“I was particularly impressed with the company’s mission to save lives. I think it’s more rewarding to work in the medical field to save other people, like doctors.


So said Joseph Witanto, 27, Deputy Director of Research and Development (R&D) at Medical IP, in a recent interview with Korea Biomedical Review.


Witanto comes from Indonesia where he obtained a bachelor’s degree in computer engineering from the Christian University of Petra. He then came to Korea to pursue a master’s degree in computer engineering at Dongseo University, Busan in 2017. After graduation, he joined Medical IP where he built his career for about three and a half years.


Medical IP R&D Deputy Director Joseph Witanto poses in front of the company logo during a recent interview with Korea Biomedical Review.


Revealing what inspired him to pursue a degree in computer science, he shared, “Computer has always been the subject I felt most confident about and could enjoy the most. Since the Internet was developing rapidly at that time, jobs in the field of web development and programming became more attractive to me. Furthermore, he pointed out the important role his parents played in his decision to come to Korea to pursue his studies in computer engineering, as Korea was and still is a leader in this field.


Although Witanto’s research in Busan has focused on general applications of artificial intelligence (AI), Witanto has revealed his reason for choosing medical IP.


“My manager recommended this company to me and I was particularly impressed with their mission to save lives. Although many industries need AI, I think it’s more rewarding to work in the medical field to save other people, like doctors.


Joseph described a typical workday in the R&D department that starts with checking the progress of training the deep learning algorithm which is often left running overnight. After the network is fully formed, it then proceeds to validation and then writes a report to contribute to the method and results of joint research with domestic and foreign universities.


“During our weekly meetings, each member of our team usually takes turns sharing an interesting journal article, similar to a lab environment.”


Due to the medical nature of the work, he mentioned, “it’s quite refreshing to collaborate with medical practitioners and not just computer engineers to receive suggestions on how best to segment the liver or diagnostic criteria. appropriate”.


On the other hand, he admitted that the work can get quite tedious when debugging the network while training the algorithm. Despite this, he reaffirmed that it is a very enriching experience to finally arrive at the final result.


Asked about the advantages and disadvantages of Korea’s medical AI industry, Witanto explained that deep learning usually requires large amounts of data, but due to the medical system and public health insurance Korea’s well-developed, accumulation of large data sets is not as difficult. He added: “So it’s easy to see the fruits of my labor directly translated into real clinical use in hospitals.”


For example, his company is well known for creating “digital twins” from scans of actual medical images of patients. This can help doctors rehearse surgical plans more accurately and patients can better understand surgical risk. It also helps medical students better understand difficult medical concepts. Witanto also said, “It’s quite exciting to work here because of the tremendous amount of research being carried out continuously in the field of medical AI in Korea.”


Regarding the disadvantages of Korea’s medical AI industry, he mentioned that while the Korean government strives to protect patients’ personal information, there are strict regulations that sometimes make it difficult to access. to the required data. “However, with Medical IP’s extensive connections, we can get the necessary data from our internal connections at the hospital, such as the CMO of Medical IP who works at SNUH.” He was quick to note that while this is an inconvenience for developers like Witanto, it is necessary to protect the privacy of patient data.


Regarding the difficulties of working in a Korean environment, he replied, “Because my team is more technical, there are no strict language requirements, especially since 90% of the work is programming.” Still, he was quick to add that knowing Korean is beneficial for effective communication with other professors, researchers and teammates.


Moreover, Witanto said he was not the only foreigner with two other Indonesians in his company, including one in his team. However, he modestly admitted that there are no language barriers within his team as he learned the language before coming to Korea. Impressively, he has achieved the highest level of proficiency in Korean, but all of his Korean proficiency is self-taught as he has never taken any Korean classes except the Korean Immigration and Absorption Program. (KIIP).


Referencing his greatest accomplishments within the company, he quickly commented on his contributions in four articles with Medical IP.


Specifically, he said he was proud of his international conference paper submitted for the Radiological Society of North America (RSNA), as his team managed to meet a tight deadline.


This was particularly memorable for Witanto as he was able to attend the conference in Chicago and attend informative seminars just before the Covid-19 pandemic pushed webinars.


Regarding future plans, Witanto has expressed its desire to continue contributing to the global medical industry through verified research on medical deep learning network with Medical IP.


“I think the possibilities with the convergence of medical data and deep learning networks are endless, so I’m excited to see where this career can take me in the next five to ten years.” remarked Witanto enthusiastically.


Source link