International Skin Imaging Collaboration-Designated Diagnoses (ISIC-DX): Consensus terminology for lesion diagnostic labeling.

BACKGROUND: A common terminology for diagnosis is critically important for clinical communication, education, research and artificial intelligence. Prevailing lexicons are limited in fully representing skin neoplasms. OBJECTIVES: To achieve expert consensus on diagnostic terms for skin neoplasms and their hierarchical mapping. METHODS: Diagnostic terms were extracted from textbooks, publications and extant diagnostic codes. Terms were hierarchically mapped to super-categories (e.g. 'benign') and cellular/tissue-differentiation categories (e.g. 'melanocytic'), and appended with pertinent-modifiers and synonyms. These terms were evaluated using a modified-Delphi consensus approach. Experts from the International-Skin-Imaging-Collaboration (ISIC) were surveyed on agreement with terms and their hierarchical mapping; they could suggest modifying, deleting or adding terms. Consensus threshold was >75% for the initial rounds and >50% for the final round. RESULTS: Eighteen experts completed all Delphi rounds. Of 379 terms, 356 (94%) reached consensus in round one. Eleven of 226 (5%) benign-category terms, 6/140 (4%) malignant-category terms and 6/13 (46%) indeterminate-category terms did not reach initial agreement. Following three rounds, final consensus consisted of 362 terms mapped to 3 super-categories and 41 cellular/tissue-differentiation categories. CONCLUSIONS: We have created, agreed upon, and made public a taxonomy for skin neoplasms and their hierarchical mapping. Further study will be needed to evaluate the utility and completeness of the lexicon.

Outcomes of Decompressive Surgery for Patients With Severe Cerebral Venous Thrombosis: DECOMPRESS2 Observational Study.

BACKGROUND: Decompressive neurosurgery is recommended for patients with cerebral venous thrombosis (CVT) who have large parenchymal lesions and impending brain herniation. This recommendation is based on limited evidence. We report long-term outcomes of patients with CVT treated by decompressive neurosurgery in an international cohort. METHODS: DECOMPRESS2 (Decompressive Surgery for Patients With Cerebral Venous Thrombosis, Part 2) was a prospective, international cohort study. Consecutive patients with CVT treated by decompressive neurosurgery were evaluated at admission, discharge, 6 months, and 12 months. The primary outcome was death or severe disability (modified Rankin Scale scores, 5-6) at 12 months. The secondary outcomes included patient and caregiver opinions on the benefits of surgery. The association between baseline variables before surgery and the primary outcome was assessed by multivariable logistic regression. RESULTS: A total of 118 patients (80 women; median age, 38 years) were included from 15 centers in 10 countries from December 2011 to December 2019. Surgery (115 craniectomies and 37 hematoma evacuations) was performed within a median of 1 day after diagnosis. At last assessment before surgery, 68 (57.6%) patients were comatose, fixed dilated pupils were found unilaterally in 27 (22.9%) and bilaterally in 9 (7.6%). Twelve-month follow-up data were available for 113 (95.8%) patients. Forty-six (39%) patients were dead or severely disabled (modified Rankin Scale scores, 5-6), of whom 40 (33.9%) patients had died. Forty-two (35.6%) patients were independent (modified Rankin Scale scores, 0-2). Coma (odds ratio, 2.39 [95% CI, 1.03-5.56]) and fixed dilated pupil (odds ratio, 2.22 [95% CI, 0.90-4.92]) were predictors of death or severe disability. Of the survivors, 56 (78.9%) patients and 61 (87.1%) caregivers expressed a positive opinion on surgery. CONCLUSIONS: Two-thirds of patients with severe CVT were alive and more than one-third were independent 1 year after decompressive surgery. Among survivors, surgery was judged as worthwhile by 4 out of 5 patients and caregivers. These results support the recommendation to perform decompressive neurosurgery in patients with CVT with impending brain herniation.

Expert Agreement on the Presence and Spatial Localization of Melanocytic Features in Dermoscopy.

Dermoscopy aids in melanoma detection; however, agreement on dermoscopic features, including those of high clinical relevance, remains poor. In this study, we attempted to evaluate agreement among experts on exemplar images not only for the presence of melanocytic-specific features but also for spatial localization. This was a cross-sectional, multicenter, observational study. Dermoscopy images exhibiting at least 1 of 31 melanocytic-specific features were submitted by 25 world experts as exemplars. Using a web-based platform that allows for image markup of specific contrast-defined regions (superpixels), 20 expert readers annotated 248 dermoscopic images in collections of 62 images. Each collection was reviewed by five independent readers. A total of 4,507 feature observations were performed. Good-to-excellent agreement was found for 14 of 31 features (45.2%), with eight achieving excellent agreement (Gwet's AC >0.75) and seven of them being melanoma-specific features. These features were peppering/granularity (0.91), shiny white streaks (0.89), typical pigment network (0.83), blotch irregular (0.82), negative network (0.81), irregular globules (0.78), dotted vessels (0.77), and blue-whitish veil (0.76). By utilizing an exemplar dataset, a good-to-excellent agreement was found for 14 features that have previously been shown useful in discriminating nevi from melanoma. All images are public (www.isic-archive.com) and can be used for education, scientific communication, and machine learning experiments.

Prospective validation of dermoscopy-based open-source artificial intelligence for melanoma diagnosis (PROVE-AI study).

The use of artificial intelligence (AI) has the potential to improve the assessment of lesions suspicious of melanoma, but few clinical studies have been conducted. We validated the accuracy of an open-source, non-commercial AI algorithm for melanoma diagnosis and assessed its potential impact on dermatologist decision-making. We conducted a prospective, observational clinical study to assess the diagnostic accuracy of the AI algorithm (ADAE) in predicting melanoma from dermoscopy skin lesion images. The primary aim was to assess the reliability of ADAE's sensitivity at a predefined threshold of 95%. Patients who had consented for a skin biopsy to exclude melanoma were eligible. Dermatologists also estimated the probability of melanoma and indicated management choices before and after real-time exposure to ADAE scores. All lesions underwent biopsy. Four hundred thirty-five participants were enrolled and contributed 603 lesions (95 melanomas). Participants had a mean age of 59 years, 54% were female, and 96% were White individuals. At the predetermined 95% sensitivity threshold, ADAE had a sensitivity of 96.8% (95% CI: 91.1-98.9%) and specificity of 37.4% (95% CI: 33.3-41.7%). The dermatologists' ability to assess melanoma risk significantly improved after ADAE exposure (AUC 0.7798 vs. 0.8161, p = 0.042). Post-ADAE dermatologist decisions also had equivalent or higher net benefit compared to biopsying all lesions. We validated the accuracy of an open-source melanoma AI algorithm and showed its theoretical potential for improving dermatology experts' ability to evaluate lesions suspicious of melanoma. Larger randomized trials are needed to fully evaluate the potential of adopting this AI algorithm into clinical workflows.

Improving Artificial Intelligence-Based Diagnosis on Pediatric Skin Lesions.

Artificial intelligence algorithms to classify melanoma are dependent on their training data, which limits generalizability. The objective of this study was to compare the performance of an artificial intelligence model trained on a standard adult-predominant dermoscopic dataset before and after the addition of additional pediatric training images. The performances were compared using held-out adult and pediatric test sets of images. We trained two models: one (model A) on an adult-predominant dataset (37,662 images from the International Skin Imaging Collaboration) and the other (model A+P) on an additional 1,536 pediatric images. We compared performance between the two models on adult and pediatric held-out test images separately using the area under the receiver operating characteristic curve. We then used Gradient-weighted Class Activation Maps and background skin masking to understand the contributions of the lesion versus background skin to algorithm decision making. Adding images from a pediatric population with different epidemiological and visual patterns to current reference standard datasets improved algorithm performance on pediatric images without diminishing performance on adult images. This suggests a way that dermatologic artificial intelligence models can be made more generalizable. The presence of background skin was important to the pediatric-specific improvement seen between models. Our study highlights the importance of carefully curated and labeled data from diverse inputs to improve the generalizability of AI models for dermatology, in this case applied to dermoscopic images of adult and pediatric lesions to improve melanoma detection.

Agreement Between Experts and an Untrained Crowd for Identifying Dermoscopic Features Using a Gamified App: Reader Feasibility Study.

BACKGROUND: Dermoscopy is commonly used for the evaluation of pigmented lesions, but agreement between experts for identification of dermoscopic structures is known to be relatively poor. Expert labeling of medical data is a bottleneck in the development of machine learning (ML) tools, and crowdsourcing has been demonstrated as a cost- and time-efficient method for the annotation of medical images. OBJECTIVE: The aim of this study is to demonstrate that crowdsourcing can be used to label basic dermoscopic structures from images of pigmented lesions with similar reliability to a group of experts. METHODS: First, we obtained labels of 248 images of melanocytic lesions with 31 dermoscopic "subfeatures" labeled by 20 dermoscopy experts. These were then collapsed into 6 dermoscopic "superfeatures" based on structural similarity, due to low interrater reliability (IRR): dots, globules, lines, network structures, regression structures, and vessels. These images were then used as the gold standard for the crowd study. The commercial platform DiagnosUs was used to obtain annotations from a nonexpert crowd for the presence or absence of the 6 superfeatures in each of the 248 images. We replicated this methodology with a group of 7 dermatologists to allow direct comparison with the nonexpert crowd. The Cohen κ value was used to measure agreement across raters. RESULTS: In total, we obtained 139,731 ratings of the 6 dermoscopic superfeatures from the crowd. There was relatively lower agreement for the identification of dots and globules (the median κ values were 0.526 and 0.395, respectively), whereas network structures and vessels showed the highest agreement (the median κ values were 0.581 and 0.798, respectively). This pattern was also seen among the expert raters, who had median κ values of 0.483 and 0.517 for dots and globules, respectively, and 0.758 and 0.790 for network structures and vessels. The median κ values between nonexperts and thresholded average-expert readers were 0.709 for dots, 0.719 for globules, 0.714 for lines, 0.838 for network structures, 0.818 for regression structures, and 0.728 for vessels. CONCLUSIONS: This study confirmed that IRR for different dermoscopic features varied among a group of experts; a similar pattern was observed in a nonexpert crowd. There was good or excellent agreement for each of the 6 superfeatures between the crowd and the experts, highlighting the similar reliability of the crowd for labeling dermoscopic images. This confirms the feasibility and dependability of using crowdsourcing as a scalable solution to annotate large sets of dermoscopic images, with several potential clinical and educational applications, including the development of novel, explainable ML tools.

Validation of artificial intelligence prediction models for skin cancer diagnosis using dermoscopy images: the 2019 International Skin Imaging Collaboration Grand Challenge.

BACKGROUND: Previous studies of artificial intelligence (AI) applied to dermatology have shown AI to have higher diagnostic classification accuracy than expert dermatologists; however, these studies did not adequately assess clinically realistic scenarios, such as how AI systems behave when presented with images of disease categories that are not included in the training dataset or images drawn from statistical distributions with significant shifts from training distributions. We aimed to simulate these real-world scenarios and evaluate the effects of image source institution, diagnoses outside of the training set, and other image artifacts on classification accuracy, with the goal of informing clinicians and regulatory agencies about safety and real-world accuracy. METHODS: We designed a large dermoscopic image classification challenge to quantify the performance of machine learning algorithms for the task of skin cancer classification from dermoscopic images, and how this performance is affected by shifts in statistical distributions of data, disease categories not represented in training datasets, and imaging or lesion artifacts. Factors that might be beneficial to performance, such as clinical metadata and external training data collected by challenge participants, were also evaluated. 25 331 training images collected from two datasets (in Vienna [HAM10000] and Barcelona [BCN20000]) between Jan 1, 2000, and Dec 31, 2018, across eight skin diseases, were provided to challenge participants to design appropriate algorithms. The trained algorithms were then tested for balanced accuracy against the HAM10000 and BCN20000 test datasets and data from countries not included in the training dataset (Turkey, New Zealand, Sweden, and Argentina). Test datasets contained images of all diagnostic categories available in training plus other diagnoses not included in training data (not trained category). We compared the performance of the algorithms against that of 18 dermatologists in a simulated setting that reflected intended clinical use. FINDINGS: 64 teams submitted 129 state-of-the-art algorithm predictions on a test set of 8238 images. The best performing algorithm achieved 58·8% balanced accuracy on the BCN20000 data, which was designed to better reflect realistic clinical scenarios, compared with 82·0% balanced accuracy on HAM10000, which was used in a previously published benchmark. Shifted statistical distributions and disease categories not included in training data contributed to decreases in accuracy. Image artifacts, including hair, pen markings, ulceration, and imaging source institution, decreased accuracy in a complex manner that varied based on the underlying diagnosis. When comparing algorithms to expert dermatologists (2460 ratings on 1269 images), algorithms performed better than experts in most categories, except for actinic keratoses (similar accuracy on average) and images from categories not included in training data (26% correct for experts vs 6% correct for algorithms, p<0·0001). For the top 25 submitted algorithms, 47·1% of the images from categories not included in training data were misclassified as malignant diagnoses, which would lead to a substantial number of unnecessary biopsies if current state-of-the-art AI technologies were clinically deployed. INTERPRETATION: We have identified specific deficiencies and safety issues in AI diagnostic systems for skin cancer that should be addressed in future diagnostic evaluation protocols to improve safety and reliability in clinical practice. FUNDING: Melanoma Research Alliance and La Marató de TV3.

A patient-centric dataset of images and metadata for identifying melanomas using clinical context.

Prior skin image datasets have not addressed patient-level information obtained from multiple skin lesions from the same patient. Though artificial intelligence classification algorithms have achieved expert-level performance in controlled studies examining single images, in practice dermatologists base their judgment holistically from multiple lesions on the same patient. The 2020 SIIM-ISIC Melanoma Classification challenge dataset described herein was constructed to address this discrepancy between prior challenges and clinical practice, providing for each image in the dataset an identifier allowing lesions from the same patient to be mapped to one another. This patient-level contextual information is frequently used by clinicians to diagnose melanoma and is especially useful in ruling out false positives in patients with many atypical nevi. The dataset represents 2,056 patients (20.8% with at least one melanoma, 79.2% with zero melanomas) from three continents with an average of 16 lesions per patient, consisting of 33,126 dermoscopic images and 584 (1.8%) histopathologically confirmed melanomas compared with benign melanoma mimickers.

Posttranslational proteolytic processing of Leda-1/Pianp involves cleavage by MMPs, ADAM10/17 and gamma-secretase.

Leda-1/Pianp is a type I transmembrane protein expressed by CNS cells, murine melanoma cell line B16F10 and rat liver sinusoidal endothelial cells. The early steps of posttranslational modifications of Leda-1/Pianp have been described to include glycosylation and processing by proprotein convertases. Here, we comprehensively characterized the subsequent steps of proteolytic processing of Leda-1/Pianp. For this purpose specific protease inhibitors and cell lines deficient in PS1, PS2, PS1/PS2 and ADAM10/17 were deployed. Leda-1/Pianp was cleaved at numerous cleavage sites within the N-terminal extracellular domain. The sheddases involved included MMPs and ADAM10/17. Ectodomain shedding yielded C-terminal fragments (CTF) of ∼15 kDa. The CTF was further processed by the γ (gamma)-secretase complex to generate the intracellular domain (ICD) of ∼10 kDa. Although PS1 was the dominant intramembrane protease, PS2 was also able to cleave Leda-1/Pianp in the absence of PS1. Thus, Leda-1/Pianp is constitutively processed by proprotein convertases, sheddases including MMPs and ADAM10/17 and intramembrane protease γ-secretase.

Counter-regulation of the ligand-receptor pair Leda-1/Pianp and Pilrα during the LPS-mediated immune response of murine macrophages.

Liver endothelial differentiation-associated protein-1 (Leda-1/Pianp) is a type-I-transmembrane protein that is able to bind and activate immune inhibitory receptor Pilrα. Here we show that Leda-1/Pianp is strain-specifically expressed in lymphoid organs and macrophages of Th2-prone BALB/c mice but not of Th1-prone C57BL/6J mice. LPS stimulation of BALB/c bone marrow-derived macrophages (BMM) and macrophage-like Raw 264.7 cells conversely regulated Leda-1/Pianp and Pilrα expression. Pilrα induction was caused by LPS-mediated transcriptional modulation and increased mRNA expression. On the other hand, the LPS-mediated decline of Leda-1/Pianp expression was the result of proteolytic degradation by matrix metalloproteinases. In summary, these findings demonstrate that counter-regulation of the ligand-receptor pair Leda-1/Pianp and Pilrα is part of the complex innate immune response of macrophages and its genetically determined strain-specific modulation.

Transitional lumbosacral segment with unilateral transverse process anomaly (Castellvi type 2A) resulting in extraforaminal impingement of the spinal nerve: a pathoanatomical study of four specimens and report of two clinical cases.

The spinal nerve can be pinched between the transverse process of the fifth lumbar vertebra and the sacral ala. The patients are divided into two types: elderly persons with degenerative scoliosis and somewhat younger adults with isthmic spondylolisthesis. For the first time, we describe extraforaminal impingement of the spinal nerve in transitional lumbosacral segment with unilateral transverse process anomaly. Selective nerve root blocks were performed in two clinical cases. One patient underwent nerve root decompression via a posterior approach. One year after operation, this patient reported no radicular or lumbar pain. The pathoanatomical study demonstrated pseudoarthrosis between the transverse process and the ala of the sacrum and showed dysplastic facet joints at the level below the transitional vertebra in all specimens. Furthermore, we present the oldest illustration of this pathological condition, published in a book by Carl Wenzel in 1824. Extraforaminal entrapment of the spinal nerve in transitional lumbosacral segment with unilateral transverse process anomaly can cause radiculopathy, and osteophytes are the cause of the entrapment. Dysplastic facet joints on the level below the transitional vertebra could be one reason for "micromotion" resulting in pseudoarthrosis with osteophytes. Sciatica relief was obtained by means of selective nerve root blocks or posterior decompression via a dorsomedial approach.

Prefrontal-striatal pathway underlies cognitive regulation of craving.

The ability to control craving for substances that offer immediate rewards but whose long-term consumption may pose serious risks lies at the root of substance use disorders and is critical for mental and physical health. Despite its importance, the neural systems supporting this ability remain unclear. Here, we investigated this issue using functional imaging to examine neural activity in cigarette smokers, the most prevalent substance-dependent population in the United States, as they used cognitive strategies to regulate craving for cigarettes and food. We found that the cognitive down-regulation of craving was associated with (i) activity in regions previously associated with regulating emotion in particular and cognitive control in general, including dorsomedial, dorsolateral, and ventrolateral prefrontal cortices, and (ii) decreased activity in regions previously associated with craving, including the ventral striatum, subgenual cingulate, amygdala, and ventral tegmental area. Decreases in craving correlated with decreases in ventral striatum activity and increases in dorsolateral prefrontal cortex activity, with ventral striatal activity fully mediating the relationship between lateral prefrontal cortex and reported craving. These results provide insight into the mechanisms that enable cognitive strategies to effectively regulate craving, suggesting that it involves neural dynamics parallel to those involved in regulating other emotions. In so doing, this study provides a methodological tool and conceptual foundation for studying this ability across substance using populations and developing more effective treatments for substance use disorders.

Intraoperative management of cystic meningiomas.

Cystic meningiomas are uncommon tumors that are easily confused with metastatic or glial tumors with cystic components. We report on our experience of intraoperative findings and management of peritumoral cyst wall and cyst fluid in cystic meningiomas. We reviewed all the meningiomas operated on at our department in a 3 1/2-year period (January 1998 to June 2001). Pathological and intraoperative findings of cystic meningiomas compared to noncystic meningiomas are examined. There were 111 cases of intracranial meningiomas operated on, including seven cystic meningiomas (6.3%). In six cases, we found peritumoral cyst configurations. The tumor locations of cystic meningiomas were the cerebral convexity and sphenoid ridge. One peritumoral cyst formation had meningioma cells in the cyst wall. Cytologic examination of the cystic fluid displayed the presence of meningiothelial cells in one case. In one case, intraoperative findings and pathological examination provided the diagnosis of two differently located meningiomas in one cyst configuration, its walls lined by clear arachnoid. Four of the seven cases had peritumoral cystic meningiomas of the atypical type according to the WHO classification. One case with intratumoral cyst configuration was associated with the anaplastic type (WHO degrees 3). Intraoperative biopsies and histopathological studies of the cyst wall are recommended in peritumoral cystic meningiomas. Our observations suggest that cystic meningiomas have the potential to spread through cystic fluid to the cystic wall in peritumoral cyst configuration. The follow-up intervals should be short in cystic meningiomas.