Refine
Has Fulltext
- yes (4)
Is part of the Bibliography
- yes (4)
Document Type
- Journal article (4)
Language
- English (4)
Keywords
- deep learning (3)
- melanoma (3)
- artificial intelligence (2)
- skin cancer (2)
- [18F]FDG-PET-CT (1)
- abdominal lymph node metastases (1)
- artificial Intelligence (1)
- dermatology (1)
- immune check inhibitor (1)
- machine learning (1)
Institute
- Klinik und Poliklinik für Dermatologie, Venerologie und Allergologie (3)
- Institut für diagnostische und interventionelle Radiologie (Institut für Röntgendiagnostik) (1)
- Klinik und Poliklinik für Allgemein-, Viszeral-, Gefäß- und Kinderchirurgie (Chirurgische Klinik I) (1)
- Klinik und Poliklinik für Nuklearmedizin (1)
- Medizinische Klinik und Poliklinik I (1)
- Pathologisches Institut (1)
Background
A basic requirement for artificial intelligence (AI)–based image analysis systems, which are to be integrated into clinical practice, is a high robustness. Minor changes in how those images are acquired, for example, during routine skin cancer screening, should not change the diagnosis of such assistance systems.
Objective
To quantify to what extent minor image perturbations affect the convolutional neural network (CNN)–mediated skin lesion classification and to evaluate three possible solutions for this problem (additional data augmentation, test-time augmentation, anti-aliasing).
Methods
We trained three commonly used CNN architectures to differentiate between dermoscopic melanoma and nevus images. Subsequently, their performance and susceptibility to minor changes (‘brittleness’) was tested on two distinct test sets with multiple images per lesion. For the first set, image changes, such as rotations or zooms, were generated artificially. The second set contained natural changes that stemmed from multiple photographs taken of the same lesions.
Results
All architectures exhibited brittleness on the artificial and natural test set. The three reviewed methods were able to decrease brittleness to varying degrees while still maintaining performance. The observed improvement was greater for the artificial than for the natural test set, where enhancements were minor.
Conclusions
Minor image changes, relatively inconspicuous for humans, can have an effect on the robustness of CNNs differentiating skin lesions. By the methods tested here, this effect can be reduced, but not fully eliminated. Thus, further research to sustain the performance of AI classifiers is needed to facilitate the translation of such systems into the clinic.
Recent research revealed the superiority of artificial intelligence over dermatologists to diagnose melanoma from images. However, 30–50% of all melanomas and more than half of those in young patients evolve from initially benign lesions. Despite its high relevance for melanoma screening, neither clinicians nor computers are yet able to reliably predict a nevus’ oncologic transformation. The cause of this lies in the static nature of lesion presentation in the current standard of care, both for clinicians and algorithms. The status quo makes it difficult to train algorithms (and clinicians) to precisely assess the likelihood of a benign skin lesion to transform into melanoma. In addition, it inhibits the precision of current algorithms since ‘evolution’ image features may not be part of their decision. The current literature reveals certain types of melanocytic nevi (i.e. ‘spitzoid’ or ‘dysplastic’ nevi) and criteria (i.e. visible vasculature) that, in general, appear to have a higher chance to transform into melanoma. However, owing to the cumulative nature of oncogenic mutations in melanoma, a more fine-grained early morphologic footprint is likely to be detectable by an algorithm. In this perspective article, the concept of melanoma prediction is further explored by the discussion of the evolution of melanoma, the concept for training of such a nevi classifier and the implications of early melanoma prediction for clinical practice. In conclusion, the authors believe that artificial intelligence trained on prospective image data could be transformative for skin cancer diagnostics by (a) predicting melanoma before it occurs (i.e. pre-in situ) and (b) further enhancing the accuracy of current melanoma classifiers. Necessary prospective images for this research are obtained via free mole-monitoring mobile apps.
Background
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.
Methods
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.
Findings
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.
Interpretation
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).
Parathyroid carcinoma (PC) is an orphan malignancy accounting for only ~1% of all cases with primary hyperparathyroidism. The localization of recurrent PC is of critical importance and can be exceedingly difficult to diagnose and sometimes futile when common sites of recurrence in the neck and chest cannot be confirmed. Here, we present the diagnostic workup, molecular analysis and multimodal therapy of a 46-year old woman with the extraordinary manifestation of abdominal lymph node metastases 12 years after primary diagnosis of PC. The patient was referred to our endocrine tumor center in 2016 with the aim to localize the tumor causative of symptomatic biochemical recurrence. In view of the extensive previous workup we decided to perform [18F]FDG-PET-CT. A pathological lymph node in the liver hilus showed slightly increased FDG-uptake and hence was suspected as site of recurrence. Selective venous sampling confirmed increased parathyroid hormone concentration in liver veins. Abdominal lymph node metastasis was resected and histopathological examination confirmed PC. Within four months, the patient experienced biochemical recurrence and based on high tumor mutational burden detected in the surgical specimen by whole exome sequencing the patient received immunotherapy with pembrolizumab that led to a biochemical response. Subsequent to disease progression repeated abdominal lymph node resection was performed in 10/2018, 01/2019 and in 01/2020. Up to now (12/2020) the patient is biochemically free of disease. In conclusion, a multimodal diagnostic approach and therapy in an interdisciplinary setting is needed for patients with rare endocrine tumors. Molecular analyses may inform additional treatment options including checkpoint inhibitors such as pembrolizumab.