AI and Cancer Research ── Prostate ── 2026-10-22
Prostate cancer: treatment, trials and AI
- Abstract
This retrospective study developed and validated a T2-weighted imaging (T2WI)-based radiomics model for preoperative prediction of apical positive surgical margins (PSMs) in patients undergoing radical prostatectomy for prostate cancer. Overall, 235 patients (74 with apical PSMs and 161 without apical PSMs) were randomly divided into a training set (n = 164; 69.8%) and an independent test set (n = 71; 30.2%). Eligible patients had preoperative multiparametric magnetic resonance imaging within 6 weeks before surgery, an index lesion involving or abutting the prostatic apex, definitive apical margin status, and standard radical prostatectomy without nerve-sparing. Patients with inadequate imaging for apical assessment or region-of-interest delineation, prior transurethral resection of the prostate, or neoadjuvant androgen-deprivation therapy were excluded. A total of 1409 radiomic features were extracted from T2WI. After normalization and removal of highly correlated features (|r| > 0.99), six optimal features were selected by recursive feature elimination. A gradient boosting machine model was constructed, and performance was assessed using the area under the receiver operating characteristic curve (AUC), Brier score, and decision curve analysis. The apical PSM rate was 31.5%. In the test set, the model achieved an AUC of 0.874, Brier score of 0.120, accuracy of 87.3%, sensitivity of 81.8%, and specificity of 89.8%. Skewness was the most important feature, contributing 34.8% to the model. Apical PSMs were significantly associated with extraprostatic extension (P = 0.001), and the tumor-margin model provided the greatest net clinical benefit. T2WI-based radiomics may support individualized preoperative risk assessment and surgical planning for prostate cancer.
Journal IF-equivalent: 2.8 (OpenAlex 2-year mean citedness, value as of 2026-10-21, retrieved 2026-10-22; not the official Clarivate IF)Reference: Liu Y, Zhao YZ, Liu S, Gao XS, Ma MW. Preoperative apical margin risk estimation from T2-weighted MRI radiomics in prostate cancer with MRI-visible apical tumors: toward multidisciplinary decision support. Asian J Androl. 2026 Oct 20 [Epub ahead of print]. doi:10.4103/aja202625. PMID: 42902531.Checked: Abstract only - Abstract
Prostate cancer is one of the most common malignancies among men, and accurate segmentation of Gleason grades is crucial for effective diagnosis and treatment planning. Current deep learning methods often struggle with fusing complementary features from CNNs and Transformers, primarily relying on naive feature fusion techniques such as concatenation or summation. These methods fail to leverage the complementary strengths of texture and global context, limiting segmentation performance. To address this challenge, we propose TexTNet, a novel texture-guided hierarchical architecture that integrates Local Binary Pattern (LBP) features into the query projection of the Swin Transformer, creating a Texture-Guided Attention mechanism. This approach directs the Transformer’s attention to texture-rich regions such as glandular borders and nuclear clusters, improving segmentation accuracy. We further enhance feature fusion with the Dual Path Squeeze-Fusion-Excitation (DP-SFE) module, which mitigates boundary blurring, and introduce Asymmetric Convolution Blocks (ACB) for efficient feature extraction. Additionally, the Cross-Directional Feature Aggregator (CDFA) ensures precise positional reconstruction and noise suppression during decoder fusion. We evaluate TexTNet on the SICAPv2, PANDA, ProstateX, and HuBMAP datasets, demonstrating superior performance over state-of-the-art methods in prostate cancer segmentation. TexTNet shows promise as a clinical decision-support tool, demonstrating robust performance on complex, real-world histopathological images and the potential to improve diagnostic reliability for prostate cancer grading.
Journal IF-equivalent: 2.6 (OpenAlex 2-year mean citedness, value as of 2026-10-08, retrieved 2026-10-09; not the official Clarivate IF)Reference: Arshad M, Chengliang W, Wajeeh Us Sima M, Shaikh JA, Alkhalaf S, Alturise F. TexTNet: a texture-guided hierarchical architecture for prostate cancer Gleason segmentation in whole slide images. Front Med. 2026 Oct 19;13:1815031. doi:10.3389/fmed.2026.1815031.Checked: Abstract only