A New Method of Artificial-Intelligence-Based Automatic Identification of Lymphovascular Invasion in Urothelial Carcinomas.

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.

A New Artificial Intelligence-Based Method for Identifying Mycobacterium Tuberculosis in Ziehl-Neelsen Stain on Tissue.

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.

Inflammation: A key process in skin tumorigenesis.

The extremely delicate shift from an inflammatory process to tumorigenesis is a field of major scientific interest. While the inflammation induced by environmental agents has well known underlying mechanisms, less is known concerning the oncogenic changes that follow an inflammatory chronic status in the tissue microenvironment that can lead to pro-tumorigenic processes. Regardless of the origin of the environmental factors, the maintenance of an inflammatory microenvironment is a clear condition that favors tumorigenesis. Inflammation sustains the proliferation and survival of malignant transformed cells, can promote angiogenesis and metastatic processes, can negatively regulate the antitumoral adaptive and innate immune responses and may alter the efficacy of therapeutic agents. There is an abundance of studies focusing on molecular pathways that trigger inflammation-mediated tumorigenesis, and these data have revealed a series of biomarkers that can improve the diagnosis and prognosis in oncology. In skin there is a clear connection between tissue destruction, inflammation and tumor onset. Inflammation is a self-limiting process in normal physiological conditions, while tumor is a constitutive process activating new pro-tumor mechanisms. Among skin cancers, the most commonly diagnosed skin cancers, squamous cell carcinoma and basal cell carcinoma (BCC) have important inflammatory components. The most aggressive skin cancer, melanoma, is extensively research in regards to the new context of novel developed immune-therapies. In skin cancers, inflammatory markers can find their place in the biomarker set for improvement of diagnosis and prognosis.

Myokines as Possible Therapeutic Targets in Cancer Cachexia.

Cachexia is an extremely serious syndrome which occurs in most patients with different cancers, and it is characterized by systemic inflammation, a negative protein and energy balance, and involuntary loss of body mass. This syndrome has a dramatic impact on the patient's quality of life, and it is also associated with a low response to chemotherapy leading to a decrease in survival. Despite this, cachexia is still underestimated and often untreated. New research is needed in this area to understand this complex phenomenon and ultimately find treatment methods and therapeutic targets. The skeletal muscle can act as an endocrine organ. Signaling between muscles and other systems is done through myokines, cytokines, and proteins produced and released by myocytes. In this review, we would like to draw attention to some of the most important myokines that could have potential as biomarkers and therapeutic targets: myostatin, irisin, myonectin, decorin, fibroblast growth factor 21, interleukin-6, interleukin-8, and interleukin-15.

Innovative array-based assay for omics pattern in melanoma.

Cutaneous melanoma remains a major health issue and still an important challenge for research. Thus, omics complex evaluation can provide a more specific molecular classification for this heterogeneous disease. Complex omics analysis based on genomic and proteomic microarrays can identify disease markers that prognosticate disease evolution or can monitor therapies efficacy. Among the technologies that gained momentum in the last years, array-based comparative genomic hybridization offered the possibility to analyze chromosomal numerical aberrations within cutaneous melanomas providing important support for molecular classification of melanoma tumors. This technology can identify new chromosomal alterations and discover new deregulated melanoma genes that can be further used as therapy targets. Integrating genetic profiling with clinical and pathological parameters would lead to seminal improvements in diagnosis, prognosis, and therapy.