Nivolumab-induced organizing pneumonia in a melanoma patient.

We report the case of a 70-year-old woman with vaginal melanoma and multiple metastases in the lung. After the third dose of nivolumab, decreased room-air resting arterial oxygen saturation with bilateral basal fine crackles on auscultation developed despite the absence of respiratory symptoms. Computed tomography showed ground-glass opacities with airspace consolidations scattered with a peculiar distribution, and most were observed around the existing metastatic tumors in the lung. From the 42nd day to the 56th day after the last administration of nivolumab, she received dexamethasone 1-2 mg/body for the prevention of adverse events after stereotactic radiation for brain metastasis. At 3 months after the last administration of nivolumab, a computed tomography scan revealed improvement of the pneumonia and a decreased size and number of metastatic lesions in the lung, although some lesions showed enlargement. Further examination is needed to clarify the relationship between the pattern of pneumonia after Nivo therapy and clinical effects.

Acetylcholine receptor binding antibody-associated myasthenia gravis and rhabdomyolysis induced by nivolumab in a patient with melanoma.

We reported an 81-year-old woman with metastatic melanoma, in whom myasthenia gravis and rhabdomyolysis developed after nivolumab monotherapy. The first symptom of myasthenia gravis was dyspnea. Ultrasonography detected hypokinesis of the bilateral diaphragm suggesting myasthenia gravis, although there was no abnormal finding of the lungs in computed tomography images. Acetylcholine receptor binding antibodies were low-titer positive in the preserved serum before administration of nivolumab, strongly suggesting that the myasthenia gravis was a nivolumab-related immune adverse event. Despite the remarkable clinical benefits of immune checkpoint inhibitors for patients with advanced melanoma, it is important to recognize unexpected immune-related adverse events.

Dermoscopic diagnostic performance of Japanese dermatologists for skin tumors differs by patient origin: A deep learning convolutional neural network closes the gap.

In the dermoscopic diagnosis of skin tumors, it remains unclear whether a deep neural network (DNN) trained with images from fair-skinned-predominant archives is helpful when applied for patients with darker skin. This study compared the performance of 30 Japanese dermatologists with that of a DNN for the dermoscopic diagnosis of International Skin Imaging Collaboration (ISIC) and Shinshu (Japanese only) datasets to classify malignant melanoma, melanocytic nevus, basal cell carcinoma and benign keratosis on the non-volar skin. The DNN was trained using 12 254 images from the ISIC set and 594 images from the Shinshu set. The sensitivity for malignancy prediction by the dermatologists was significantly higher for the Shinshu set than for the ISIC set (0.853 [95% confidence interval, 0.820-0.885] vs 0.608 [0.553-0.664], P < 0.001). The specificity of the DNN at the dermatologists' mean sensitivity value was 0.962 for the Shinshu set and 1.00 for the ISIC set and significantly higher than that for the human readers (both P < 0.001). The dermoscopic diagnostic performance of dermatologists for skin tumors tended to be less accurate for patients of non-local populations, particularly in relation to the dominant skin type. A DNN may help close this gap in the clinical setting.