Marcelo Costa Oliveira

A Bag-of-Tasks approach to speed up the lung nodules retrieval in the BigData age

The Content-Based Image Retrieval (CBIR) has received great attention in the medical community because it is capable of retrieving similar images that have known pathologies. However, the sheer volume of data produced in radiology centers has precluded the use of CBIR in the daily routine of hospitals. The volume of medical images produced in medical centers has increased fast. The annual data produced from exams in the big radiology centers is greater than 10 Terabytes. Therefore, we have reached to an unprecedented age of “BigData”. We here present a bag-of task approach to speed up the images retrieval of lung nodules stored in a large medical images database. This solution combines texture attributes and registration algorithms that together are capable of retrieving images of benign lung nodules with greater-than-72% precision and greater-than-67% in malignant cases, yet running in a few minutes over the Grid, making it usable in the clinical routine.

Cloud-Based NoSQL Open Database of Pulmonary Nodules for Computer-Aided Lung Cancer Diagnosis and Reproducible Research.

Lung cancer is the leading cause of cancer-related deaths in the world, and its main manifestation is pulmonary nodules. Detection and classification of pulmonary nodules are challenging tasks that must be done by qualified specialists, but image interpretation errors make those tasks difficult. In order to aid radiologists on those hard tasks, it is important to integrate the computer-based tools with the lesion detection, pathology diagnosis, and image interpretation processes. However, computer-aided diagnosis research faces the problem of not having enough shared medical reference data for the development, testing, and evaluation of computational methods for diagnosis. In order to minimize this problem, this paper presents a public nonrelational document-oriented cloud-based database of pulmonary nodules characterized by 3D texture attributes, identified by experienced radiologists and classified in nine different subjective characteristics by the same specialists. Our goal with the development of this database is to improve computer-aided lung cancer diagnosis and pulmonary nodule detection and classification research through the deployment of this database in a cloud Database as a Service framework. Pulmonary nodule data was provided by the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), image descriptors were acquired by a volumetric texture analysis, and database schema was developed using a document-oriented Not only Structured Query Language (NoSQL) approach. The proposed database is now with 379 exams, 838 nodules, and 8237 images, 4029 of them are CT scans and 4208 manually segmented nodules, and it is allocated in a MongoDB instance on a cloud infrastructure.

Performance Evaluation of Medical Image Similarity Analysis in a Heterogeneous Architecture

The volume of data has increased fast, particularly medical images, in big hospitals over the last years. This increase imposes a big challenge to medical specialists: the maintenance of high interpretation accuracy of image-based diagnosis. Computer-Aided Diagnosis software allied to the Content-Based Image Retrieval (CBIR) can provide decision support to specialists by allowing them to find images from a database that are similar to a reference image. However, a well known challenge of CBIR is the processing time that it takes to process all comparisons between the reference image and the image database. This paper proposes a performance evaluation of medical Image Similarity Analysis (ISA) in a heterogeneous single-, multi- and many-core architecture using the high performance parallel OpenCL framework. A CBIR algorithm was implemented to validate the proposal. The algorithm used a Lung Cancer image database with 131, 072 Computed Tomography scans, Texture Attributes for image features and Euclidean Distance for image comparison metrics. The results showed that the OpenCL parallelism can increase the performance of ISA, especially using the GPU, with speedups of 3x, 36x and 64x. The results also showed that it is not worth the use of GPU local memory for the Euclidean Distance metrics due to its low performance improvement and high implementation complexity in comparison to the GPU global memory. That being said, GPU is a safer medical CBIR approach than further distributed environments as clusters, cloud and grid computing because GPU usage does not require the patient data to be transfered to other machines.

Grades computacionais na recuperação de imagens médicas baseada em conteúdo

OBJECTIVE: To utilize the grid computing technology to enable the utilization of a similarity measurement algorithm for content-based medical image retrieval. MATERIALS AND METHODS: The content-based images retrieval technique is comprised of two sequential steps: texture analysis and similarity measurement algorithm. These steps have been adopted for head and knee images for evaluation of accuracy in the retrieval of images of a single plane and acquisition sequence in a databank with 2,400 medical images. Initially, texture analysis was utilized as a preselection resource to obtain a set of the 1,000 most similar images as compared with a reference image selected by a clinician. Then, these 1,000 images were processed utilizing a similarity measurement algorithm on a computational grid. RESULTS: The texture analysis has demonstrated low accuracy for sagittal knee images (0.54) and axial head images (0.40). Nevertheless, this technique has shown effectiveness as a filter, pre-selecting images to be evaluated by the similarity measurement algorithm. Content-based images retrieval with similarity measurement algorithm applied on these pre-selected images has demonstrated satisfactory accuracy - 0.95 for sagittal knee images, and 0.92 for axial head images. The high computational cost of the similarity measurement algorithm was balanced by the utilization of grid computing. CONCLUSION: The approach combining texture analysis and similarity measurement algorithm for content-based images retrieval resulted in an accuracy of > 90%. Grid computing has shown to be essential for the utilization of similarity measurement algorithm in the content-based images retrieval that otherwise would be limited to supercomputers.

Grid computing to make viable the content based medical image retrieval through the image registration techniques

The content-based image retrieval (CBIR) has great interest of the medical community, because it is capable of retrieval similar images stored in servers that have known pathologies. However, an efficient and reliable CBIR solution has not been achieved yet, due to the complexity of the medical image and the great volume they represent. This work proposes a new methodology based on higher processing provided by Grid Computing technology to achieve the CBIR using the registration algorithms. The registration procedure use two metrics, square difference metric (SDM) and cross correlation (CC). Both metrics showed higher efficiency, SDM obtained precision average of 0.83% (breast image) and 0.94% (head image), the CC showed precision of 0.81% (breast) and 0.52% (head). The higher computational cost related to the registration algorithms was amortized by Grid Computing, that was capable of ensure data secure and represent a low cost solution to small clinics and public hospitals. Grid technologies open new opportunities to investigate the contribution on applying the registration algorithms to CBIR and new advances are expected.

Integrating 3D image descriptors of margin sharpness and texture on a GPU-optimized similar pulmonary nodule retrieval engine

Due to the difficulty to diagnose lung cancer, it is important to integrate content-based image retrieval methods with the pulmonary nodule classification process, since they are capable of retrieving similar cases from large image databases that were previously diagnosed. The goal of this paper is to evaluate an integrated image feature vector, composed of 3D attributes of margin sharpness and texture, on similar pulmonary nodule retrieval, and to optimize the runtime of nodule comparison process with a graphics processing unit (GPU). Retrieval efficiency was evaluated on the ten most similar cases, on different multiprocessor architectures. Results showed that integrated attributes obtained higher efficiency on similar nodule retrieval, with an increase of up to 2.6 percentage points compared to isolated margin sharpness and texture descriptors. Results also showed that GPU increased nodule retrieval performance with a speedup of 23.7

Characterization of Pulmonary Nodules Based on Features of Margin Sharpness and Texture

\times

Automatic weighing attribute to retrieve similar lung cancer nodules

× on nodule comparison runtime.