This study aims to develop and prospectively validate radiomic models based on MRI to predict lymphovascular invasion (LVI) status in patients with HER2-positive breast cancer. A total of 225 patients with HER2-positive breast cancer who preoperatively underwent breast MRI were selected, forming the training set (n = 99 LVI-positive, n = 126 LVI-negative). A prospective validation cohort included 130 patients with breast cancer from the Affiliated Zhongshan Hospital of Dalian University (n = 57 LVI-positive, n = 73 LVI-negative). A total of 390 radiomic features and eight conventional radiological characteristics were extracted. For the optimum feature selection phase, the LASSO regression model with tenfold cross-validation (CV) was employed to identify features with non-zero coefficients. The conventional radiological (CR) model was determined based on visual morphological (VM) features and the optimal radiomic features correlated with LVI, identified through multivariate logistic analyses. Subsequently, various machine learning (ML) models were developed using algorithms such as support vector machine (SVM), k-nearest neighbor (KNN), gradient boosting machine (GBM), and random forest (RF). The performance of ML and CR models. The results show that the AUC of the CR model in the training and validation sets were 0.81 (95% confidence interval [CI], 0.74-0.86) and 0.82 (95% CI, 0.69-0.89), respectively. The ML model achieved the best performance, with AUCs of 0.96 (95% CI, 0.99-1.00) in the training set and 0.95 (95% CI, 0.89-0.96) in the validation set. There were significant differences between the CR and ML models in predicting LVI status. Our study demonstrated that the machine learning models exhibited superior performance in predicting LVI status based on pretreatment MRI compared to the CR model, which does not necessarily rely on a priori knowledge of visual morphology.

Download full-text PDF

Source
http://dx.doi.org/10.1007/s10278-024-01329-xDOI Listing

Publication Analysis

Top Keywords

breast cancer
16
machine learning
12
her2-positive breast
12
lvi status
12
predict lymphovascular
8
lymphovascular invasion
8
patients her2-positive
8
training set
8
radiomic features
8
conventional radiological
8

Similar Publications

N-methyladenosine (mA) modification is the most common epitranscriptomic modification in eukaryotic RNA and has garnered extensive attention in the context of breast cancer research. The mA modification significantly impacts tumorigenesis and tumor progression by regulating RNA stability, splicing, translation, and degradation. In this review we summarize recent advances in understanding the roles of mA modification in the mechanisms underlying angiogenesis and vasculogenic mimicry in breast cancer.

View Article and Find Full Text PDF

Background: We investigated the perioperative outcome and oncologic safety of performing nipple-sparing mastectomy (NSM) through a single axillary incision (NSM-SAI) compared with performing NSM through a conventional incision (NSM-C).

Methods: We retrospectively reviewed 725 patients who underwent NSM for breast cancer between January 2010 and December 2023; 333 patients who underwent NSM with immediate reconstruction (IR) were enrolled. Surgical outcomes and oncologic outcomes of NSM-C (n = 184), NSM performed through SAI with a freehand approach (NSM-SAI-F; n = 92), and with an endoscopic approach (NSM-SAI-E; n = 57) were demonstrated.

View Article and Find Full Text PDF

Regional Hereditary Cancer Program in Chile: A scalable model of genetic counseling and molecular diagnosis to improve clinical outcomes for patients with hereditary cancer across Latin America.

Biol Res

December 2024

Unidad de Innovación en Prevención y Oncología de Precisión Centro Oncológico, Facultad de Medicina, Unidad de Innovación en Prevención y Oncología de Precisión Universidad Católica del Maule, Talca, 3480094, Chile.

Background: Breast cancer is a leading cause of cancer-related mortality worldwide, with hereditary forms accounting for approximately 10% of cases. In Chile, significant gaps exist in genetic counseling and testing, particularly within the public health system. This study presents the implementation and outcomes of the first regional hereditary cancer program in the Maule region of Chile, aimed at improving detection and management of hereditary breast cancer.

View Article and Find Full Text PDF

We report a case of solid papillary carcinoma (SPC) that developed at the site of a previous intraductal papilloma (IDP) with atypical ductal hyperplasia. This case supports IDP as a potential precursor lesion to SPC.

View Article and Find Full Text PDF

Angiogenesis, a key point in the association of gut microbiota and its metabolites with disease.

Eur J Med Res

December 2024

Department of Gastrointestinal Surgery, Shandong Provincial Hospital, Shandong University, Jinan, 250021, Shandong, China.

The gut microbiota is a complex and dynamic ecosystem that plays a crucial role in human health and disease, including obesity, diabetes, cardiovascular diseases, neurodegenerative diseases, inflammatory bowel disease, and cancer. Chronic inflammation is a common feature of these diseases and is closely related to angiogenesis (the process of forming new blood vessels), which is often dysregulated in pathological conditions. Inflammation potentially acts as a central mediator.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!