One of the most common problems in hydroponic farming is tip-burn stress of the leafy vegetables, which is defined as yellowed tips on younger leaves. It is frequently caused by a calcium deficit and made worse by poor transpiration circumstances. In this paper, we proposed a novel approach using convolutional neural networks (CNNs) to identify tip-burn stress in lettuce cultivated indoors. To this end, a strong dataset of 3800 images from our own hydroponic farm with different lighting and backgrounds are collected. The deep learning method is trained on the extensive dataset for 100 epochs using a custom-designed CNN model. With a remarkable 98% classification accuracy for tip-burn instances and a respectable 95% classification accuracy for healthy leaves, the performance of the proposed model was analyzed by a confusion matrix which shows its remarkable effectiveness in classifying the tip-burn and healthy lettuce leaf. This deep learning-based lettuce tip-burn detection method has the potential to enhance disease identification and lettuce crop management in indoor situations.