Sparse Representation Based Multi-Instance Learning for Breast Ultrasound Image Classification

Abstract

We propose a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL). After image enhancement and segmentation, concentric circle is used to extract the global and local features for improving the accuracy in diagnosis and prediction. The classification problem of ultrasound image is converted to sparse representation based MIL problem. Each instance of a bag is represented as a sparse linear combination of all basis vectors in the dictionary, and then the bag is represented by one feature vector which is obtained via sparse representations of all instances within the bag. The sparse and MIL problem is further converted to a conventional learning problem that is solved by relevance vector machine (RVM). Results of single classifiers are combined to be used for classification. Experimental results on the breast cancer datasets demonstrate the superiority of the proposed method in terms of classification accuracy as compared with state-of-the-art MIL methods.

Artificial Intelligence System Reduces False-Positive Findings in the Interpretation of Breast Ultrasound Exams

“…Computer-aided diagnosis (CAD) systems have been proposed to assist radiologists in the interpretation of breast US exams over a decade ago [18]. Early CAD systems often relied on handcrafted visual features that are difficult to generalize across US images that were acquired using different protocols and US units [19,20,21,22,23,24]. Recent advances in deep learning have facilitated the development of AI systems for the automated diagnosis of breast cancer from US images [25,26,27].…”

Artificial intelligence in breast ultrasound

“…According to the similarity of algorithm functions and forms, machine learning generally includes support vector machine, fuzzy logic, artificial neural network, etc ., and each has its own advantages and disadvantages. Bing et al[16] proposed a novel method based on sparse representation for breast ultrasound image classification under the framework of multi-instance learning (MIL). Compared with state-of-the-art MIL method, this method achieved its obvious superiority in classification accuracy.…”

Optimasi Algoritma Learning Vector Quantization (Lvq) Dalam Pengklasifikasian Citra Daging Sapi Dan Daging Babi Berbasis GLCM Dan HSV

“…Salah satunya adalah dengan memanfaatkan pengolahan citra digital, dengan pengolahan citra digital ini maka akan dapat membuat sebuah sistem pengenalan daging secara komputerisasi yang bisa membedakan antara daging sapi dengan daging babi seperti halnya manusia [2]. Dalam pengolahan citra ada beberapa proses atau tahap yang bisa dilakukan untuk mengetahui karakteristik pada suatu citra yang meliputi preprocessing, segmentasi, filtering, ektraksi, klasifikasi, dan lain sebagainya.…”

“…Preprocessing merupakan tahapan yang bertujuan untuk mendapatkan Region Of Interest (ROI) dengan cara memotong citra, mengubah ukuran gambar, dan lain sebagainnya [2]. Pada penelitian ini, diawali dengan pemotongan (cropping) citra asli sesuai dengan ukuran daging.…”