Artificial intelligence in digital pathology of cutaneous lymphomas: a review of the current state and future perspectives

Dermatoscopic Patterns in Mycosis Fungoides: Observations from a Case-Series Retrospective Analysis and a Review of the Literature

Background: Dermoscopy, a non-invasive diagnostic technique, is being increasingly used to evaluate cutaneous T-cell lymphomas such as mycosis fungoides (MF) and Sézary syndrome (SS). However, its diagnostic accuracy and role in staging remain underexplored. Objective: This study aimed to assess the dermoscopic patterns in MF and SS, correlating the findings with the disease stage and lesion type to evaluate dermoscopy's diagnostic utility. Methods: A retrospective, monocentric analysis was conducted on patients with histologically confirmed MF or SS. Dermoscopic images were evaluated for vascular patterns, pigmentation, scaling, and keratin plugs. The statistical analysis assessed the correlations between these dermoscopic features and the TNMB staging and lesion type. A literature review was also performed to contextualize the findings, focusing on studies describing dermoscopic features in MF based on retrospective, prospective, and cross-sectional data. Results: The study included 30 patients with histologically confirmed MF or SS (19 males and 11 females; mean age: 64.5 years). The dermoscopic evaluation revealed that all the lesions were pigment-free, with vascular structures as the predominant feature. Linear vessels (40%) and serpentine vessels (13.3%) were the most frequently observed, along with dotted vessels (36.7%) and clods (10%). The vessel distribution was diffuse (40%) or perifollicular (36.7%), with a predominant red (56.7%) or orange (40%) background. Scaling was present in 76.7% of cases, either diffuse (40%) or perifollicular (36.7%), and keratin plugs were detected in 40% of the lesions. No statistically significant correlations were found between dermoscopic features and the TNMB stage or lesion type (p > 0.05). A cluster analysis identified two patient groups with differing vascular and scaling features but no clear association with disease stage. The literature review identified studies that commonly reported features in MF dermoscopy, including fine, short linear vessels and an orange-yellow background, particularly in early-stage MF. Spermatozoa-like structures have been marked as highly specific for diagnosing MF. Some studies also suggested a transition in vascular morphology from linear vessels in early disease to branched vessels and ulceration in advanced stages. Conclusions: Our results showed some vascular patterns have some potential but lack sensitivity for staging MF and SS. The terminology used and the reproducibility of our results compared to those reported in the literature showed little consistency, with none of our cases showing spermatozoa-like structures. Moreover, the same issues with the use of non-reproducible terminology were noted across the studies because it is not standardized and due to different incongruent dermoscopic patterns. More significant prospective studies with standardized descriptors and larger groups are needed to refine its diagnostic and staging utility.

From Morphology to Gene Expression Profiling in Mycosis Fungoides: Is It Still a Diagnostic Challenge?

Background: We herein review the most important clinico-pathological features of mycosis fungoides (MF). These evolving clinico-pathological aspects are paired with innovative therapeutic schemes. Moreover, we indicate cutaneous lymphomas as a new frontier of artificial intelligence application. Methods: We encompass new diagnostic and prognostic data derived from the recent medical literature describing the possible histological features which could be the targets of deep learning in conjunction with available clinical data. Results: In spite of decades of research, MF diagnosis still represents the most challenging debate from a dermatopathologist's point of view. Genetic alterations have been identified mainly in late stages of the disease, and their importance for disease initiation is still unclear. The exploration of the genome-wide expression of individual genes in skin samples may be useful in elucidating MF pathogenesis and improving early diagnosis, while artificial intelligence could offer the possibility of searching for biomarkers of disease progression. Conclusions: MF still deserves the name of the 'great imitator', both clinically and histopathologically. The goal of summing up all the clinico-pathological information before reaching a final diagnosis is the approach needed to reach diagnostic accuracy, especially in early MF cases. It is advisable to think of the most common clinical presentations, to be aware of the most common histopathological features, and to interpret the results of ancillary studies only in the right clinico-pathological context.

Breaking Down the Barriers for Patients With Cutaneous T-Cell Lymphoma: Current Controversies and Challenges for Radiation Oncologists in 2024

Cutaneous T-cell lymphomas (CTCL) are a rare collection of diseases, frequently associated with diagnostic challenges and complex management dilemmas. The multidisciplinary team is vital for accurate clinico-pathological diagnoses and for collaborative therapeutic decisions throughout the management journey, which frequently involves multiple lines of therapy. Radiotherapy (RT) is a highly effective skin-directed therapy for CTCL, commonly delivered as localised fields or as total skin electron beam therapy (TSEBT). Mycosis fungoides (MF) is the most common of the CTCL, and patients typically experience high rates of morbidity and long natural histories of relapse and progression. Patients with MF typically present with incurable disease; in these patients, RT has an established role in symptom- and disease-control, achieving excellent response rates and proven therapeutic benefits. The role of RT continues to evolve, with modern practices favouring lower doses to reduce toxicity risks and allow for re-irradiation. Less commonly, there are situations where RT has an integral role in the potential cure of patients with MF: firstly, in the setting of unilesional MF where localised RT alone may be curative, and secondly, in the setting of preconditioning prior to curative-intent allogeneic hematopoietic stem cell transplant for patients with advanced MF/Sezary syndrome, where conventional-dose TSEBT is indicated as the most effective single agent for maximal debulking of skin disease. Radiotherapy also has an important role in the management of the less common CTCL, including the curative treatment of localised primary cutaneous anaplastic large cell lymphoma. Despite proven efficacy and quality of life benefits, disparity exists in access to RT and TSEBT. World-wide, stronger multidisciplinary collaborations and greater patient advocacy are required to increase access to RT and improve equity of care for our patients with CTCL.

Artificial Intelligence Applications in Lymphoma Diagnosis and Management: Opportunities, Challenges, and Future Directions

Lymphoma, a heterogeneous group of blood cancers, presents significant diagnostic and therapeutic challenges due to its complex subtypes and variable clinical outcomes. Artificial intelligence (AI) has emerged as a promising tool to enhance the accuracy and efficiency of lymphoma pathology. This review explores the potential of AI in lymphoma diagnosis, classification, prognosis prediction, and treatment planning, as well as addressing the challenges and future directions in this rapidly evolving field.

A decision support system for the detection of cutaneous fungal infections using artificial intelligence

Cutaneous fungal infections are one of the most common skin conditions, hence, the burden of determining fungal elements upon microscopic examination with periodic acid-Schiff (PAS) and Gomori methenamine silver (GMS) stains, is very time consuming. Despite some morphological variability posing challenges to training artificial intelligence (AI)-based solutions, these structures are favored potential targets, enabling the recruitment of promising AI-based technologies. Herein, we present a novel AI solution for identifying skin fungal infections, potentially providing a decision support system for pathologists. Skin biopsies of patients diagnosed with a cutaneous fungal infection at the Sheba Medical Center, Israel between 2014 and 2023, were used. Samples were stained with PAS and GMS and digitized by the Philips IntelliSite scanner. DeePathology® STUDIO fungal elements were annotated and deemed as ground truth data after an overall revision by two specialist pathologists. Subsequently, they were used to create an AI-based solution, which has been further validated in other regions of interests. The study participants were divided into two cohorts. In the first cohort, the overall sensitivity of the algorithm was 0.8, specificity 0.97, F1 score 0.78; in the second, the overall sensitivity of the algorithm was 0.93, specificity 0.99, F1 score 0.95. The results obtained are encouraging as proof of concept for an AI-based fungi detection algorithm. DeePathology® STUDIO can be employed as a decision support system for pathologists when diagnosing a cutaneous fungal infection using PAS and GMS stains, thereby, saving time and money.

Artificial intelligence in dermatopathology: Updates, strengths, and challenges

Artificial intelligence (AI) has evolved to become a significant force in various domains, including medicine. We explore the role of AI in pathology, with a specific focus on dermatopathology and neoplastic dermatopathology. AI, encompassing machine learning and deep learning, has demonstrated its potential in tasks ranging from diagnostic applications on whole slide imaging to predictive and prognostic functions in skin pathology. In dermatopathology, studies have assessed AI's ability to identify skin lesions, classify melanomas, and improve diagnostic accuracy. Results indicate that AI, particularly convolutional neural networks, can outperform human pathologists in terms of sensitivity and specificity. AI aids in predicting disease outcomes, identifying aggressive tumors, and differentiating between various skin conditions. Neoplastic dermatopathology showcases AI's prowess in classifying melanocytic lesions, discriminating between melanomas and nevi, and aids dermatopathologists in making accurate diagnoses. Studies emphasize the reproducibility and diagnostic aid that AI provides, especially in challenging cases. In inflammatory and lymphoproliferative dermatopathology, limited research exists, but studies show attempts to use AI to differentiate conditions such as mycosis fungoides and eczema. Although some results are promising, further exploration is needed in these areas. We highlight the extraordinary interest AI has garnered in the scientific community and its potential to assist clinicians and pathologists. Despite the advancements, we have stressed the importance of collaboration between medical professionals, computer scientists, bioinformaticians, and engineers to harness AI's benefits and acknowledging its limitations and risks. The integration of AI into dermatopathology holds great promise, positioning it as a valuable tool rather than as a replacement for human expertise.

[Artificial intelligence in pathological anatomy]

The review presents key concepts and global developments in the field of artificial intelligence used in pathological anatomy. The work examines two types of artificial intelligence (AI): weak and strong ones. A review of experimental algorithms using both deep machine learning and computer vision technologies to work with WSI images of preparations, diagnose and make a prognosis for various malignant neoplasms is carried out. It has been established that weak artificial intelligence at this stage of development of computer (digital) pathological anatomy shows significantly better results in speeding up and refining diagnostic procedures than strong artificial intelligence having signs of general intelligence. The article also discusses three options for the further development of AI assistants for pathologists based on the technologies of large language models (strong AI) ChatGPT (PathAsst), Flan-PaLM2 and LIMA. As a result of the analysis of the literature, key problems in the field were identified: the equipment of pathology institutions, the lack of experts in training neural networks, the lack of strict criteria for the clinical viability of AI diagnostic technologies.