Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model

The scope of the research is to develop an artificial intelligence AI model that makes use of a hybrid deep learning technique of object detection and classification backbones for defining the protozoa trypanosome specie, namely trypanosoma cruzi, T.brucei, and T.evansi, from oil immersion, microscopic images on the in-house, low-code AI platform CiRA CORE. The most recent development in our field of research is the development of the learning algorithms that can identify and classify trypanosome species from microscopic images. This program has the potential to revolutionize the surveillance and control by providing a rapid automated and accurate screening method that can be used by local staff in remote areas.

Using the modified and hybrid algorithms between two different deep learning models within the purpose AI program can overcome many challenges. Identification of shared morphology, mixed and immature infection, and precise species characterization enables automatic standard taxonomy. To begin, move the DeepTrain function from the general toolbar onto the screen to initiate data labeling and training.

Click on the Load Images button within the DeepTrain tool settings and navigate to the directory containing the images to import and label images. Then click and hold the left mouse button to label the objects and assign names to the selected objects. Click Save GT to save a gt file in the same directory.

Before starting the model training, click the Gen Setting button to access data augmentation features. Utilize four types of augmentations, namely rotation, contrast, noise, and blur, to enrich the dataset. To begin the model training, click on the Training button located within the DeepTrain tool.

In the Generate Training Files function, choose the models, batch size, and subdivisions. Click the Generate button to generate data and save it in the directory. After configuring all settings, click the Train button to initiate the model training.

The program will automatically execute and adjust the dataset weight while it assesses the training loss. Upon achieving optimal loss, click the Export button and save the weight file in the directory. To proceed with object detection model evaluation, select Evaluate in the plugin toolbar and move the EvalDetect function onto the screen.

Afterward, click on the Setting button. Wait for the three functions, Detection, Evaluate, and Plot, to appear. To start the model evaluation, click the Load Config button and import the trained weight file from the directory.

To import test images from the image file directory, click the Browse button. Then click on the Load GT button to import the gt file. Next, click the Evaluation button to assess the detection model in the directory.

Upon completion, the results will be automatically saved as a csv file in the same directory sorted by class name, containing key parameters, such as true positive, false positive, false negative, recall, and precision for each class. To generate the precision recall or PR curve, navigate to the Plot function. Click on Browse to import the csv files from the directory.

Select the desired classes from the list and click the Plot button to visualize the PR curve. Click on the save button to save an image with AUC values of the PR curve in the required image format at the selected directory. To select the Image Classification Model Training function, navigate to the image toolbar, select DeepClassif, and move ClassifTrain onto the screen.

To import images for training, click on the open folder button within the ClassifTrain tool settings and navigate to the directory containing the images. Before training, enrich the dataset by clicking on the Augmentation button and applying techniques such as rotation, contrast, flipping, noise, and blur. To initiate the model training process, click the GenTrain button within the ClassifTrain tool.

Under GenTrain, select the desired models, batch size, and subdivisions. Assign a directory to save the generated data and click the Generate button. Once all configurations are complete, click on the Start button.

The program will run continuously assessing the training loss and adjusting the weight of the dataset as needed. Upon achieving the desired loss level, click the Export button and store the weight file in the specified directory. To begin, navigate to the plugin toolbar.

Then drag and drop the EvaluateClassif function onto the screen. Click on the Evaluate button located within the EvaluateClassif tool. Click the Load folder image button to import test images and Load Config to import the trained weight file from the directory.

Then click the Start button to evaluate the classification model. After evaluation, click the Export to CSV button to save the results as a csv file in the directory. To evaluate data at every threshold, click on the Start all threshold to save the csv file in the directory with class names, including parameters such as recall, true positive rate, false positive rate, and precision for each class.

To plot the receiver operating characteristics curve, click on the Plot ROC button located within the EvaluateClassif tool. Click on the Browse button and import the csv files from the directory. Inspect the imported class list and select each class label to plot the ROC curve.

Next, to visualize the ROC curve, click on the Plot button. Make any desired adjustments to the image properties, such as font size, font colors, rounding decimals, line styles, and line colors. Finally, click the Save button to save the ROC curve image with the AUC values in the required image format in the directory.

To begin, navigate to the general toolbar, click on ButtonRun, then click Debug to start the hybrid testing model. Next, move to the image toolbar, choose Acquisition, and select ImageSlide. Go to DeepComposite and click on DeepD-C.

Before beginning the testing phase for the images, click on the Setting option available in the ImageSlide tool and import the test images. Then click the Setting option in the DeepD-C tool to import the two saved trained weight files. For the Detect function, click on the Config button, Plus button, and select the backend CUDA or CPU.

Provide a name and click OK.Select the weight file directory and click Choose. For the Classif function, click the Config button, followed by the Plus button, and then select the backend. Provide a name and click OK.After this, select the directory for the weight file and click Choose.

To view the test image results, click on the Image function available in the Debug tool. Lastly, to evaluate the predicted results for each image, click on the Run button found in the ButtonRun tool.