RiFNet: Automated rib fracture detection in postmortem computed tomography

Artificial intelligence in the practice of forensic medicine: a scoping review

Forensic medicine is a thriving application field for artificial intelligence (AI). Indeed, AI applications intended to forensic pathologists or forensic physicians have emerged since the last decade. For example, AI models were developed to help estimate the biological age of migrants or human remains. However, the uses of AI applications by forensic pathologists or physicians and their levels of integration in medicolegal practices are not well described yet. Therefore, a scoping review was conducted on PubMed, ScienceDirect, and Scopus databases. This review included articles that mention any AI application used by forensic pathologists or physicians in practice or any AI model applied in one expertise field of the forensic pathologist or physician. Articles in other languages than English or French or dealing mainly with complementary analyses handled by experts who are not forensic pathologists or physicians or with AI to analyze data for research purposes in forensic medicine were excluded from this review. All the relevant information was retrieved in each article from a grid analysis derived and adapted from the TRIPOD checklist. This review included 35 articles and revealed that AI applications are developed in thanatology and in clinical forensic medicine. However, those applications seem to mainly remain in research and development stages. Indeed, the use of AI applications by forensic pathologists or physicians is not actual due to issues discussed in this article. Finally, the integration of AI in daily medicolegal practice involves not only forensic pathologists or physicians but also legal professionals.

Deep learning for acute rib fracture detection in CT data: a systematic review and meta-analysis

OBJECTIVES

To review studies on deep learning (DL) models for classification, detection, and segmentation of rib fractures in CT data, to determine their risk of bias (ROB), and to analyse the performance of acute rib fracture detection models.

METHODS

Research articles written in English were retrieved from PubMed, Embase, and Web of Science in April 2023. A study was only included if a DL model was used to classify, detect, or segment rib fractures, and only if the model was trained with CT data from humans. For the ROB assessment, the Quality Assessment of Diagnostic Accuracy Studies tool was used. The performance of acute rib fracture detection models was meta-analysed with forest plots.

RESULTS

A total of 27 studies were selected. About 75% of the studies have ROB by not reporting the patient selection criteria, including control patients or using 5-mm slice thickness CT scans. The sensitivity, precision, and F1-score of the subgroup of low ROB studies were 89.60% (95%CI, 86.31%-92.90%), 84.89% (95%CI, 81.59%-88.18%), and 86.66% (95%CI, 84.62%-88.71%), respectively. The ROB subgroup differences test for the F1-score led to a p-value below 0.1.

CONCLUSION

ROB in studies mostly stems from an inappropriate patient and data selection. The studies with low ROB have better F1-score in acute rib fracture detection using DL models.

ADVANCES IN KNOWLEDGE

This systematic review will be a reference to the taxonomy of the current status of rib fracture detection with DL models, and upcoming studies will benefit from our data extraction, our ROB assessment, and our meta-analysis.

Classification of rib fracture types from postmortem computed tomography images using deep learning

Human or time resources can sometimes fall short in medical image diagnostics, and analyzing images in full detail can be a challenging task. With recent advances in artificial intelligence, an increasing number of systems have been developed to assist clinicians in their work. In this study, the objective was to train a model that can distinguish between various fracture types on different levels of hierarchical taxonomy and detect them on 2D-image representations of volumetric postmortem computed tomography (PMCT) data. We used a deep learning model based on the ResNet50 architecture that was pretrained on ImageNet data, and we used transfer learning to fine-tune it to our specific task. We trained our model to distinguish between "displaced," "nondisplaced," "ad latus," "ad longitudinem cum contractione," and "ad longitudinem cum distractione" fractures. Radiographs with no fractures were correctly predicted in 95-99% of cases. Nondisplaced fractures were correctly predicted in 80-86% of cases. Displaced fractures of the "ad latus" type were correctly predicted in 17-18% of cases. The other two displaced types of fractures, "ad longitudinem cum contractione" and "ad longitudinem cum distractione," were correctly predicted in 70-75% and 64-75% of cases, respectively. The model achieved the best performance when the level of hierarchical taxonomy was high, while it had more difficulties when the level of hierarchical taxonomy was lower. Overall, deep learning techniques constitute a reliable solution for forensic pathologists and medical practitioners seeking to reduce workload.

Artificial Intelligence Model Trained with Sparse Data to Detect Facial and Cranial Bone Fractures from Head CT

The presence of cranial and facial bone fractures is an important finding on non-enhanced head computed tomography (CT) scans from patients who have sustained head trauma. Some prior studies have proposed automatic cranial fracture detections, but studies on facial fractures are lacking. We propose a deep learning system to automatically detect both cranial and facial bone fractures. Our system incorporated models consisting of YOLOv4 for one-stage fracture detection and improved ResUNet (ResUNet++) for the segmentation of cranial and facial bones. The results from the two models mapped together provided the location of the fracture and the name of the fractured bone as the final output. The training data for the detection model were the soft tissue algorithm images from a total of 1,447 head CT studies (a total of 16,985 images), and the training data for the segmentation model included 1,538 selected head CT images. The trained models were tested on a test dataset consisting of 192 head CT studies (a total of 5,890 images). The overall performance achieved a sensitivity of 88.66%, a precision of 94.51%, and an F1 score of 0.9149. Specifically, the cranial and facial regions were evaluated and resulted in a sensitivity of 84.78% and 80.77%, a precision of 92.86% and 87.50%, and F1 scores of 0.8864 and 0.8400, respectively. The average accuracy for the segmentation labels concerning all predicted fracture bounding boxes was 80.90%. Our deep learning system could accurately detect cranial and facial bone fractures and identify the fractured bone region simultaneously.

An automatic fresh rib fracture detection and positioning system using deep learning

OBJECTIVE

To evaluate the performance and robustness of a deep learning-based automatic fresh rib fracture detection and positioning system (FRF-DPS).

METHODS

CT scans of 18,172 participants admitted to eight hospitals from June 2009 to March 2019 were retrospectively collected. Patients were divided into development set (14,241), multicenter internal test set (1612), and external test set (2319). In internal test set, sensitivity, false positives (FPs) and specificity were used to assess fresh rib fracture detection performance at the lesion- and examination-levels. In external test set, the performance of detecting fresh rib fractures by radiologist and FRF-DPS were evaluated at lesion, rib, and examination levels. Additionally, the accuracy of FRF-DPS in rib positioning was investigated by the ground-truth labeling.

RESULTS

In multicenter internal test set, FRF-DPS showed excellent performance at the lesion- (sensitivity: 0.933 [95%CI, 0.916-0.949], FPs: 0.50 [95%CI, 0.397-0.583]) and examination-level. In external test set, the sensitivity and FPs at the lesion-level of FRF-DPS (0.909 [95%CI, 0.883-0.926], p < 0.001; 0.379 [95%CI, 0.303-0.422], p = 0.001) were better than the radiologist (0.789 [95%CI, 0.766-0.807]; 0.496 [95%CI, 0.383-0.571]), so were the rib- and patient-levels. In subgroup analysis of CT parameters, FRF-DPS were robust (0.894-0.927). Finally, FRF-DPS(0.997 [95%CI, 0.992-1.000], p < 0.001) is more accurate than radiologist (0.981 [95%CI, 0.969-0.996]) in rib positioning and takes 20 times less time.

CONCLUSION

FRF-DPS achieved high detection rate of fresh rib fractures with low FP values, and precise positioning of ribs, thus can be used in clinical practice to improve the detection rate and work efficiency.

ADVANCES IN KNOWLEDGE

We developed the FRF-DPS system which can detect fresh rib fractures and rib position, and evaluated by a large amount of multicenter data.

Composite Attention Residual U-Net for Rib Fracture Detection

Computed tomography (CT) images play a vital role in diagnosing rib fractures and determining the severity of chest trauma. However, quickly and accurately identifying rib fractures in a large number of CT images is an arduous task for radiologists. We propose a U-net-based detection method designed to extract rib fracture features at the pixel level to find rib fractures rapidly and precisely. Two modules are applied to the segmentation network-a combined attention module (CAM) and a hybrid dense dilated convolution module (HDDC). The features of the same layer of the encoder and the decoder are fused through CAM, strengthening the local features of the subtle fracture area and increasing the edge features. HDDC is used between the encoder and decoder to obtain sufficient semantic information. Experiments show that on the public dataset, the model test brings the effects of Recall (81.71%), F1 (81.86%), and Dice (53.28%). Experienced radiologists reach lower false positives for each scan, whereas they have underperforming neural network models in terms of detection sensitivities with a long time diagnosis. With the aid of our model, radiologists can achieve higher detection sensitivities than computer-only or human-only diagnosis.