Results obtained strong well-performance, achieving area under receiver operating characteristics curve 0.865 (95% CI 0.772–0.931). significantly discerned high low-risk patients, exhibited significant benefit clinical use. Conclusion deep-leaning contributed NSCLC. may be as potential tool individual management.

Language: Английский

---

Deep learning in radiology for lung cancer diagnostics: A systematic review of classification, segmentation, and predictive modeling techniques

Expert Systems with Applications, Journal Year: 2024, Volume and Issue: 255, P. 124665 - 124665

Published: July 5, 2024

Language: Английский

---

Immunotherapy and Cancer: The Multi-Omics Perspective

International Journal of Molecular Sciences, Journal Year: 2024, Volume and Issue: 25(6), P. 3563 - 3563

Published: March 21, 2024

Immunotherapies have revolutionized cancer treatment approaches. Because not all patients respond positively to immune therapeutic agents, it represents a challenge for scientists who strive understand the mechanisms behind such resistance. In-depth exploration of tumor biology, using novel technologies as omics science, can help decode role microenvironment (TIME) in producing response blockade strategies. It also identify biomarkers patient stratification and personalized treatment. This review aims explore these new models highlight their possible pivotal changing clinical practice.

Language: Английский

---