Automatic differentiation of thyroid scintigram by deep convolutional neural network: a dual center study.

BACKGROUND: 99mTc-pertechnetate thyroid scintigraphy is a valid complementary avenue for evaluating thyroid disease in the clinic, the image feature of thyroid scintigram is relatively simple but the interpretation still has a moderate consistency among physicians. Thus, we aimed to develop an artificial intelligence (AI) system to automatically classify the four patterns of thyroid scintigram. METHODS: We collected 3087 thyroid scintigrams from center 1 to construct the training dataset (n = 2468) and internal validating dataset (n = 619), and another 302 cases from center 2 as external validating datasets. Four pre-trained neural networks that included ResNet50, DenseNet169, InceptionV3, and InceptionResNetV2 were implemented to construct AI models. The models were trained separately with transfer learning. We evaluated each model's performance with metrics as following: accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), recall, precision, and F1-score. RESULTS: The overall accuracy of four pre-trained neural networks in classifying four common uptake patterns of thyroid scintigrams all exceeded 90%, and the InceptionV3 stands out from others. It reached the highest performance with an overall accuracy of 92.73% for internal validation and 87.75% for external validation, respectively. As for each category of thyroid scintigrams, the area under the receiver operator characteristic curve (AUC) was 0.986 for 'diffusely increased,' 0.997 for 'diffusely decreased,' 0.998 for 'focal increased,' and 0.945 for 'heterogeneous uptake' in internal validation, respectively. Accordingly, the corresponding performances also obtained an ideal result of 0.939, 1.000, 0.974, and 0.915 in external validation, respectively. CONCLUSIONS: Deep convolutional neural network-based AI model represented considerable performance in the classification of thyroid scintigrams, which may help physicians improve the interpretation of thyroid scintigrams more consistently and efficiently.

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

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.

Clinical applications of single-photon emission computed tomography/computed tomography in post-ablation 131iodine scintigraphy in children and young adults with differentiated thyroid carcinoma.

BACKGROUND: The utility of integrated single-photon emission computed tomography/computed tomography (SPECT/CT) in children and young adults with differentiated thyroid carcinoma is incompletely studied. OBJECTIVE: To determine the value of adding SPECT/CT to conventional whole-body scintigraphy in post-ablation iodine-131 (131I) scintigraphy for children and young adults with differentiated thyroid carcinoma. MATERIALS AND METHODS: Planar scintigraphy and SPECT/CT were performed on 42 post-surgical children and young adults (32 female, 10 male; mean age 14.3±4.9 years, range 7-20 years) with differentiated thyroid carcinoma (39 papillary, 2 follicular, 1 mixed) 5 days after the therapeutic administration of 1.9-7.4 GBq of 131I. Planar and SPECT/CT images were interpreted independently, and sites of uptake were categorized as positive or equivocal with respect to thyroid bed, lymph node and distant metastasis uptake. An experienced thyroid endocrinologist used a combination of surgical histopathology and scintigraphic findings to determine whether the addition of SPECT/CT would change patient management. RESULTS: Planar scintigraphy evidenced 88 radioiodine-avid foci and SPECT/CT confirmed all foci. No additional foci were disclosed by SPECT/CT. SPECT/CT correctly classified 16/88 (18%) foci that were unclear or wrongly classified at planar scintigraphy. Globally, SPECT/CT showed an incremental value over planar scintigraphy in 9 (21.4%) patients and changed therapeutic management in 3 (7.1%; 95% confidence interval, 2-20%) patients. CONCLUSION: SPECT/CT improved localization and characterization of focal 131I uptake on post-ablation whole-body scintigraphy in children and young adults with differentiated thyroid carcinoma. Further prospective evaluation in a larger series is justified to prove the effect of post-ablation SPECT/CT-based management decisions.

Retroperitoneal Liposarcoma on 99mTc-DTPA Renal Scintigraphy.

Retroperitoneal liposarcoma is usually large and can press on other organs. We report a case of a 66-year-old woman with a history of retroperitoneal liposarcoma resection who presented to the emergency department with abdominal pain. Ultrasonography revealed a large abdominal mass with renal displacement. Dynamic renal scintigraphy with Tc-DTPA was conducted to evaluate renal function. However, severe impairment of the right kidney function and abnormal tracer accumulation were observed during the examination. SPECT/CT was performed; 2 kidneys were successfully localized, and the recurrence of tumor was correctly detected.

Automated diagnosis of bone metastasis based on multi-view bone scans using attention-augmented deep neural networks.

Bone scintigraphy is accepted as an effective diagnostic tool for whole-body examination of bone metastasis. However, the manual analysis of bone scintigraphy images requires extensive experience and is exhausting and time-consuming. An automated diagnosis system for such images is therefore much desired. Although automatic or semi-automatic methods for the diagnosis of bone scintigraphy images have been widely studied, they employ various steps to classify the images, including segmentation of the entire skeleton, detection of hot spots, and feature extraction, which are complex and inadequately validated on small datasets, thereby resulting in low accuracy and reliability. In this paper, we describe the development of a deep convolutional neural network to determine the absence or presence of bone metastasis. This model consisting of three sub-networks that aim to extract, aggregate, and classify high-level features in a data-driven manner. There are two main innovations behind this method; First, the diagnosis is performed by jointly analyzing both anterior and posterior views, which leads to high accuracy. Second, a spatial attention feature aggregation operator is proposed to enhance the spatial location information. A large annotated bone scintigraphy image dataset containing 15,474 examinations from 13,811 patients was constructed to train and evaluate the model. The proposed method is compared with three human experts. The high classification accuracy achieved demonstrates the effectiveness of the proposed architecture for the diagnosis of bone scintigraphy images, and that it can be applied as a clinical decision support tool.

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

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.

Remarkable Response of Pulmonary Metastases Rather Than Remnant Thyroid in 131I Therapy of Follicular Thyroid Cancer.

A 66-year-old man with follicular thyroid cancer after total thyroidectomy was referred for I therapy. Thyroid function tests before I administration exhibited severe thyrotoxicosis although the patient did not take levothyroxine after thyroidectomy. A 185 MBq I whole-body scintigraphy and SPECT/CT revealed multiple iodine-avid pulmonary metastases with the largest tumor diameter of 1.4 cm and remnant thyroid. A diagnosis of thyrotoxicosis caused by hyperfunctioning pulmonary metastases was then made. The patient was administered 7.4 GBq of I. Six months after I therapy, a significant reduction of the pulmonary metastatic disease and thyroglobulin level was observed. However, the remnant thyroid was still visualized.

EFFECTIVE RADIATION DOSE OF 18F-FDG PET/CT: HOW MUCH DOES DIAGNOSTIC CT CONTRIBUTE?

The aim was to estimate the effective doses associated with different types of scanning protocols and how much the diagnostic computed tomography (DCT) scan contributed to the total dose of the dual-modality positron emission tomography/computed tomography (PET/CT) examinations. The results showed that an average radiation dose of 8.19 ± 0.83 mSv and 13.44 ± 5.14 mSv for the PET and CT components, respectively, resulting in a total dose of 21.64 ± 5.20 mSv. Approximately 92.7% (980 of 1057) of the patients underwent additional DCT protocols. The DCT protocols contributed 42% of the overall effective radiation doses, which was larger than the percentage contributed by the PET component (38%) and LCT protocols (20%). Reducing the diagnostic area of the DCT scans that patients undergo and decreasing the use of chest-abdomen-pelvis (CAP), abdomen-pelvis (AP) and chest DCT protocols, especially the CAP protocol, will be helpful in decreasing the effective radiation doses of PET/CT scan.