Using AI to Macrodissect: a New AI Clinical Way AI is Helping

Indica Labs introduces Lung Macrodissect AI, transforming tumour content assessment and macrodissection in molecular pathology with AI precision.

Indica Labs, a leader in AI-powered digital pathology solutions, has announced the launch of Lung Macrodissect AI, a tool designed to revolutionise slide macrodissection and molecular pathology workflows. This tool aims to be a significant advancement in integrating artificial intelligence with digital pathology, offering pathologists a streamlined workflow that minimises human error and enhances efficiency.

Lung Macrodissect AI fits into a market that has been historically dominated by manual methods of tumour content estimation and macrodissection. Traditional approaches involve labour-intensive and error-prone processes, where pathologists manually annotate tumour regions on slides using a pen and a light microscope. These annotations guide technicians in removing the specified areas from unstained serial sections of the same paraffin block.

Advanced techniques like laser capture microdissection provide higher precision but are costly and require significant technical expertise. These methods, although precise, are less accessible for routine use in many pathology labs due to their high costs and the need for specialised training.

Lung Macrodissect AI offers a middle ground, providing the precision and consistency of advanced methods while being more accessible and less labour-intensive than manual processes. The integration of this AI-powered tool into HALO AP®, Indica Labs’ enterprise digital pathology platform, and its potential combination with the Tissector robotic macrodissectors from Xyall, create a fully automated and auditable workflow. This not only enhances accuracy and operational efficiency but also frees pathologists to focus on more complex diagnostic tasks.

Indica Labs presents Lung Macrodissect AI as standardising tumour content assessment, reducing subjectivity and errors, and provides real-time data on tumour cell quantity within annotated regions. Clinical validation involved 317 primary and metastatic whole slide images, comparing tumour content estimations by five pathologists with and without AI assistance. The results indicated significant improvements in agreement and consistency when using the AI tool. Without AI, the consistency between pathologists (ICC) was low at 0.45, and the agreement measure (Fleiss’ kappa) was 0.27. With AI assistance, the ICC score increased to 0.75, and the Fleiss’ kappa statistic rose to 0.66, indicating a substantial improvement.

Additionally, Indica Labs asserts that by highlighting cancerous tissue and calculating tumour cell counts within annotated regions of interest (ROIs), Lung Macrodissect AI ensures that only adequately concentrated specimens are sent for expensive downstream genetic sequencing and molecular testing. This standardisation improves the quality and reliability of macrodissection workflows, enhancing overall efficiency.

If Lung Macrodissect AI performs as described, its impact on pathology practices could be impressive. The reduction in manual labour and human error could lead to more consistent and reliable results, ultimately improving the accuracy of downstream molecular analyses. This would not only enhance diagnostic precision, but also potentially improve patient outcomes by ensuring that the most accurate data guides treatment decisions.

Furthermore, the integration of Lung Macrodissect AI with robotic macrodissectors like the Tissector from Xyall could streamline workflows in pathology labs, making high-throughput, precise macrodissection more feasible. This could reduce turnaround times for diagnostic tests and free up pathologists and technicians to focus on more complex and critical tasks, thereby increasing overall laboratory efficiency.

For more information, you can see more about Indica Labs’ Lung Macrodissect AI at the link.