Weakly-supervised learning-based pathology detection and localization in 3D chest CT scans.

BACKGROUND: Recent advancements in anomaly detection have paved the way for novel radiological reading assistance tools that support the identification of findings, aimed at saving time. The clinical adoption of such applications requires a low rate of false positives while maintaining high sensitivity. PURPOSE: In light of recent interest and development in multi pathology identification, we present a novel method, based on a recent contrastive self-supervised approach, for multiple chest-related abnormality identification including low lung density area ("LLDA"), consolidation ("CONS"), nodules ("NOD") and interstitial pattern ("IP"). Our approach alerts radiologists about abnormal regions within a computed tomography (CT) scan by providing 3D localization. METHODS: We introduce a new method for the classification and localization of multiple chest pathologies in 3D Chest CT scans. Our goal is to distinguish four common chest-related abnormalities: "LLDA", "CONS", "NOD", "IP" and "NORMAL". This method is based on a 3D patch-based classifier with a Resnet backbone encoder pretrained leveraging recent contrastive self supervised approach and a fine-tuned classification head. We leverage the SimCLR contrastive framework for pretraining on an unannotated dataset of randomly selected patches and we then fine-tune it on a labeled dataset. During inference, this classifier generates probability maps for each abnormality across the CT volume, which are aggregated to produce a multi-label patient-level prediction. We compare different training strategies, including random initialization, ImageNet weight initialization, frozen SimCLR pretrained weights and fine-tuned SimCLR pretrained weights. Each training strategy is evaluated on a validation set for hyperparameter selection and tested on a test set. Additionally, we explore the fine-tuned SimCLR pretrained classifier for 3D pathology localization and conduct qualitative evaluation. RESULTS: Validated on 111 chest scans for hyperparameter selection and subsequently tested on 251 chest scans with multi-abnormalities, our method achieves an AUROC of 0.931 (95% confidence interval [CI]: [0.9034, 0.9557], p $ p$ -value < 0.001) and 0.963 (95% CI: [0.952, 0.976], p $ p$ -value < 0.001) in the multi-label and binary (i.e., normal versus abnormal) settings, respectively. Notably, our method surpasses the area under the receiver operating characteristic (AUROC) threshold of 0.9 for two abnormalities: IP (0.974) and LLDA (0.952), while achieving values of 0.853 and 0.791 for NOD and CONS, respectively. Furthermore, our results highlight the superiority of incorporating contrastive pretraining within the patch classifier, outperforming Imagenet pretraining weights and non-pretrained counterparts with uninitialized weights (F1 score = 0.943, 0.792, and 0.677 respectively). Qualitatively, the method achieved a satisfactory 88.8% completeness rate in localization and maintained an 88.3% accuracy rate against false positives. CONCLUSIONS: The proposed method integrates self-supervised learning algorithms for pretraining, utilizes a patch-based approach for 3D pathology localization and develops an aggregation method for multi-label prediction at patient-level. It shows promise in efficiently detecting and localizing multiple anomalies within a single scan.

Detection and severity quantification of pulmonary embolism with 3D CT data using an automated deep learning-based artificial solution.

PURPOSE: The purpose of this study was to propose a deep learning-based approach to detect pulmonary embolism and quantify its severity using the Qanadli score and the right-to-left ventricle diameter (RV/LV) ratio on three-dimensional (3D) computed tomography pulmonary angiography (CTPA) examinations with limited annotations. MATERIALS AND METHODS: Using a database of 3D CTPA examinations of 1268 patients with image-level annotations, and two other public datasets of CTPA examinations from 91 (CAD-PE) and 35 (FUME-PE) patients with pixel-level annotations, a pipeline consisting of: (i), detecting blood clots; (ii), performing PE-positive versus negative classification; (iii), estimating the Qanadli score; and (iv), predicting RV/LV diameter ratio was followed. The method was evaluated on a test set including 378 patients. The performance of PE classification and severity quantification was quantitatively assessed using an area under the curve (AUC) analysis for PE classification and a coefficient of determination (R²) for the Qanadli score and the RV/LV diameter ratio. RESULTS: Quantitative evaluation led to an overall AUC of 0.870 (95% confidence interval [CI]: 0.850-0.900) for PE classification task on the training set and an AUC of 0.852 (95% CI: 0.810-0.890) on the test set. Regression analysis yielded R² value of 0.717 (95% CI: 0.668-0.760) and of 0.723 (95% CI: 0.668-0.766) for the Qanadli score and the RV/LV diameter ratio estimation, respectively on the test set. CONCLUSION: This study shows the feasibility of utilizing AI-based assistance tools in detecting blood clots and estimating PE severity scores with 3D CTPA examinations. This is achieved by leveraging blood clots and cardiac segmentations. Further studies are needed to assess the effectiveness of these tools in clinical practice.

BERT-based natural language processing analysis of French CT reports: Application to the measurement of the positivity rate for pulmonary embolism.

Rationale and objectives: To develop a Natural Language Processing (NLP) method based on Bidirectional Encoder Representations from Transformers (BERT) adapted to French CT reports and to evaluate its performance to calculate the diagnostic yield of CT in patients with clinical suspicion of pulmonary embolism (PE). Materials and methods: All the CT reports performed in our institution in 2019 (99,510 reports, training and validation dataset) and 2018 (94,559 reports, testing dataset) were included after anonymization. Two BERT-based NLP sentence classifiers were trained on 27.700, manually labeled, sentences from the training dataset. The first one aimed to classify the reports' sentences into three classes ("Non chest", "Healthy chest", and "Pathological chest" related sentences), the second one to classify the last class into eleven sub classes pathologies including "pulmonary embolism". F1-score was reported on the validation dataset. These NLP classifiers were then applied to requested CT reports for pulmonary embolism from the testing dataset. Sensitivity, specificity, and accuracy for detection of the presence of a pulmonary embolism were reported in comparison to human analysis of the reports. Results: The F1-score for the 3-Classes and 11-SubClasses classifiers was 0.984 and 0.985, respectively. 4,042 examinations from the testing dataset were requested for pulmonary embolism of which 641 (15.8%) were positively evaluated by radiologists. The sensitivity, specificity, and accuracy of the NLP network for identifying pulmonary embolism in these reports were 98.2%, 99.3% and 99.1%, respectively. Conclusion: BERT-based NLP sentences classifier enables the analysis of large databases of radiological reports to accurately determine the diagnostic yield of CT screening.