Leveraging Mid-Level Semantic Boundary Cues for Automated Lymph Node Detection

Abstract

Abstract. Histograms of oriented gradients (HOG) are widely employed image descriptors in modern computer-aided diagnosis systems. Built upon a set of local, robust statistics of low-level image gradients, HOG features are usually computed on raw intensity images. In this paper, we explore a learned image transformation scheme for producing higher-level inputs to HOG. Leveraging semantic object boundary cues, our methods compute data-driven image feature maps via a supervised boundary detector. Compared with the raw image map, boundary cues offer mid-level, more object-specific visual responses that can be suited for subsequent HOG encoding. We validate integrations of several image transformation maps with an application of computer-aided detection of lymph nodes on thoracoabdominal CT images. Our experiments demonstrate that semantic boundary cues based HOG descriptors complement and enrich the raw intensity alone. We observe an overall system with substantially improved results (∼78% versus 60% recall at 3 FP/volume for two target regions). The proposed system also moderately outperforms the state-of-the-art deep convolutional neural network (CNN) system in the mediastinum region, without relying on data augmentation and requiring significantly fewer training samples.

Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning

“…Many of our CNN models achieve notably better (FROC-AUC and TPR/3FP) results than the previous state-of-the-art models [36] for mediastinal LN detection: GoogLeNet-RI-L obtains an \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}${\rm AUC}=0.95$\end{document} and 0.85 TPR/3FP, versus \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}${\rm AUC}=0.92$\end{document} and 0.70 TPR/3FP [22] and 0.78 TPR/3FP [36] which uses stacked shallow learning. This difference lies in the fact that annotated lymph node segmentation masks are required to learn a mid-level semantic boundary detector [36] , whereas CNN approaches only need LN locations for training [22] . In abdominal LN detection, [22] obtains the best trade-off between its CNN model complexity and sampled data configuration.…”

“…To facilitate comparison, we adopt the data preparation protocol of [22] , where positive and negative LN candidates are sampled with the fields-of-view (FOVs) of 30 mm to 45 mm, surrounding the annotated and detected LN centers (obtained by a candidate generation process). More precisely, [22] , [41] , [36] follow a coarse-to-fine CADe scheme, partially inspired by [42] , which operates with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}$\sim 100\%$\end{document} detection recalls at the cost of approximately 40 false or negative LN candidates per patient scan. In this work, positive and negative LN candidate are first sampled up to 200 times with translations and rotations.…”

“…On mediastinal LN detection, we surpass all currently reported results. We obtain 86% sensitivity on 3 false positives (FP) per patient, versus the prior state-of-art sensitivities of 78% [36] (stacked shallow learning) and 70% [22] (CNN), as prior state-of-the-art. For the first time, ILD classification results under the patient-level five-fold cross-validation protocol (CV5) are investigated and reported.…”

Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans

“…Recently, the deep learning techniques have been introduced to the medical image analysis domain with promising results on various applications, like the computerized prognosis for Alzheimer’s disease and mild cognitive impairment 32 , organ segmentations 33 and detection 34 , ultrasound standard plane selection 35 , etc., on 3D or 4D image data, etc. In the context of CAD, most works focused on the problem of abnormality detection (CADe) 36 37 38 . For the problem of CADx, a specific convolutional neural network model, OverFeat 39 , was employed in the work 40 to classify the specific type of peri-fissural nodules with the ensemble fashion in AUC performance around 0.86.…”

Progress in Fully Automated Abdominal CT Interpretation

“…In general, the RECIST guidelines are used to evaluate lymph nodes in such patients [52]. A number of investigators have developed automated software for detection and measurement of abdominal adenopathy [53–61] (Fig. 2).…”