An artificial intelligence-powered PD-L1 combined positive score (CPS) analyser in urothelial carcinoma alleviating interobserver and intersite variability

AIMS

Immune checkpoint inhibitors targeting programmed death-ligand 1 (PD-L1) have shown promising clinical outcomes in urothelial carcinoma (UC). The combined positive score (CPS) quantifies PD-L1 22C3 expression in UC, but it can vary between pathologists due to the consideration of both immune and tumour cell positivity.

METHODS AND RESULTS

An artificial intelligence (AI)-powered PD-L1 CPS analyser was developed using 1,275,907 cells and 6175.42 mm2 of tissue annotated by pathologists, extracted from 400 PD-L1 22C3-stained whole slide images of UC. We validated the AI model on 543 UC PD-L1 22C3 cases collected from three institutions. There were 446 cases (82.1%) where the CPS results (CPS ≥10 or <10) were in complete agreement between three pathologists, and 486 cases (89.5%) where the AI-powered CPS results matched the consensus of two or more pathologists. In the pathologist's assessment of the CPS, statistically significant differences were noted depending on the source hospital (P = 0.003). Three pathologists reevaluated discrepancy cases with AI-powered CPS results. After using the AI as a guide and revising, the complete agreement increased to 93.9%. The AI model contributed to improving the concordance between pathologists across various factors including hospital, specimen type, pathologic T stage, histologic subtypes, and dominant PD-L1-positive cell type. In the revised results, the evaluation discordance among slides from different hospitals was mitigated.

CONCLUSION

This study suggests that AI models can help pathologists to reduce discrepancies between pathologists in quantifying immunohistochemistry including PD-L1 22C3 CPS, especially when evaluating data from different institutions, such as in a telepathology setting.

Endocrine and metabolic comorbidities in primary cicatricial alopecia: A nationwide population-based study

Primary cicatricial alopecia (PCA) is a rare, scarring, hair loss disorder. Due to its low incidence, little is known about endocrine and metabolic comorbidities in patients with PCA. Thus, we aimed to investigate the association between PCA and endocrine and metabolic disorders. This nationwide, population-based, cross-sectional study included patients diagnosed with PCA or non-cicatricial alopecia (NCA) and normal individuals without history of alopecia registered in the Korean National Health Insurance Service database between January 1, 2011, and December 31, 2020. We calculated the odds ratios of endocrine and metabolic comorbidities of patients with PCA compared to all patients or age- and sex-matched patients with NCA or normal individuals using multivariable logistic regression models. A total of 3 021 483 individuals (mean age [SD], 38.7 [15.0] years, 1 607 380 [53.2%] men), including 11 956 patients with PCA, 601 852 patients with NCA, and 2 407 675 normal participants, were identified. Patients with PCA had an increased risk for dyslipidemia (adjusted odds ratio [aOR] 1.14, 95% confidence interval [CI] 1.06-1.24), diabetes (aOR 1.38, 95% CI 1.24-1.53), and hypertension (aOR 1.10, 95% CI 1.02-1.19) compared to matched patients with NCA. Regarding PCA subtypes, lichen planopilaris/frontal fibrosing alopecia was positively associated with hypothyroidism (aOR 2.03, 95% CI 1.44-2.86) compared to NCA. Folliculitis decalvans and dissecting cellulitis were positively associated with dyslipidemia (aOR 1.16, 95% CI 1.05-1.28 and aOR 1.16, 95% CI 1.04-1.29, respectively), diabetes (aOR 1.38, 95% CI 1.20-1.58 and aOR 1.52, 95% CI 1.32-1.74, respectively), and hypertension (aOR 1.10, 95% CI 1.00-1.20 and aOR 1.14, 95% CI 1.02-1.27, respectively). Similar trends were observed when each PCA subgroup was compared with the normal control group. This study demonstrates that patients with PCA are more likely to have endocrine and metabolic comorbidities than patients without PCA. Further research on these comorbidities may improve the understanding of PCA.

Augmented interpretation of HER2, ER, and PR in breast cancer by artificial intelligence analyzer: enhancing interobserver agreement through a reader study of 201 cases

BACKGROUND

Accurate classification of breast cancer molecular subtypes is crucial in determining treatment strategies and predicting clinical outcomes. This classification largely depends on the assessment of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), and progesterone receptor (PR) status. However, variability in interpretation among pathologists pose challenges to the accuracy of this classification. This study evaluates the role of artificial intelligence (AI) in enhancing the consistency of these evaluations.

METHODS

AI-powered HER2 and ER/PR analyzers, consisting of cell and tissue models, were developed using 1,259 HER2, 744 ER, and 466 PR-stained immunohistochemistry (IHC) whole-slide images of breast cancer. External validation cohort comprising HER2, ER, and PR IHCs of 201 breast cancer cases were analyzed with these AI-powered analyzers. Three board-certified pathologists independently assessed these cases without AI annotation. Then, cases with differing interpretations between pathologists and the AI analyzer were revisited with AI assistance, focusing on evaluating the influence of AI assistance on the concordance among pathologists during the revised evaluation compared to the initial assessment.

RESULTS

Reevaluation was required in 61 (30.3%), 42 (20.9%), and 80 (39.8%) of HER2, in 15 (7.5%), 17 (8.5%), and 11 (5.5%) of ER, and in 26 (12.9%), 24 (11.9%), and 28 (13.9%) of PR evaluations by the pathologists, respectively. Compared to initial interpretations, the assistance of AI led to a notable increase in the agreement among three pathologists on the status of HER2 (from 49.3 to 74.1%, p < 0.001), ER (from 93.0 to 96.5%, p = 0.096), and PR (from 84.6 to 91.5%, p = 0.006). This improvement was especially evident in cases of HER2 2+ and 1+, where the concordance significantly increased from 46.2 to 68.4% and from 26.5 to 70.7%, respectively. Consequently, a refinement in the classification of breast cancer molecular subtypes (from 58.2 to 78.6%, p < 0.001) was achieved with AI assistance.

CONCLUSIONS

This study underscores the significant role of AI analyzers in improving pathologists' concordance in the classification of breast cancer molecular subtypes.

Reduced economic disparity in biologics use for psoriasis after introducing the reducing copayment program

Biologics for psoriasis are efficient and safe, but very expensive. We investigated the association of the reducing copayment program (RCP) with changes in biologics use patterns depending on the income levels of patients with moderate-to-severe psoriasis. This nationwide cohort study included patients identified as having moderate-to-severe psoriasis between 2014 and 2020. Logistic regression models were used to estimate the odds ratio for the use of biologics according to income levels. Among 57,139 patients with moderate-to-severe psoriasis, 3464 (6.1%) used biologics for psoriasis from 2014 to 2020. After the introduction of RCP in 2017, the proportion of patients with moderate-to-severe psoriasis using biologics rapidly increased from 5.0% in 2016 to 19.2% in 2020; the increase was more remarkable in patients with the lowest or mid-low income compared to those with Medical Aid. Drug survival of biologics was higher in patients with the highest income before the RCP, but became comparable between those with high and low incomes after RCP introduction. The introduction of RCP was associated with an increased use of biologics in patients with moderate-to-severe psoriasis of all income levels; however, the effect was more pronounced in low-income patients. The RCP may contribute to alleviating the disparity in access to biologics.

Discontinuation risk from adverse events: immunotherapy alone vs. combined with chemotherapy: a systematic review and network meta-analysis

BACKGROUND

While immunotherapy combined with chemotherapy (Chemo-IO) is generally recognized for providing superior outcomes compared to monotherapy (mono-IO), it is associated with a higher incidence of treatment-related adverse events (TRAEs), which may lead to treatment discontinuation. In this study, we compared the rates of treatment discontinuation between mono-IO and Chemo-IO as first-line treatments for various solid tumors.

METHODS

We systematically reviewed clinical trials from databases (PubMed, Embase, Cochrane Library, and an additional source) published from January 1, 2018, to July 10, 2023. We included phase III randomized controlled trials (RCTs) that utilized immunotherapy agents in at least one arm as first-line treatments for a variety of solid tumors. Data extraction followed the Preferred Reporting Items for Systematic Reviews (PRISMA) extension statement for network meta-analysis. A random effects model was used for the network meta-analysis, with the risk of bias assessed using the Cochrane risk-of-bias tool II. The primary outcomes encompassed treatment discontinuation rates due to TRAEs among patients who underwent immunotherapy, either alone or combined with chemotherapy, for various solid tumors. Pooled relative risks (RRs) with 95% confidence intervals (CIs) were calculated to compare between treatment groups.

RESULTS

From 29 RCTs, a total of 21,677 patients and 5 types of treatment were analyzed. Compared to mono-IO, Chemo-IO showed a significantly higher rate of discontinuation due to TRAEs (RR 2.68, 95% CI 1.98-3.63). Subgroup analysis for non-small cell lung cancer (NSCLC) patients also exhibited a greater risk of discontinuation due to TRAEs with Chemo-IO compared to mono-IO (RR 2.93, 95% CI 1.67-5.14). Additional analyses evaluating discontinuation rates due to either treatment emergent adverse events (TEAEs) or AEs regardless of causality (any AEs) consistently revealed an elevated risk associated with Chemo-IO.

CONCLUSIONS

Chemo-IO was associated with an elevated risk of treatment discontinuation not only due to TRAEs but also any AEs or TEAEs. Given that the treatment duration can impact clinical outcomes, a subset of patients might benefit more from mono-IO than combination therapy. Further research is imperative to identify and characterize this subset.

Explore highly relevant questions in the Baumann skin type questionnaire through the digital skin analyzer: A retrospective single-center study in South Korea

BACKGROUND

Baumann skin type questionnaire (BSTQ) has been widely used for evaluating skin types in dermatology. However, it requires excessive assessment time and lacks sufficient clinical validation for the Asian population.

AIMS

We aimed to establish optimized BSTQ based on dermatological assessment of the Asian population.

METHODS

This was a single-center retrospective study, where the patient completed a modified BSTQ and a digital photography examination. The answers to four question groups for evaluating skin properties, including oily versus dry (O-D), sensitive versus resistant (S-R), pigmented versus non-pigmented (P-N), and wrinkled versus tight (W-T) were compared with the measurements. Highly relevant questions are selected using two different strategies and used to determine the threshold level, which was compared with skin-type measurement.

RESULTS

In O-D, S-R, P-N, and W-T, 3-5 out of 6, 2-6 out of 9, 3-6 out of 7, and 4-9 out of 11 questions were selected, respectively. As a result, skin type scores from two strategies and measurements showed similar Pearson correlation coefficient values compared to modified BSTQ (for O-D and sebum, 0.236/0.266 vs. 0.232; for O-D and porphyrin, 0.230/0.267 vs. 0.230; for S-R and redness, 0.157/0.175 vs. 0.095; for S-R and porphyrin, 0.061 vs. 0.051; for P-N and melanin pigmentation, 0.156/0.208 vs. 0.150; for W-T and wrinkle, 0.265/0.269 vs. 0.217).

CONCLUSION

Two strategies for optimizing BSTQ are proposed and validated for Asian patients. Compared to the BSTQ, our methods show comparable performance with a significantly reduced number of questions.

Generation of a Melanoma and Nevus Data Set From Unstandardized Clinical Photographs on the Internet

Importance

Artificial intelligence (AI) training for diagnosing dermatologic images requires large amounts of clean data. Dermatologic images have different compositions, and many are inaccessible due to privacy concerns, which hinder the development of AI.

Objective

To build a training data set for discriminative and generative AI from unstandardized internet images of melanoma and nevus.

Design, Setting, and Participants

In this diagnostic study, a total of 5619 (CAN5600 data set) and 2006 (CAN2000 data set; a manually revised subset of CAN5600) cropped lesion images of either melanoma or nevus were semiautomatically annotated from approximately 500 000 photographs on the internet using convolutional neural networks (CNNs), region-based CNNs, and large mask inpainting. For unsupervised pretraining, 132 673 possible lesions (LESION130k data set) were also created with diversity by collecting images from 18 482 websites in approximately 80 countries. A total of 5000 synthetic images (GAN5000 data set) were generated using the generative adversarial network (StyleGAN2-ADA; training, CAN2000 data set; pretraining, LESION130k data set).

Main Outcomes and Measures

The area under the receiver operating characteristic curve (AUROC) for determining malignant neoplasms was analyzed. In each test, 1 of the 7 preexisting public data sets (total of 2312 images; including Edinburgh, an SNU subset, Asan test, Waterloo, 7-point criteria evaluation, PAD-UFES-20, and MED-NODE) was used as the test data set. Subsequently, a comparative study was conducted between the performance of the EfficientNet Lite0 CNN on the proposed data set and that trained on the remaining 6 preexisting data sets.

Results

The EfficientNet Lite0 CNN trained on the annotated or synthetic images achieved higher or equivalent mean (SD) AUROCs to the EfficientNet Lite0 trained using the pathologically confirmed public data sets, including CAN5600 (0.874 [0.042]; P = .02), CAN2000 (0.848 [0.027]; P = .08), and GAN5000 (0.838 [0.040]; P = .31 [Wilcoxon signed rank test]) and the preexisting data sets combined (0.809 [0.063]) by the benefits of increased size of the training data set.

Conclusions and Relevance

The synthetic data set in this diagnostic study was created using various AI technologies from internet images. A neural network trained on the created data set (CAN5600) performed better than the same network trained on preexisting data sets combined. Both the annotated (CAN5600 and LESION130k) and synthetic (GAN5000) data sets could be shared for AI training and consensus between physicians.

Artificial Intelligence in Breast Cancer Diagnosis and Personalized Medicine

Breast cancer is a significant cause of cancer-related mortality in women worldwide. Early and precise diagnosis is crucial, and clinical outcomes can be markedly enhanced. The rise of artificial intelligence (AI) has ushered in a new era, notably in image analysis, paving the way for major advancements in breast cancer diagnosis and individualized treatment regimens. In the diagnostic workflow for patients with breast cancer, the role of AI encompasses screening, diagnosis, staging, biomarker evaluation, prognostication, and therapeutic response prediction. Although its potential is immense, its complete integration into clinical practice is challenging. Particularly, these challenges include the imperatives for extensive clinical validation, model generalizability, navigating the "black-box" conundrum, and pragmatic considerations of embedding AI into everyday clinical environments. In this review, we comprehensively explored the diverse applications of AI in breast cancer care, underlining its transformative promise and existing impediments. In radiology, we specifically address AI in mammography, tomosynthesis, risk prediction models, and supplementary imaging methods, including magnetic resonance imaging and ultrasound. In pathology, our focus is on AI applications for pathologic diagnosis, evaluation of biomarkers, and predictions related to genetic alterations, treatment response, and prognosis in the context of breast cancer diagnosis and treatment. Our discussion underscores the transformative potential of AI in breast cancer management and emphasizes the importance of focused research to realize the full spectrum of benefits of AI in patient care.

Deep learning model improves tumor-infiltrating lymphocyte evaluation and therapeutic response prediction in breast cancer

Tumor-infiltrating lymphocytes (TILs) have been recognized as key players in the tumor microenvironment of breast cancer, but substantial interobserver variability among pathologists has impeded its utility as a biomarker. We developed a deep learning (DL)-based TIL analyzer to evaluate stromal TILs (sTILs) in breast cancer. Three pathologists evaluated 402 whole slide images of breast cancer and interpreted the sTIL scores. A standalone performance of the DL model was evaluated in the 210 cases (52.2%) exhibiting sTIL score differences of less than 10 percentage points, yielding a concordance correlation coefficient of 0.755 (95% confidence interval [CI], 0.693-0.805) in comparison to the pathologists' scores. For the 226 slides (56.2%) showing a 10 percentage points or greater variance between pathologists and the DL model, revisions were made. The number of discordant cases was reduced to 116 (28.9%) with the DL assistance (p < 0.001). The DL assistance also increased the concordance correlation coefficient of the sTIL score among every two pathologists. In triple-negative and human epidermal growth factor receptor 2 (HER2)-positive breast cancer patients who underwent the neoadjuvant chemotherapy, the DL-assisted revision notably accentuated higher sTIL scores in responders (26.8 ± 19.6 vs. 19.0 ± 16.4, p = 0.003). Furthermore, the DL-assistant revision disclosed the correlation of sTIL-high tumors (sTIL ≥ 50) with the chemotherapeutic response (odd ratio 1.28 [95% confidence interval, 1.01-1.63], p = 0.039). Through enhancing inter-pathologist concordance in sTIL interpretation and predicting neoadjuvant chemotherapy response, here we report the utility of the DL-based tool as a reference for sTIL scoring in breast cancer assessment.

Automated Facial Acne Lesion Detecting and Counting Algorithm for Acne Severity Evaluation and Its Utility in Assisting Dermatologists

BACKGROUND

Although lesion counting is an evaluation method that effectively analyzes facial acne severity, its usage is limited because of difficult implementation.

OBJECTIVES

We aimed to develop and validate an automated algorithm that detects and counts acne lesions by type, and to evaluate its clinical applicability as an assistance tool through a reader test.

METHODS

A total of 20,699 lesions (closed and open comedones, papules, nodules/cysts, and pustules) were manually labeled on 1213 facial images of 398 facial acne photography sets (frontal and both lateral views) acquired from 258 patients and used for training and validating algorithms based on a convolutional neural network for classifying five classes of acne lesions or for binary classification into noninflammatory and inflammatory lesions.

RESULTS

In the validation dataset, the highest mean average precision was 28.48 for the binary classification algorithm. Pearson's correlation of lesion counts between algorithm and ground-truth was 0.72 (noninflammatory) and 0.90 (inflammatory), respectively. In the reader test, eight readers (100.0%) detected and counted lesions more accurately using the algorithm compared with the reader-alone evaluation.

CONCLUSIONS

Overall, our algorithm demonstrated clinically applicable performance in detecting and counting facial acne lesions by type and its utility as an assistance tool for evaluating acne severity.

Risk of Skin Cancer and Actinic Keratosis in Patients with Rosacea: A Nationwide Population-based Cohort Study

The association between rosacea and skin cancer remains inconclusive, with conflicting reports. The aim of this nationwide population-based cohort study was to determine the risk of skin cancer in patients with rosacea. A rosacea cohort (n = 11,420) was formulated and evaluated from 2010 to 2019. The incidence rate ratios of actinic keratosis, cutaneous melanoma, keratinocyte carcinoma and gastric, colorectal, and liver cancer were analysed in comparison with a matched control group, and multivariable stratified Cox proportional hazards model analysis was performed. The risk of actinic keratosis and keratinocyte carcinoma was increased in the rosacea group compared with the control group, with adjusted hazard ratios of 6.05 (95% confidence interval 3.63–10.09) and 2.66 (1.53–4.61), respectively. The risk of cutaneous melanoma and gastric, colorectal and liver cancer was not increased, with adjusted hazard ratios of 1.69 (0.25–11.37), 0.81 (0.59–1.10), 0.91 (0.69–1.18) and 1.32 (0.89–1.95), respectively. These results reveal an increased risk of actinic keratosis and keratinocyte carcinoma in patients with rosacea.

Abstract 6172: Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes reveals immune-excluded phenotype is correlated with TGF-beta pathway related genomic aberrations

Aberrant transforming growth factor-beta(TGF-B) pathway in the tumor microenvironment has been highlighted as one of the core resistance pathways of immunotherapy, by excluding tumor-infiltrating lymphocytes (TIL) out of the tumor area. However, no studies have coupled immune phenotypes classified by spatial analysis of TIL in whole slide images (WSI) with TGF-B pathway analysis on a large-scale database. Here, we hypothesized that the immune-excluded phenotype classified by a deep-learning spatial analysis model, Lunit SCOPE IO, would be correlated with the aberrant TGF-B pathway in The Cancer Genome Atlas (TCGA) cohorts. Aberrant TGF-B pathway was measured by Trimmed Mean of M-values (TMM) normalized and transformed to log2 of counts-per-million of previously published gene sets of fibroblast-specific TGF-beta responsive gene signature, using edgeR packages from TCGA RNA-sequencing data (n=6,709) across the 23 cancer types. Lunit SCOPE IO was developed to identify immune phenotypes trained and validated from 3,166 multi-cancer H&E WSI with sections of 2.8e+9 mm2 tumor tissue containing 5.9e+6 TIL annotated by 52 board-certified pathologists. Lunit SCOPE IO classified immune phenotypes as immune-inflamed and -excluded according to the proportion of TIL density either highly conserved in cancer epithelium (CE) or cancer stroma (CS), respectively, and otherwise, classified as immune-desert with low TIL density in CE and CS. Aberrant TGF-B expression was highly enriched in multiple cancer types including pancreatic cancer, head and neck cancer, kidney clear cell carcinoma, lung squamous cell carcinoma, and breast cancer, in ascending order. TGF-B expression was increased in microsatellite-stable tumor samples (p = 7.4e-15) or samples with low tumor mutational burden (TMB, &lt; 10/megabase, p = 4.9e-8), compared to those with microsatellite instability-high or high TMB, respectively. Interestingly, TGF-B expression was highly correlated with the proportion of cancer stroma in WSI (R = 0.315, p &lt; 2.2e-16) and the proportion of immune-excluded phenotype (R = 0.115, p &lt; 2.2e-16) across multiple cancer types. Tumor samples with SMAD4 mutations (n = 161, 2.4%) had significantly higher TGF-B expression (p = 0.0190), and a higher proportion of immune-excluded phenotype (p &lt; 2.2e-16) in WSI, compared to wild-type SMAD4. Aberrant TGF-B pathway is clearly associated with increased proportion of cancer stroma, and excluded TIL, or immune-excluded phenotype in a large-scale pan-carcinoma analysis.

Citation Format: Gahee Park, Sanghoon Song, Hyung-Gyo Cho, Soo Ick Cho, Wonkyung Jung, Lunit AI team, Sergio Pereira, Donggeun Yoo, Kyunghyun Paeng, Chan-Young Ock. Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes reveals immune-excluded phenotype is correlated with TGF-beta pathway related genomic aberrations [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 6172.

Abstract 644: Deep learning-based H&E analyzer reveals distinct immune profiles and clinical outcomes among immune phenotypes in uterine corpus endometrial carcinoma

Introduction: Deep learning-based H&E analyzer can classify the tumor microenvironment as three immune phenotypes: the immune-inflamed, excluded and desert. Our previous study demonstrated a distinct transcriptomic and immunologic landscape amongst the phenotypes in non-small cell lung cancer (NSCLC). However, it has not been fully investigated in other cancers. Here, we explore the immune profiles and clinical outcomes between the three immune phenotypes in uterine corpus endometrial carcinoma (UCEC).

Methods: Tissue H&E slide images, sequencing data, and clinical data were utilized from The Cancer Genome Atlas (TCGA). Lunit-SCOPE IO was trained with multi-cancer 3,166 H&E whole slide images annotated by pathologists. Based on the proportion of tumor infiltrating lymphocytes (TIL) highly conserved either in cancer epithelium (CE) or cancer stroma (CS), Lunit-SCOPE IO classifies tumors as immune-inflamed and excluded, respectively. Also, it classifies tumors with low TIL density in CE and CS as immune-desert.

Results: Among 486 patients with UCEC, the frequency of immune-inflamed, excluded and desert was 174 (35.8%), 160 (32.9%), and 156 (32%), respectively. In the three subgroup comparison, immune-inflamed was associated with the best survival outcome and -excluded was associated with the worst survival outcome (Inflamed vs excluded, HR 0.30 95% CI 0.17-0.55, p&lt;.001; desert vs excluded, HR 0.50 95% CI 0.30-0.84, p=0.009). Likewise, inflamed subtype showed better overall survival (HR 0.43, 95% CI 0.25-0.75, p=0.003) compared to others. In microsatellite instability high (MSI-H) tumors, we observed a similar tendency of improved overall survival in the tumors of inflamed subtype, both compared to the excluded subtype and to a combination of other subtypes. (Inflamed vs excluded, HR 0.18 95% CI 0.05-0.73, p=0.017; inflamed vs others, HR 0.21 95% CI 0.06-0.72, p=0.014). Immune-inflamed had significantly higher cytolytic activity (Inflamed 7.25 vs others 6.34, p&lt;.001) and was associated with higher PD-L1 expression (Inflamed 19.03 vs others 10.7, p=0.003) and CTLA4 expression (Inflamed 60.62 vs others 31.5, p&lt;.001). Immune-inflamed had a higher proportion of CD8 positive T cell (Inflamed 16.7% vs 12.8%, p&lt;.001) and M1 macrophage (Inflamed 3.9% vs others 2.8%, p&lt;.001) and a lower proportion of M2 macrophage (Inflamed 15% vs others 17.9%, p&lt;.001).

Conclusion: The three tissue phenomic subtypes showed distinct immune profiles and clinical outcomes, with immune-inflamed having the best overall survival outcome. In particular, non-inflamed group was associated with worse overall survival even in MSI-H tumors deemed to have more favorable prognosis compared to MSS tumors. Given the definite differences in the survival outcome, tissue H&E based tumor microenvironment classification may serve as a potential prognostic biomarker in UCEC.

Citation Format: Horyun Choi, Leeseul Kim, Jinah Kim, Yeun Ho Lee, Hyung-Gyo Cho, Na Hyun Kim, Gahyun Gim, Sanghoon Song, Gahee Park, Soo Ick Cho, Sergio Pereira, Donggeun Yoo, Kyunghyun Paeng, Chan-Young Ock, Young Kwang Chae. Deep learning-based H&E analyzer reveals distinct immune profiles and clinical outcomes among immune phenotypes in uterine corpus endometrial carcinoma [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 644.

Artificial intelligence (AI)–powered spatial analysis of tumor-infiltrating lymphocytes (TIL) for prediction of response to neoadjuvant chemotherapy (NAC) in triple-negative breast cancer (TNBC)

595

Background: Stromal TIL are a well-recognized prognostic and predictive biomarker in breast cancer. There is a need for tools assisting visual assessment of TIL, to improve reproducibility as well as for convenience. This study aims to assess the clinical significance of AI-powered spatial TIL analysis in the prediction of pathologic complete response (pCR) after NAC in TNBC patients. Methods: H&E stained slides and clinical outcomes data were obtained from stage I – III TNBC patients treated with NAC in two centers in Korea. For spatial TIL analysis, we used Lunit SCOPE IO, an AI-powered H&E Whole-Slide Image (WSI) analyzer, which identifies and quantifies TIL within the cancer or stroma area. Lunit SCOPE IO was developed with a 13.5 x 109 micrometer2 area and 6.2 x 106 TIL from 17,849 H&E WSI of multiple cancer types, annotated by 104 board-certified pathologists. iTIL score and sTIL score were defined as area occupied by TIL in the intratumoral area (%) and the surrounding stroma (%), respectively. Immune phenotype (IP) of each slide was defined from spatial TIL calculation, as inflamed (high TIL density in tumor area), immune-excluded (high TIL density in stroma), or desert (low TIL density overall). Results: A total of 954 TNBC patients treated from 2006 to 2019 were included in this analysis. pCR (ypT0N0) was confirmed in 261 (27.4%) patients. The neoadjuvant regimens used were mostly anthracycline (97.8%) and taxane (75.1%) -based, with 116 (12.1%) patients receiving additional platinum and 41 (4.3%) patients treated as part of immune checkpoint inhibitor or PARP inhibitor clinical trials. The median iTIL score and sTIL score were 4.3% (IQR 3.2 – 5.8) and 8.1% (IQR 6.3 – 13.4), respectively. The mean iTIL score was significantly higher in patients who achieved pCR after NAC (5.8% vs. 4.5%, p < 0.001), and a similar difference was observed with sTIL score (12.1%.1 vs. 9.4%, p < 0.001). iTIL score was found to remain as an independent predictor of pCR along with cT stage and Ki-67 in the multivariable analysis (adjusted odds ratio 1.211 (95% CI 1.125 – 1.304) per 1 point (%) change in the score, p <0.001). By IP groups, 291 (30.5%) patients were classified as inflamed, 502 (52.6%) as excluded, and 161 (16.9%) as desert phenotype. The patients with inflamed phenotype were more likely to achieve pCR (44.7%) than other phenotypes (19.8%, p < 0.001). Conclusions: AI-powered spatial TIL analysis could assess TIL densities in the cancer area and surrounding stroma of TNBC, and TIL density scores and IP classification could predict pCR after NAC.

Artificial intelligence-powered human epidermal growth factor receptor 2 (HER2) analyzer in breast cancer as an assistance tool for pathologists to reduce interobserver variation

e12543

Background: Human epidermal growth factor receptor 2 (HER2) expression is a predictive marker for HER2-targeted therapy in breast cancer patients. Interobserver variation in the interpretation of HER2 levels exists among pathologists, thus a method to increase the consistency of evaluation is needed. This study aimed to evaluate the performance of the artificial intelligence (AI)-based Lunit SCOPE HER2 in assisting pathologists to evaluate HER2 expression levels in breast cancer. Methods: Lunit SCOPE HER2 was developed with a 1.04 x 1010 μm2 area and 7.31 x 105 tumor cells from 1,133 HER2 immunohistochemistry stained whole-slide images (WSI) of breast cancer, annotated by 113 board-certified pathologists. The AI model was developed based on a semantic segmentation algorithm, which consists of two atrous spatial pyramid pooling blocks for tissue level classification and for tumor cell level classification. To validate the model, a total of 209 HER2 WSIs diagnosed with breast cancer were obtained from Kyung Hee University Hospital in Korea and were assigned as an external validation set. Three board-certified pathologists evaluated slide level HER2 expression (3+, 2+, 1+, and 0) twice, first without AI assistance and second, with it. The second reading was performed for WSIs where the pathologist's reading showed discrepancy with the AI model. Results: In the external validation set, all pathologists scored the same HER2 grade in 103 WSIs (49.3%), and the Fleiss kappa value was 0.512. The HER2 grade from the AI model and pathologists was the same in 151 WSIs (72.2%), and the weighted kappa value was 0.844. The pathologists re-evaluate 43, 63, and 83 WSIs, respectively. After AI assistance, all pathologists scored the same HER2 grade in 156 WSIs (74.6%), and the Fleiss kappa value increased to 0.762 (Table). Conclusions: This study demonstrates that an AI-powered HER2 analyzer can help achieve consistent HER2 expression level evaluation in breast cancer by reducing interobserver variability. Thus, the AI model can be applied as an assistance tool for pathologists in HER2 grade evaluation.[Table: see text]

Artificial intelligence-powered whole-slide image analyzer reveals a distinctive distribution of tumor-infiltrating lymphocytes in neuroendocrine tumors and carcinomas

e16214

Background: Immune checkpoint inhibitors (ICIs) have shown promising treatment outcomes for various types of tumors. However, in neuroendocrine tumors and carcinomas (NET/NEC), ICI has proven to be applicable for only limited cases. In addition, little is known about the immunoprofile of NET/NEC. Here we investigate the landscape of tumor-infiltrating lymphocytes (TIL) using artificial intelligence (AI)-powered H&E whole-slide image (WSI) analyzer to elucidate the tumor microenvironment of NET/NEC. Methods: A total of 240 H&E stained pathologic slides diagnosed with NET/NEC were obtained from Ajou University Medical Center in Korea (from January 2020 to December 2021). For spatial TIL analysis, we used Lunit SCOPE IO, an AI-powered H&E WSI analyzer, which identifies and quantifies TIL within the cancer or stroma area. The AI was developed with a 13.5 x 109 μm2 area and 6.2 x 106 TIL from 17,849 H&E WSI of multiple cancer types, annotated by 104 board-certified pathologists. Intra-tumoral TIL, stromal TIL, and combined (cancer + stroma) TIL density were defined as the TIL count divided by the area of interest respectively. NET with histological grade 1 and 2 were labeled as low grade and NET with histological grade 3 and together with NEC were labeled as high grade. Primary origins of the NET/NEC were grouped by colorectum, stomach, small intestine, hepatopancreatobiliary, lung, and other organs (including anus, appendix, breast, cervix, and larynx). Results: Total slides classified as low grade and high grade were 211 and 29, respectively; 175 samples were from colorectal, 19 from stomach, 16 from small intestine, 16 from hepatopancreaticobiliary, seven from lung, and seven from other organs. The median intra-tumoral TIL, stromal TIL, and combined TIL density were 4.2/mm2 (IQR 1.718 - 11.478), 139.1/mm2 (IQR 75.4 - 313.9), and 62.4/mm2 (IQR 36.3 - 162.6), respectively. The median intra-tumoral TIL density was significantly higher in patients with high grade NET/NEC compared with low grade (11.9/mm2 [IQR 4.51 - 30.9] vs 3.45/mm2 [IQR 1.63 - 9.81], p < 0.001). However, statistical differences in stromal TIL density and combined TIL density were not observed between low grade and high grade NET/NEC. The highest intra-tumoral TIL density in the group classified according to primary origins was lung (n = 7, median: 16.5/mm2, IQR 5.01 - 34.1) and was followed by stomach (n = 19, median: 11.8/mm2, IQR 8.64 - 20.8), and small intestine (n = 16, median: 7.23/mm2, IQR 4.12 - 25.2). Conclusions: AI-powered TIL analysis reveals that the intra-tumoral TIL density is significantly higher in high grade NET/NEC than low grade NET. Our findings align with recent evidence that ICIs are effective against large cell NEC and small cell carcinoma.Therefore, AI-powered TIL analysis should be investigated as a predictive biomarker for ICI response in NET/NEC.

Observer performance study to examine the feasibility of the AI-powered PD-L1 analyzer to assist pathologists’ assessment of PD-L1 expression using tumor proportion score in non–small cell lung cancer

8529

Background: Programmed death ligand 1 (PD-L1) expression is the standard biomarker for PD-L1 inhibitors in advanced non-small cell lung cancer (NSCLC). However, evaluation of PD-L1 tumor proportion score (TPS) by pathologists causes inter-observer variation and demands time to interpret. This study aimed to evaluate the benefit of the artificial intelligence (AI) algorithm in assisting pathologists to determine TPS on PD-L1 immunohistochemistry (IHC) whole-slide images (WSIs) in NSCLC. Methods: Lunit SCOPE PD-L1, an AI-powered PD-L1 TPS analyzer, was developed from 393,565 tumor cells annotated by board-certified pathologists for PD-L1 expression in 802 WSIs stained by 22C3 pharmDx IHC. The AI model was developed based on a region-based convolutional neural network, and the model can detect and count PD-L1 positive or negative tumor cells from WSIs to calculate TPS. Seven independent board-certified pathologists scored ground truth (GT) of PD-L1 TPS from 199 WSI of NSCLC stained by 22C3 pharmDx IHC. TPS from each GT reader was grouped as negative (< 1%), low (1% to 49%), or high (≥ 50%). The GT of each slide was determined by the consensus of GT readers. Another twelve independent board-certified pathologists scored PD-L1 TPS from the same WSIs as observer performance testers (OPT). They scored TPS twice with a washout interval of 4 weeks, with or without AI assistance. TPS accuracy change and reading time of OPT reader according to the presence or absence of AI assistance were analyzed. Results: The standalone accuracy of the AI model was 0.809 (95% CI: 0.690–0.941). With AI assistance, the overall accuracy of TPS had been changed from 0.799 (95% confidence interval [CI]: 0.764–0.836) to 0.832 (95% CI: 0.796–0.869) (P = 0.004). AI assistance increased the accuracy rate in 11 out of 12 OPT readers. The result of the generalized linear mixed model revealed that AI assistance and specimen type affected the probability of correct answer, while the order of reading did not (Table). The mean time to read with AI was 195.4±506.5 (mean±standard deviation) seconds, which was significantly shorter than the mean time to read without AI (285.1±1578.4, P <0.001). Conclusions: This study demonstrates that an AI-powered PD-L1 TPS analyzer can assist board-certified pathologists in evaluating TPS of NSCLC by improving the accuracy of TPS group evaluation and reducing the time to read slides.[Table: see text]

Risks of Comorbidities in Patients With Palmoplantar Pustulosis vs Patients With Psoriasis Vulgaris or Pompholyx in Korea

Importance

Palmoplantar pustulosis (PPP) has been reported to be accompanied by systemic conditions. However, the risks of comorbidities in patients with PPP have rarely been evaluated.

Objective

To assess the risks of comorbidities in patients with PPP compared with patients with psoriasis vulgaris or pompholyx.

Design, Setting, and Participants

This nationwide population-based cross-sectional study used data from the Korean National Health Insurance database and the National Health Screening Program collected from January 1, 2010, to December 31, 2019. Data were analyzed from July 1, 2020, to October 31, 2021. Korean patients diagnosed with PPP, psoriasis vulgaris, or pompholyx who visited a dermatologist between January 1, 2010, and December 31, 2019, were enrolled.

Exposures

Presence of PPP.

Main Outcomes and Measures

The risks of comorbidities among patients with PPP vs patients with psoriasis vulgaris or pompholyx were evaluated using a multivariable logistic regression model.

Results

A total of 37 399 patients with PPP (mean [SD] age, 48.98 [17.20] years; 51.7% female), 332 279 patients with psoriasis vulgaris (mean [SD] age, 47.29 [18.34] years; 58.7% male), and 365 415 patients with pompholyx (mean [SD] age, 40.92 [17.63] years; 57.4% female) were included in the analyses. Compared with patients with pompholyx, those with PPP had significantly higher risks of developing psoriasis vulgaris (adjusted odds ratio [aOR], 72.96; 95% CI, 68.19-78.05; P < .001), psoriatic arthritis (aOR, 8.06; 95% CI, 6.55-9.92; P < .001), ankylosing spondylitis (aOR, 1.91; 95% CI, 1.61-2.27; P < .001), type 1 diabetes (aOR, 1.33; 95% CI, 1.16-1.52; P < .001), type 2 diabetes (aOR, 1.33; 95% CI, 1.29-1.38; P < .001), Graves disease (aOR, 1.25; 95% CI, 1.11-1.42; P < .001), Crohn disease (aOR, 1.63; 95% CI, 1.11-2.40; P = .01), and vitiligo (aOR, 1.87; 95% CI, 1.65-2.12; P < .001) after adjusting for demographic covariates. The risks of ankylosing spondylitis (aOR, 1.37; 95% CI, 1.16-1.62; P < .001) and Graves disease (aOR, 1.40; 95% CI, 1.23-1.58; P < .001) were significantly higher among patients with PPP vs psoriasis vulgaris. However, the risks of psoriatic arthritis (aOR, 0.54; 95% CI, 0.47-0.63; P < .001), systemic lupus erythematosus (aOR, 0.67; 95% CI, 0.46-0.97; P = .04), Sjögren syndrome (aOR, 0.70; 95% CI, 0.50-0.96; P = .03), systemic sclerosis (aOR, 0.29; 95% CI, 0.11-0.77; P = .01), vitiligo (aOR, 0.53; 95% CI, 0.47-0.60; P < .001), and alopecia areata (aOR, 0.88; 95% CI, 0.81-0.95; P = .001) were significantly lower among those with PPP vs psoriasis vulgaris.

Conclusions and Relevance

The results of this cross-sectional study suggest that patients with PPP have an overlapping comorbidity profile with patients with psoriasis vulgaris but not patients with pompholyx. However, the risks of comorbidities among patients with PPP may be substantially different from those among patients with psoriasis vulgaris.

An Analysis of Judicial Cases Concerning Analgesic-Related Medication Errors in the Republic of Korea

OBJECTIVES

Analgesic-related medication errors can be a threat to patient safety. This study aimed to identify and describe medication errors that can cause serious adverse drug events (ADEs) related to analgesic use.

METHODS

This retrospective, observational, medicolegal study analyzed closed cases concerning complications induced by medication errors involving 3 commonly used analgesics: opioids, nonsteroidal anti-inflammatory drugs (NSAIDs), and acetaminophen (AAP). Cases closed between 1994 and 2019 that were available in the Korean Supreme Court judgment database system were included. Medication errors were categorized using a classification system (developed by our group) based on the stage of drug administration. Clinical characteristics and judgment statuses were analyzed.

RESULTS

A total of 71 cases were included in the final analysis (opioids, n = 30; NSAIDs, n = 35; AAP, n = 6). Among them, 43 claims (60.6%) resulted in payments to the plaintiffs, with a median payment of $86,607 (interquartile range, $34,554-$193,782). The severity of ADEs was high (National Association of Insurance Commissioners scale ≥6) in 88.7% (n = 63) of claims, with a total of 44 (62%) deaths. The most common types of ADEs associated with opioid, NSAID, and AAP use were respiratory depression, anaphylactic shock, and fulminant hepatitis, respectively. The most common recognized medication errors associated with opioid, NSAIDs, and AAP were inappropriate patient monitoring (n = 10; 33.3%), improper analgesic choice (n = 15; 42.9%), and inappropriate treatment after ADEs (n = 3; 50%), respectively.

CONCLUSIONS

Our findings indicate that efforts should be made to reduce medication errors related to analgesic use to prevent permanent injury and potential malpractice claims.

Abstract P4-05-07: Assistance with an artificial intelligence-powered tumor infiltrating lymphocytes (TIL) analyzer reduces interobserver variation in pathologic scoring of TIL in breast cancer

Background Tumor infiltrating lymphocytes (TIL) is a promising prognostic marker in breast cancer. However, TIL is manually scored by pathologists, thus laborious work is required and interobserver heterogeneity exists in the results. In this study, we aimed to evaluate the clinical utility of an artificial intelligence (AI)-powered TIL analyzer in terms of reducing the interobserver variation. Methods Lunit SCOPE IO, AI-powered TIL analyzer was trained and validated with a 2.8 x 109 micrometer2 area and 5.9 x 106 TIL from 3,166 H&E Whole-Slide Images (WSI) of multiple cancer types including breast cancer, annotated by 52 board-certified pathologists. Three independent board-certified pathologists scored TIL% of H&E slides of breast cancer from an external cohort (N = 199). TIL% was calculated referenced on the guideline of Immuno-Oncology Biomarker Working Group on Breast Cancer. For the cases of TIL score difference between each pathologist and AI model more than 15%, the pathologists were asked to revise TIL% in assistance with AI model which displays both stromal area and TIL. Finally, we compared the interobserver variation based on intraclass correlation coefficients (ICC) before and after AI assistance. Results The distribution of TIL score by 3 pathologists was 7% (5-20%), 15% (5-50%), and 20% (10-40%), respectively [median (25%-75% quantile)]. The ICC value of the initial TIL score evaluation was 0.716 (95% confidence interval, 0.560-0.811). Afterward, pathologists revised their initial scoring with assistance of AI model for the cases of difference more than 15% (n = 19, 72, and 73, respectively for each pathologist). After rescoring, number of slides with 15% or more difference of TIL% between raters significantly decreased from 109 slides (54.8%) to 75 slides (37.7%, p &lt; 0.001). The ICC value after re-scoring TIL% was 0.831 (95% confidence interval, 0.725-0.890). Conclusions There was a notable interobserver variation to score TIL% in breast cancer. Assistance with AI-powered TIL analyzer substantially improved the pathologist’s consensus and could be regarded as one of references for the final labeling of TIL%.

Citation Format: Soo Ick Cho, Wonkyung Jung, Sangjoon Choi, Seokhwi Kim, Sanghoon Song, Gahee Park, Minuk Ma, Seonwook Park, Sergio Pereira, Sangheon Ahn, Brian Jaehong Aum, Seunghwan Shin, Kyunghyun Paeng, Donggeun Yoo, Chan-Young Ock. Assistance with an artificial intelligence-powered tumor infiltrating lymphocytes (TIL) analyzer reduces interobserver variation in pathologic scoring of TIL in breast cancer [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P4-05-07.

Clinical and Histological Effects of Topical Epidermal Growth Factor on Acne and Acne Scars

BACKGROUND

The inflammatory lesions of acne leave scars which greatly affect patients' quality of life. Treatment options targeting both acne and acne scars are still lacking.

OBJECTIVES

To evaluate the clinical efficacy of epidermal growth factor ointment (EGFO) on acne and acne scars.

METHODS

The study design was 12-week, prospective, split-face, single-blinded. The 36 patients with mild to moderate acne vulgaris applied EGFO on one side of the face and the vehicle ointment on the other side twice daily. The patients were assessed every 4 weeks by acne lesion and scar counts, investigator's global assessment for acne (IGA) and scar (SGA), and the ECCA scar grading scale. Biopsies were performed before and after treatment.

RESULTS

Acne and acne scars were significantly improved on EGFO-treated sides, while control sides were not. Acne lesion and scar counts were significantly reduced after 4 weeks, while IGA, SGA, and ECCA grade significantly decreased after 8 weeks. Immunohistochemistry showed decreased expression of keratin 16, NF-κB p65, IL-1α, and IL-8, and increased expression of TGF-β1, elastin, and collagen type 1, 3 after treatment.

CONCLUSIONS

EGFO can be a treatment option targeting acne and acne scars.

Practical Training Approaches for Discordant Atopic Dermatitis Severity Datasets: Merging Methods with Soft-label and Train-set Pruning

Objective assessment of atopic dermatitis (AD) is essential for choosing proper management strategies. This study investigated the performance of convolutional neural networks (CNN) models in grading the severity of AD. Five board-certified dermatologists independently evaluated the severity of 9,192 AD images. The severity of AD was evaluated based on an Investigator's Global Assessment (IGA) and six signs of AD. For CNN training, we applied three distinct approaches: 1) ensemble vs. integration 2) hard-label vs. soft-label and 3) train-set pruning. For the IGA prediction, the two best models were chosen based on the macro-averaged AUROC and F-1 score. The ensemble-soft-label-pruning model was chosen based on AUROC 0.943, 0.927 for the internal and external validation set respectively, and integration-soft-label-whole dataset model was chosen based on the F1-score 0.750, 0.721 for the internal and external validation set respectively. CNN models trained by multi-evaluator dataset outperformed the models by an individual evaluator dataset, and they performed better to the dataset in which the assessment of dermatologists was concordant. In conclusion, CNN models for AD could be improved by labeled dataset from multiple evaluators, merging methods with soft-label and train-set pruning.

830 Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes reveals immune-excluded phenotype related to APOBEC signature and clonal evolution of cancer

Background

Little is known about bridging clonal heterogeneity into the resistance of immune checkpoint inhibitors (ICI). Recent reports showed that excluded tumor-infiltrating lymphocytes (TIL) into stroma assessed by an artificial intelligence (AI)-powered spatial TIL analyzer, Lunit SCOPE IO, was related to loss-of-heterozygosity of HLA genes which would be one of crucial resistance pathways of ICI.1 In the current study, we hypothesized that Immune-excluded phenotype called by Lunit SCOPE IO would be related to clonal heterogeneity resulted from genome-wide accidents during early carcinogenesis which may cause an improper targeting of TIL for diverse clones with multiple genomic aberrations.

Methods

For spatial TIL analysis, we applied Lunit SCOPE IO1 which automatically detects TIL and segmentizes cancer area and stroma, then it classified Immune phenotype of 1 mm2-sized grid in H&E image. Inflamed score or Immune-excluded score were defined as the proportion of Inflamed phenotype, which is high intra-tumoral TIL density, or Immune-excluded phenotype, which is exclusively high TIL density only in stroma, within a whole-slide image, respectively. We evaluated the correlation of Immune phenotype with APOBEC mutational signature by single-base substitution (SBS) signature 2 and/or SBS13,2 whole-genome doubling, and subclonal genome fraction which reflects intra-tumoral heterogeneity,3 and clusters of T cell receptor (TCR) repertoire 4 derived from previous reports of The Cancer Genome Atlas (TCGA), consists of 7,467 tumor samples from 22 cancer types.

Abstract 830 Table 1

Correlation between immune phenotype and clonal evolution of cancer [* Median (95% confidence interval)]

Results

In the TCGA pan-carcinoma database, APOBEC mutational signature was significantly correlated with increased ratio of cancer stroma to cancer epithelium (median 0.866 vs 1.19, fold change +37.4%), and increased TIL density in cancer stroma (median 558 vs 764 / mm2, fold change +36.9%), but it was not correlated with intra-tumoral TIL density (median 63 vs 59 / mm2, fold change -6.3%). Interestingly, Immune-excluded score (IES) called by Lunit SCOPE IO was positively correlated with APOBEC mutational signature as well as expression levels of APOBEC1, APOBEC3A, and APOBEC3B, whole-genome doubling, and subclonal genome fraction, respectively, while Inflamed score (IS) or immune cytolytic activity (GZMA and PRF1 expressions) was negatively or not significantly correlated to those variables (table 1). TCR repertoire was expanded in the tumor samples with high IS (spearman rho = 0.279), but it was not increased in those with high IES (spearman rho = -0.0595).

Conclusions

There is a significant correlation between distinct TIL deposition in stroma, or Immune-excluded phenotype, with APOBEC-attributed clonal expansion of cancer, without proper expansion of TCR repertoire.

References

Ock CY, Park C, Paeng K, Yoo D, Kim S, Park S, Lee SH, Mok T, Bang YJ. Artificial intelligence-powered spatial analysis of tumor-infiltrating lymphocytes reveals distinct genomic profile of immune excluded phenotype in pan-carcinoma. Cancer Res 2021;81(Supp 13):1908.

Alexandrov LB, Kim J, Haradhvala NJ, Huang MN, Tian Ng AW, Wu Y, Boot A, Covington KR, Gordenin DA, Bergstrom EN, Islam SMA, Lopez-Bigas N, Klimczak LJ, McPherson JR, Morganella S, Sabarinathan R, Wheeler DA, Mustonen V, PCAWG Mutational Signatures Working Group, Getz G, Rozen SG, Stratton MR, PCAWG Consortium. The repertoire of mutational signatures in human cancer. Nature 2020;578(7793):94–101.

Taylor AM, Shih J, Ha G, Gao GF, Zhang X, Berger AC, Schumacher SE, Wang C, Hu H, Liu J, Lazar AJ, Cancer Genome Atlas Research Network, Cherniack AD, Beroukhim R, Meyerson M. Genomic and functional approaches to understanding cancer aneuploidy. Cancer Cell 2018;33(4):676–689.e3.

Zhang H, Liu L, Zhang J, Chen J, Ye J, Shukla S, Qiao J, Zhan X, Chen H, Wu CJ, Fu YX, Li B. Investigation of antigen-specific T-Cell receptor clusters in human cancers. Clin Cancer Res 2020;26(6):1359–1371.

Pilot study of fractional microneedling radiofrequency for hidradenitis suppurativa assessed by clinical response and histology

BACKGROUND

Hidradenitis suppurativa (HS) is a devastating chronic inflammatory skin disease with frequent recurrences. Various systemic treatments and procedures have been used but the efficacy of fractional microneedling radiofrequency (FMR) has not been reported.

AIM

To evaluate the clinical and histological efficacy of FMR in the treatment of HS lesions.

METHODS

An 8-week, prospective, split-body, unblinded study was conducted, which enrolled 10 adult patients with mild to moderate HS to receive 3 sessions of FMR treatment biweekly. HS severity was assessed using the number and type of lesions, HS Physician Global Assessment (HS-PGA) and the modified Sartorius score (mSS). Skin biopsies were performed on participants to assess change in inflammation before and after FMR.

RESULTS

Severity of HS was significantly reduced on the FMR-treated side of the body, but not on the control side. Inflammatory HS lesions were significantly reduced after 4 weeks, while HS-PGA and mSS were significantly decreased after 6 weeks. Immunohistochemistry staining showed decreased expression of inflammatory markers including neutrophil elastases, interleukin (IL)-8 and IL-17, tumour necrosis factor-α, transforming growth factor-β1 and matrix metalloproteinases.

CONCLUSION

FMR may be a viable treatment option for mild to moderate HS.

Intradermal Microdroplet Injection of Diluted Incobotulinumtoxin-A for Sebum Control, Face Lifting, and Pore Size Improvement

BACKGROUND

Intradermal injections of botulinum toxin have been reported to improve sebum secretion, facial skin laxity, and facial pores. However, the effects of Incobotulinumtoxin-A for these indications have not been reported.

OBJECTIVE

To evaluate the efficacy of Incobotulinumtoxin-A for the improvement of sebum secretion, face laxity, and facial pores.

MATERIALS AND METHODS

This single-center retrospective study included patients treated with Incobotulinumtoxin-A to improve facial skin laxity, sebum secretion, and facial pores. The microdroplet injection protocol included injection points on the lateral face, anterior medial cheek, mandibular line, depressor anguli oris points, mid-glabella area, and chin. Outcomes were measured using a Sebumeter and three-dimensional scanner and were evaluated by facial laxity ratings and the Global Aesthetic Improvement Scale.

RESULTS

Twenty patients were included in the analysis. Sebum secretion, mandibular length, facial pores, and facial laxity ratings were improved at 1 week and results were sustained through 12 weeks. All outcomes showed maximum improvement after 4 weeks. Evaluation using the Global Aesthetic Improvement Scale showed that all subjects reported at least a score of 2 (improved) after 4 weeks.

CONCLUSION

This study showed that intradermal injection with Incobotulinumtoxin-A could be effective for face lifting, reduced sebum production, and improved facial pores. J Drugs Dermatol. 2021;20(1):49-54. doi:10.36849/JDD.5616.

Association of Metabolic Comorbidities with Pediatric Psoriasis: A Systematic Review and Meta-Analysis

Background

An evident relationship has been shown between psoriasis and metabolic comorbidities. However, the results in pediatric psoriasis vary from study to study, and no meta-analysis exists on the association of metabolic comorbidities with pediatric psoriasis.

Objective

To evaluate the association between psoriasis and metabolic comorbidities in pediatric patients.

Methods

We searched articles published in PubMed, EMBASE, and Cochrane Library databases from inception to April 30, 2019. All observational studies reporting the prevalence of obesity or metabolic comorbidities in pediatric patients with psoriasis were included.

Results

The meta-analysis included 16 unique studies meeting the inclusion criteria. The pooled odds ratios in pediatric patients with psoriasis was 2.40 (95% confidence interval [CI], 1.60~3.59) for obesity (13 studies), 2.73 (95% CI, 1.79~4.17) for hypertension (8 studies), 2.01 (95% CI, 1.09~3.73) for diabetes mellitus (8 studies), 1.67 (95% CI, 1.42~1.97) for dyslipidemia (7 studies), and 7.49 (95% CI, 1.86~30.07) for metabolic syndrome (4 studies).

Conclusion

Pediatric patients with psoriasis showed a significantly higher prevalence of obesity, hypertension, diabetes, dyslipidemia, and metabolic syndrome. Adequate monitoring and timely management of metabolic comorbidities should be considered in these patients.

Histone Deacetylase 1 Reduces Lipogenesis by Suppressing SREBP1 Transcription in Human Sebocyte Cell Line SZ95

Proper regulation of sebum production is important for maintaining skin homeostasis in humans. However, little is known about the role of epigenetic regulation in sebocyte lipogenesis. We investigated histone acetylation changes and their role in key lipogenic gene regulation during sebocyte lipogenesis using the human sebaceous gland cell line SZ95. Sebocyte lipogenesis is associated with a significant increase in histone acetylation. Treatment with anacardic acid (AA), a p300 histone acetyltransferase inhibitor, significantly decreased the lipid droplet number and the expression of key lipogenic genes, including sterol regulatory-binding protein 1 (SREBP1), fatty acid synthase (FAS), and acetyl-CoA carboxylase (ACC). In contrast, treatment with trichostatin A (TSA), a histone deacetylase (HDAC) inhibitor, increased the expression of these genes. Global HDAC enzyme activity was decreased, and HDAC1 and HDAC2 expression was downregulated during sebaceous lipogenesis. Interestingly, HDAC1 knockdown increased lipogenesis through SREBP1 induction, whereas HDAC1 overexpression decreased lipogenesis and significantly suppressed SREBP1 promoter activity. HDAC1 and SREBP1 levels were inversely correlated in human skin sebaceous glands as demonstrated in immunofluorescence images. In conclusion, HDAC1 plays a critical role in reducing SREBP1 transcription, leading to decreased sebaceous lipogenesis. Therefore, HDAC1 activation could be an effective therapeutic strategy for skin diseases related to excessive sebum production.

Analysis of trends and status of physician-based evaluation methods in acne vulgaris from 2000 to 2019

Various evaluation methods for acne severity have been used without standardization, and the diversity of acne outcome measures is an obstacle to the integrated analysis of various acne studies. In this study, we sought to investigate physician-based evaluation methods used in clinical studies of acne vulgaris and to determine differences according to time, region and study design. PubMed was searched for articles on acne published from January 2000 to June 2019 in five dermatology journals: Journal of the American Academy of Dermatology, JAMA Dermatology, British Journal of Dermatology, Journal of the European Academy of Dermatology and Venereology and Acta Dermato-Venereologica. A total of 186 articles with acne evaluation methods were selected. Among the selected studies, region, study design, type of intervention and the number of subjects were identified and analyzed. Articles from 2010 to 2019 used Investigator Global Assessment (IGA; odds ratio [OR], 5.808; 95% CI, 1.894-17.811) more often and the Leeds technique (OR, 0.282; 95% CI, 0.098-0.812) less often compared with articles from 2000 to 2009. Controlled experimental studies preferred lesion counting (OR, 238.637; 95% CI, 46.795-1216.954), IGA (OR, 9.177; 95% CI, 3.053-27.586) and Leeds Revised Acne Grading System (LRAGS; OR, 10.844; 95% CI, 3.050-38.559) compared with observational studies. North American studies applied lesion counting (OR, 4.573; 95% CI, 1.173-17.836) and IGA (OR, 11.330; 95% CI, 3.487-36.818) more often and LRAGS (OR, 0.171; 95% CI, 0.039-0.758) less often compared with European studies. This study demonstrated the diversity and heterogeneity of acne outcome measures even in highly influential dermatology journals. This is due to the limitations of current methods and suggests the importance of developing a core outcome measure.

Granulomatous Rosacea in Korean Patients: Diagnosis Based on Combining Clinical and Histological Findings

BACKGROUND

Granulomatous rosacea (GR) is a rare inflammatory skin disease, which is considered a variant of rosacea, apart from other types of rosacea.

OBJECTIVE

This study aimed to summarize the characteristics of Korean patients diagnosed with GR by combining clinical and histological findings.

METHODS

Fifteen cases, both clinically and histologically consistent with GR, were selected and were subsequently analyzed to describe clinical and histological characteristics.

RESULTS

A total of 20 patients showed granulomatous infiltration in skin biopsies, but only 15 of them were clinically consistent with GR. Five patients who showed granulomatous inflammation were clinically consistent with erythematotelangiectatic or papulopustular rosacea. Among 15 patients, 13 (86.7%) were female and 2 (13.3%) were male. The most frequently involved area was the cheek, and none of the patients showed extrafacial lesions. There seems to be a possibility that treatment duration may be associated with the treatment response.

CONCLUSIONS

This study confirms clinical characteristics of GR based on the diagnosis combining both clinical and histological findings.

Association of COVID-19 with skin diseases and relevant biologics: a cross-sectional study using nationwide claim data in South Korea

Background

As the coronavirus disease 2019 (COVID‐19) pandemic has spread, information about COVID‐19 and skin disease or related biologics is still lacking.

Objectives

To identify the association between COVID‐19 and skin diseases or biologics.

Methods

A nationwide claim dataset relevant to COVID‐19 in South Korea was analysed. This dataset included insurance claim data before and during COVID‐19 treatment and clinical outcomes. Claim data related to skin diseases and relevant biologics were analysed to determine the association of COVID‐19 with skin diseases and relevant biologics.

Results

The dataset contained a total of 234 427 individuals (111 947 male and 122 480 female) who underwent COVID‐19 testing. Of them, 7590 (3·2%) were confirmed as having COVID‐19, and 227 (3·0%) confirmed patients died. Among various skin diseases and biologics, no significant increase in the presence of specific skin diseases or exposure to biologics was observed in the COVID‐19‐positive group, even after adjusting for or matching covariates. The presence of skin diseases and exposure to biologics also did not seem to affect clinical outcomes including mortality.

Conclusions

Underlying skin diseases did not appear to increase susceptibility to COVID‐19 or mortality from COVID‐19. Considering the risks and benefits, biologics for dermatological conditions might be continuously used during the COVID‐19 pandemic.

Tumor growth rate as a prognostic factor of acral melanoma in a Korean population

Rapid growth of cutaneous melanoma is associated with aggressive histopathologic features and poor prognosis. However, the impact of growth rate (GR) in acral melanoma (AM) remains largely unknown.We performed this study to identify the impact of GR on lymph node metastasis and survival in AM.We analyzed cases of invasive AM diagnosed at our institution between 1998 and 2017. We investigated the impact of GR on the prognosis of AM.A total of 126 cases of invasive AM were included. Log (GR) was significant associated with lymph node metastasis in the univariate logistic regression analysis (P = .005). The log-rank test revealed statistically significant differences in disease-free survival (DFS) and disease-specific survival (DSS) among the GR quartiles. In the Cox regression analysis, log (GR) was an independent predictor for DFS (P = .041), but not for DSS in multivariate analysis. In the subgroup analysis, log (GR) was an independent predictor for early-stage (≤2A) AM (DFS, P = .002; DSS, P = .004).The limitations of this study include the retrospective design of the study and possible recall bias.Our results suggest that GR is an important prognostic factor for DFS and DSS in AM patients and an independent predictor for early-stage AM.

Analysis of judicial precedent cases regarding epidural injection in chronic pain management in Republic of Korea

BACKGROUND

Although there is a low incidence of complications associated with epidural injections, pain physicians should still remain vigilant for potentially serious adverse outcomes. This study aimed to identify and describe the major complications of epidural injections.

METHODS

This retrospective, observational, medicolegal study analyzed closed cases of precedents involving complications of epidural injections from January 1997 to August 2019 using the database of the Supreme Court of Korea's judgement system. Clinical characteristics and judgement statuses were analyzed.

RESULTS

Of the 73 potential cases assessed for eligibility, a total of 49 malpractice cases were included in the final analysis. Thirty-three claims resulted in payments to the plaintiffs, with a median payment of US$103 828 (IQR: US$45 291-US$265 341). The most common complication was infection (n=13, 26.5%), followed by worsening pain (n=8, 16.3%). Physician malpractice before, during, and after the procedure was claimed by plaintiffs in 18 (36.7%), 44 (89.8%), and 31 (63.3%) cases, respectively. Of these cases, 6 (33.3%), 19 (43.2%), and 15 (48.4%), respectively, were adjudicated in favor of the plaintiffs by the courts. In cases involving postprocedural physician errors, the majority (13/15) of the plaintiff verdicts were related to delayed management. Violation of the physician's duty of informed consent was claimed by plaintiffs in 31 (63.3%) cases, and 14 (45.2%) of these cases were judged medical malpractice.

CONCLUSIONS

Our data will allow pain physicians to become acquainted with the major epidural injection-associated complications that underlie malpractice cases.

Schwannoma Presenting as a Scalp Mass: A Case Report with Magnetic Resonance Imaging Findings

A schwannoma can develop anywhere along the course of nerves. However, a schwannoma presenting as a scalp nodule is rare. Here, we present a rare case of schwannoma on the scalp with a review of magnetic resonance imaging (MRI) findings, which was initially misdiagnosed as an epidermal cyst or vascular malformation despite various radiologic examinations. Recognition of characteristic MRI features of schwannomas, such as low signal margin, target, entering-and-exiting-nerve, and fascicular signs, may result in an accurate diagnosis and proper management of tumors. In this report, we summarized differential characteristics of a schwannoma with an epidermal cyst and a lipoma.

Association of frequent intake of fast foods, energy drinks, or convenience food with atopic dermatitis in adolescents

PURPOSE

Specific food consumption, besides food allergy, may aggravate atopic dermatitis (AD). However, previous reports on the association between AD and food intake in adolescents are scarce. The aim of this study was to determine the relationship between AD and specific food consumption frequency in adolescents.

METHODS

A cross-sectional analysis using data from the Korea Youth Risk Behavior Web-based Survey 2017 was performed. The frequency of food consumption in the recent-diagnosed AD group (AD diagnosed within 12 months) compared to those in the previous-diagnosed AD (AD diagnosed more than 12 months ago) or control group were investigated.

RESULTS

A total of 53,373 participants were eligible for this study. The weighted prevalence of the recent-diagnosed AD and the previous-diagnosed AD was 7.39% and 18.00%, respectively. When compared with subjects with the previous-diagnosed AD, those with the recent-diagnosed AD were significantly more likely to frequently consume fast foods (odds ratio OR 1.405; 95% CI 1.150-1.717), energy drinks (OR 1.457; 95% CI 1.175-1.807), or convenience food (OR 1.304; 95% CI 1.138-1.495). Patients of the recent-diagnosed AD were significantly more likely to frequently consume fast foods (OR 1.374; 95% CI 1.155-1.634) than the control group. The differences in the frequency of specific food consumption among groups were more pronounced in high school students than in middle school students.

CONCLUSIONS

Frequent intake of fast foods, energy drinks, and convenience food was related to the recent-diagnosed AD in adolescents. Prospective cohort and interventional studies are needed to identify causal relationships.