Error using trainFaste​rR​CNNObje​ctD​etecto​r

I'm currently using the example code under object detection using faster RCNN, for localizing and classifying the lung ROI in grayscale chest x rays. The input image dimensions are 224 by 224 while the object (lung) spans almost 3/4 of the entire image i.e. the bounding box would be of dimensions 180*180 to 200*200 approximately. As mentioned in the example, for detection tasks, the CNN needs to analyze smaller sections of the image, so the input size must be similar in size to the smallest object in the data set. In my dataset, the lung ROI is at least [180 180], so I selected an input size of [224 224 1] for the custom CNN. I used ('NegativeOverlapRange', [0 0.3], 'PositiveOverlapRange', [0.6 1], 'NumRegionsToSample', 128, 'BoxPyramidScale', 1.2) for this task. However, when I run the code, i get the following error:

Error using vision.internal.cnn.fastrcnn.RegionReader (line 146) Unable to find any region proposals to use as positive or negative training samples.

What input parameters and training options do you suggest for my image and object dimensions?

Also kindly suggest what input parameters and training options I need to use for the pretrained models like Alexnet and VGG16 for the current task. Your assistance is highly appreciated.