Skin lesion segmentation using a semi-supervised U-NetSC model with an adaptive loss function.

Skin lesion segmentation is a crucial step in cancer detection. Deep learning has shown promising results for lesion segmentation. However, the performance of these models depends on accessing lots of training samples with pixel-level annotations. Employing a semi-supervised approach reduces the need for a large number of annotated samples. Accordingly, a semi-supervised strategy is proposed based on the high correlation of segmentation and classification tasks. The U - N et Segmentation and Classification model (U-NetSC) is a unified architecture containing segmentation and classification modules. The classification module uses feature maps from the last layer of the segmentation model to increase the collaboration of two tasks. U-NetSC can be trained with only class-level or both class-level and pixel-level ground truth using an adaptive loss function. U-NetSC achieves ~2%, ~ 2%, ~ 3%, and ~ 1 % improvement in Jaccard Index, Dice coefficient, precision, and accuracy, respectively, in comparison with a supervised attention-gated U-Net model. Clinical relevance - The paper proposes an automatic skin lesion segmentation model in a semi-supervised manner. Training the segmentation model is based on a combination of class-level and pixel-level information without requiring a large number of labeled samples.

Chess therapy: A new approach to curing panic attack.

OBJECTIVES: To study the effect of playing cell phone chess game on treating panic attack. METHODS: The chess game on an android cell phone was played by the researcher who was affected by panic attack as a post-traumatic disorder immediately after or before feeling of the start of symptoms. The right level of difficulty, i.e., levels 2-4, was selected for optimal results. RESULTS: Playing chess game on the android cell phone prevented the manifestation of panic attack and led to the cure of this traumatic condition. CONCLUSION: Chess therapy with the right level of difficulty can be recommended as a very effective non-pharmaceutical method for the successful treatment of panic attacks.

Effects of cannabinoid and glutamate receptor antagonists and their interactions on learning and memory in male rats.

INTRODUCTION: Despite previous findings on the effects of cannabinoid and glutamatergic systems on learning and memory, the effects of the combined stimulation or the simultaneous inactivation of these two systems on learning and memory have not been studied. In addition, it is not clear whether the effects of the cannabinoid system on learning and memory occur through the modulation of glutamatergic synaptic transmission. Hence, in this study, we examined the effects of the simultaneous inactivation of the cannabinoid and glutamatergic systems on learning and memory using a passive avoidance (PA) test in rats. MATERIALS AND METHODS: On the test day, AM251, which is a CB1 cannabinoid receptor antagonist; MK-801, which is a glutamate receptor antagonist; or both substances were injected intraperitoneally into male Wistar rats 30min before placing the animal in a shuttle box. A learning test (acquisition) was then performed, and a retrieval test was performed the following day. RESULTS: Learning and memory in the PA test were significantly different among the groups. The CB1 receptor antagonist improved the scores on the PA acquisition and retention tests. However, the glutamatergic receptor antagonist decreased the acquisition and retrieval scores on the PA task. The CB1 receptor antagonist partly decreased the glutamatergic receptor antagonist effects on PA learning and memory. CONCLUSIONS: These results indicated that the acute administration of a CB1 antagonist improved cognitive performance on a PA task in normal rats and that a glutamate-related mechanism may underlie the antagonism of cannabinoid by AM251 in learning and memory.