Early detection of breast cancer via mammography enhances patient survival rates, prompting this study to assess object detection models—Cascade R-CNN, YOLOv12 (S, L, and X variants), RTMDet-X, and RT-DETR-X—for detecting masses and calcifications across four public datasets (INbreast, CBIS-DDSM, VinDr-Mammo, and EMBED). The evaluation employs a standardized preprocessing approach (CLAHE, cropping) and augmentation (rotations, scaling), with transfer learning tested by training on combined datasets (e.g., INbreast + CBIS-DDSM) and validating on held-out sets (e.g., VinDr-Mammo). Performance is measured using precision, recall, mean Average Precision at IoU 0.5 (${\mathrm{mAP}}_{50}$), and F1-score. YOLOv12-L excels in mass detection with an ${\mathrm{mAP}}_{50}$ of 0.963 and F1-score up to 0.917 on INbreast, while RTMDet-X achieves an ${\mathrm{mAP}}_{50}$ of 0.697 on combined datasets with transfer learning. Preprocessing improves ${\mathrm{mAP}}_{50}$ by up to 0.209, and transfer learning elevates INbreast performance to an ${\mathrm{mAP}}_{50}$ of 0.995, though it incurs 5–11% drops on CBIS-DDSM (0.566 to 0.447) and VinDr-Mammo (0.59 to 0.5) due to domain shifts. EMBED yields a low ${\mathrm{mAP}}_{50}$ of 0.306 due to label inconsistencies, and calcification detection remains weak (${\mathrm{mAP}}_{50}$ < 0.116), highlighting the value of high-capacity models, preprocessing, and augmentation for mass detection while identifying calcification detection and domain adaptation as key areas for future investigation.

Breast cancer is one of the main causes of cancer-related death for women worldwide, and enhancing patient outcomes still depends on early detection. The most common imaging technique for diagnosing and screening for breast cancer is mammography, which has a high potential for early lesion detection. With an emphasis on the incorporation of deep learning (DL) techniques, this review examines the changing role of mammography in early breast cancer detection. We examine recent advancements in DL-based approaches for mammogram analysis, including tasks such as classification, segmentation, and lesion detection. Additionally, we assess the limitations of traditional mammographic methods and highlight how DL can enhance diagnostic accuracy, reduce false positives and negatives, and support clinical decision-making. The review emphasizes the potential of DL to assist radiologists in clinical decision-making, as well as increases in diagnostic accuracy and decreases in false positives and negatives. We also discuss issues like interpretability, generalization across populations, and data scarcity. This review summarizes the available data to highlight the revolutionary potential of DL-enhanced mammography in breast cancer screening and to suggest future research avenues for more reliable, transparent, and clinically useful AI-driven solutions.

Many historical handwritten records in low-resource languages remain difficult to access through modern digital systems. This limits efforts to preserve and study cultural heritage at scale. Chagatai manuscripts exemplify these challenges within the Eastern Turki tradition. For centuries, it served as a major written language across Central Asia and supported a rich literary tradition. Large collections of Chagatai manuscripts still survive today, yet only a small amount of this material exists in digital form. As the technical literature specifically focused on Chagatai-HTR remains in its nascent stage, this review synthesizes indirect evidence from taxonomically related Perso-Arabic scripts to establish a foundational research framework. This article presents a systematic literature review following the PRISMA guidelines to examine artificial intelligence methods for handwritten text recognition (HTR) and text restoration in low-resource languages. Analyzing 50 studies published between 2020 and 2026, the review categorizes research trends into handwritten text recognition (HTR), optical character recognition (OCR), script classification, dataset development, and multimodal vision–language systems. The findings reveal a significant architectural shift from traditional segmentation-based CNN and RNN models toward transformer architectures and multimodal approaches. However, for Chagatai specifically, the primary obstacle is not the lack of advanced models but a critical scarcity of basic research infrastructure, including expert-verified transcriptions, annotation standards, and open benchmark datasets. Consequently, this article proposes a concrete development roadmap focusing on systematic digitization, expert annotation, transfer learning, and the creation of baseline models to enable reproducible evaluations.

Digitizing the historical Chagatai manuscripts of the Gunnar Jarring Collection is severely hindered by cursive orthographic complexity and extreme data scarcity. This study establishes a rigorous empirical HTR benchmark, comparing two distinct paradigms under identical, highly constrained conditions: a convolutional recurrent neural network (CRNN) trained from scratch and pretrained Vision-Transformer-based architectures (TrOCR Base and Large). To eliminate intra-page data leakage, a strict page-level 80/10/10 partitioning protocol is enforced across the 2531 manually annotated text lines derived from 230 pages. To guarantee statistical reliability, all configurations are evaluated across three independent random seeds. The fine-tuned TrOCR Large model with architecture-specific data augmentation achieved the highest accuracy, yielding a Character Error Rate (CER) of 9.82 ± 0.05% and a Word Error Rate (WER) of 33.27 ± 0.77%, outperforming the from-scratch CRNN baseline (18.07 ± 0.79% CER) by 8.25% absolute. Our decoupled evaluations reveal that while pretraining provides a robust prior that stabilizes learning, spatial augmentation acts as a crucial regularizer. Our decoupled evaluations reveal that the performance advantage of fine-tuned Vision Transformers over scratch-trained CRNNs stems primarily from the stabilizing prior of pretrained transfer learning, while spatial augmentation acts as a crucial regularizer under extreme data scarcity. Character-level error taxonomies identify systemic failure modes, including deletion biases in Transformers and insertion-heavy “diacritic babbling” in connectionist temporal classification models.