Identification of diatom taxonomy by a combination of region-based full convolutional network, online hard example mining, and shape priors of diatoms.

Diatom test is one of the commonly used diagnostic methods for drowning in forensic pathology, which provides supportive evidence for drowning. However, in forensic practice, it is time-consuming and laborious for forensic experts to classify and count diatoms, whereas artificial intelligence (AI) is superior to human experts in processing data and carrying out classification tasks. Some AI techniques have focused on searching diatoms and classifying diatoms. But, they either could not classify diatoms correctly or were time-consuming. Conventional detection deep network has been used to overcome these problems but failed to detect the occluded diatoms and the diatoms similar to the background heavily, which could lead to false positives or false negatives. In order to figure out the problems above, an improved region-based full convolutional network (R-FCN) with online hard example mining and the shape prior of diatoms was proposed. The online hard example mining (OHEM) was coupled with the R-FCN to boost the capacity of detecting the occluded diatoms and the diatoms similar to the background heavily and the priors of the shape of the common diatoms were explored and introduced to the anchor generation strategy of the region proposal network in the R-FCN to locate the diatoms precisely. The results showed that the proposed approach significantly outperforms several state-of-the-art methods and could detect the diatom precisely without missing the occluded diatoms and the diatoms similar to the background heavily. From the study, we could conclude that (1) the proposed model can locate the position and identify the genera of common diatoms more accurately; (2) this method can reduce the false positives or false negatives in forensic practice; and (3) it is a time-saving method and can be introduced.

[Deep learning network-based recognition and localization of diatom images against complex background].

ObjectiveWe propose a deep learning network-based method for recognizing and locating diatom targets with interference by complex background in autopsy.MethodThe system consisted of two modules: the preliminary positioning module and the accurate positioning module. In preliminary positioning, ZFNet convolution and pooling were utilized to extract the high-level features, and Regional Proposal Network (RPN) was applied to generate the regions where the diatoms may exist. In accurate positioning, Fast R-CNN was used to modify the position information and identify the types of the diatoms.ResultsWe compared the proposed method with conventional machine learning methods using a self-built database of images with interference by simple, moderate and complex backgrounds. The conventional methods showed a recognition rate of diatoms against partial background interference of about 60%, and failed to recognize or locate the diatom objects in the datasets with complex background interference. The deep learning network-based method effectively recognized and located the diatom targets against complex background interference with an average recognition rate reaching 85%.ConclusionThe proposed method can be applied for recognition and location of diatom targets against complex background interference in autopsy.