Dermatopathology of Malignant Melanoma in the Era of Artificial Intelligence: A Single Institutional Experience

Histological interpretation of spitzoid tumours: an extensive machine learning-based concordance analysis for improving decision making

The histopathological classification of melanocytic tumours with spitzoid features remains a challenging task. We confront the complexities involved in the histological classification of these tumours by proposing machine learning (ML) algorithms that objectively categorise the most relevant features in order of importance. The data set comprises 122 tumours (39 benign, 44 atypical and 39 malignant) from four different countries. BRAF and NRAS mutation status was evaluated in 51. Analysis of variance score was performed to rank 22 clinicopathological variables. The Gaussian naive Bayes algorithm achieved in distinguishing Spitz naevus from malignant spitzoid tumours with an accuracy of 0.95 and kappa score of 0.87, utilising the 12 most important variables. For benign versus non-benign Spitz tumours, the test reached a kappa score of 0.88 using the 13 highest-scored features. Furthermore, for the atypical Spitz tumours (AST) versus Spitz melanoma comparison, the logistic regression algorithm achieved a kappa value of 0.66 and an accuracy rate of 0.85. When the three categories were compared most AST were classified as melanoma, because of the similarities on histological features between the two groups. Our results show promise in supporting the histological classification of these tumours in clinical practice, and provide valuable insight into the use of ML to improve the accuracy and objectivity of this process while minimising interobserver variability. These proposed algorithms represent a potential solution to the lack of a clear threshold for the Spitz/spitzoid tumour classification, and its high accuracy supports its usefulness as a helpful tool to improve diagnostic decision-making.

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 (ML) and Deep Learning (DL), has demonstrated its potential in tasks ranging from diagnostic applications on Whole Slide Imaging (WSI) 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 (CNNs), can outperform human pathologists in terms of sensitivity and specificity. Moreover, 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 aiding 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 like Mycosis Fungoides and eczema. While 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 stress edthe importance of collaboration between medical professionals, computer scientists, bioinformaticians, and engineers to harness AI's benefits while 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 Melanoma Dermatopathology: A Review of Literature

ABSTRACT

Pathology serves as a promising field to integrate artificial intelligence into clinical practice as a powerful screening tool. Melanoma is a common skin cancer with high mortality and morbidity, requiring timely and accurate histopathologic diagnosis. This review explores applications of artificial intelligence in melanoma dermatopathology, including differential diagnostics, prognosis prediction, and personalized medicine decision-making.

A Novel Automatic Algorithm to Support Lung Ultrasound Non-Expert Physicians in Interstitial Pneumonia Evaluation: A Single-Center Study

INTRODUCTION

Lung ultrasound (LUS) is widely used in clinical practice for identifying interstitial lung diseases (ILDs) and assessing their progression. Although high-resolution computed tomography (HRCT) remains the gold standard for evaluating the severity of ILDs, LUS can be performed as a screening method or as a follow-up tool post-HRCT. Minimum training is needed to better identify typical lesions, and the integration of innovative artificial intelligence (AI) automatic algorithms may enhance diagnostic efficiency.

AIM

This study aims to assess the effectiveness of a novel AI algorithm in automatic ILD recognition and scoring in comparison to an expert LUS sonographer. The "SensUS Lung" device, equipped with an automatic algorithm, was employed for the automatic recognition of the typical ILD patterns and to calculate an index grading of the interstitial involvement.

METHODS

We selected 33 Caucasian patients in follow-up for ILDs exhibiting typical HRCT patterns (honeycombing, ground glass, fibrosis). An expert physician evaluated all patients with LUS on twelve segments (six per side). Next, blinded to the previous evaluation, an untrained operator, a non-expert in LUS, performed the exam with the SensUS device equipped with the automatic algorithm ("SensUS Lung") using the same protocol. Pulmonary functional tests (PFT) and DLCO were conducted for all patients, categorizing them as having reduced or preserved DLCO. The SensUS device indicated different grades of interstitial involvement named Lung Staging that were scored from 0 (absent) to 4 (peak), which was compared to the Lung Ultrasound Score (LUS score) by dividing it by the number of segments evaluated. Statistical analyses were done with Wilcoxon tests for paired values or Mann-Whitney for unpaired samples, and correlations were performed using Spearman analysis; p < 0.05 was considered significant.

RESULTS

Lung Staging was non-inferior to LUS score in identifying the risk of ILDs (median SensUS 1 [0-2] vs. LUS 0.67 [0.25-1.54]; p = 0.84). Furthermore, the grade of interstitial pulmonary involvement detected with the SensUS device is directly related to the LUS score (r = 0.607, p = 0.002). Lung Staging values were inversely correlated with forced expiratory volume at first second (FEV1%, r = -0.40, p = 0.027), forced vital capacity (FVC%, r = -0.39, p = 0.03) and forced expiratory flow (FEF) at 25th percentile (FEF25%, r = -0.39, p = 0.02) while results directly correlated with FEF25-75% (r = 0.45, p = 0.04) and FEF75% (r = 0.43, p = 0.01). Finally, in patients with reduced DLCO, the Lung Staging was significantly higher, overlapping the LUS (reduced median 1 [1-2] vs. preserved 0 [0-1], p = 0.001), and overlapping the LUS (reduced median 18 [4-20] vs. preserved 5.5 [2-9], p = 0.035).

CONCLUSIONS

Our data suggest that the considered AI automatic algorithm may assist non-expert physicians in LUS, resulting in non-inferior-to-expert LUS despite a tendency to overestimate ILD lesions. Therefore, the AI algorithm has the potential to support physicians, particularly non-expert LUS sonographers, in daily clinical practice to monitor patients with ILDs. The adopted device is user-friendly, offering a fully automatic real-time analysis. However, it needs proper training in basic skills.

PRAME Is an Effective Tool for the Diagnosis of Nevus-Associated Cutaneous Melanoma

(1) Background: Nevus-associated cutaneous melanoma (CM) is relatively common in the clinical practice of dermatopathologists. The correct diagnosis and staging of nevus-associated cutaneous melanoma (CM) mainly relies on the correct discrimination between benign and malignant cells. Recently, PRAME has emerged as a promising immunohistochemical marker of malignant melanocytes. (2) Methods: PRAME immunohistochemistry (IHC) was performed in 69 cases of nevus-associated CMs. Its expression was evaluated using a score ranging from 0 to 4+ based on the percentage of melanocytic cells with a nuclear expression. PRAME IHC sensitivity, specificity, positive predictive values, and negative predictive values were assessed. Furthermore, the agreement between morphological data and PRAME expression was evaluated for the diagnosis of melanoma components and nevus components. (3) Results: PRAME IHC showed a sensitivity of 59%, a specificity of 100%, a positive predictive value of 100%, and a negative predictive value of 71%. The diagnostic agreement between morphology and PRAME IHC was fair (Cohen's Kappa: 0.3); the diagnostic agreement regarding the benign nevus components associated with CM was perfect (Cohen's Kappa: 1.0). PRAME was significantly more expressed in thick invasive CMs than in thin cases (p = 0.02). (4) Conclusions: PRAME IHC should be considered for the diagnostic evaluation of nevus-associated CM and is most useful in cases of thick melanomas. Pathologists should carefully consider that a PRAME-positive cellular population within the context of a nevus could indicate a CM associated with the nevus. A negative result does not rule out this possibility.

Artificial intelligence-assisted dermatology diagnosis: From unimodal to multimodal

Artificial Intelligence (AI) is progressively permeating medicine, notably in the realm of assisted diagnosis. However, the traditional unimodal AI models, reliant on large volumes of accurately labeled data and single data type usage, prove insufficient to assist dermatological diagnosis. Augmenting these models with text data from patient narratives, laboratory reports, and image data from skin lesions, dermoscopy, and pathologies could significantly enhance their diagnostic capacity. Large-scale pre-training multimodal models offer a promising solution, exploiting the burgeoning reservoir of clinical data and amalgamating various data types. This paper delves into unimodal models' methodologies, applications, and shortcomings while exploring how multimodal models can enhance accuracy and reliability. Furthermore, integrating cutting-edge technologies like federated learning and multi-party privacy computing with AI can substantially mitigate patient privacy concerns in dermatological datasets and further fosters a move towards high-precision self-diagnosis. Diagnostic systems underpinned by large-scale pre-training multimodal models can facilitate dermatology physicians in formulating effective diagnostic and treatment strategies and herald a transformative era in healthcare.

Paediatric Spitzoid Neoplasms: 10-Year Retrospective Study Characterizing Histological, Clinical, Dermoscopic Presentation and FISH Test Results

INTRODUCTION

Spitzoid lesions are a wide tumour class comprising Spitz nevus (SN), atypical Spitz tumour (AST) and Spitz melanoma (SM).

MATERIALS AND METHODS

We conducted a single-centre-based retrospective survey on all histologically diagnosed spitzoid lesions of paediatric patients (1-18 years) of the last 10 years (2012-2022). Histopathological reports and electronic records of patients were used to retrieve relevant data regarding patients' features, clinical and dermatoscopical aspects of lesions when recorded, and FISH tests when present.

RESULTS

Of 255 lesions, 82% were histologically benign, 17% atypical, 1% malignant. Clinically, 100% of SM were large (≥6 mm) and raised; AST were mainly large (63%), raised (98%), pink (95%). Small (≤5 mm), pigmented, flat lesions correlated with benign histology (respectively 90%, 97%, 98% SN) (p < 0.0001). Dermatoscopical patterns were analysed in 100 patients: starburst pattern correlated with benign histology (26% SN (p = 0.004)), while multicomponent pattern correlated with atypical/malignant lesions (56% AST, 50% SM (p = 0.0052)). Eighty-five lesions were subjected to fluorescence in situ hybridization (FISH): 34 (71% AST; 29% SN) were FISH-positive; 51 (63% SN; 37% AST) were FISH-negative (p = 0.0038).

DISCUSSION

This study confirmed predominant benign histology (82%) of paediatric spitzoid lesions, thus detecting 17% AST and 1% SM, highlighting the need for caution in handling spitzoid lesions.

CONCLUSION

Until AST are considered potentially malignant proliferations and no reliable criteria are identified to distinguish them, the authors suggest a prudent approach, especially in children.

Artificial Intelligence Applied to a First Screening of Naevoid Melanoma: A New Use of Fast Random Forest Algorithm in Dermatopathology

Malignant melanoma (MM) is the "great mime" of dermatopathology, and it can present such rare variants that even the most experienced pathologist might miss or misdiagnose them. Naevoid melanoma (NM), which accounts for about 1% of all MM cases, is a constant challenge, and when it is not diagnosed in a timely manner, it can even lead to death. In recent years, artificial intelligence has revolutionised much of what has been achieved in the biomedical field, and what once seemed distant is now almost incorporated into the diagnostic therapeutic flow chart. In this paper, we present the results of a machine learning approach that applies a fast random forest (FRF) algorithm to a cohort of naevoid melanomas in an attempt to understand if and how this approach could be incorporated into the business process modelling and notation (BPMN) approach. The FRF algorithm provides an innovative approach to formulating a clinical protocol oriented toward reducing the risk of NM misdiagnosis. The work provides the methodology to integrate FRF into a mapped clinical process.

Pulsatilla Saponins Inhibit Experimental Lung Metastasis of Melanoma via Targeting STAT6-Mediated M2 Macrophages Polarization

Pulsatilla saponins (PS) extracts from Pulsatilla chinensis (Bge.) Regel, are a commonly used traditional Chinese medicine. In the previous study, we found Pulsatilla saponins displayed anti-tumor activity without side effects such as bone marrow suppression. However, the mechanism of the anti-tumor effect was not illustrated well. Since M2-like tumor-associated macrophages (TAMs) that required activation of the signal transducer and activator of transcription 6 (STAT6) for polarization are the important immune cells in the tumor microenvironment and play a key role in tumor progress and metastasis, this study aimed to confirm whether Pulsatilla saponins could inhibit the development and metastasis of tumors by inhibiting the polarization of M2 macrophages. We investigated the relevance of M2 macrophage polarization and the anti-tumor effects of Pulsatilla saponins in vitro and in vivo. In vitro, Pulsatilla saponins could decrease the mRNA level of M2 marker genes Arg1, Fizz1, Ym1, and CD206, and the down-regulation effect of phosphorylated STAT6 induced by IL-4; moreover, the conditioned medium (CM) from bone marrow-derived macrophages (BMDM) treated with Pulsatilla saponins could inhibit the proliferation and migration of B16-F0 cells. In vivo, Pulsatilla saponins could reduce the number of lung metastasis loci, down-regulate the expression of M2 marker genes, and suppress the expression of phosphorylated STAT6 in tumor tissues. Furthermore, we used AS1517499 (AS), a STAT6 inhibitor, to verify the role of PS on M2 macrophage polarization both in vitro and in vivo. We found that Pulsatilla saponins failed to further inhibit STAT6 activation; the mRNA level of Arg1, Fizz1, Ym1, and CD206; and the proliferation and migration of B16-F0 cells after AS1517499 intervention in vitro. Similar results were obtained in vivo. These results illustrated that Pulsatilla saponins could effectively suppress tumor progress by inhibiting the polarization of M2 macrophages via the STAT6 signaling pathway; this revealed a novel mechanism for its anti-tumor activity.

Editorial on Special Issue "Artificial Intelligence in Pathological Image Analysis"

The artificial intelligence (AI), especially deep learning models, is highly compatible with medical images and natural language processing and is expected to be applied to pathological image analysis and other medical fields [...].

H. pylori Related Atrophic Gastritis Detection Using Enhanced Convolution Neural Network (CNN) Learner

Atrophic gastritis (AG) is commonly caused by the infection of the Helicobacter pylori (H. pylori) bacteria. If untreated, AG may develop into a chronic condition leading to gastric cancer, which is deemed to be the third primary cause of cancer-related deaths worldwide. Precursory detection of AG is crucial to avoid such cases. This work focuses on H. pylori-associated infection located at the gastric antrum, where the classification is of binary classes of normal versus atrophic gastritis. Existing work developed the Deep Convolution Neural Network (DCNN) of GoogLeNet with 22 layers of the pre-trained model. Another study employed GoogLeNet based on the Inception Module, fast and robust fuzzy C-means (FRFCM), and simple linear iterative clustering (SLIC) superpixel algorithms to identify gastric disease. GoogLeNet with Caffe framework and ResNet-50 are machine learners that detect H. pylori infection. Nonetheless, the accuracy may become abundant as the network depth increases. An upgrade to the current standards method is highly anticipated to avoid untreated and inaccurate diagnoses that may lead to chronic AG. The proposed work incorporates improved techniques revolving within DCNN with pooling as pre-trained models and channel shuffle to assist streams of information across feature channels to ease the training of networks for deeper CNN. In addition, Canonical Correlation Analysis (CCA) feature fusion method and ReliefF feature selection approaches are intended to revamp the combined techniques. CCA models the relationship between the two data sets of significant features generated by pre-trained ShuffleNet. ReliefF reduces and selects essential features from CCA and is classified using the Generalized Additive Model (GAM). It is believed the extended work is justified with a 98.2% testing accuracy reading, thus providing an accurate diagnosis of normal versus atrophic gastritis.

Skin Lesion Detection Using Hand-Crafted and DL-Based Features Fusion and LSTM

The abnormal growth of cells in the skin causes two types of tumor: benign and malignant. Various methods, such as imaging and biopsies, are used by oncologists to assess the presence of skin cancer, but these are time-consuming and require extra human effort. However, some automated methods have been developed by researchers based on hand-crafted feature extraction from skin images. Nevertheless, these methods may fail to detect skin cancers at an early stage if they are tested on unseen data. Therefore, in this study, a novel and robust skin cancer detection model was proposed based on features fusion. First, our proposed model pre-processed the images using a GF filter to remove the noise. Second, the features were manually extracted by employing local binary patterns (LBP), and Inception V3 for automatic feature extraction. Aside from this, an Adam optimizer was utilized for the adjustments of learning rate. In the end, LSTM network was utilized on fused features for the classification of skin cancer into malignant and benign. Our proposed system employs the benefits of both ML- and DL-based algorithms. We utilized the skin lesion DermIS dataset, which is available on the Kaggle website and consists of 1000 images, out of which 500 belong to the benign class and 500 to the malignant class. The proposed methodology attained 99.4% accuracy, 98.7% precision, 98.66% recall, and a 98% F-score. We compared the performance of our features fusion-based method with existing segmentation-based and DL-based techniques. Additionally, we cross-validated the performance of our proposed model using 1000 images from International Skin Image Collection (ISIC), attaining 98.4% detection accuracy. The results show that our method provides significant results compared to existing techniques and outperforms them.