In recent years, advancements in technology and emphasis on precision medicine have paved the path for the development of artificial intelligence (AI) based techniques to enable quantitative and qualitative assessment of pathology samples. Specifically, AI-based digital pathology allows scanning of slides via computer monitors, replacing the conventional microscopic approaches. Further, by converting glass slides to images, samples can be transmitted from diagnostic centers to pathologists, within a fraction of the time taken through conventional approaches. It is worth mentioning that the integration of AI in pathology workflow has significantly enhanced the understanding of tissue micro-environment. In fact, AI-based digital pathology enables identification of optimal treatment plans based on patient profiles, by utilizing digital methods for patient classification and selection of diagnostic tests. Moreover, AI has lately had an unprecedented influence on medicine and can have a significant impact in pathology. Given the massive amount of data generated in the pathology sector, AI may present an opportunity for all related subdomains to innovate and offer a revolutionary care delivery model in both imaging and non-imaging applications.Owing to the considerable advantages (some of which have been mentioned above) over conventional approaches in the field of pathology, AI-based digital pathology market has witnessed a significant growth in the past few years and these solutions have become very popular across research, development and clinical practices.
Applications of AI-based Digital Pathology Solutions
The different applications of AI-based digital pathology solutions have been depicted in the image below.
- Diagnosis: In recent years,numerous diagnostic AI tools have been developed. Industry players aim to make tools that enable histological diagnosis, which is comparable to pathologists, as well as provide insights that pathologists may find difficult to recognize. Other significant advantages of using AI in diagnosis include accurate assessment of quantitative features (such as immunohistochemical biomarker assessment and counting cells) and evaluation of degree of various tissue features (such as spatial arrangement of cells, density of structures, pattern of distribution and architecture of the tissue).
- Prognostic and Predictive Applications: The ability to anticipate a patient’s prognosis and responsiveness to a particular therapy based on morphological features is one of the most promising applications of AI in pathology. Although, very few well-known pathological characteristics (such as tumor grade) have been demonstrated to have prognostic value, as the direct correlation between pathology images and a variety of features (including surrounding microenvironment and genetic profiles)are still majorly unexplored. However, recent AI-based digital pathology techniques have been used in cancer staging to perform diagnostic, prognostic and therapy prediction-related tasks. Further, AI techniques have the ability to transcend constraints of traditional tumor, nodes and metastases (TNM) staging and tumor grading methodologies, thereby, offering a direct prediction of cancer prognosis, regardless of the tumor stage or grade.
- Patient Genomics / Genetic Profiles: AI tools intended for pathological applications have been observed to be capable of linking morphological traits to genetic / genomic profiles of tumors; this ability of AI-based tools has garnered a lot of attention from industry stakeholders. To provide more context, this ability is important for comprehending the biological principles underlying cancer development and selecting targeted therapy. Determining the relationship between morphological traits and tumor genetic profiles, or predicting molecular changes based on morphological aspects, appears to be an effective strategy for cancer diagnosis.
- Workflow Effectiveness: In order to enhance patient management systems, advancement of pathology services is a major concern that needs to be dealt with, in the healthcare domain. As cellular pathology services become increasingly digitized, the use of AI becomes conceivable and possibility for boosting service efficiency via the use of various AI tools has become more essential than ever before. AI applications could benefit pathology services in a number of ways, including reduced human error in specimen handling and processing, faster turnaround times, workload management, quality control and quality assurance measures, automatic requests for relevant tests in certain cases, and automatic reporting.
- Training and Education: Historically, textbooks, glass slides and traditional microscopy were used to provide pathology instructions and training. The amount of web-based pathology resources has grown rapidly over the past two decades, with centralized pathological materials being supplied to many students. AI tools also offer annotations and other interactive features, which can be used to train the future generation of pathologists. Further, diagnostic AI tools may be utilized to assist pathology trainees and biological professionals, with primary reporting. Such instructional models will supplement the traditional educational procedures offered by professionals, at least in the early transitional phase and will supply vital information resources. This incorporation of AI tools into the reporting workflow can provide trainees with additional information, such as list of differential diagnoses and potential auxiliary tests that can be requested, the level of difficulty and subjectivity of diagnosis, as well as the relevant educational resources, all of which can potentially improve their training.
AI-based Digital Pathology: Regulatory Requirements
The FDA, the European Medicines Agency (EMA) and other regulatory organizations have developed a framework for AI-based digital pathology software and devices. To ensure the strictness and consistency of the given metrics, the regulatory framework suggests ways for assessing the performance of image-based AI systems. For instance, at present, WSI scanners are approved for use in the European Union under the European Commission Directive 98/79/EC for in-vitro diagnostic use. Further, the CE mark for in vitro diagnostic devices may be issued to digital pathology software, including WSI viewers or automatically generated image analysis tools. In addition, conformity is primarily dependent on the manufacturer’s self-declaration. Currently, several scanners and accompanying software are currently CE-IVD labelled (including Philips, Roche / Ventana, Leica / Aperio, Hamamatsu and 3DHISTECH). Furthermore, according to the European parliament’s new in-vitro diagnostic medical device legislation (IVDR), all in-vitro medical devices, including slides canners and digital pathology software, must apply for CE-marking, as of May 2022. It is worth mentioning that, in US, only two WSI platforms have received FDA approval for primary surgical pathology (histopathological diagnosis). Previously, in 2017, the Philips IntelliSite became the first received the first digital pathology solution to receive FDA clearance. It is a closed system that includes a scanner / image management system, as well as display. A digital pathology module by Sectra, in combination with Leica Biosystems’ scanner AT2 DX, which was FDA authorized in May 2020, is the second platform to have received FDA clearance for primary diagnosis.
Challenges Associated with Use of AI in Digital Pathology
Although AI technologies hold great potential for the healthcare sector, there are still significant obstacles to overcome. The concern associated with use of AI in digital pathology includes difficulty in fully automating the diagnostic / clinical route and potential of AI to be generalized in clinical practices. In fact, installing an AI-based digital pathology model is more than just a software component. Workflow design, data streaming, storage and interaction with other information systems are all required while installing such models. Leadership support is also one of the key operational success indicators for implementing and deploying decision support systems. These include enterprise leadership, professional pathologists to deploy and utilize AI-based digital pathology to validate results, students in academic centers, skilled laboratory personnel for all pre-analytical procedures, and a competent information technology staff that is essential for ensuring the data is properly transformed for processing. In addition to this, medical and legal issues surrounding responsibility and liability for decisions made or supported by machines is difficult. Furthermore, manufacturers of AI-capable instruments are currently facing multiple regulatory issues, and the requirement to demonstrate reproducibility and accuracy on sizable patient populations that contain outliers and non-representative individuals may present challenges for AI development.
The digital revolution of pathology is projected to accelerate in the coming years, considering multiple growth drivers, including growing number of laboratories adopting high throughput digital scanning and software technologies to assist diagnostic practice. In addition, factors, including shortage of skilled pathologists in remote areas, increasing pathology workloads due to ageing populations, higher rate of cancer screening programs, rising complexity of pathology testing and time constraints, and requirement for pathology labs to outsource expertise in the field, also contributes significantly towards the need for AI-based digital pathology solutions.
Moreover, the same driving forces are pushing the development of AI-based digital pathology to assist pathologists with diagnostic issues that they confront in the present scenario. By incorporating AI-based digital pathology technologies into clinical processes, possible savings may be realized, in terms of turn-around times, as well as patient outcomes, which are enabled through better detection and repeatability. Such advancements are expected to play a significant role in increasing the overall quality of AI-based digital pathology solutions. Given the aforementioned characteristics, we anticipate that the AI-based digital pathology industry will experience substantial growth over the next decade.
Roots Analysis is a global leader in the pharma / biotech market research. Having worked with over 750 clients worldwide, including Fortune 500 companies, start-ups, academia, venture capitalists and strategic investors for more than a decade, we offer a highly analytical / data-driven perspective to a network of over 450,000 senior industry stakeholders looking for credible market insights. All reports provided by us are structured in a way that enables the reader to develop a thorough perspective on the given subject. Apart from writing reports on identified areas, we provide bespoke research / consulting services dedicated to serve our clients in the best possible way.