I am training and testing a MaskRCNN model for detecting the anomaly in patterns of brain. The image size is 112*112 (3 channels) and format is .dicom. While testing the model on the actual radiographic images, the result shows blank image with the below warning message.
However, I have checked the standard deviation to check the contrast and intensity of images. Also, I applied Gamma correction and other contrast enhancement with the failed testing images. But, still getting the same issue.
Please help me on this! Do we have any solution to handle such situation in MaskRCNN?
