The development of next generation sequencers hasmade it possible to not only sequence germline genomes, but also to identifygenetic mutations in cancer cells. In order to realize cancer genome medicine,it is necessary to accurately identify all the mutations in somatic genomesequences in tumor tisuees. For this purpose, bioinformatics has been playing avery important role in the development of technologies for processing the largeamount of DNA sequence information obtained from next generation sequencers. Inthis review, I would like to introduce the role of bioinformatics in precisionmedicine and the application of artificial intelligence to pathological imagesfor new cancer genomics. In addition, I would like to introduce some importantfactors related to the new aspects of cancer that are needed to make precisionmedicine more precise.

In this paper, I explain the achievements and challenges of second-generation AI in medical image from the standpoint of an engineer and manager, had worked for a medical device company for more than 20 years, followed by the current status of commercialization ofthird-generation AI in the United States and Japan, and how these challenges are being improved as social implementation of AI products accelerates, and also discuss the future direction of medical image AI.

Due to the respiratory diseases such as chronic obstructive pulmonary disease and lower respiratory tract infections nearly 8 million people were died worldwide each year. Reducing the number of deaths from respiratory diseases is a challenge to be solved worldwide. Early detection is the most efficient way to reduce the number of deaths in respiratory illness. As a result, the spread of infection can be suppressed, and the therapeutic effect can be enhanced. Currently, auscultation is performed as a promising method for early detection of respiratory diseases. Auscultation can estimate respiratory diseases by distinguishing abnormal sounds contained in respiratory sounds. However, medical staff need to be trained to perform auscultation with high accuracy. Also, the diagnostic results depend on each staff subjectively, which can lead to inconsistent results. Therefore, in some environments, a shortage of specialized health care workers can lead to the spread of respiratory illness. To solve this problem, an application that analyzes respiratory sounds and outputs diagnostic results is needed. In this paper, we use a newly proposed deep learning model to automatically classify the respiratory sound data from the ICBHI 2017 Challenge Dataset. Short-Time Fourier Transform, Constant-Q Transform, and Continuous Wavelet Transform are applied to the respiratory sound data to convert it into the time-frequency region. Then, the obtained three types of breath sound images are input to CRNN (Convolutional Recurrent Neural Network) having scSE (Spatial and Channel Squeeze & Excitation) Block. The accuracy is improved by weighting the features of each image. As a result, AUC (Area Under the Curve): (Normal:0.87, Crackle:0.88, Wheeze:0.92, Both:0.89), Sensitivity: 0.67, Specificity: 0.82, Average Score: 0.75, Harmonic Score: 0.74, Accuracy: 0.75 were obtained.