Home

Telepathology in Tanzania: Expanding Access to Expert Cancer Diagnosis Jordan Rosenfeld - June 16, 2026

For years, the pathology department at Kilimanjaro Christian Medical Centre (KCMC) in Tanzania has been understaffed, making it difficult to get specialists to weigh in on certain kinds of cancer diagnoses. 

That began to change in 2018, when a collaboration between the American Society for Clinical Pathology (ASCP), Duke University, and KCMC launched a telepathology consultation platform using whole slide imaging (WSI). This allowed pathologists in Tanzania to digitize slides and securely share them with subspecialty experts in the United States and the Netherlands for remote review.

A recently published study in the American Journal of Clinical Pathology (AJCP) led by ASCP Global Health Fellow, Aisha Mohamed, MD, a third-year pathology resident at the University of Minnesota Department of Lab Medicine and Pathology, found that telepathology improved access to expert consultation, supported education and mentorship, and in many cases changed diagnoses in ways that directly affected patient care. 

Dr. Mohamed says, “This paper also provides a template for other similarly resourced pathology departments to follow. It provides a cost breakdown of the implementation of telepathology at KCMC.”

Building a pathology service with limited resources

Before telepathology, between 2006 and 2015, KCMC’s pathology department did not have a full-time local pathologist. The time between visiting pathologist consultations could range from weeks to months, according to Alex Mremi, MD, PhD, Head of Pathology at KCMC. The staff pathologists also had limited access to immunohistochemistry and subspecialty expertise. “It was challenging and therefore telepathology is very important,” Dr. Mremi says.

While telepathology has been essential in giving “generalists access to subspecialty expertise that otherwise would not have been available,” Dr. Mremi stresses that “telepathology did not replace local pathologists at KCMC.” It enhanced their work.

How whole-slide imaging makes remote consultation possible

Whole slide imaging expands access by scanning traditional glass slides into high-resolution digital images that can be reviewed remotely. At KCMC, laboratory staff use a Motic whole slide imaging system and upload files to a secure cloud-based platform, which can then be shared with consultants abroad. The AJCP study found that 92 percent of the digital images were considered “diagnostically adequate.” 

The WSI and telepathology enables KCMC pathologists to consult pathologists in subspecialties, which Dr. Mremi calls a form of “external quality control but also teaching and networking.” 

Dr. Mohamed adds that “Telepathology offers an avenue for pathologists in high-resourced settings to give back by providing mentorship to junior pathologists abroad and their expertise on challenging cases, without having to cross an ocean.”

Measuring diagnostic agreement across subspecialties

The AJCP study analyzed 1,266 challenging pathology cases submitted for teleconsultation between 2018 and 2025. Researchers compared the local pathologist’s initial diagnosis with the consulting expert’s interpretation to measure concordance, partial concordance, and clinically significant discordance. They found a 44.8 percent full concordance rate, a 19.75 percent partial concordance rate, and a 32.78 percent discordance rate — meaning the expert's diagnosis differed from the local pathologist's enough to have an impact. 

The discordance rate is a likely result of “comparing difficult cases,” Dr. Mremi said. He explains that many of the cases submitted for teleconsultation were especially rare or diagnostically difficult. These were often evaluated using only routine H&E staining without the broader immunohistochemistry or molecular testing panels commonly available in higher-resource settings. “I believe if we also had access to immuno, perhaps the concordance rates would be much improved,” Dr. Mremi says. 

Even so, the study demonstrated that remote consultation could still meaningfully improve diagnostic confidence and help clinicians make more informed treatment decisions.

When a second opinion changes treatment

One of the study’s key findings was that telepathology did improve workflow; turnaround time substantially improved over the study timeline, dropping from pandemic-era highs in 2020 to less than five days in 2025. Additionally, in many cases, an expert consultation of the preliminary report altered or refined the diagnosis, allowing treatment decisions to be adjusted accordingly. 

Dr. Mremi says, “If now we get the feedback which is contrary to the primary diagnosis, then we will update the report accordingly. So that's how the data in the platform can influence the treatment.” 

For patients with cancer or rare tumors, those revised diagnoses could influence everything from surgical decisions to chemotherapy planning.

Mentorship, training, and long-term capacity building

The telepathology platform’s value extended well beyond second opinions. Regular interaction between Tanzanian pathologists and subspecialists abroad created ongoing mentorship, educational exchange, and collaborative research opportunities.

Dr. Mremi says, “we gained a lot of insights from the pathologists who are reviewing our cases.” In particular, he explains, “Having junior pathologists interacting with the very senior, to me, is very much critical for career development, but also [to] improve the services.”

The future of the fellowship

Kenneth Landgraf, MS, Director of the Center for Global Health at ASCP, sees the study as one example of a broader pattern of successful partnerships the Global Health Fellowship produces. “This research demonstrates the long-term collaborative partnerships that are formed through the fellowship program,” he says.

For Mr. Landgraf, the fellowship’s value lies in the mutual exchange it fosters. ASCP fellows and their host pathologists learn from each other, building the kind of practical knowledge and cross-institutional relationships that directly translate to better patient care.

Mr. Landgraf points out that the pathologist workforce shortage in LMIC settings extends beyond raw numbers. Due to limited fellowship training pathways and resources, most pathologists in these settings practice as generalists, with some engaging in subspecialty interest groups as a means of continued learning.

”This study demonstrates that telepathology is a viable model to expand access to advanced subspecialty diagnoses in resource-constrained settings,” he says, “improving patient care and supporting the development of local pathologists along the way.”

Dr. Mremi looks forward to a forthcoming multi-site study with ASCP involving deep learning-aided breast cancer pathology analysis, drawing from low- and middle-income countries (LMIC) cohorts across Africa and beyond.

Additionally, thanks to a recent commitment from the ASCP Foundation, the Global Health Fellowship has secured ongoing annual funding into the foreseeable future, with applications for 2027 opening later this summer. 

What sets the fellowship apart, Mr. Landgraf emphasizes, is that it doesn’t end when the fellow returns home. “It’s not just a month in-country and then forgotten,” he explains. “The relationships continue virtually for months and years ahead.” This study is itself evidence of that: Dr. Mohamed, Dr. Mremi, and Mr. Landgraf have continued collaborating on research for more than a year since the fellowship concluded.

Dr. Mohamed expresses gratitude for her opportunity, not only “to learn from and work with Dr. Mremi and his colleagues at KCMC during my global health fellowship” but also to Mr. Landgraf, “who was another great research mentor.” 

She highly recommends that residents apply for the global health fellowship, which she calls, “A mutually beneficial opportunity where you learn to become a better pathologist by relying on your morphology skills while your host institution will benefit from hearing your perspective on things based on the training you had.”

So long as LMIC settings like Sub-Saharan Africa face understaffing in pathology, Mr. Landgraf sees tools like telepathology as “a way to make sure that patients get the right diagnosis.”

With additional research collaborations and AI-assisted pathology studies already underway, KCMC’s telepathology program may represent the beginning of a broader transformation in cancer diagnostics across low- and middle-income countries.

In Their Own Words: Residency Team Critical Values - June 9, 2026

Third year residents and ASCP Resident Council members, Lauren Miller and Tayler Gant—Chair-Elect—know what the first year of pathology residency is like and have advice for residents at the beginning of their programs.

In this video, they reflect on those first few months of their residencies, share the advice they’d give their first-year selves, the impact a mentor has on your residency experience, and more.

This video was originally published on thepathologist.com in May 2026.

Advancing Cervical Cancer Screening Through Data and AI Jordan Rosenfeld - June 2, 2026

Cervical cancer screening in the U.S. still faces major challenges, including inconsistent reporting and data that does not fully reflect all populations. To address these challenges, the American Society for Clinical Pathology (ASCP), with an inaugural grant from the Alliance for Women’s Health and Prevention (AWHP), spearheaded the Cervical Cancer Screening Collaborative.

Using large-scale, multi-site datasets, and a novel natural language processing (NLP)-based algorithm, the project aims to improve cervical cancer screening accuracy and equity across diverse populations in the U.S.

A preventable cancer still showing troubling gaps

Even with effective screening and HPV testing tools widely available, cervical cancer continues to disproportionately affect women who face barriers to care, particularly women of color and women in rural communities, according to Millicent Gorham, PhD (Hon), MBA, FAAN, Chief Executive Officer of the Alliance for Women's Health and Prevention.

Those disparities reveal a need for a broader and more inclusive understanding of how screening performs across different populations and geographic regions.

“Cervical cancer is one of the most preventable cancers we have,” Dr. Gorham says. Yet advanced cases rising disproportionately among Black and Hispanic women, women in rural communities, and women with limited access to care are “a signal that the system meant to catch this disease early is not reaching everyone it needs to,” she adds.

What also drew AWHP to ASCP’s Cervical Cancer Screening is that much of the U.S.-based evidence informing national screening guidelines comes from a single integrated health system: Kaiser Permanente Northern California. “What we are questioning is whether one health system in one region can tell us what we need to know about cervical cancer screening for every woman in this country. It cannot,” Dr. Gorham says.

Hence their support of research like ASCP’s project, which “broadens the evidence base, so that guidelines, coverage, and access are built on data that reflects the full diversity of women in this country,” Dr. Gorham adds.

A more representative national dataset

The initiative is built upon a large retrospective study drawing data from 10 participating sites across the United States. It combines Pap test results, HPV testing data, and cervical biopsy findings collected over roughly a decade, allowing researchers to analyze screening outcomes longitudinally and across diverse patient populations by age, ZIP code, race, and ethnicity.

Sachin Gupta, PhD, MBA, MLS(ASCPⁱ)MBⁱ, LSSBB, CPHQ, ASCP’s Scientific Director in the Center for Quality and Patient Care, explains that one of the aims of the project is to study how Pap testing diagnostics rates and HPV positivity rates vary across demographics and geographic regions. The project could eventually help validate “whether current screening guidelines are appropriate and up to date or not,” Dr. Gupta says.

By aggregating data from multiple institutions, ASCP hopes to create a broader evidence base that more accurately reflects the populations’ current screening guidelines are intended to serve.

Why cervical biopsy reports are difficult to analyze at scale

Although Pap and HPV test results are often captured in structured fields in a pathology report, cervical biopsy reports frequently exist as narrative “unstructured text,” Dr. Gupta explains, making large-scale analysis and standardized data extraction more difficult.

“The cervical biopsy result can hide within a lengthy description,” Dr. Gupta says. It’s not sustainable to pull these findings out through manual review, “given the rapid growth in documentation and expanding demand for data-driven clinical insights.”

Traditionally, extracting information from these reports would require a person to manually examine patient charts one by one. That process is labor-intensive, and prone to human error, especially when analyzing tens of thousands of pathology reports across multiple institutions.

To address that challenge, ASCP is using their Performance & Diagnostics Insights (PDI) platform and developed an NLP-based approach capable of converting narrative pathology reports into structured, analyzable data. In other words, ASCP developed a tool that can read the pathology reports and automatically sort the information into organized data, making it easier to study and spot patterns across thousands of cases.

Training an NLP model to understand pathology language

Many existing pathology NLP libraries are tissue-specific and do not generalize well to cervical biopsy data, making a custom solution necessary.

“ASCP developed a hybrid framework that integrates deep learning techniques along with BERT (Bidirectional Encoder Representations from Transformers),” Dr. Gupta says. Instead of generating text, the system interprets clinical language and extracts diagnostic information from pathology narratives.

Understanding context is critical because pathologists may phrase findings differently across institutions or reporting styles.

“Every pathologist writes their report a little differently. It’s not a kind of standardized template, so to speak. And a diagnosis can be hidden in a long text string somewhere,” Dr. Gupta says.

The system uses multiple processing steps, including text preprocessing, information extraction, feature engineering, and sentiment analysis, to help interpret the meaning behind narrative pathology language. Rather than simply searching for keywords, the model is trained to understand how pathologists communicate diagnostic findings within clinical context.

Validating the model across multiple health systems

After training and validating the algorithm on more than 10,000 pathology reports from one participating site, ASCP is now applying the model to data from additional institutions. “Our algorithm's performance turned out to be great with superb accuracy and precision and now we are in the process of using it for datasets of additional sites,” Dr. Gupta says.

Each new site introduces differences in reporting structure, formatting, and terminology, giving researchers an opportunity to evaluate how well the model adapts across real-world practice settings.

Shaping quality improvement and future guidelines

Dr. Gupta says the work may help standardize reporting practices and improve researchers’ ability to study incidence rates and screening outcomes in specific populations. The project could also create new opportunities for benchmarking and population health analysis across participating institutions.

From Dr. Gorham’s perspective, “Cervical cancer screening guidelines in this country should rest on evidence that reflects every woman the guidelines are meant to serve.”

Ultimately, the goal is fewer women diagnosed with advanced cervical cancer, Dr. Gorham adds. “We know how to prevent this disease. The work is making sure access to preventive care reaches everyone.”

The laboratory’s role in shaping the future of screening

Although the initiative relies on advanced AI and NLP tools, Dr. Gorham stresses the importance of pathologists and laboratory professionals, who are “central to this project — without them, it does not happen.”

While AI may dominate healthcare headlines in abstract terms, this project represents a highly practical application grounded in pathology workflows and laboratory data.

3 Questions with Aadil Ahmed, MD, FASCP Team Critical Values - May 28, 2026

Medicine is not practiced on assumptions, and the realization that pathology provides the most objective and definitive evidence of disease in medicine is what drew Aadil Ahmed, MD, FASCP, to the field. To see how diseases evolve in real time under the microscope and through molecular testing, whether watching blast counts decrease after induction therapy, or seeing chimerism patterns shift in a transplant patient, is powerful to witness. It underlines the fact that pathology doesn’t just diagnose disease; it tracks the response to therapy, shapes prognosis, and guides critical decisions for both clinicians and patients.

Dr. Ahmed was also drawn in by the realization of how essential pathology is for documenting disease in a way that is recognized not only medically but also administratively. The requirements for insurance coverage, treatment authorization, and clinical eligibility decisions underscore the responsibility to how central pathology is to ensure patients receive the care they need.

Here, Dr. Ahmed shares his thoughts on his career in the laboratory.

What is something that has surprised you about working in the lab?

Every single step of processing a patient’s specimen is absolutely critical. From accessioning to grossing, embedding, sectioning, staining, and interpretation, each step forms a chain, and if even one link is weak or overlooked, it affects everything downstream. You might think a small deviation is inconsequential, but in pathology, even minor errors can compromise a diagnosis or delay the information clinicians rely on.

That’s why succeeding in this field requires more than technical skill; it requires genuine passion, attention to detail, and vigilance. People who truly care about the work are the ones who notice when something looks off, when a block feels unusual to cut, when a stain doesn’t appear quite right. This sense of ownership and pride in the process is what keeps the entire diagnostic pathway safe and reliable for patients. All of these steps also require that there is camaraderie among the staff. Everyone from the lab assistants to the histotechnologists to the pathologists plays a vital role.

The lab may seem quiet from the outside, but there is always a lot happening to ensure results are accurate and timely.

What is your favorite test to perform and why?

My favorite test to perform, if I can call it a test, is reviewing a good H&E stain. To me, H&E is the most powerful stain in all of pathology. It’s basic, it’s universal, and yet it delivers the greatest amount of information a tissue can offer. Call me old‑fashioned, but pathology is, at its core, a visual discipline.

Even in an era where we have impressive ancillary tools, immunohistochemistry panels, molecular assays, flow cytometry, sequencing, there are times when those studies yield non-diagnostic or inconclusive results. Everything starts with morphology, and while the fundamental patterns of diseases are consistent, the finer details are often subtly different. Those small deviations challenge you to slow down, and to appreciate nuances that no molecular test will point out for you. It’s in those details where the art and science of pathology truly meet.

How do you approach difficult cases, and collaborate and communicate with clinicians to maintain a strong sense of purpose and connection to the human side of healthcare?

I see challenging cases as important opportunities to reinforce that pathology does not function in isolation, even though, as a behind-the-scenes specialty, our role can sometimes be overlooked. In these situations, I’m not hesitant to pick up the phone and speak directly with the clinician to gather additional clinical context or discuss management considerations. Having a working understanding of treatment strategies is especially valuable here; it not only improves diagnostic precision but also demonstrates the broader clinical perspective we bring, which helps build trust with our clinicians over time.

At the same time, I’m intentional in how I communicate through my reports. I try to use clear, active language that reflects thoughtful interpretation, so it’s evident that there is a physician actively engaged in the diagnostic process. That approach helps me feel more connected to patient care, while also fostering a sense of collaboration and confidence among the clinicians who rely on our work.

The Diagnostic Bottleneck: Rethinking Patient Navigation in Global Oncology, Part II Kenneth Landgraf - May 26, 2026

In Part I of this two-part article, I discussed patient navigation in low- and middle-income countries, and the impact that can have on patient care and outcomes. Patient navigation can be critical to the continuity of care, but it’s important to understand how it can be implemented and the gaps that remain. Part II will look at this as well as lessons learned. Part I of this article can be found here.

Patient navigation in action

To understand how patient navigation functions in practice across LMIC settings, it is useful to examine real-world implementation efforts. Through the Coalition for Implementation Research in Global Oncology (CIRGO), an initiative administered by ASCP with the financial support of Bristol Myers Squibb, a series of grants were awarded to support diverse navigation-related projects across multiple countries in Sub-Saharan Africa. These initiatives, typically funded at approximately $50,000, tested a range of approaches adapted to local health system needs and constraints.

The projects illustrate the flexibility of navigation models. In Uganda, a navigation program integrated with Project ECHO connected frontline providers and navigators with oncology specialists, while also incorporating peer support to improve patient engagement and adherence to care. In Mozambique, a breast cancer database was paired with a navigation system to track patients from diagnosis through treatment, strengthening referral pathways and clinical decision-making. In Rwanda, a tablet-based electronic medical record enabled patient tracking and re-engagement, functioning as a digital navigation system even without that designation. Other models emphasized low-cost communication, as seen in Côte d’Ivoire, where clinical officers and patient advocates used WhatsApp to facilitate consultation and referral to oncologists.

Insights from CIRGO

Findings from a two-year follow-up survey we conducted of CIRGO grant recipients (initial findings presented in conference abstracts; manuscript in preparation) provide a practical view of how patient navigation is being implemented across LMIC settings, along with early signs of sustainability and system-level impact. Although the specific approaches differ, several consistent lessons emerge that are relevant for future program design and scale-up.

Navigation functions appear most effective when embedded within existing clinical workflows rather than introduced as standalone roles. Across settings, programs often build on existing structures, such as patient databases, communication platforms, or clinical coordination processes, to improve follow-up and continuity of care. This approach allows navigation to strengthen systems without requiring new administrative layers.

Across CIRGO projects, the most consistent impact is on follow-up and timeliness of care. Navigation approaches improve the ability to track patients across multiple steps, reduce delays between diagnosis and treatment, and support adherence to recommended care. As one project team noted, “Patient follow up continues and the interaction with the navigators continues even when patients return to the community.” These findings align with broader portfolio data that showed improvements in quality of care and patient access. The projects also highlight the role of digital tools as enablers of navigation. Electronic medical records, messaging platforms, and patient databases can strengthen tracking and communication, but their effectiveness depends on active follow-up by providers or navigators.

The data also suggest that navigation programs can be sustained beyond initial seed funding. The majority of CIRGO-supported projects continued after the grant period ended, with some integrated into routine operations or incorporated into national guidelines and programs. Several have been replicated or expanded. These findings demonstrate that relatively small, locally led investments can contribute to longer-term improvements in care delivery.

The remaining gaps: From pilots to systems

The experiences from CIRGO and similar efforts demonstrate that patient navigation can improve coordination, timeliness, and patient engagement. They also highlight the next set of challenges. Patient navigation remains inconsistently defined. Programs vary in scope, workforce, and level of integration within health systems, making it difficult to compare models or build a shared evidence base. Measurement is similarly fragmented. Although indicator sets exist, they are not widely applied, limiting the ability to identify where patients are lost or which interventions are most effective.

Another critical gap is the limited availability of cost and economic data. Many programs report improvements in efficiency and coordination, but few are able to quantify costs, savings, or return on investment. This lack of data makes it difficult for health systems and policymakers to justify sustained funding or to incorporate navigation into national cancer control strategies.

Finally, most navigation efforts remain small in scale. Moving from pilot programs to routine practice will require clearer approaches to financing, workforce development, and integration into national cancer control strategies. These gaps highlight the need for coordinated multi-organizational approaches that extend beyond the scope of individual programs.

The role of the Global Alliance for Cancer Patient Navigation

The Global Alliance for Cancer Patient Navigation provides a platform for this coordination. By bringing together organizations across countries and disciplines, it supports the translation of locally successful models into more consistent approaches to implementation. As Anu Agrawal, Head of Global Health at the American Cancer Society and Co-Chair of the Alliance, explains:

“We are at a tipping point in integrating patient navigation as a core component of patient-centered cancer care. The Global Alliance for Cancer Patient Navigation is building awareness and supporting the evidence base for patient navigation so that policymakers can move from identifying patient navigation as a useful tool to systematically and actionably incorporating it as a sustainable solution to help persons with cancer and their caregivers.”

By connecting existing frameworks and implementation efforts, the Alliance can help clarify shared principles of patient navigation while still allowing for local adaptation. The Alliance can also support the exchange of implementation experience across countries. As health systems consider how to incorporate navigation into routine care, they will require practical guidance, examples of sustainable models, and opportunities for shared learning. Through these functions, the Alliance can help move navigation from a collection of promising initiatives toward a more established component of cancer care delivery.

Why diagnostics matter: A critical opportunity for ASCP

Efforts to strengthen patient navigation must account for the central role of diagnostics in the cancer care continuum. In many LMIC settings, gaps at the diagnostic stage, including limited access to biomarker testing, frequent stock-outs, and communication breakdowns between laboratories and clinical teams, contribute directly to treatment delays and loss to follow-up. Strengthening specimen tracking, improving turnaround time, and ensuring that results are acted upon are areas where the application of navigation principles to the laboratory can directly improve continuity of care.

An additional dimension of navigation that remains underdeveloped is patient understanding of diagnostic information. Cancer diagnoses and biomarker results increasingly guide treatment decisions, yet many patients have limited access to clear explanations of what their results mean. Emerging models like Pathology Clinics demonstrate the value of direct communication between pathologists and patients. In one small study, 78 percent of respondents strongly agreed that they felt more empowered after seeing their disease through the microscope.2  While these models may not be easily scalable in all settings, they underscore an important principle: supporting patients in understanding their diagnosis can improve engagement in care and adherence to treatment.

Advancing patient navigation in global cancer care

The evidence from CIRGO and other global health efforts suggests that patient navigation in LMICs has reached an inflection point. The focus now shifts from demonstrating feasibility to integrating navigation into routine care in ways that are practical and sustainable.

For the pathology and laboratory medicine community, this transition represents an opportunity. Pathologists and laboratory professionals can help ensure that the diagnostic stage, often the most vulnerable point in the care pathway, is more effectively connected to treatment. This includes strengthening systems for specimen tracking, improving turnaround and communication of results, supporting appropriate use of biomarker testing, and ensuring that diagnostic information leads to timely clinical action.

Improving cancer outcomes in LMICs will depend in part on the ability of health systems to ensure that patients complete each step in care and understand the decisions that follow. Strengthening patient navigation, including its integration with diagnostics, offers a practical path forward. The next phase of progress will depend not only on moving patients through the system, but on ensuring that they are informed participants in their care.

The woman at the Tanzanian district clinic in Part One — with her suspicious mass and uncertain referral pathway — should never have been a vignette of failure. Whether her fine needle aspirate moves cleanly through transport, processing, reporting, and treatment is, in the end, a navigation question; and the laboratory is a central actor in answering it.