Mycobacteria identification is crucial to diagnose tuberculosis. Since the bacillus is very small, finding it in Ziehl–Neelsen (ZN)-stained slides is a long task requiring significant pathologist’s effort. We developed an automated (AI-based) method of identification of mycobacteria. We prepared a training dataset of over 260,000 positive and over 700,000,000 negative patches annotated on scans of 510 whole slide images (WSI) of ZN-stained slides (110 positive and 400 negative). Several image augmentation techniques coupled with different custom computer vision architectures were used. WSIs automatic analysis was followed by a report indicating areas more likely to present mycobacteria. Our model performs AI-based diagnosis (the final decision of the diagnosis of WSI belongs to the pathologist). The results were validated internally on a dataset of 286,000 patches and tested in pathology laboratory settings on 60 ZN slides (23 positive and 37 negative). We compared the pathologists’ results obtained by separately evaluating slides and WSIs with the results given by a pathologist aided by automatic analysis of WSIs. Our architecture showed 0.977 area under the receiver operating characteristic curve. The clinical test presented 98.33% accuracy, 95.65% sensitivity, and 100% specificity for the AI-assisted method, outperforming any other AI-based proposed methods for AFB detection.

Space Surveillance and Tracking is a task that requires the development of systems that can accurately discriminate between natural and man-made objects that orbit around Earth. To manage the discrimination between these objects, it is required to analyze a large amount of partially annotated astronomical images collected using a network of on-ground and potentially space-based optical telescopes. Thus, the main objective of this article is to propose a novel architecture that improves the automatic annotation of astronomical images. To achieve this objective, we present a new method for automatic detection and classification of space objects (point-like and streaks) in a supervised manner, given real-world partially annotated images in the FITS (Flexible Image Transport System) format. Results are strongly dependent on the preprocessing techniques applied to the images. Therefore, different techniques were tested including our method for object filtering and bounding box extraction. Based on our relabeling pipeline, we can easily follow how the number of detected objects is gradually increasing after each iteration, achieving a mean average precision of 98%.

Tuberculosis is the primary cause of death due to infection in the world. Identification of Mycobacterium tuberculosis in sputum is a diagnostic test, which can be used in screening programs—especially in countries with a high incidence of tuberculosis—to identify and treat those persons with the highest risk of disseminating the infection. We previously developed an algorithm which is able to automatically detect mycobacteria on tissue; in particular, our algorithm identified acid-fast bacilli on tissue with 100% specificity, 95.65% sensitivity, and 98.33% accuracy. We tested this algorithm on 1059 Ziehl–Neelsen-stained sputum smears to evaluate its results as a possible tool for screening. The results were displayed as a heat map of 32 × 32 pixel patches. Analysis of the positive patches revealed a good specificity (86.84%) and 100% sensitivity for patches with a level of confidence over 90; furthermore, the accuracy remained over 95% for all levels of confidence over 80, except the class (95–100]. The modest specificity is caused by the peculiarities of smears (uneven thickness, dust contamination, lack of coverslip). We will train the algorithm on sputum smears to increase the specificity to over 95%. However, as our algorithm showed no false negatives, it is suitable for screening.

The presence of lymphovascular invasion (LVI) in urothelial carcinoma (UC) is a poor prognostic finding. This is difficult to identify on routine hematoxylin–eosin (H&E)-stained slides, but considering the costs and time required for examination, immunohistochemical stains for the endothelium are not the recommended diagnostic protocol. We developed an AI-based automated method for LVI identification on H&E-stained slides. We selected two separate groups of UC patients with transurethral resection specimens. Group A had 105 patients (100 with UC; 5 with cystitis); group B had 55 patients (all with high-grade UC; D2-40 and CD34 immunohistochemical stains performed on each block). All the group A slides and 52 H&E cases from group B showing LVI using immunohistochemistry were scanned using an Aperio GT450 automatic scanner. We performed a pixel-per-pixel semantic segmentation of selected areas, and we trained InternImage to identify several classes. The DiceCoefficient and Intersection-over-Union scores for LVI detection using our method were 0.77 and 0.52, respectively. The pathologists’ H&E-based evaluation in group B revealed 89.65% specificity, 42.30% sensitivity, 67.27% accuracy, and an F1 score of 0.55, which is much lower than the algorithm’s DCC of 0.77. Our model outlines LVI on H&E-stained-slides more effectively than human examiners; thus, it proves a valuable tool for pathologists.

Background: Whole-slide images (WSIs) are crucial in pathology for digitizing tissue slides, enabling pathologists and AI models to analyze cancer patterns at gigapixel scale. However, their large size incorporates artifacts and non-tissue regions that slow AI processing, consume resources, and introduce errors like false positives. Tissue detection serves as the essential first step in WSI pipelines to focus on relevant areas, but deep learning detection methods require extensive manual annotations. Methods: This study benchmarks four thumbnail-level tissue detection methods—Otsu’s thresholding, K-Means clustering, our novel annotation-free Double-Pass hybrid, and GrandQC’s UNet++ on 3322 TCGA WSIs from nine cancer cohorts, evaluating accuracy, speed, and efficiency. Results: Double-Pass achieved an mIoU of 0.826—very close to the deep learning GrandQC model’s 0.871—while processing slides on a CPU in just 0.203 s per slide, markedly faster than GrandQC’s 2.431 s per slide on the same hardware. As an annotation-free, CPU-optimized method, it therefore enables efficient, scalable thumbnail-level tissue detection on standard workstations. Conclusions: The scalable, annotation-free Double-Pass pipeline reduces computational bottlenecks and facilitates high-throughput WSI preprocessing, enabling faster and more cost-effective integration of AI into clinical pathology and research workflows. Comparing Double-Pass against established methods, this benchmark demonstrates its novelty as a fast, robust and annotation-free alternative to supervised methods.