Clinical case
Our patient is 69-year-old heavy smoker with history of DM, coronary artery disease and kidney transplant. He presented to our hospital because of SOB.
Plain X-ray was performed on 12 October, 2021 and was compared to previous plain film done 4 January 2020. Using AI-Rad Companion chest X-ray software points to faint lung nodule seen on the right midlung zone which was not seen in the previous January 2020 film.
The radiologist recommended CT of the chest as the lesion is recently seen in high-risk patient. CT done on 24 October2021 shows:
• A well-defined nearly rounded lesion is noted along the undersurface of the minor fissure on the right side. The lesion measures about 1.6 x 1.4 cm in largest diameters. The lesion is of soft tissue attenuation with no calcification.
• Enlarged lymph node is seen in the aortopulmonary window measures 2.1 x 1.7 cm in largest diameters. Otherwise no significantly enlarged lymph nodes in the mediastinum. Background of the centrilobular emphysema is identified mainly at upper lobes.
• The impression was suspicious of lung cancer in view of patient’s history of smoking and in the presence of abnormal aortopulmonary lymph node and emphysema. Further evaluation by PET-CT or biopsy was requested.
Discussion
According to experts, the benefits of AI for radiology are numerous.
It can reduce workload by doing tedious tasks like segmenting structures. That can then enable more quantitative imaging, which most believe will improve the ‘product’ of radiology. It can also help to detect lesions that may be subtle, which can be particularly useful when the radiologist is tired or distracted. Finally, we think that it can find information in images that is not perceived by humans. Several ways in which deploying AI within radiology can not only improve healthcare outcomes, but also offer a return on investment for hospitals and private practice groups.
1. Incidental Findings
A truly exciting development within diagnostic imaging is a potential shift from active primary diagnostics due to a patient presenting clinical symptoms to a framework of proactive detection of medical illnesses. Trained algorithms may have the keen capability of assisting radiologists in the detection of pathologies that are outside the primary reason a patient presents to the clinic or emergency room. Incidental findings offer healthcare systems the opportunity to offer the right treatment to the right patient at the right time.
2. Prioritization
A minimal reduction in length of stay for all patients analyzed with an AI-enabled imaging tool may have significant economic benefits on an annualized basis.
3. Improved Workflow and Reading Time
Radiologists work against the clock to deliver accurate diagnostic assessments in a timely manner. At the core of a patient’s workflow and clinical management pathway rests the radiologist’s ability to not only offer a precise diagnosis, but to do so in a timely and efficient manner. The economics of improving workflow and reading time with AI-enhanced algorithms could potentially offer both private practices and hospitals with a lucrative return on investment.