Skip to content
Open access

STL‐DeepBDC: A Robust Few‐Shot Learning Framework for Multiclass Ovarian Tumor Classification in Ultrasound Outperforms Conventional Transfer Learning

Aug 2026 · Cancer Medicine · Vol 15 · 0 citations · 28 references
Medicine

TL;DR

An exploratory deep learning framework for multiclass ovarian tumor classification under small‐sample conditions is developed and evaluated.

Abstract

Accurate preoperative pathological classification of malignant and borderline ovarian tumors (OMTs) can support surgical planning, fertility preservation, and prognosis, but ultrasound‐based subtype assessment remains difficult because imaging phenotypes are heterogeneous, class imbalance is common, and interpretation varies among operators. This study developed and evaluated an exploratory deep learning framework for multiclass ovarian tumor classification under small‐sample conditions.

Read PDF

Similar papers

Open access Aug 2026

TFE3‐DualNet: An Interpretable Foundation Model‐Based Deep Learning Ensemble for Diagnosing TFE3‐Rearranged Renal Cell Carcinoma From Whole‐Slide Images in a Two‐Center Cohort

TFE3‐rearranged renal cell carcinoma (TFE3‐rRCC) is a rare, aggressive subtype that predominantly affects adolescents and young adults. Its marked morphologic heterogeneity can delay recognition and downstream confirmatory testing.

Yu-Hang Chen, Quanhui Xu, Haohua Yao et al. · 0 citations
Preprint Jul 2026

Multimodal Assessment of Pancreatic Cancer Resectability Using Deep Learning

Accurate determination of pancreatic ductal adenocarcinoma (PDAC) resectability relies on evaluating how the tumor interacts with major peripancreatic vessels on CT imaging, yet expert assessment often shows substantial variability. We introduce a fully automated multimodal deep learning framework that jointly analyzes 3D contrast enhanced CT and structured clinical information to classify patients into the three National Comprehensive Cancer Network (NCCN) resectability categories (upfront resectable, borderline resectable, locally advanced). The approach uses a Swin-UNETR backbone to obtain anatomy aware image representations through auxiliary segmentation of pancreas, tumor, and vascular structures. These features are fused with a compact clinical embedding derived from 17 routinely collected variables and processed by a lightweight classification head. Model training is guided by a dynamic multitask objective that adapts the balance between segmentation and classification based on current tumor Dice performance, promoting feature representations that remain both anatomically informed and discriminative.

V. Ochs, C. Kuemmerli, Florentin Bieder et al. · 0 citations
Open access Jul 2026

Deep learning for preoperative MRI-based endometrial cancer staging prediction.

Endometrial carcinoma ranks among the most common malignancies of the female reproductive system. Accurate early-stage staging is essential for devising appropriate treatment plans and assessing patient prognosis. This study aims to enhance diagnostic precision by overcoming the limitations of traditional imaging methods and existing deep learning models.To address challenges such as dependency on physician expertise, inefficiency, and deficiencies in feature transmission, boundary detail restoration, and multi-scale feature integration, we propose a novel architecture termed GCMF-UNet (Group Convolution and Multi-Scale Fusion U-Net). Furthermore, for classification tasks, we introduce MSFA-Net (Multi-Scale Fusion Attention Network), which integrates a ResNet-18 backbone with a multi-scale feature aggregation module, squeeze-and-excitation (SE) attention, and a Swin Transformer for global contextual modeling. Experimental results indicate that GCMF-UNet improves Accuracy from 90.1% to 94.2% and Recall from 89.3% to 94.8% compared to the standard U-Net. In classification performance, MSFA-Net improves F1-score from 0.901 to 0.938 over baseline ResNet-18, demonstrating enhanced capability in identifying critical lesion features. The proposed GCMF-UNet and MSFA-Net architectures effectively mitigate limitations of conventional diagnostic and deep learning approaches, offering more accurate lesion segmentation and classification. These advancements offer a technical basis for further exploration of automated diagnosis and staging in endometrial carcinoma.

Caili Gong, Yetong Qi, Ying Su et al. · 0 citations
Open access Jul 2026

MD-Mamba: A multi-scale dilated state-space network for breast cancer histopathology image classification

Highlights • MD-Mamba integrates state-space modeling with multi-scale dilated convolutions.• Dual-path attention improves interpretability and focuses on diagnostic tissue regions.• Achieves 96.25% accuracy with perfect malignant classification on BACH dataset.• Enables efficient, interpretable image biomarkers for breast cancer pathology.

Gengxun Liu, Shengquan Luo, Can Wu et al. · 0 citations
2026

Performance Disparities in Very Deep Super-Resolution Learning for Malignant versus Benign Breast Histopathological Images

VDSR networks enhance breast histopathological image resolution, but performance is significantly higher for malignant (PSNR=38dB, SSIM=0.992) than benign lesions (PSNR=36dB, SSIM=0.980), necessitating optimization. Prospective studies on segmentation and classification pipelines will support scalable AI-assisted pathology.

T. Bozkurt, Gokhan Ertas · 0 citations
Review Open access 2026

Artificial Intelligence in Pulmonary Nodule Assessment: From Radiomics to Multimodal Integration

: Accurate characterization of pulmonary nodules is critical for early lung cancer diagnosis and treatment planning. Recent advances in artificial intelligence (AI) have demonstrated substantial potential in automating nodule detection, segmentation, malignancy classification, and invasiveness prediction. This review summarizes key developments across radiomics, deep learning, pathomics, vision-language models, and liquid biopsy, highlighting the transition from single-modality analysis to multimodal integration. Representative studies are discussed to illustrate the performance gains and remaining challenges in clinical translation, including generalizability, interpretability, and implementation feasibility.

Yueying Zhou, Jianming Dong · 0 citations