Search

Simple Summary: Bowen's disease (malignant) and seborrheic keratosis (benign) are frequent cutaneous neoplasms. Our study assessed the potential of artificial intelligence to distinguish these entities histologically. A dermatopathologist trained deep learning network diagnosed Bowen's disease and seborrheic keratosis with AUCs of 0.9858 and 0.9764 and sensitivities of 0.9511 and 0.9394, respectively. The algorithm proved robust to slides prepared in three different labs and two different scanner models. Nevertheless, challenges, such as distinguishing irritated seborrheic keratosis from Bowen's disease remained. We believe our findings demonstrate that deep learning algorithms can aid in clinical routine; however, results should be confirmed by qualified histopathologists. Background: Some of the most common cutaneous neoplasms are Bowen's disease and seborrheic keratosis, a malignant and a benign proliferation, respectively. These entities represent a significant fraction of a dermatopathologists' workload, and in some cases, histological differentiation may be challenging. The potential of deep learning networks to distinguish these diseases is assessed. Methods: In total, 1935 whole-slide images from three institutions were scanned on two different slide scanners. A U-Net-based segmentation deep learning algorithm was trained on data from one of the centers to differentiate Bowen's disease, seborrheic keratosis, and normal tissue, learning from annotations performed by dermatopathologists. Optimal thresholds for the class distinction of diagnoses were extracted and assessed on a test set with data from all three institutions. Results: We aimed to diagnose Bowen's diseases with the highest sensitivity. A good performance was observed across all three centers, underlining the model's robustness. In one of the centers, the distinction between Bowen's disease and all other diagnoses was achieved with an AUC of 0.9858 and a sensitivity of 0.9511. Seborrheic keratosis was detected with an AUC of 0.9764 and a sensitivity of 0.9394. Nevertheless, distinguishing irritated seborrheic keratosis from Bowen's disease remained challenging. Conclusions: Bowen's disease and seborrheic keratosis could be correctly identified by the evaluated deep learning model on test sets from three different centers, two of which were not involved in training, and AUC scores > 0.97 were obtained. The method proved robust to changes in the staining solution and scanner model. We believe this demonstrates that deep learning algorithms can aid in clinical routine; however, the results should be confirmed by qualified histopathologists. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is a highly malignant skin cancer with the highest mortality of all cutaneous tumors. Relevant genetic events have been identified, which shape the tumor and also the response to treatment. Recurrent ARID1A mutations have been identified, which are associated with improved outcomes to immune checkpoint inhibition in various tumors. Not much was known about the role of ARID1A mutations in melanoma to date. We investigated the largest cohort of ARID1A mutated melanoma to date and were able to show that despite a high mutational load the described beneficial treatment response is not apparent in melanoma. (1) Background: Melanoma has the highest mortality of all cutaneous tumors, despite recent treatment advances. Many relevant genetic events have been identified in the last decade, including recurrent ARID1A mutations, which in various tumors have been associated with improved outcomes to immunotherapy. (2) Methods: Retrospective analysis of 116 melanoma samples harboring ARID1A mutations. Assessment of clinical and genetic characteristics was performed as well as correlations with treatment outcome applying Kaplan–Meier (log-rank test), Fisher's exact and Chi-squared tests. (3) Results: The majority of ARID1A mutations were in cutaneous and occult melanoma. ARID1A mutated samples had a higher number of mutations than ARID1A wild-type samples and harbored UV-mutations. A male predominance was observed. Many samples also harbored NF1 mutations. No apparent differences were noted between samples harboring genetically inactivating (frame-shift or nonsense) mutations and samples with other mutations. No differences in survival or response to immunotherapy of patients with ARID1A mutant melanoma were observed. (4) Conclusions: ARID1A mutations primarily occur in cutaneous melanomas with a higher mutation burden. In contrast to findings in other tumors, our data does not support ARID1A mutations being a biomarker of favorable response to immunotherapies in melanoma. Larger prospective studies would still be warranted. [ABSTRACT FROM AUTHOR]

Melanocytic neoplasms have been genetically characterized in detail during the last decade. Recurrent CTNNB1 exon 3 mutations have been recognized in the distinct group of melanocytic tumors showing deep penetrating nevus-like morphology. In addition, they have been identified in 1-2% of advanced melanoma. Performing a detailed genetic analysis of difficult-to-classify nevi and melanomas with CTNNB1 mutations, we found that benign tumors (nevi) show characteristic morphological, genetic and epigenetic traits, which distinguish them from other nevi and melanoma. Malignant CTNNB1 -mutant tumors (melanomas) demonstrated a different genetic profile, instead grouping clearly with other non- CTNNB1 melanomas in methylation assays. To further evaluate the role of CTNNB1 mutations in melanoma, we assessed a large cohort of clinically sequenced melanomas, identifying 38 tumors with CTNNB1 exon 3 mutations, including recurrent S45 ( n = 13, 34%), G34 ( n = 5, 13%), and S27 ( n = 5, 13%) mutations. Locations and histological subtype of CTNNB1 -mutated melanoma varied; none were reported as showing deep penetrating nevus-like morphology. The most frequent concurrent activating mutations were BRAF V600 ( n = 21, 55%) and NRAS Q61 ( n = 13, 34%). In our cohort, four of seven (58%) and one of nine (11%) patients treated with targeted therapy (BRAF and MEK Inhibitors) or immune-checkpoint therapy, respectively, showed disease control (partial response or stable disease). In summary, CTNNB1 mutations are associated with a unique melanocytic tumor type in benign tumors (nevi), which can be applied in a diagnostic setting. In advanced disease, no clear characteristics distinguishing CTNNB1 -mutant from other melanomas were observed; however, studies of larger, optimally prospective, cohorts are warranted.