No abstract

A wide variety of superficial soft-tissue masses may be seen in clinical practice, but a systematic approach can help achieve a definitive diagnosis or limit a differential diagnosis. Superficial soft-tissue masses can generally be categorized as mesenchymal tumors, skin appendage lesions, metastatic tumors, other tumors and tumorlike lesions, or inflammatory lesions. With regard to their imaging features, these masses may be further divided into lesions that arise in association with the epidermis or dermis (cutaneous lesions), lesions that arise within the substance of the subcutaneous adipose tissue, or lesions that arise in intimate association with the fascia overlying the muscle. The differential diagnosis may be limited further by considering the age of the patient, anatomic location of the lesion, salient imaging features, and clinical manifestations.

Mixed Integer Programming (MIP) solvers rely on an array of sophisticated heuristics developed with decades of research to solve large-scale MIP instances encountered in practice. Machine learning offers to automatically construct better heuristics from data by exploiting shared structure among instances in the data. This paper applies learning to the two key sub-tasks of a MIP solver, generating a high-quality joint variable assignment, and bounding the gap in objective value between that assignment and an optimal one.Our approach constructs two corresponding neural network-based components, Neural Diving and Neural Branching, to use in a base MIP solver such as SCIP. Neural Diving learns a deep neural network to generate multiple partial assignments for its integer variables, and the resulting smaller MIPs for un-assigned variables are solved with SCIP to construct high quality joint assignments. Neural Branching learns a deep neural network to make variable selection decisions in branch-and-bound to bound the objective value gap with a small tree. This is done by imitating a new variant of Full Strong Branching we propose that scales to large instances using GPUs. We evaluate our approach on six diverse real-world datasets, including two Google production datasets and MIPLIB, by training separate neural networks on each. Most instances in all the datasets combined have 10 3 − 10 6 variables and constraints after presolve, which is significantly larger than previous learning approaches. Comparing solvers with respect to primal-dual gap averaged over a held-out set of instances, the learning-augmented SCIP is 2× to 10× better on all datasets except one on which it is 10 5 × better, at large time limits. To the best of our knowledge, ours is the first learning approach to demonstrate such large improvements over SCIP on both large-scale real-world application datasets and MIPLIB.

Background. Docetaxel (Taxotere) is a microtubule‐stabilizing agent that is potentially important in chemotherapy for a variety of malignancies. Methods. A clinical study of the cutaneous reactions experienced by a group of patients receiving docetaxel chemotherapy was undertaken. Patients were examined before initiation of therapy, before and after each cycle of therapy, and were followed subsequent to the completion of docetaxel chemotherapy. Results. Three patients developed diffuse lower extremity edema (3‐18 kg) and subsequent scleroderma‐like changes after receiving multiple cycles of docetaxel therapy. These patients had different underlying malignancies and dissimilar prior therapy. Rheumatoid factor, antinuclear antibodies, anticentromere, and topoisomerase antibodies were not present in any patient. The diffuse lower extremity edema did not resolve with diuretic therapy. Cutaneous biopsies in two patients revealed diffuse sclerosis. One patient had a normal lymphangiogram during the edematous phase. Discontinuation of docetaxel correlated with resolution of edema and softening of the skin. Conclusion. The etiology of the scleroderma‐like skin changes is unclear but appears to be either a toxic effect of docetaxel or an effect of polysorbate 80 (Tween 80), the vehicle for docetaxel.

Pemphigus herpetiformis (PH), a rare type of pemphigus, is characterized by immunologic findings consistent with pemphigus but with a unique clinical and pathologic presentation. PH was first described as resembling dermatitis herpetiformis clinically, but because of its variable presentation, it can also resemble linear immunoglobulin A bullous dermatosis and bullous pemphigoid. We reviewed reported cases to analyze the most frequent clinical, pathologic, and immunologic characteristics and to propose corresponding diagnostic criteria. Through a comprehensive review of Medline and PubMed databases, 96 publications and 158 cases were identified. After reviewing the reported characteristics of PH, we suggest the following diagnostic criteria: Clinical: 1) pruritic herpetiform intact blisters with/without erosions; and/or 2) pruritic annular or urticarial erythematous plaques with/without erosions; Pathologic: 1) intraepidermal eosinophils or neutrophils, or both; and/or 2) intraepidermal split with/without acantholysis; Immunologic: 1) direct immunofluorescence showing immunoglobulin G with/without C3 intercellular deposits; and/or 2) indirect immunofluorescence showing immunoglobulin G to epithelial cell surface; and/or 3) detection of serum autoantibodies against desmogleins (1,3) or desmocollins (1,2,3), or both. Diagnosis requires one clinical, one pathologic, and one immunologic feature. We also report three new cases diagnosed at our institution to demonstrate the applicability of the suggested criteria.