Dataset Information

Deep neural network based artificial intelligence assisted diagnosis of bone scintigraphy for cancer bone metastasis.

ABSTRACT: Bone scintigraphy (BS) is one of the most frequently utilized diagnostic techniques in detecting cancer bone metastasis, and it occupies an enormous workload for nuclear medicine physicians. So, we aimed to architecture an automatic image interpreting system to assist physicians for diagnosis. We developed an artificial intelligence (AI) model based on a deep neural network with 12,222 cases of 99mTc-MDP bone scintigraphy and evaluated its diagnostic performance of bone metastasis. This AI model demonstrated considerable diagnostic performance, the areas under the curve (AUC) of receiver operating characteristic (ROC) was 0.988 for breast cancer, 0.955 for prostate cancer, 0.957 for lung cancer, and 0.971 for other cancers. Applying this AI model to a new dataset of 400 BS cases, it represented comparable performance to that of human physicians individually classifying bone metastasis. Further AI-consulted interpretation also improved human diagnostic sensitivity and accuracy. In total, this AI model performed a valuable benefit for nuclear medicine physicians in timely and accurate evaluation of cancer bone metastasis.

SUBMITTER: Zhao Z

PROVIDER: S-EPMC7550561 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep neural network based artificial intelligence assisted diagnosis of bone scintigraphy for cancer bone metastasis.

Zhao Zhen Z Pi Yong Y Jiang Lisha L Xiang Yongzhao Y Wei Jianan J Yang Pei P Zhang Wenjie W Zhong Xiao X Zhou Ke K Li Yuhao Y Li Lin L Yi Zhang Z Cai Huawei H

Scientific reports 20201012 1

Bone scintigraphy (BS) is one of the most frequently utilized diagnostic techniques in detecting cancer bone metastasis, and it occupies an enormous workload for nuclear medicine physicians. So, we aimed to architecture an automatic image interpreting system to assist physicians for diagnosis. We developed an artificial intelligence (AI) model based on a deep neural network with 12,222 cases of <sup>99m</sup>Tc-MDP bone scintigraphy and evaluated its diagnostic performance of bone metastasis. Th ...[more]

PMID: 33046779

Similar Datasets

Project description:BONENAVI, a computer-aided diagnostic system, is used in bone scintigraphy. This system provides the artificial neural network (ANN) and bone scan index (BSI) values. ANN is associated with the possibility of bone metastasis, while BSI is related to the amount of bone metastasis. The degree of uptake on bone scintigraphy can be affected by the type of bone metastasis. Therefore, the ANN value provided by BONENAVI may be influenced by the characteristics of bone metastasis. In this study, we aimed to assess the relationship between ANN value and characteristics of bone metastasis.We analyzed 50 patients (36 males,14 females; age range: 87-42 yrs median age:72.5 yrs) with prostate, breast, or lung cancer who had undergone bone scintigraphy and were diagnosed with bone metastasis (32 cases of prostate cancer, nine cases of breast cancer, and nine cases of lung cancer). Those who had received systematic therapy over the past years were excluded. Bone metastases were diagnosed clinically, and the type of bone metastasis (osteoblastic, mildly osteoblastic, osteolytic, and mixed components) was decided visually by the agreement of two radiologists. We compared the ANN values (case-based and lesion-based) among the three primary cancers and four types of bone metastasis.There was no significant difference in case-based ANN values among prostate, breast, and lung cancers. However, the lesion-based ANN values were the highest in cases with prostate cancer and the lowest in cases of lung cancer (median values: prostate cancer, 0.980; breast cancer 0.909; and lung cancer, 0.864). Mildly osteoblastic lesions showed significantly lower ANN values than the other three types of bone metastasis (median values: osteoblastic,; 0.939 mildly osteoblastic; 0.788, mixed type; 0.991, and osteolytic. 0.969) The possibility of a lesion-based ANN value below 0.5 was %10.9 for bone metastasis in prostate cancer, %12.9 for breast cancer, and %37.2 for lung cancer. The corresponding possibility were %14.7 for osteoblastic metastases, %23.9 for mildly osteoblastic metastases, %7.14 for mixed-type metastases, and %16.0 for osteolytic metastases.The lesion-based ANN values calculated by BONENAVI can be influenced by the type of primary cancer and bone metastasis.

Project description:In order to explore the application of the image recognition model based on multi-stage convolutional neural network (MS-CNN) in the deep learning neural network in the intelligent recognition of commodity images and the recognition performance of the method, in the study, the features of color, shape, and texture of commodity images are first analyzed, and the basic structure of deep convolutional neural network (CNN) model is analyzed. Then, 50,000 pictures containing different commodities are constructed to verify the recognition effect of the model. Finally, the MS-CNN model is taken as the research object for improvement to explore the influence of label errors (p = 0.03, 0.05, 0.07, 0.09, 0.12) with different parameter settings and different probabilities (size of convolutional kernel, Dropout rate) on the recognition accuracy of MS-CNN model, at the same time, a CIR system platform based on MS-CNN model is built, and the recognition performance of salt and pepper noise images with different SNR (0, 0.03, 0.05, 0.07, 0.1) was compared, then the performance of the algorithm in the actual image recognition test was compared. The results show that the recognition accuracy is the highest (97.8%) when the convolution kernel size in the MS-CNN model is 2*2 and 3*3, and the average recognition accuracy is the highest (97.8%) when the dropout rate is 0.1; when the error probability of picture label is 12%, the recognition accuracy of the model constructed in this study is above 96%. Finally, the commodity image database constructed in this study is used to identify and verify the model. The recognition accuracy of the algorithm in this study is significantly higher than that of the Minitch stochastic gradient descent algorithm under different SNR conditions, and the recognition accuracy is the highest when SNR = 0 (99.3%). The test results show that the model proposed in this study has good recognition effect in the identification of commodity images in scenes of local occlusion, different perspectives, different backgrounds, and different light intensity, and the recognition accuracy is 97.1%. To sum up, the CIR platform based on MS-CNN model constructed in this study has high recognition accuracy and robustness, which can lay a foundation for the realization of subsequent intelligent commodity recognition technology.

Dataset Information

Deep neural network based artificial intelligence assisted diagnosis of bone scintigraphy for cancer bone metastasis.

Publications

Deep neural network based artificial intelligence assisted diagnosis of bone scintigraphy for cancer bone metastasis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets