Learning Without Real Data Annotations to Detect Hepatic Lesions in PET Images.

OBJECTIVE: Deep neural networks have been recently applied to lesion identification in fluorodeoxyglucose (FDG) positron emission tomography (PET) images, but they typically rely on a large amount of well-annotated data for model training. This is extremely difficult to achieve for neuroendocrine tumors (NETs), because of low incidence of NETs and expensive lesion annotation in PET images. The objective of this study is to design a novel, adaptable deep learning method, which uses no real lesion annotations but instead low-cost, list mode-simulated data, for hepatic lesion detection in real-world clinical NET PET images. METHODS: We first propose a region-guided generative adversarial network (RG-GAN) for lesion-preserved image-to-image translation. Then, we design a specific data augmentation module for our list-mode simulated data and incorporate this module into the RG-GAN to improve model training. Finally, we combine the RG-GAN, the data augmentation module and a lesion detection neural network into a unified framework for joint-task learning to adaptatively identify lesions in real-world PET data. RESULTS: The proposed method outperforms recent state-of-the-art lesion detection methods in real clinical 68Ga-DOTATATE PET images, and produces very competitive performance with the target model that is trained with real lesion annotations. CONCLUSION: With RG-GAN modeling and specific data augmentation, we can obtain good lesion detection performance without using any real data annotations. SIGNIFICANCE: This study introduces an adaptable deep learning method for hepatic lesion identification in NETs, which can significantly reduce human effort for data annotation and improve model generalizability for lesion detection with PET imaging.

The effect of gadolinium-based intravenous contrast in the initial characterization of musculoskeletal soft tissue tumors.

OBJECTIVE: To determine if gadolinium-based contrast agents increase the sensitivity, specificity or reader confidence of malignant potential in musculoskeletal soft tissue tumors. METHODS: Pre- and post-contrast MRI studies from 87 patients were read by three independent radiologists of different experience. Readers noted malignant potential and confidence in their diagnosis based on pre-contrast and post-contrast MRI studies. Statistical models assessed for agreement between MRI reader diagnosis and pathologic results as well as analyzing effects of contrast on reader confidence. Inter- and intra-observer variabilities of malignant potential were also calculated. RESULTS: 87 patients (48 benign and 39 malignant; mean [± SD] age 51 ± 17.9 and 57.1 ± 17.1, respectively) were evaluated. For all readers, pre-contrast and post-contrast sensitivities were 68.1 % and 70.6 % while pre-contrast and post-contrast specificities were 84.6 % and 83.8 %, respectively without significant change (p=0.88). There was not a significant association with the use of contrast and prediction of malignant potential with or without the resident reader (p=0.65 and p=0.82). Use of contrast was significantly associated with higher levels of reader confidence (p=0.02) for all readers. Inter- and intra-observer variabilities were in good agreement (W = 0.77 and 0.70). CONCLUSION: The addition of a post-contrast sequence increased reader confidence in their diagnosis without a corresponding significant increase in accurate prediction of malignant potential.

Improving Generalizability of PET DL Algorithms: List-Mode Reconstructions Improve DOTATATE PET Hepatic Lesion Detection Performance.

Deep learning (DL) algorithms used for DOTATATE PET lesion detection typically require large, well-annotated training datasets. These are difficult to obtain due to low incidence of gastroenteropancreatic neuroendocrine tumors (GEP-NETs) and the high cost of manual annotation. Furthermore, networks trained and tested with data acquired from site specific PET/CT instrumentation, acquisition and processing protocols have reduced performance when tested with offsite data. This lack of generalizability requires even larger, more diverse training datasets. The objective of this study is to investigate the feasibility of improving DL algorithm performance by better matching the background noise in training datasets to higher noise, out-of-domain testing datasets. 68Ga-DOTATATE PET/CT datasets were obtained from two scanners: Scanner1, a state-of-the-art digital PET/CT (GE DMI PET/CT; n = 83 subjects), and Scanner2, an older-generation analog PET/CT (GE STE; n = 123 subjects). Set1, the data set from Scanner1, was reconstructed with standard clinical parameters (5 min; Q.Clear) and list-mode reconstructions (VPFXS 2, 3, 4, and 5-min). Set2, data from Scanner2 representing out-of-domain clinical scans, used standard iterative reconstruction (5 min; OSEM). A deep neural network was trained with each dataset: Network1 for Scanner1 and Network2 for Scanner2. DL performance (Network1) was tested with out-of-domain test data (Set2). To evaluate the effect of training sample size, we tested DL model performance using a fraction (25%, 50% and 75%) of Set1 for training. Scanner1, list-mode 2-min reconstructed data demonstrated the most similar noise level compared that of Set2, resulting in the best performance (F1 = 0.713). This was not significantly different compared to the highest performance, upper-bound limit using in-domain training for Network2 (F1 = 0.755; p-value = 0.103). Regarding sample size, the F1 score significantly increased from 25% training data (F1 = 0.478) to 100% training data (F1 = 0.713; p < 0.001). List-mode data from modern PET scanners can be reconstructed to better match the noise properties of older scanners. Using existing data and their associated annotations dramatically reduces the cost and effort in generating these datasets and significantly improves the performance of existing DL algorithms. List-mode reconstructions can provide an efficient, low-cost method to improve DL algorithm generalizability.

Automated liver lesion detection in 68Ga DOTATATE PET/CT using a deep fully convolutional neural network.

BACKGROUND: Gastroenteropancreatic neuroendocrine tumors most commonly metastasize to the liver; however, high normal background 68Ga-DOTATATE activity and high image noise make metastatic lesions difficult to detect. The purpose of this study is to develop a rapid, automated and highly specific method to identify 68Ga-DOTATATE PET/CT hepatic lesions using a 2D U-Net convolutional neural network. METHODS: A retrospective study of 68Ga-DOTATATE PET/CT patient studies (n = 125; 57 with 68Ga-DOTATATE hepatic lesions and 68 without) was evaluated. The dataset was randomly divided into 75 studies for the training set (36 abnormal, 39 normal), 25 for the validation set (11 abnormal, 14 normal) and 25 for the testing set (11 abnormal, 14 normal). Hepatic lesions were physician annotated using a modified PERCIST threshold, and boundary definition by gradient edge detection. The 2D U-Net was trained independently five times for 100,000 iterations using a linear combination of binary cross-entropy and dice losses with a stochastic gradient descent algorithm. Performance metrics included: positive predictive value (PPV), sensitivity, F1 score and area under the precision-recall curve (PR-AUC). Five different pixel area thresholds were used to filter noisy predictions. RESULTS: A total of 233 lesions were annotated with each abnormal study containing a mean of 4 ± 2.75 lesions. A pixel filter of 20 produced the highest mean PPV 0.94 ± 0.01. A pixel filter of 5 produced the highest mean sensitivity 0.74 ± 0.02. The highest mean F1 score 0.79 ± 0.01 was produced with a 20 pixel filter. The highest mean PR-AUC 0.73 ± 0.03 was produced with a 15 pixel filter. CONCLUSION: Deep neural networks can automatically detect hepatic lesions in 68Ga-DOTATATE PET. Ongoing improvements in data annotation methods, increasing sample sizes and training methods are anticipated to further improve detection performance.