Dataset Information

Automatic identification of suspicious bone metastatic lesions in bone scintigraphy using convolutional neural network.

ABSTRACT:

Background

We aimed to construct an artificial intelligence (AI) guided identification of suspicious bone metastatic lesions from the whole-body bone scintigraphy (WBS) images by convolutional neural networks (CNNs).

Methods

We retrospectively collected the ^99mTc-MDP WBS images with confirmed bone lesions from 3352 patients with malignancy. 14,972 bone lesions were delineated manually by physicians and annotated as benign and malignant. The lesion-based differentiating performance of the proposed network was evaluated by fivefold cross validation, and compared with the other three popular CNN architectures for medical imaging. The average sensitivity, specificity, accuracy and the area under receiver operating characteristic curve (AUC) were calculated. To delve the outcomes of this study, we conducted subgroup analyses, including lesion burden number and tumor type for the classifying ability of the CNN.

Results

In the fivefold cross validation, our proposed network reached the best average accuracy (81.23%) in identifying suspicious bone lesions compared with InceptionV3 (80.61%), VGG16 (81.13%) and DenseNet169 (76.71%). Additionally, the CNN model's lesion-based average sensitivity and specificity were 81.30% and 81.14%, respectively. Based on the lesion burden numbers of each image, the area under the receiver operating characteristic curve (AUC) was 0.847 in the few group (lesion number n ≤ 3), 0.838 in the medium group (n = 4-6), and 0.862 in the extensive group (n > 6). For the three major primary tumor types, the CNN-based lesion identifying AUC value was 0.870 for lung cancer, 0.900 for prostate cancer, and 0.899 for breast cancer.

Conclusion

The CNN model suggests potential in identifying suspicious benign and malignant bone lesions from whole-body bone scintigraphic images.

SUBMITTER: Liu Y

PROVIDER: S-EPMC8417997 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The spinal cord is frequently affected by atrophy and/or lesions in multiple sclerosis (MS) patients. Segmentation of the spinal cord and lesions from MRI data provides measures of damage, which are key criteria for the diagnosis, prognosis, and longitudinal monitoring in MS. Automating this operation eliminates inter-rater variability and increases the efficiency of large-throughput analysis pipelines. Robust and reliable segmentation across multi-site spinal cord data is challenging because of the large variability related to acquisition parameters and image artifacts. In particular, a precise delineation of lesions is hindered by a broad heterogeneity of lesion contrast, size, location, and shape. The goal of this study was to develop a fully-automatic framework - robust to variability in both image parameters and clinical condition - for segmentation of the spinal cord and intramedullary MS lesions from conventional MRI data of MS and non-MS cases. Scans of 1042 subjects (459 healthy controls, 471 MS patients, and 112 with other spinal pathologies) were included in this multi-site study (n = 30). Data spanned three contrasts (T1-, T2-, and T2∗-weighted) for a total of 1943 vol and featured large heterogeneity in terms of resolution, orientation, coverage, and clinical conditions. The proposed cord and lesion automatic segmentation approach is based on a sequence of two Convolutional Neural Networks (CNNs). To deal with the very small proportion of spinal cord and/or lesion voxels compared to the rest of the volume, a first CNN with 2D dilated convolutions detects the spinal cord centerline, followed by a second CNN with 3D convolutions that segments the spinal cord and/or lesions. CNNs were trained independently with the Dice loss. When compared against manual segmentation, our CNN-based approach showed a median Dice of 95% vs. 88% for PropSeg (p ≤ 0.05), a state-of-the-art spinal cord segmentation method. Regarding lesion segmentation on MS data, our framework provided a Dice of 60%, a relative volume difference of -15%, and a lesion-wise detection sensitivity and precision of 83% and 77%, respectively. In this study, we introduce a robust method to segment the spinal cord and intramedullary MS lesions on a variety of MRI contrasts. The proposed framework is open-source and readily available in the Spinal Cord Toolbox.

Project description:BackgroundThe efficient and accurate diagnosis of pulmonary adenocarcinoma before surgery is of considerable significance to clinicians. Although computed tomography (CT) examinations are widely used in practice, it is still challenging and time-consuming for radiologists to distinguish between different types of subcentimeter pulmonary nodules. Although there have been many deep learning algorithms proposed, their performance largely depends on vast amounts of data, which is difficult to collect in the medical imaging area. Therefore, we propose an automatic classification system for subcentimeter pulmonary adenocarcinoma, combining a convolutional neural network (CNN) and a generative adversarial network (GAN) to optimize clinical decision-making and to provide small dataset algorithm design ideas.MethodsA total of 206 nodules with postoperative pathological labels were analyzed. Among them were 30 adenocarcinomas in situ (AISs), 119 minimally invasive adenocarcinomas (MIAs), and 57 invasive adenocarcinomas (IACs). Our system consisted of two parts, a GAN-based image synthesis, and a CNN classification. First, several popular existing GAN techniques were employed to augment the datasets, and comprehensive experiments were conducted to evaluate the quality of the GAN synthesis. Additionally, our classification system processes were based on two-dimensional (2D) nodule-centered CT patches without the need of manual labeling information.ResultsFor GAN-based image synthesis, the visual Turing test showed that even radiologists could not tell the GAN-synthesized from the raw images (accuracy: primary radiologist 56%, senior radiologist 65%). For CNN classification, our progressive growing wGAN improved the performance of CNN most effectively (area under the curve =0.83). The experiments indicated that the proposed GAN augmentation method improved the classification accuracy by 23.5% (from 37.0% to 60.5%) and 7.3% (from 53.2% to 60.5%) in comparison with training methods using raw and common augmented images respectively. The performance of this combined GAN and CNN method (accuracy: 60.5%±2.6%) was comparable to the state-of-the-art methods, and our CNN was also more lightweight.ConclusionsThe experiments revealed that GAN synthesis techniques could effectively alleviate the problem of insufficient data in medical imaging. The proposed GAN plus CNN framework can be generalized for use in building other computer-aided detection (CADx) algorithms and thus assist in diagnosis.