Application progress of artificial intelligence in tumor diagnosis and treatment

Frontiers in Artificial Intelligence, Journal Year: 2025, Volume and Issue: 7

Published: Jan. 7, 2025

The rapid advancement of artificial intelligence (AI) has introduced transformative opportunities in oncology, enhancing the precision and efficiency tumor diagnosis treatment. This review examines recent advancements AI applications across imaging diagnostics, pathological analysis, treatment optimization, with a particular focus on breast cancer, lung liver cancer. By synthesizing findings from peer-reviewed studies published over past decade, this paper analyzes role diagnostic accuracy, streamlining therapeutic decision-making, personalizing strategies. Additionally, addresses challenges related to integration into clinical workflows regulatory compliance. As continues evolve, its oncology promise further improvements patient outcomes, though additional research is needed address limitations ensure ethical effective deployment.

Language: Английский

---

Development and external multicentric validation of a deep learning-based clinical target volume segmentation model for whole-breast radiotherapy

Physics and Imaging in Radiation Oncology, Journal Year: 2025, Volume and Issue: unknown, P. 100749 - 100749

Published: March 1, 2025

Language: Английский

---

Smart contours: deep learning-driven internal gross tumor volume delineation in non-small cell lung cancer using 4D CT maximum and average intensity projections

Radiation Oncology, Journal Year: 2025, Volume and Issue: 20(1)

Published: April 18, 2025

Delineating the internal gross tumor volume (IGTV) is crucial for treatment of non-small cell lung cancer (NSCLC). Deep learning (DL) enables automation this process; however, current studies focus mainly on multiple phases four-dimensional (4D) computed tomography (CT), which leads to indirect results. This study proposed a DL-based method automatic IGTV delineation using maximum and average intensity projections (MIP AIP, respectively) from 4D CT. We retrospectively enrolled 124 patients with NSCLC divided them into training (70%, n = 87) validation (30%, 37) cohorts. Four-dimensional CT images were acquired, corresponding MIP AIP generated. The IGTVs contoured used as ground truth (GT). or images, along (IGTVMIP-manu IGTVAIP-manu, respectively), fed DL models validation. assessed performance three segmentation models-U-net, attention U-net, V-net-using Dice similarity coefficient (DSC) 95th percentile Hausdorff distance (HD95) primary metrics. U-net model trained presented mean DSC 0.871 ± 0.048 HD95 2.958 2.266 mm, whereas achieved 0.852 0.053 3.209 2.136 mm. Among models, similar results, considerably surpassing V-net. can automate streamline contouring, enhance accuracy consistency radiotherapy planning improve patient outcomes.

Language: Английский

---

Comparison of the use of a clinically implemented deep learning segmentation model with the simulated study setting for breast cancer patients receiving radiotherapy

Acta Oncologica, Journal Year: 2024, Volume and Issue: 63, P. 477 - 481

Published: June 20, 2024

Deep learning (DL) models for auto-segmentation in radiotherapy have been extensively studied retrospective and pilot settings. However, these studies might not reflect the clinical setting. This study compares use of a clinically implemented in-house trained DL segmentation model breast cancer to previously performed assess possible differences performance or acceptability.

Language: Английский

---

Automated segmentation in planning-CT for breast cancer radiotherapy: A review of recent advances

Radiotherapy and Oncology, Journal Year: 2024, Volume and Issue: 202, P. 110615 - 110615

Published: Nov. 1, 2024

Postoperative radiotherapy (RT) has been shown to effectively reduce disease recurrence and mortality in breast cancer (BC) treatment. A critical step the planning workflow is accurate delineation of clinical target volumes (CTV) organs-at-risk (OAR). This literature review evaluates recent advancements deep-learning (DL) atlas-based auto-contouring techniques for CTVs OARs BC planning-CT images RT. It examines their performance regarding geometrical dosimetric accuracy, inter-observer variability, time efficiency. Our findings indicate that both DL- methods generally show comparable across CTVs, with DL slightly outperforming consistency accuracy. Auto-segmentation most achieved robust results segmentation quality planning. However, lymph node levels (LNLs) presented greatest challenge auto-segmentation significant impact on The translation these into practice limited by geometric metrics lack dose evaluation studies. Additionally, algorithms showed diverse structure sets, while training datasets varied size, origin, patient positioning imaging protocols, affecting model sensitivity. Guideline inconsistencies varying definitions ground truth led substantial suggesting a need reliable consensus dataset. Finally, our highlights popularity U-Net architecture. In conclusion, automated contouring proven efficient many breast-CTV, further improvements are necessary LNL delineation, analysis, building.

Language: Английский

---

Performance of Commercial Deep Learning-Based Auto-Segmentation Software for Breast Cancer Radiation Therapy Planning: A Systematic Review

Multimodal Technologies and Interaction, Journal Year: 2024, Volume and Issue: 8(12), P. 114 - 114

Published: Dec. 20, 2024

As yet, no systematic review on commercial deep learning-based auto-segmentation (DLAS) software for breast cancer radiation therapy (RT) planning has been published, although NRG Oncology highlighted the necessity such. The purpose of this is to investigate performances DLAS packages RT and methods their performance evaluation. A literature search was conducted with use electronic databases. Fifteen papers met selection criteria were included. included studies evaluated eight (Limbus Contour, Manteia AccuLearning, Mirada DLCExpert, MVision.ai Contour+, Radformation AutoContour, RaySearch RayStation, Siemens syngo.via Image Suite/AI-Rad Companion Organs RT, Therapanacea Annotate). Their findings show that could contour ten organs at risk (body, contralateral breast, esophagus-overlapping area, heart, ipsilateral humeral head, left right lungs, liver, sternum trachea) three clinical target volumes (CTVp_breast, CTVp_chestwall, CTVn_L1) up clinically acceptable standard. This can contribute 45.4%–93.7% contouring time reduction per patient. Although NRO suggested every center should conduct its own evaluation before implementation, such testing appears particularly crucial Contour+ as a result methodological weaknesses corresponding studies, small datasets collected retrospectively from single centers

Language: Английский

---

New technologies from bench to bedside – report from the Nordic association for clinical physics 2023 symposium

Acta Oncologica, Journal Year: 2023, Volume and Issue: 62(10), P. 1157 - 1160

Published: Oct. 3, 2023

Language: Английский

---