Predicting malignant risk of ground-glass nodules using convolutional neural networks based on dual-time-point 18F-FDG PET/CT

Cancer Imaging, Год журнала: 2025, Номер 25(1)

Опубликована: Фев. 18, 2025

Accurately predicting the malignant risk of ground-glass nodules (GGOs) is crucial for precise treatment planning. This study aims to utilize convolutional neural networks based on dual-time-point 18F-FDG PET/CT predict GGOs. Retrospectively analyzing 311 patients with 397 GGOs, this identified 118 low-risk GGOs and 279 high-risk through pathology follow-up according new WHO classification. The dataset was randomly divided into a training set comprising 239 (318 lesions) testing 72 (79 lesions), we employed self-configuring 3D nnU-net network majority voting method segment Three independent segmentation prediction models were developed thin-section lung CT, early-phase PET/CT, respectively. Simultaneously, results model compared diagnostic nuclear medicine physicians. achieving Dice coefficient 0.84 ± 0.02 demonstrating high accuracy (84.81%), specificity (84.62%), sensitivity (84.91%), AUC (0.85) in risk. CT 73.42%, 78.48%, both which are lower than model. resident, junior expert physicians 67.09%, 74.68%, (84.81%) significantly higher that Based images, method, demonstrates excellent performance methodology serves as valuable adjunct assessment

Язык: Английский

---

Predicting Surgical Difficulty in Rectal Cancer Surgery: A Systematic Review of Artificial Intelligence Models Applied to Pre-Operative MRI

Cancers, Год журнала: 2025, Номер 17(5), С. 812 - 812

Опубликована: Фев. 26, 2025

Introduction: Following the rapid advances in minimally invasive surgery, there are a multitude of surgical modalities available for resecting rectal cancers. Robotic resections represent current pinnacle approaches. Currently, decisions on modality depend local resources and expertise team. Given limited access to robotic developing tools based pre-operative data that can predict difficulty surgery would streamline efficient utilisation resources. This systematic review aims appraise existing literature artificial intelligence (AI)-driven preoperative MRI analysis prediction identify knowledge gaps promising models warranting further clinical evaluation. Methods: A narrative synthesis were undertaken accordance with PRISMA SWiM guidelines. Systematic searches performed Medline, Embase, CENTRAL Trials register. Studies published between 2012 2024 included where AI was applied imaging adult cancer patients undergoing surgeries, any approach, purpose stratifying difficulty. Data extracted according pre-specified protocol capture study characteristics design; objectives performance outcome metrics summarised. Results: database returned 568 articles, 40 ultimately this review. support assessments identified across eight domains (direct grading, extramural vascular invasion (EMVI), lymph node metastasis (LNM), lymphovascular (LVI), perineural (PNI), T staging, requirement multiple linear stapler firings. For each, at least one model very good (AUC scores >0.80), several showing excellent considerably above threshold. Conclusions: assessment surgeries emerging, progressing development strong many models. These warrant evaluation, which aid personalised approaches ensure adequate

Язык: Английский

---

Imaging genomics of cancer: a bibliometric analysis and review

Cancer Imaging, Год журнала: 2025, Номер 25(1)

Опубликована: Март 4, 2025

Imaging genomics is a burgeoning field that seeks to connections between medical imaging and genomic features. It has been widely applied explore heterogeneity predict responsiveness disease progression in cancer. This review aims assess current applications advancements of Literature on cancer was retrieved selected from PubMed, Web Science, Embase before July 2024. Detail information articles, such as systems features, were extracted analyzed. Citation Science Scopus. Additionally, bibliometric analysis the included studies conducted using Bibliometrix R package VOSviewer. A total 370 articles study. The annual growth rate 24.88%. China (133) USA (107) most productive countries. top 2 keywords plus "survival" "classification". research mainly focuses central nervous system (121) genitourinary (110, including 44 breast articles). Despite different utilizing modalities, more than half each employed radiomics Publication databases provide data support for research. development artificial intelligence algorithms, especially feature extraction model construction, significantly advanced this field. conducive enhancing related-models' interpretability. Nonetheless, challenges sample size standardization construction must overcome. And trends revealed study will guide future contribute accurate diagnosis treatment clinic.

Язык: Английский

---

Magnetic resonance imaging‐based radiomics analysis for prediction of treatment response to neoadjuvant chemoradiotherapy and clinical outcome in patients with locally advanced rectal cancer: A large multicentric and validated study

MedComm, Год журнала: 2024, Номер 5(7)

Опубликована: Июнь 20, 2024

Our study investigated whether magnetic resonance imaging (MRI)-based radiomics features could predict good response (GR) to neoadjuvant chemoradiotherapy (nCRT) and clinical outcome in patients with locally advanced rectal cancer (LARC). Radiomics were extracted from the T2 weighted (T2W) Apparent diffusion coefficient (ADC) images of 1070 LARC retrospectively prospectively recruited three hospitals. To create radiomic models for GR prediction, classifications utilized. The model best performance was integrated important MRI combined model. Finally, two ten chosen prediction. model, constructed tumor size, MR-detected extramural venous invasion, signature generated by Support Vector Machine (SVM), showed promising discrimination GR, area under curves 0.799 (95% CI, 0.760-0.838), 0.797 0.733-0.860), 0.754 0.678-0.829), 0.727 0.641-0.813) training validation datasets, respectively. Decision curve analysis verified usefulness. Furthermore, according Kaplan-Meier curves, a high likelihood as determined had better disease-free survival than those low probability. This developed based on large-sample multicenter prospective quality score, also utility.

Язык: Английский

---

Prognostic Value of Separate Extramural Vascular Invasion Reporting in Operative Samples of Rectal Cancer: Single-Institutional Experience

Cancers, Год журнала: 2024, Номер 16(21), С. 3579 - 3579

Опубликована: Окт. 24, 2024

Vascular invasion, especially extramural vascular invasion (EMVI), has emerged as a prognostic parameter for rectal cancer (RC) in recent years. Prediction of recurrence and metastasis development poses significant challenge oncologists, who need markers prediction adverse outcome. The aim this study was to examine the significance pathohistologically detected EMVI untreated its implications separate reporting.

Язык: Английский

---

A Machine Learning Model Based on MRI Radiomics to Predict Response to Chemoradiation Among Patients with Rectal Cancer

Life, Год журнала: 2024, Номер 14(12), С. 1530 - 1530

Опубликована: Ноя. 22, 2024

Background: With rectum-sparing protocols becoming more common for rectal cancer treatment, this study aimed to predict the pathological complete response (pCR) preoperative chemoradiotherapy (pCRT) in patients using pre-treatment MRI and a radiomics-based machine learning approach. Methods: We divided MRI-data from 102 into training cohort (n = 72) validation 30). In cohort, 52 were classified as non-responders 20 pCR based on histological results total mesorectal excision. Results: trained various models radiomic features capture disease heterogeneity between responders non-responders. The best-performing model achieved receiver operating characteristic area under curve (ROC-AUC) of 73% an accuracy 70%, with sensitivity 78% positive predictive value (PPV) 80%. showed 81%, specificity 75%, Conclusions: These highlight potential radiomics predicting treatment support integration advanced imaging computational methods personalized management.

Язык: Английский

---

Implementation of template-based reporting for rectal cancer

Acta Radiologica, Год журнала: 2024, Номер unknown

Опубликована: Сен. 23, 2024

Язык: Английский

---

Improving Rectal Tumor Segmentation with Anomaly Fusion Derived from Anatomical Inpainting: A Multicenter Study

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2024, Номер unknown

Опубликована: Окт. 16, 2024

Abstract Accurate rectal tumor segmentation using magnetic resonance imaging (MRI) is paramount for effective treatment planning. It allows volumetric and other quantitative assessments, potentially aiding in prognostication response evaluation. Manual delineation of tumors surrounding structures time-consuming typically. Over the past few years, deep learning has shown strong results automated MRI. Current studies on segmentation, however, focus solely tumoral regions without considering anatomical entities often lack a solid multicenter external validation. In this study, we improved by incorporating anomaly maps derived from inpainting. This inpainting was implemented U-Net-based model trained to reconstruct healthy rectum mesorectum prostate T2-weighted images (T2WI). The were generated difference between original reconstructed pseudo-healthy slices during inference. used downstream tasks fusing them as an additional input channel (AAnnUNet). Alternative methods integrating knowledge evaluated baselines, including Multi-Target nnUNet (MTnnUNet), which added auxiliary tasks, Multi-Channel (MCnnUNet), utilized masks channel. As part benchmarked nine models large dataset preoperative T2WI baseline outperformed eight dataset. MTnnUNet demonstrated improvements both supervised semi-supervised settings (AI-generated mesoretum used) compared nnUNet, while MCnnUNet showed benefits only setting. Importantly, strongly associated with regions, their integration within AAnnUNet led best across settings. effectiveness value maps, indicating promising direction improving robustness data.

Язык: Английский

---

Generalizability, robustness, and correction bias of segmentations of thoracic organs at risk in CT images

European Radiology, Год журнала: 2024, Номер unknown

Опубликована: Дек. 31, 2024

Язык: Английский

---