Several recent publications have demonstrated the use of convolutional neural networks to classify images of melanoma at par with board-certified dermatologists. However, the non-availability of a ...public human benchmark restricts the comparability of the performance of these algorithms and thereby the technical progress in this field.
An electronic questionnaire was sent to dermatologists at 12 German university hospitals. Each questionnaire comprised 100 dermoscopic and 100 clinical images (80 nevi images and 20 biopsy-verified melanoma images, each), all open-source. The questionnaire recorded factors such as the years of experience in dermatology, performed skin checks, age, sex and the rank within the university hospital or the status as resident physician. For each image, the dermatologists were asked to provide a management decision (treat/biopsy lesion or reassure the patient). Main outcome measures were sensitivity, specificity and the receiver operating characteristics (ROC).
Total 157 dermatologists assessed all 100 dermoscopic images with an overall sensitivity of 74.1%, specificity of 60.0% and an ROC of 0.67 (range = 0.538–0.769); 145 dermatologists assessed all 100 clinical images with an overall sensitivity of 89.4%, specificity of 64.4% and an ROC of 0.769 (range = 0.613–0.9). Results between test-sets were significantly different (P < 0.05) confirming the need for a standardised benchmark.
We present the first public melanoma classification benchmark for both non-dermoscopic and dermoscopic images for comparing artificial intelligence algorithms with diagnostic performance of 145 or 157 dermatologists. Melanoma Classification Benchmark should be considered as a reference standard for white-skinned Western populations in the field of binary algorithmic melanoma classification.
•This paper provides the first open access melanoma classification benchmark for both non-dermoscopic and dermoscopic images.•Algorithms can now be easily compared to the performance of dermatologists in terms of sensitivity, specificity and ROC.•The melanoma benchmark allows comparability between algorithms of different publications and provides a new reference standard.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Lymphoid and myeloid cells are abundant in the tumor microenvironment, can be quantified by immunohistochemistry and shape the disease course of human solid tumors. Yet, there is no comprehensive ...understanding of spatial immune infiltration patterns ('topography') across cancer entities and across various immune cell types. In this study, we systematically measure the topography of multiple immune cell types in 965 histological tissue slides from N = 177 patients in a pan-cancer cohort. We provide a definition of inflamed ('hot'), non-inflamed ('cold') and immune excluded patterns and investigate how these patterns differ between immune cell types and between cancer types. In an independent cohort of N = 287 colorectal cancer patients, we show that hot, cold and excluded topographies for effector lymphocytes (CD8) and tumor-associated macrophages (CD163) alone are not prognostic, but that a bivariate classification system can stratify patients. Our study adds evidence to consider immune topographies as biomarkers for patients with solid tumors.
Melanoma is the most dangerous type of skin cancer but is curable if detected early. Recent publications demonstrated that artificial intelligence is capable in classifying images of benign nevi and ...melanoma with dermatologist-level precision. However, a statistically significant improvement compared with dermatologist classification has not been reported to date.
For this comparative study, 4204 biopsy-proven images of melanoma and nevi (1:1) were used for the training of a convolutional neural network (CNN). New techniques of deep learning were integrated. For the experiment, an additional 804 biopsy-proven dermoscopic images of melanoma and nevi (1:1) were randomly presented to dermatologists of nine German university hospitals, who evaluated the quality of each image and stated their recommended treatment (19,296 recommendations in total). Three McNemar's tests comparing the results of the CNN's test runs in terms of sensitivity, specificity and overall correctness were predefined as the main outcomes.
The respective sensitivity and specificity of lesion classification by the dermatologists were 67.2% (95% confidence interval CI: 62.6%–71.7%) and 62.2% (95% CI: 57.6%–66.9%). In comparison, the trained CNN achieved a higher sensitivity of 82.3% (95% CI: 78.3%–85.7%) and a higher specificity of 77.9% (95% CI: 73.8%–81.8%). The three McNemar's tests in 2 × 2 tables all reached a significance level of p < 0.001. This significance level was sustained for both subgroups.
For the first time, automated dermoscopic melanoma image classification was shown to be significantly superior to both junior and board-certified dermatologists (p < 0.001).
•Recent publications demonstrated that deep learning is capable to classify images of benign nevi and melanoma with dermatologist-level precision.•A systematic outperformance of dermatologists was not demonstrated to date.•This study shows the first systematic (p < 0.001) outperformance of board-certified dermatologists in dermoscopic melanoma image classification.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Immune-checkpoint blockade (ICB) has demonstrated efficacy in many tumor types, but predictors of responsiveness to anti-PD1 ICB are incompletely characterized. In this study, we analyzed a ...clinically annotated cohort of patients with melanoma (n = 144) treated with anti-PD1 ICB, with whole-exome and whole-transcriptome sequencing of pre-treatment tumors. We found that tumor mutational burden as a predictor of response was confounded by melanoma subtype, whereas multiple novel genomic and transcriptomic features predicted selective response, including features associated with MHC-I and MHC-II antigen presentation. Furthermore, previous anti-CTLA4 ICB exposure was associated with different predictors of response compared to tumors that were naive to ICB, suggesting selective immune effects of previous exposure to anti-CTLA4 ICB. Finally, we developed parsimonious models integrating clinical, genomic and transcriptomic features to predict intrinsic resistance to anti-PD1 ICB in individual tumors, with validation in smaller independent cohorts limited by the availability of comprehensive data. Broadly, we present a framework to discover predictive features and build models of ICB therapeutic response.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
For clear cell renal cell carcinoma (ccRCC) risk-dependent diagnostic and therapeutic algorithms are routinely implemented in clinical practice. Artificial intelligence-based image analysis has the ...potential to improve outcome prediction and thereby risk stratification. Thus, we investigated whether a convolutional neural network (CNN) can extract relevant image features from a representative hematoxylin and eosin-stained slide to predict 5-year overall survival (5y-OS) in ccRCC. The CNN was trained to predict 5y-OS in a binary manner using slides from TCGA and validated using an independent in-house cohort. Multivariable logistic regression was used to combine of the CNNs prediction and clinicopathological parameters. A mean balanced accuracy of 72.0% (standard deviation SD = 7.9%), sensitivity of 72.4% (SD = 10.6%), specificity of 71.7% (SD = 11.9%) and area under receiver operating characteristics curve (AUROC) of 0.75 (SD = 0.07) was achieved on the TCGA training set (n = 254 patients / WSIs) using 10-fold cross-validation. On the external validation cohort (n = 99 patients / WSIs), mean accuracy, sensitivity, specificity and AUROC were 65.5% (95%-confidence interval CI: 62.9–68.1%), 86.2% (95%-CI: 81.8–90.5%), 44.9% (95%-CI: 40.2–49.6%), and 0.70 (95%-CI: 0.69–0.71). A multivariable model including age, tumor stage and metastasis yielded an AUROC of 0.75 on the TCGA cohort. The inclusion of the CNN-based classification (Odds ratio = 4.86, 95%-CI: 2.70–8.75, p < 0.01) raised the AUROC to 0.81. On the validation cohort, both models showed an AUROC of 0.88. In univariable Cox regression, the CNN showed a hazard ratio of 3.69 (95%-CI: 2.60–5.23, p < 0.01) on TCGA and 2.13 (95%-CI: 0.92–4.94, p = 0.08) on external validation. The results demonstrate that the CNN’s image-based prediction of survival is promising and thus this widely applicable technique should be further investigated with the aim of improving existing risk stratification in ccRCC.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Tumorigenesis is correlated with abnormal expression and activity of G protein-coupled receptors (GPCRs) and associated G proteins. Oncogenic mutations in both GPCRs and G proteins (
,
or
) encoding ...genes have been identified in a significant number of tumors. Interestingly, uveal melanoma driver mutations in
/
were identified for a decade, but their discovery did not lead to mutation-specific drug development, unlike it the case for
mutations in cutaneous melanoma which saw enormous success. Moreover, new immunotherapies strategies such as immune checkpoint inhibitors have given underwhelming results. In this review, we summarize the current knowledge on cancer-associated alterations of GPCRs and G proteins and we focus on the case of uveal melanoma. Finally, we discuss the possibilities that this signaling might represent in regard to novel drug development for cancer prevention and treatment.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Gastrointestinal cancers account for approximately 20% of all cancer diagnoses and are responsible for 22.5% of cancer deaths worldwide. Artificial intelligence–based diagnostic support systems, in ...particular convolutional neural network (CNN)–based image analysis tools, have shown great potential in medical computer vision. In this systematic review, we summarise recent studies reporting CNN-based approaches for digital biomarkers for characterization and prognostication of gastrointestinal cancer pathology.
Pubmed and Medline were screened for peer-reviewed papers dealing with CNN-based gastrointestinal cancer analyses from histological slides, published between 2015 and 2020.Seven hundred and ninety titles and abstracts were screened, and 58 full-text articles were assessed for eligibility.
Sixteen publications fulfilled our inclusion criteria dealing with tumor or precursor lesion characterization or prognostic and predictive biomarkers: 14 studies on colorectal or rectal cancer, three studies on gastric cancer and none on esophageal cancer. These studies were categorised according to their end-points: polyp characterization, tumor characterization and patient outcome. Regarding the translation into clinical practice, we identified several studies demonstrating generalization of the classifier with external tests and comparisons with pathologists, but none presenting clinical implementation.
Results of recent studies on CNN-based image analysis in gastrointestinal cancer pathology are promising, but studies were conducted in observational and retrospective settings. Large-scale trials are needed to assess performance and predict clinical usefulness. Furthermore, large-scale trials are required for approval of CNN-based prediction models as medical devices.
•Computational medical image analysis is rising in gastrointestinal cancer pathology.•Several studies deal with CNN–based identification of biomarkers on HE slides.•Results are promising but studies are at early stages.•Further studies are needed to assess performance and potential clinical usefulness.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Monoclonal antibodies directed against cytotoxic T lymphocyte–associated antigen-4 (CTLA-4), such as ipilimumab, yield considerable clinical benefit for patients with metastatic melanoma by ...inhibiting immune checkpoint activity, but clinical predictors of response to these therapies remain incompletely characterized. To investigate the roles of tumor-specific neoantigens and alterations in the tumor microenvironment in the response to ipilimumab, we analyzed whole exomes from pretreatment melanoma tumor biopsies and matching germline tissue samples from 110 patients. For 40 of these patients, we also obtained and analyzed transcriptome data from the pretreatment tumor samples. Overall mutational load, neoantigen load, and expression of cytolytic markers in the immune microenvironment were significantly associated with clinical benefit. However, no recurrent neoantigen peptide sequences predicted responder patient populations. Thus, detailed integrated molecular characterization of large patient cohorts may be needed to identify robust determinants of response and resistance to immune checkpoint inhibitors.
Full text
Available for:
BFBNIB, NMLJ, NUK, PNG, SAZU, UL, UM, UPUK
Summary Background Previously, a study of ours showed that the combination of dabrafenib and trametinib improves progression-free survival compared with dabrafenib and placebo in patients with BRAF ...Val600Lys/Glu mutation-positive metastatic melanoma. The study was continued to assess the secondary endpoint of overall survival, which we report in this Article. Methods We did this double-blind phase 3 study at 113 sites in 14 countries. We enrolled previously untreated patients with BRAF Val600Glu or Val600Lys mutation-positive unresectable stage IIIC or stage IV melanoma. Participants were computer-randomised (1:1) to receive a combination of dabrafenib (150 mg orally twice daily) and trametinib (2 mg orally once daily), or dabrafenib and placebo. The primary endpoint was progression-free survival and overall survival was a secondary endpoint. This study is registered with ClinicalTrials.gov , number NCT01584648. Findings Between May 4, 2012, and Nov 30, 2012, we screened 947 patients for eligibility, of whom 423 were randomly assigned to receive dabrafenib and trametinib (n=211) or dabrafenib only (n=212). The final data cutoff was Jan 12, 2015, at which time 222 patients had died. Median overall survival was 25·1 months (95% CI 19·2–not reached) in the dabrafenib and trametinib group versus 18·7 months (15·2–23·7) in the dabrafenib only group (hazard ratio HR 0·71, 95% CI 0·55–0·92; p=0·0107). Overall survival was 74% at 1 year and 51% at 2 years in the dabrafenib and trametinib group versus 68% and 42%, respectively, in the dabrafenib only group. Based on 301 events, median progression-free survival was 11·0 months (95% CI 8·0–13·9) in the dabrafenib and trametinib group and 8·8 months (5·9–9·3) in the dabrafenib only group (HR 0·67, 95% CI 0·53–0·84; p=0·0004; unadjusted for multiple testing). Treatment-related adverse events occurred in 181 (87%) of 209 patients in the dabrafenib and trametinib group and 189 (90%) of 211 patients in the dabrafenib only group; the most common was pyrexia (108 patients, 52%) in the dabrafenib and trametinib group, and hyperkeratosis (70 patients, 33%) in the dabrafenib only group. Grade 3 or 4 adverse events occurred in 67 (32%) patients in the dabrafenib and trametinib group and 66 (31%) patients in the dabrafenib only group. Interpretation The improvement in overall survival establishes the combination of dabrafenib and trametinib as the standard targeted treatment for BRAF Val600 mutation-positive melanoma. Studies assessing dabrafenib and trametinib in combination with immunotherapies are ongoing. Funding GlaxoSmithKline.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Despite the remarkable success of immune checkpoint inhibitors (ICIs) in melanoma treatment, resistance to them remains a substantial clinical challenge. Myeloid-derived suppressor cells (MDSCs) ...represent a heterogeneous population of myeloid cells that can suppress antitumor immune responses mediated by T and natural killer cells and promote tumor growth. They are major contributors to ICI resistance and play a crucial role in creating an immunosuppressive tumor microenvironment. Therefore, targeting MDSCs is considered a promising strategy to improve the therapeutic efficacy of ICIs. This Review describes the mechanism of MDSC-mediated immune suppression, preclinical and clinical studies on MDSC targeting, and potential strategies for inhibiting MDSC functions to improve melanoma immunotherapy.
PDF
