Refine
Has Fulltext
- yes (2)
Is part of the Bibliography
- yes (2)
Year of publication
- 2021 (2) (remove)
Document Type
- Journal article (2)
Language
- English (2)
Keywords
- [18F]FDG-PET-CT (1)
- abdominal lymph node metastases (1)
- artificial intelligence (1)
- deep learning (1)
- dermatology (1)
- immune check inhibitor (1)
- machine learning (1)
- melanoma (1)
- molecular diagnostics (1)
- neural networks (1)
- nevus (1)
- parathyroid carcinoma (1)
- pembrolizumab (1)
- repeated surgery (1)
- skin neoplasms (1)
Institute
- 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 Dermatologie, Venerologie und Allergologie (1)
- Klinik und Poliklinik für Nuklearmedizin (1)
- Medizinische Klinik und Poliklinik I (1)
- Pathologisches Institut (1)
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.
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.