Effective 3D object detection and regression using probabilistic segmentation features in CT images

Lü, Le; Bi, Jinbo; Wolf, Matthias; Salganicoff, Marcos

doi:10.1109/cvpr.2011.5995359

Cited by 29 publications

(24 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the detection purpose, our modeling of the voxel-level unary energy term (in a CRF sense) appears mostly sufficient. However the rough segmentation accuracy by detection is statistically lower than [17,24], e.g., for size measurement (tuned by τ towards over-segmentation for high detection sensitivity).…”

Section: Supervised Probabilistic Voxel Map Labeling ℘ In Roimentioning

confidence: 97%

“…3), After connected component base non-maximum pruning, we can effectively remove false positive responses while keeping high sensitivity. Based on our empirical evaluation, highly optimized segmentation procedures [6,11,17,24] may not improve the learned features with significantly better discriminativeness. For the detection purpose, our modeling of the voxel-level unary energy term (in a CRF sense) appears mostly sufficient.…”

Section: Supervised Probabilistic Voxel Map Labeling ℘ In Roimentioning

confidence: 99%

See 1 more Smart Citation

Computer Aided Diagnosis Using Multilevel Image Features on Large-Scale Evaluation

Lü

Devarakota²,

Vikal³

et al. 2014

Medical Computer Vision. Large Data in Medical Imaging

Self Cite

View full text Add to dashboard Cite

Abstract. Computer aided diagnosis (CAD) of cancerous anatomical structures via 3D medical images has emerged as an intensively studied research area. In this paper, we present a principled three-tiered image feature learning approach to capture task specific and data-driven class discriminative statistics from an annotated image database. It integrates voxel-, instance-, and database-level feature learning, aggregation and parsing. The initial segmentation is proceeded as robust voxel labeling and thresholding. After instance-level spatial aggregation, extracted features can also be flexibly tuned for classifying lesions, or discriminating different subcategories of lesions. We demonstrate the effectiveness in the lung nodule detection task which handles all types of solid, partial-solid, and ground-glass nodules using the same set of learned features. Our hierarchical feature learning framework, which was extensively trained and validated on large-scale multiple site datasets of 879 CT volumes (510 training and 369 validation), achieves superior performance than other state-of-the-art CAD systems. The proposed method is also shown to be applicable for colonic polyp detection, including all polyp morphological subcategories, via 770 tagged-prep CT scans from multiple medical sites (358 training and 412 validation).

show abstract

Section: Supervised Probabilistic Voxel Map Labeling ℘ In Roimentioning

confidence: 97%

Section: Supervised Probabilistic Voxel Map Labeling ℘ In Roimentioning

confidence: 99%

Computer Aided Diagnosis Using Multilevel Image Features on Large-Scale Evaluation

Lü

Devarakota²,

Vikal³

et al. 2014

Medical Computer Vision. Large Data in Medical Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…4 shows a typical large abdominal LN missed by a single template approach. Addressing this imbalance in the training/testing datasets, we extend our model by training two classifiers via a variation of size gating [11]. With a 15 mm size threshold (calibrated as the median ground truth LN size), one classifier is trained using all positives linked to LNs ≥15 mm and another is trained with the rest.…”

Section: Methodsmentioning

confidence: 99%

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

Seff

Lü

Barbu

et al. 2015

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…However, none of these methods could robustly handle touching cell segmentation challenges exhibited in lung cancer images. Lu et al [23] has proposed a supervised learning-based segmentation algorithm to support new image features extraction and polyp detection on CT images, and a flexible, hierarchical feature learning framework integrating different levels of discriminative and descriptive information is presented in [24]. Supervised learning is a potential approach to tackle these challenges, but it requires a lot of labeled training data provided by experienced pathologists.…”

Section: Introductionmentioning

confidence: 99%

Novel image markers for non-small cell lung cancer classification and survival prediction

Wang

Xing

et al. 2014

BMC Bioinformatics

View full text Add to dashboard Cite

BackgroundNon-small cell lung cancer (NSCLC), the most common type of lung cancer, is one of serious diseases causing death for both men and women. Computer-aided diagnosis and survival prediction of NSCLC, is of great importance in providing assistance to diagnosis and personalize therapy planning for lung cancer patients.ResultsIn this paper we have proposed an integrated framework for NSCLC computer-aided diagnosis and survival analysis using novel image markers. The entire biomedical imaging informatics framework consists of cell detection, segmentation, classification, discovery of image markers, and survival analysis. A robust seed detection-guided cell segmentation algorithm is proposed to accurately segment each individual cell in digital images. Based on cell segmentation results, a set of extensive cellular morphological features are extracted using efficient feature descriptors. Next, eight different classification techniques that can handle high-dimensional data have been evaluated and then compared for computer-aided diagnosis. The results show that the random forest and adaboost offer the best classification performance for NSCLC. Finally, a Cox proportional hazards model is fitted by component-wise likelihood based boosting. Significant image markers have been discovered using the bootstrap analysis and the survival prediction performance of the model is also evaluated.ConclusionsThe proposed model have been applied to a lung cancer dataset that contains 122 cases with complete clinical information. The classification performance exhibits high correlations between the discovered image markers and the subtypes of NSCLC. The survival analysis demonstrates strong prediction power of the statistical model built from the discovered image markers.

show abstract

Effective 3D object detection and regression using probabilistic segmentation features in CT images

Cited by 29 publications

References 22 publications

Computer Aided Diagnosis Using Multilevel Image Features on Large-Scale Evaluation

Computer Aided Diagnosis Using Multilevel Image Features on Large-Scale Evaluation

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

Novel image markers for non-small cell lung cancer classification and survival prediction

Contact Info

Product

Resources

About