Deep-learning-based, computer-aided classifier developed with a small dataset of clinical images surpasses board-certified dermatologists in skin tumour diagnosis.

BACKGROUND: Application of deep-learning technology to skin cancer classification can potentially improve the sensitivity and specificity of skin cancer screening, but the number of training images required for such a system is thought to be extremely large. OBJECTIVES: To determine whether deep-learning technology could be used to develop an efficient skin cancer classification system with a relatively small dataset of clinical images. METHODS: A deep convolutional neural network (DCNN) was trained using a dataset of 4867 clinical images obtained from 1842 patients diagnosed with skin tumours at the University of Tsukuba Hospital from 2003 to 2016. The images consisted of 14 diagnoses, including both malignant and benign conditions. Its performance was tested against 13 board-certified dermatologists and nine dermatology trainees. RESULTS: The overall classification accuracy of the trained DCNN was 76·5%. The DCNN achieved 96·3% sensitivity (correctly classified malignant as malignant) and 89·5% specificity (correctly classified benign as benign). Although the accuracy of malignant or benign classification by the board-certified dermatologists was statistically higher than that of the dermatology trainees (85·3% ± 3·7% and 74·4% ± 6·8%, P < 0·01), the DCNN achieved even greater accuracy, as high as 92·4% ± 2·1% (P < 0·001). CONCLUSIONS: 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 to transcriptional intermediary factor-1ß as a myositis-specific antibody: clinical correlation with clinically amyopathic dermatomyositis or dermatomyositis with mild myopathy.

BACKGROUND: Myositis-specific autoantibodies (MSAs) are associated with unique clinical subsets in polymyositis/dermatomyositis (PM/DM). Autoantibodies against transcriptional intermediary factor (TIF)-1γ and TIF-1α are known to be MSAs. Previously, we reported that TIF-1ß is also targeted in patients with DM with or without concomitant anti-TIF-1α/γ antibodies. OBJECTIVES: To evaluate the clinical features of seven cases with anti-TIF-1ß antibodies alone. METHODS: Serum autoantibody profiles were determined, and protein and RNA immunoprecipitation studies were conducted. Western blotting was performed to confirm autoantibody reactivity against TIF-1ß. RESULTS: Anti-TIF-1ß antibody was identified by immunoprecipitation assay in 24 cases. Among them, seven patients were positive for anti-TIF-1ß antibody alone. Six of the seven patients were classified as having DM. Among the six cases of DM, two patients had no muscle weakness and normal creatine kinase (CK) levels, and were classified as having clinically amyopathic DM. Four patients had muscle weakness, but three of them had normal serum CK levels that responded well to systemic steroids. Characteristic features of DM included skin rashes, such as Gottron sign, periungual erythema, punctate haemorrhage on the perionychium and facial erythema including heliotrope, which were observed in 86%, 57%, 86% and 71% of our cases, respectively. One of the seven patients had appendiceal cancer. None of the patients had interstitial lung disease. CONCLUSIONS: Seven patients were confirmed to have anti-TIF-1ß antibody without any other MSAs, including TIF-1α/γ antibodies, and six of them were diagnosed with DM. We suggest that anti-TIF-1ß antibody is an MSA, and that it is associated with clinically amyopathic DM or DM with mild myopathy.

Intravenous immunoglobulin contributes to the control of antimelanoma differentiation-associated protein 5 antibody-associated dermatomyositis with palmar violaceous macules/papules.

Autoantibodies to melanoma differentiation-associated protein 5 (MDA5) are associated with a subset of patients with dermatomyositis (DM) who have rapidly progressive interstitial lung disease (RP-ILD) with poor prognosis. Intensive immunosuppressive therapy is initiated before irreversible lung damage can occur; however, there are few lines of evidence for the treatment of RP-ILD. Here, we report three cases of anti-MDA5 antibody-associated DM with RP-ILD in which the patients were treated with combined-modality therapy, including high-dose prednisolone, tacrolimus, intravenous cyclophosphamide and intravenous immunoglobulin (IVIG). In all three cases, serum ferritin levels, which are known to represent the disease activity of RP-ILD, were decreased after IVIG administration. IVIG might contribute to the control of the disease activity of anti-MDA5 antibody-positive DM. Moreover, palmar violaceous macules/papules around the interphalangeal joints, which was observed in all three cases in the incipient stage, might be a useful sign in suggesting a diagnosis of anti-MDA5 antibody-associated DM.

Seborrheic area erythema as a common skin manifestation in Japanese patients with dermatomyositis.

BACKGROUND: Although dermatomyositis (DM)-associated facial erythema was noted in the nasolabial folds of Japanese patients, DM-associated facial erythema other than heliotrope rash has drawn little attention in previous studies. OBJECTIVES: To characterize phenotypical features and frequencies of erythema, especially those in the seborrheic area of the head, in DM patients. METHODS: A retrospective study on skin manifestations in 33 DM patients followed up at our department during the past 15 years was conducted. RESULTS: Macular violaceous erythema (MVE) in the seborrheic area of the face was most frequent (67%). Patients with facial MVE had also MVE in the scalp significantly more frequently than those without facial MVE. The pathology of the facial MVE was dominated by DM-associated changes with slight changes compatible with seborrheic dermatitis (SD). CONCLUSIONS: Japanese DM patients had MVE frequently in the seborrheic area of the head. Its phenotypical features suggested that it might be triggered by SD.

Fluorogenic and fluorescent labeling reagents with a benzofurazan skeleton.

Fluorogenic and fluorescent labeling reagents having a benzofurazan (2,1,3-benzoxadiazole) skeleton such as 4-fluoro-7-nitro-2,1,3-benzoxadiazole (NBD-F), 4-N,N-dimethylaminosulfonyl-7-fluoro-2,1,3-benzoxadiazole (DBD-F), 4-aminosulfonyl-7-fluoro-2,1,3-benzoxadiazole (ABD-F), ammonium 7-fluoro-2,1,3-benzoxadiazole-4-sulfonate (SBD-F), 4-hydrazino-7-nitro-2,1,3-benzoxadiazole (NBD-H), 4-N,N-dimethylaminosulfonyl-7-hydrazino-2,1,3-benzoxadiazole (DBD-H), 4-nitro-7-N-piperazino-2,1,3-benzoxadiazole (NBD-PZ), 4-N,N-dimethylaminosulfonyl-7-N-piperazino-2,1,3-benzoxadiazole (DBD-PZ), 4-(N-chloroformylmethyl-N-methyl)amino-7-N,N-dimethylaminosulfonyl-2,1,3-benzoxadiazole (DBD-COCl) and 7-N,N-dimethylaminosulfonyl-4-(2,1,3-benzoxadiazolyl) isothiocyanate (DBD-NCS) are reviewed in terms of synthetic method, reactivity, fluorescence characteristics, sensitivity and application to analytes.