We have developed an efficient skin tumour classifier using a DCNN trained on a relatively small dataset. The DCNN classified images of skin tumours more accurately than board-certified dermatologists. Collectively, the current system may have capabilities for screening purposes in general medical practice, particularly because it requires only a single clinical image for classification.

'Autoantibody-based classification' of dermatomyositis subsets is now a useful strategy for comprehending the heterogeneous spectrum of dermatomyositis.

No abstract

No abstract

The most widely accepted treatment for cutaneous angiosarcoma (CAS) is wide local excision and postoperative radiation to decrease the risk of recurrence. Positive surgical margins and large tumors (T2, >5 cm) are known to be associated with poor prognosis. Moreover, T2 tumors are known to be associated with positive surgical margins. According to previous reports, the majority of CAS patients in Japan had T2 tumors, whereas less than half of the patients in the studies from western countries did so. Consequently, the reported 5-year overall survival of Japanese CAS patients without distant metastasis was only 9%, lower than that for stage-IV melanoma. For patients with T2 tumors, management of subclinical metastasis should be considered when planning the initial treatment. Several attempts to control subclinical metastasis have been reported, such as using adjuvant/neoadjuvant chemotherapy in addition to conventional surgery plus radiation. Unfortunately, those attempts did not show any clinical benefit. Besides surgery, new chemotherapeutic approaches for advanced CAS have been introduced in the past couple of decades, such as paclitaxel and docetaxel. We proposed the use of chemoradiotherapy (CRT) using taxanes instead of surgery plus radiation for patients with T2 tumors without distant metastasis and showed a high response ratio with prolonged survival. However, this prolonged survival was seen only in patients who received maintenance chemotherapy after CRT, indicating that continuous chemotherapy is mandatory to control subclinical residual tumors. With the recent development of targeted drugs for cancer, many potential drugs for CAS are now available. Given that CAS expresses a high level of vascular endothelial growth factor (VEGF) receptor, drugs that target VEGF signaling pathways such as anti-VEGF monoclonal antibody and tyrosine kinase inhibitors are also promising, and several successful treatments have been reported. Besides targeted drugs, several new cytotoxic anticancer drugs such as eribulin or trabectedin have also been shown to be effective for advanced sarcoma. However, most of the clinical trials did not include a sufficient number of CAS patients. Therefore, clinical trials focusing only on CAS should be performed to evaluate the effectiveness of these new drugs.

No abstract

No abstract

ObjectiveTo identify the characteristic pathologic features of dermatomyositis (DM) associated with anti-Mi-2 autoantibodies (anti-Mi-2 DM).MethodsWe reviewed 188 muscle biopsies from patients (1) pathologically diagnosed with DM through the sarcoplasmic expression for the myxovirus-resistant protein A and (2) serologically positive for 1 of 5 DM-specific autoantibodies (DMSAs) (anti-Mi-2, n = 30; other DMSAs, n = 152) or negative for all 5 DMSAs (n = 6). We then compared the histopathologic and immunohistochemical features of patients with anti-Mi-2 DM to those with non-Mi-2 DM and patients with anti-synthetase syndrome (ASS) (n = 212) using the t test, Fisher exact test, and a logistic regression model.ResultsPatients with anti-Mi-2 DM showed significantly higher severity scores in muscle fiber and inflammatory domains than non-Mi-2 DM patients. The presence of perifascicular necrosis, increased perimysial alkaline phosphatase activity, and sarcolemmal membrane attack complex deposition was more frequent in patients with anti-Mi-2 DM (p < 0.01). After Bonferroni correction, there were no significant differences in the percentages of the features mentioned above between the patients with anti-Mi-2 DM and those with ASS (p > 0.01).ConclusionPerifascicular necrosis and perimysial pathology, features previously reported in ASS, are common in patients with anti-Mi-2 DM. Our findings not only assist in differentiating anti-Mi-2 DM from other DM subtypes but also suggest the possibility of an overlapping mechanism between anti-Mi-2 DM and ASS.Classification of EvidenceThis study provides Class II evidence that the muscle biopsies of DM patients with anti-Mi-2 autoantibodies are more likely to demonstrate higher severity scores in muscle fiber and inflammatory domains.