Analysis of High-Frequency Ultrasound in the differential Diagnosis of Lumps in Foot and Hand

Objective:To investigate the ultrasonogram characteristics of common lumps in hand and foot,pursuing for greater understanding of hand and foot lumps.Methods:65 cases of ultrasonographic characteristics of lumps in hand and foot were retrospectively analyzed,including the location,size,shape,boundary,internal echo and posterior echo,surrounding relationship and blood flow.Results:Among 65 cases,there were 26 cases of tendon sheath cyst,16 cases of tenosynovitis giant cell tumor,10 cases of hemangioma,4 cases of tendon sheath fibroma,3 cases of epidermoid cyst,2 cases of Schwannoma,2 cases of fibrolipoma,1 case of angiolipoma and 1 case of neurofibroma.The preoperative and postoperative pathological diagnoses of 45 cases,accounting for 69.23%,were consistent,3 cases(4.62%)were misdiagnosed,which included that 2 cases of tenosynovitis giant cell tumor were misdiagnosed as tendon sheath cyst,1 case of neurofibroma as epidermoid cyst,and the preoperative diagnosis of the rest 17 cases(26.15%)were indefinite.Conclusion:The high-frequency ultrasound can diagnose properties of lumps in foot and hand well,providing diagnosis basis for further treatment in clinic.

Key-Part Attention Retrieval for Robotic Object Recognition

The ability to recognize novel objects with a few visual samples is critical in the robotic applications.Existing methods mainly concern the recognition of inter-category objects,however,the object recognition fromdifferent sub-classes within the same category remains challenging due to their similar appearances.In thispaper,we propose a key-part attention retrieval solution to distinguish novel objects of different sub-classesaccording to a few samples without re-training.Especially,an object encoder,including convolutional neuralnetwork with attention and key-part aggregation,is designed to generate object attention map and extract theobject-level embedding,where object attention map from the middle stage of the backbone is used to guide thekey-part aggregation.Besides,to overcome the non-differentiability drawback of key-part attention,the objectencoder is trained in a two-step scheme,and a more stable object-level embedding is obtained.On this basis,the potential objects are located from a scene image by mining connected domains of the attention map.Bymatching the embedding of each potential object and embeddings from support data,the recognition of thepotential objects is achieved.The effectiveness of the proposed method is verified by experiments.