Lianxin Medical Expands AI Beyond Diagnostic Assistance to Oncology Treatment, Deployed in Over 10 Hospitals Ahead of IPO

With the current state of artificial intelligence (AI) development, I believe most industry professionals are quite familiar with it. According to VCBeat’s database, there are 20 domestic medical AI companies engaged in AI-assisted diagnosis for medical imaging. We frequently encounter news headlines such as “Empowering Dermatological Diagnosis: China’s First AI-Assisted Diagnostic System for Skin Diseases Released” and “How Was a 92.5% Diagnostic Accuracy Rate for Breast Cancer Achieved?”

Artificial intelligence indeed plays a significant role in the field of assisted diagnosis, butLianxin Medical, however, has chosen to apply artificial intelligence in the field of adjuvant cancer therapy.By providing more precise, intelligent, and efficient personalized clinical radiotherapy plans, we aim to improve the cure rate of cancer through radiotherapy, reduce damage to normal tissues, and ultimately extend the lives of cancer patients. Currently, Lianxin Medical's products are being used in more than 10 top-tier tertiary hospitals and have received support from Guoke Jiahe., Anlong Fund andA $12 million angel financing round co-invested by Xike Angel Fund.

Zhang Hua, founder of Lianxin Medical, stated in an interview with VCBeat (WeChat ID: vcbeat): “Once a patient is diagnosed with a tumor, they are often overwhelmed by panic; even the slightest physical change prompts them to consult their physician, whereas renowned”Oncology Department of a Grade A Tertiary HospitalIt is often overcrowded. In addition to clinical duties, physicians are burdened with other responsibilities such as scientific research. Consequently, they may become frustrated when faced with endless questions from patients.

Oncologist at Primary Healthcare Institutions“Lacking experience, they are often hesitant to devise treatment plans for patients and have no choice but to refer them elsewhere, which further exacerbates the doctor-patient tensions at tertiary hospitals. Therefore, leveraging new technologies to enhance physicians’ efficiency and improve the clinical competence and confidence of primary care providers is a key priority for hospitals—and precisely what Lianxin Medical is undertaking.”

When asked by reporters why artificial intelligence technology is being applied to tumor treatment rather than diagnosis, Zhang Hua stated that compared to diagnosis,Treatment Goes to the Core of Healthcare. Two tasks consume a significant amount of physicians’ time and energy during the course of tumor treatment., namely target volume delineation and treatment planning。

According to VCBeat, each cancer patient has around 200 CT images, and doctors need to annotate the organs and tumor locations on each image during the delineation process.This process traditionally takes physicians 3–5 hours., after locating the tumor, the physician must also design a specific radiation therapy plan or surgical approach based on the tumor’s size, shape, and other characteristics; this includes varying radiation doses for different anatomical locations.

If all goes well, the patient is treated according to the doctor’s initial plan, improves, and ultimately recovers. However, things do not always go as planned. In some cases, the first course of treatment proves ineffective (with less than a 30% reduction in tumor tissue) due to inaccurate delineation of the target volume or changes in the tumor. In such situations, the treatment plan must be adjusted, requiring the physician to re-delineate the targets and develop a new plan for the patient.

Zhang Hua told VCBeat that the average waiting time for cancer patients in China is two to three weeks. When doctors devote their time to one patient, others must continue to wait, which may result in missing the optimal treatment window.

Although target volume delineation and treatment plan design require a certain level of technical expertise and experience, these labor-intensive tasks are precisely where artificial intelligence excels. Leveraging AI for these processes will significantly save oncologists' time.

The Oncology Information System integrates and consolidates data generated by various independent subsystems and stages throughout the cancer treatment process, enabling control and management of oncology care workflows while simultaneously facilitating quality control within the oncology department. The general workflow is as follows:

The system automatically generates imaging studies, such as CT scans, based on the specific cancer type. It then employs image recognition and AI technologies to automatically delineate the corresponding target volumes using the CT images. After the system generates a detailed radiotherapy plan or surgical plan, it is submitted to physicians for final confirmation. To ensure quality control, the system provides end-to-end tracking of the aforementioned processes, as well as subsequent treatment and diagnostic outcomes.。

Before the hospital had this system,, the physician downloads the patient data after a 2-3 week wait, spends 3-5 hours delineating the target volume, and then devotes additional time to designing the treatment plan.After Using the System, the data downloaded by physicians includes target volumes automatically delineated by the system, along with radiotherapy or surgical plans. Physicians need only to modify and correct them as necessary.

Zhang Hua stated that Lianxin Medical has relatively mature technologies in the treatment of breast cancer, nasopharyngeal cancer, lung cancer, and liver cancer, with an overlap rate of over 80%-87% between the automatically delineated target volumes and those manually delineated by physicians.。

When using this system, primary care physicians who are uncertain about the treatment plans and delineated target volumes provided by the machine do not readily draw conclusions.At this point, they can leverage Lianxin Medical’s remote treatment system to transmit data to specialists at tertiary hospitals. Zhang Hua stated that they would receive a response within 24 hours.。

Since the launch of Lianxin Medical’s products at the beginning of the year, more than 10 hospitals have adopted their solutions, and the remote system has served over 50 patients. Zhang Hua stated that the total number of patients served by these hospitals has not yet been tallied. Physicians have spoken highly of the system, confirming that it has indeed helped them resolve many issues, as promoted by Lianxin Medical. However, doctors have also offered three suggestions to Lianxin Medical in hopes of further improvements.

1. The operation and interaction interface is somewhat complex; we hope it will be optimized as soon as possible;

Second, the computational speed is still insufficient. If a physician needs to adjust the treatment plan and redraw the target volume, the system requires more than 30 minutes, whereas physicians expect it to be completed within 5–10 minutes;

3. Compatibility: Currently, the Lianxin Medical product exhibits excellent compatibility when accessed via Google Chrome, but performance is suboptimal on other browsers.

Zhang Hua told VCBeat that Lianxin Medical’s current system does indeed have these three issues, but solutions are already in place. The user interface and interaction design are being optimized and will be updated soon; these issues, along with compatibility concerns, are relatively easier to resolve. Regarding the second issue, Zhang Hua stated that it is a technical challenge.They have signed technology licensing agreements with the University of Texas Southwestern Medical Center and the U.S. National Institutes of Health (NIH)., this issue will be resolved by the end of this year, at which point the speed will be more satisfactory to physicians.