TBDx™ Study Presents the Cost Effectiveness Case for Automated Microscopy

Applied Visual Sciences, Inc.  (APVS.OB)

Today PLoS One (the Public Library of Science) releases the results of a TBDx™ study that models the cost effectiveness of combining TBDx™ with molecular diagnostic technologies, such as GeneXpert.  Entitled Cost Effectiveness of Automated Digital Microscopy for Diagnosis of Active Tuberculosis (1), the study has been authored by renowned experts in the field of tuberculosis and diagnostic technologies.

Study Phase One

This is the second study of a two-phased research effort. The first study, published by the American Journal of Respiratory and Clinical Care Management, presented the evaluation of the TBDx™ automated microscopy system in algorithms for the diagnosis of TB.

This first phase concluded:  “The TBDx™ system demonstrated potential as a useful triage tool, with GXP used to confirm intermediate results. This novel system could also potentially serve as a triage test for other emerging technologies, ensuring that these tools are efficiently used while maintaining good performance. As a stand-alone microscopy system, its performance was equivalent to that of a highly experienced TB microscopist, and its use has the potential to improve upon the existing diagnostic standard of care.”

 Study Phase Two

The purpose of this second phase has been to assess the cost effectiveness of TBDx™ as a triage technology, in highly burdened countries, particularly where molecular tests are too expensive for routine use. The study evaluated the costs and effectiveness of four approaches:

  1. sputum smear microscopy alone;
  2. TBDx™ alone;
  3. TBDx™ with confirmation of low positive results using molecular testing; and,
  4. TBDx™ with confirmation of ALL positive results using molecular testing.

Performance data were drawn from the first phase, and unit costs were obtained from existing scientific literature for sputum microscopy, GeneXpert, and TBDx™.  Overhead, utilities, quality assurance, training, shipping, import duties, maintenance, personnel, capital hardware and software licenses, and treatment costs were included in the overall evaluation.

Summary Findings Provided in the Report:

In both moderate (30 test / day) and high (100+ tests / day) volume laboratory settings the per-test cost of TBDx™ is approximately 33% of the cost of GeneXpert (Xpert MTB/RIF) (or 67% less than Xpert)

If TBDx™ is used as a triage technology, where Xpert confirms ONLY low positive cases, and all heavily burdened cases are automatically placed on treatment, 79% – 84% of Xpert positive cases could be diagnosed at 50%-60% of the cost of Xpert. This strategy has a favorable cost-effectiveness ratio of $1,280 per TB diagnosis, relative to manual smear microscopy performing at a 68% sensitivity rate. If manual sputum smears performance drops to 50% sensitivity (the performance of an average microscopist) the TBDx™ usage would lower the costs to $677 per TB diagnosis.

Use of TBDx™ as a triage tool would be a preferred strategy where resources are insufficient for universal Xpert testing, or where the “willingness to pay” falls within a cost ranging from $1,280 ($677 if smear microscopy performance averages 50%) and $1, 927.

Under most sensitivity analysis, the algorithm providing the most TB diagnosis per dollar spent was a TBDx™ triage test, followed by Xpert confirmation of low positive results, counting “Scanty 1” cases as negative.

Triage tests are intended to reduce costs, and provide a more favorable cost effectiveness ratio such that it is preferable to perform the triage test on the full population rather than the confirmatory test on part of it. This economic evaluation demonstrates precisely this result, specifically that automated digital microscopy can reduce the overall costs of diagnostic testing substantially, and be performed at a cost-effectiveness ratio that is generally favorable to that of universal Xpert.  As the data show, TBDx™ is particularly attractive in settings where manual microscopy cannot be performed with consistent quality.

By reducing the costs of Xpert MTB / RIF testing while still providing the majority of the benefits (in terms of TB diagnosis) automated digital microscopy has the potential to fill an important niche in the TB diagnostic landscape.

(1)  The study authors represent industry-leading universities and institutions who have played leadership roles in the evaluation and analysis of TB diagnostic technologies,. These include the Department of Epidemiology, The Johns Hopkins Bloomberg School of Public Health; The Center for Tuberculosis National Institute for Communicable Diseases in Johannesburg, South Africa; the Department of Microbiology at the University of Pretoria, Pretoria, South Africa; Aurum Institute in Johannesburg, South Africa; MRC Tropical Epidemiology Group, Department of Infectious Disease Epidemiology, London School of Hygiene and Tropical Medicine, London, UK; and, School of Public Health, University of the Witswatersrand, Johannesburg, South Africa.


Posted in Corporate, Healthcare, TB

TBDx™ Activities and Continuing Progress: A Quick Snapshot

Applied Visual Sciences, Inc. (APVS.OB)

Over the past several months TBDx has been engaged in evaluations in several countries or has been involved in the publication of those results. Here is a quick update:

  • Appearing in the same publication is an editorial entitled, Automated Digital Microscopy in New Tuberculosis Diagnostic Algorithms: Can it Boost Case Finding? Jose A. Caminero and Dr. Giovanni Battista Migliori authored the article.  Dr. Caminero is affiliated with Dr. Negrin University Hospital of Gran Canaria in Las Palmas, Spain and with the Multi-Drug Resistant Tuberculosis Unit of the International Union Against Tuberculosis and Lung Disease (IUTLD). Dr. Migliori is affiliated with the World Health Organization in Tradate, Italy.  The editorial, while complementary of the study and of the digital imaging technology, acknowledges that TBDx could be a “bridging” technology until such time as molecular tests are more affordable and more prevalent in the healthcare systems.

We agree with the authors that TBDx may represent a bridging technology. As technologists we see and actively participate in this disruptive process daily, and we realize that all technology eventually is displaced by newer, more innovative technology.  In that regard, molecular testing also can be considered a bridging technology to the next wave of future innovation that we see emerging in laser technologies and photonics.  The real challenge for all technology companies, ours included, is to accurately understand the pace of this anticipated replacement, something that is largely influenced by both price and performance considerations. Computer-vision software development and image analysis technology has a decided advantage in its cost structure, which greatly influences the price of the technology.  It is easy to see the day when a TB test will be a fraction of a dollar.

Today the world of infectious diseases demands more affordable, more mobile, more responsive technologies that perform as triage to the more expensive molecular testing. In a scenario of limited global funding availability, the use of a computer-vision-based technology to weed out negative cases, with a high rate of predictive value, and focus the more expensive molecular testing on only those cases of potential disease will provide the highest sensitivity and specificity at the lowest overall cost of diagnosis, today. We see computer-vision technology working in cooperation with molecular tests rather than two technologies competing against each other.

As computer-vision technologies get better and better, with modest refinements in the software, the detection performance of TBDx will draw closer to that of molecular tests, putting downward pressures on the price of both technologies.  Combined with the miniaturization of hardware platforms, such as mobile phones and tablets, our TBDx diagnostic platform will quickly evolve into an even less expensive miniature-imaging platform capable of diagnosing a dozen or more infectious diseases, each detection application employing computer-vision technology similar to that of IBM’s Watson.

  • In the South Africa evaluation one important study element that required additional analysis was the economic impact of using TBDx as a triage tool. This analysis has been under the direction of Dr. David Dowdy of the Bloomberg School of Public Health at Johns Hopkins University.  An economic model has been developed and the results are expected to be presented in first draft later this month.
  • Data accumulation and the study evaluation in Nigeria has been completed. Dr. Luis Cuevas of the Liverpool School of Tropical Medicine, along with his colleagues, have drafted the outline of the initial version of the report, and it is anticipated that they will complete final drafting later this month.
  • The FIND-sponsored evaluations in Peru and Vietnam have been completed. Though not all of the culture results are known yet, making the final results incomplete, we have received the preliminary findings and have observed the following:
  • As discussed in previous blogs, both Peru and Vietnam evaluated TBDx using concentrated and direct smear slides. TBDx performance in Peru, irrespective of the smear preparation method, demonstrated similar performance to that of South Africa. In Vietnam the concentrated smear results were only marginally lower than South Africa, however the direct smear results are approximately 18 basis points lower.  The lower sensitivity was not unexpected as the quality of smears has a direct impact on the quality of the images captured.  Direct smears have more topological variation than concentrated smears and result in more objects being out of focus.
  • Early analysis of the Vietnam cases missed by TBDx indicate that some cases classified incorrectly as TB Negative, in fact, included TB bacilli. However, the captured image was too blurred to facilitate the proper segmentation and classification of the case. Anticipating that we might encounter focus difficulties due to the nature of the direct smears, we had already developed an “image stacking” function to address this issue. The stacking function may have had minimal impact in Peru, but would most likely have produced improved performance in Vietnam.  We elected not to deploy the stacking functionality so as to better assess the performance capabilities and limitations of TBDx.
  • FIND hopes to complete a full analysis of both sites by the end of this month, at which time a go-forward strategy to achieve FDA acceptance will be determined.

All of these studies, and resulting data, represent a steady movement towards international classification of digital sputum microscopy as an acceptable alternative to routine smear microscopy and as a possible triage tool that either screens in or screens out the possibility of suspected TB.

Applied Visual Sciences, Inc. is a computer-vision software technology company publicly-traded on the OTC Bulletin Board under the trading symbol, APVS.  The company has developed intelligent, next-generation imaging analytics and informatics technologies for the extraction, analysis, and detection of objects-of-interest within any digital image format (still or video).

Posted in Corporate, Healthcare, TB | Tagged , , , , , , , , , , , , ,

APVS Research Indicates that BCDx™ Breast Cancer Detection Technology Routinely Diagnoses Ductal Carcinoma In Situ

Applied Visual Sciences, Inc. (APVS.OB)

“I share this to educate others that a second opinion is critical to your health. You have nothing to lose if both opinions match up for the good, and everything to gain if something that was missed is found, which does happen. Early diagnosis is key.” – Rita Wilson, wife of Tom Hanks

About 1 in 8 (12%) women in the US will develop invasive breast cancer during their lifetime. The American Cancer Society estimates about 231,840 new cases of invasive breast cancer will be diagnosed in 2015.

Breast cancer can be separated into different types based on the way the cancer cells look under the microscope. Most breast cancers are carcinomas, a type of cancer that starts in the cells. In fact, breast cancers are most often a type of carcinoma called adenocarcinoma, which is carcinoma that starts in glandular tissue. Other types of cancers can occur in the breast, too, such as sarcomas, which start in the cells of muscle, fat, or connective tissue.

Ductal carcinoma in situ (DCIS) is considered non-invasive or pre-invasive breast cancer. DCIS means that cells that line the ducts have changed to look like cancer cells. The difference between DCIS and invasive cancer is that the cells have not invaded through the walls of the ducts into the surrounding breast tissue. Because it hasn’t invaded, DCIS can’t spread (metastasize) outside the breast. DCIS is considered a pre-cancer because some cases can go on to become invasive cancers. About 1 in 5 new breast cancer cases will be DCIS. Nearly all women diagnosed at this early stage of breast cancer can be cured.

Invasive ductal carcinoma (IDC) is the most common type of breast cancer. IDC starts in a milk duct of the breast, breaks through the wall of the duct, and grows into the fatty tissue of the breast. At this point, it may be able to metastasize to other parts of the body through the lymphatic system and bloodstream. About 8 of 10 invasive breast cancers are infiltrating ductal carcinomas.

Invasive lobular carcinoma (ILC) starts in the milk-producing glands (lobules). Like IDC, it can metastasize to other parts of the body. About 1 in 10 invasive breast cancers is an ILC. Invasive lobular carcinoma may be harder to detect by a mammogram than invasive ductal carcinoma.

On Tuesday, Tom Hanks’ wife Rita Wilson announced that she had been diagnosed with invasive lobular breast cancer and had undergone a bilateral mastectomy and breast reconstruction. In her published statement she explained that her first test for cancer came back negative (including 2 negative biopsies), but that she was correctly diagnosed after seeking a second opinion. Before the diagnosis, she had vigilantly monitored her health with mammograms and MRIs because she knew she had an underlying condition of lobular carcinoma in situ.

Ms. Wilson’s profound statements about the need for a second opinion supports the strategic positioning of our breast cancer detection product, BCDx™, which we believe delivers a critical second look at the original generated mammogram, in ways never before seen by radiologists.  Using BCDx™, the mammogram can be processed using sophisticated, proprietary image processing algorithms to generate enhanced observations of the underlying breast tissue.  The sensitivity of the algorithms exposes the subtle changes that occur at the cellular level, thereby rendering conditions such as Atypical Hyperplasia and DCIS visible to the human eye. Additional quantitative data supports the visual presentation.  BCDx™ delivers information that is not otherwise available to the decision-making process. Information is knowledge, and knowledge leads to more intelligent and confident decisions, which in turn leads to better patient outcomes. The earlier the diagnosis, the better the prognosis.

We recently received a breast cancer case that exhibits characteristics similar to the progression of breast cancer in the Rita Wilson case. The woman’s cancer was diagnosed in 2014 (supported by both mammography and MRI results), and from our analysis originated from DCIS in 2010, the earliest images available for our analysis.  We appreciate and thank this woman for her contribution to our technology and to future generations of woman for whom access to earlier detection will be a reality.

We processed each year of mammograms using the most current version of  BCDx™, which includes newly developed imaging processes created for high sensitivity to the presence of DCIS, and an additional precancerous condition known as Atypical Hyperplasia. Our examination began with the 2014 mammographic confirmation of breast cancer.   The red arrows indicate the locations identified by the radiologist. We then correlated BCDx™ results with these known cancer-confirmed locations. (Click on any image to view in larger format)

2014_L CC_0002_Orig_1K_arrows

2014_L CC_0002_color_1K_arrows

The image on the left represents the application of the BCDx™ Color Mapping algorithm.  Areas appearing as islands, outlined in green, display the structure and growth pattern of the cancer, and match identically to those areas indicated as cancer by the radiologist.  This pattern consistently presents whenever cancer is present, whether as cells growing in a Petri dish, in a mammogram, or an MRI. 2014_L CC_0002_AOI_1K_arrows

Using the M Intensity algorithm, the image on the right visually isolates the cancer structures and the penetration of the cancer through the duct walls into the healthy breast tissue.

We continued to process her prior year’s mammograms to determine the earliest cancer onset that could be detected. In each year prior to 2014, our algorithms indicated the presence of cancer

While breast cancer was detected by BCDx™ in both breasts, in each of the years from 2010 to 2014, the condition known as DCIS was detected in 2010 in her left breast mammogram. Areas of cells lining one area of her ducts had become cancerous, but were contained within the duct and had not invaded into the surrounding healthy breast tissue. The image below was reviewed by her radiologist and the DCIS was overlooked.  2010_L_MLO_Mammogram_E38_Original

2010_L_MLO_Mammogram_E38_Color arrows

2010_L_MLO_Mammogram_E38_AOI arrowsThe Color Mapped image to the right and the M Intensity image to the left clearly indicate
the existence of abnormal cells within the breast ducts.  Arrows point to locations (corresponding to the radiologist findings of cancer in the 2014 mammogram) where the green  “islands of cancer” indicate the presence of DCIS. Note the narrowness of the islands, an indication that the cancer had been contained within the ductal walls.2011_L_MLO_mammogram_687D_color arrows

The image to the right is the 2011 mammogram processed using the Color Mapping algorithm. Note the progression of the cancer contained within the circled area.  The cells are beginning to penetrate the ducts and invade healthy breast tissue.

Numerous radiologists and clinicians have indicated that the ability to identify the presence of DCIS and Atypical Hyperplasia in standard 2D mammograms provides the earliest detection of breast cancer in radiology, regardless of the imaging modality employed, including those of 3D Tomosynthesis, ultrasound, and MRI scans.

As we have requested in previous blogs, if you have been diagnosed with breast cancer (or your breast studies have been inconclusive) and you would like to contribute to our research and the potential for earlier diagnosis of breast cancer, please forward a CD of your breast study images (the more years the better):

Applied Visual Sciences, Inc.  –  C/O Thomas Ramsay  –  525K East Market Street  –  #116  –  Leesburg, VA  20176

Your information will be held in strictest confidence.

Posted in Breast Cancer, Corporate, Healthcare, Mammography | Tagged , , , , , , , , ,

South Africa Evaluation Manuscript Officially Accepted for Publication by AJRCCM

This morning Dr. Nazir Ismail, Director of the Center for Tuberculosis in Johannesburg, received word from the editor of the American Journal of Respiratory and Critical Care Medicine (AJRCCM) accepting the article that presents the analysis of the TBDx™ evaluation in South Africa. The email he received is reprinted below (in part):

Dear Dr. Ismail:
Congratulations! We are pleased to inform you that your manuscript
"Performance of a Novel Algorithm Using Automated Digital 
Microscopy for Diagnosing Tuberculosis" has now been officially 
accepted for publication in the American Journal of Respiratory 
and Critical Care Medicine (AJRCCM).

Your paper will be published online within 48 hours before it has
been copy edited, proofed, or typeset. It will appear in the 
Articles in Press section of the AJRCCM website 

AJRCCM Articles in Press establish publication priority and can 
be cited and searched. The official publication date appears below
the title followed by the Digital Object Identifier (DOI), an 
automatically generated identifier unique for intellectual 
property in the digital environment. 

Jadwiga A. Wedzicha, MD
American Journal of Respiratory and Critical Care Medicine

Indeed, the article is available online now. Subscribers have online access and can download the article. Non-subscribers have access to the Abstract and can purchase the full article for a fee.

We would like to extend our congratulations and our sincere thanks to the team of authors and investigators who have dedicated their personal and professional time to evaluate our TBDx™ technology. The list of authors as they will appear in the article include:

Dr. Nazir A. Ismail,
Dr. Shaheed V. Omar
Dr. James J. Lewis
Dr. David W. Dowdy
Dr. Andries W. Dreyer
Hermina van der Meulan
George Nconjana
Dr. David A. Clark
Dr. Gavin J. Churchyard

The authors represent the renown institutions of the National Institute of Communicable Diseases in South Africa, the University of Pretoria in South Africa, the London School of Hygiene and Tropical Medicine in the United Kingdom, the Bloomberg School of Public Health at John Hopkins University in the USA, the University of Witwatersrand in South Africa, the Aurum Institute in South Africa, and the School of Public Health at the University of Witwatersrand in South Africa.

Posted in Healthcare, TB | Tagged , , , , , , , , , , , , | 1 Comment

TBDx™ Evaluations Ready for Journal Publication and Nearing Completion

Applied Visual Sciences, Inc. (APVS.OB) – March 30, 2015 – Leesburg, Virginia

As is true with the introduction of any new TB diagnostic technology today, gathering scientific evidence of its routine performance is a necessary step towards endorsement and acceptance within a healthcare system. Oftentimes these data are gathered from evaluations conducted by interested health care systems or through the collective work of independent scientific organizations.

These evaluations not only follow strict procedural protocols, but also the results are subjected to unbiased scrutiny from industry experts, and often lead to peer-reviewed scientific publications. Evaluations advise prospective users on the performance characteristics of the technology, guide how best to use the technology within their laboratory process, and provide the technology developer with insights into performance and operational characteristics.

For the past few years TBDx™ has been a part of several technology evaluations. Three such evaluations have been completed, and two evaluations are nearing completion. We thought our readers would welcome an update on our progress.

South Africa

Two evaluations have been completed by the Center for Tuberculosis. In 2011 a “proof of concept” evaluation led to the conclusion that TBDx’s™ automated sputum microscopy could be a viable alternative to routine smear microscopy. With improvements in the algorithm, TBDx™ could be used as a stand-alone diagnostic, or could perform in tandem with another diagnostic test. PLOS ONE, the Public Library of Science, an open access peer-reviewed scientific journal, published these results.

In 2013 the evaluation focused on the potential of TBDx™ to be used as a triage or “rule-out” TB test where positive cases could be confirmed by a more specific diagnostic test. A high-level presentation of the 2013 evaluation results was described during the 2013 Union World Conference on Lung Health.

The team of industry-leading evaluators have organized the final results of this recent evaluation into a manuscript and submitted it for publication to the American Journal of Respiratory and Critical Care Medicine (AJRCCM). The working title of the manuscript is Performance of a novel algorithm using automated digital microscopy for diagnosing tuberculosis. The twice-monthly AJRCCM is a peer-reviewed medical journal of the American Thoracic Society. The manuscript has been reviewed and is likely to be accepted for publication following the modest edits that were requested. According to the AJRCCM website “officially accepted articles are posted within 48 hours; print versions are posted within 2 months.”.

This second published evaluation continues our effort to present clear and convincing scientific evidence of the performance characteristics of the technology. A follow-on article is expected later this summer when the current authors present an analysis of the economic impact of TBDx™ as a sole diagnostic test, and as a “rule-out” triage test where TBDx™ positive cases are confirmed by GeneXpert.


Under the direction of the Liverpool School of Tropical Medicine, the National and FCT Tuberculosis and Leprosy Control Programs, and the Zankli Medical Center in Abuja, the preliminary performance analysis was presented last October during the 2014 Union World Conference on Lung Health. TBDx™ slide processing completed prior to the end of the year; however, the corresponding culture tests were not finalized until last month. The complete results are now under review by the primary investigators and we are told that a review of these data should be available at the end of March, or the early part of April. The intent is to submit the evaluation results to a scientific journal for peer review and publication, likely in May.

Based upon the interim results, we anticipate the performance results will be similar to the performance of a highly experienced laboratory microscopist, though not as high as results from South Africa. This is the first time TBDx™ has evaluated direct sputum smears, and industry research evidence shows that detection rates are lower in direct smears than their concentrated sputum smear counterparts (such as what was used in South Africa). Additionally, TBDx™ processed one slide while the microscopist examined two. The published research comparing the detection rates when using one or two slides always shows that detection rates are higher using two slides.

Peru and Vietnam

Last Spring we entered into a Cooperation Agreement with the Foundation for Innovative New Diagnostics (FIND). FIND is well regarded as an objective evaluator of new diagnostic technologies. In exchange for providing our TBDx™ technology to the evaluation sites, FIND agreed to develop the necessary study protocols and test TBDx™ using their laboratory network of approved hospitals and clinics. Evaluations were scheduled for Lima, Peru and Ho Chi Minh City, Vietnam. The intent of the evaluations has been to measure the performance of the technology and learn more about its operational characteristics. Most importantly, it represented an evaluation that included both direct and concentrated sputum smears, hoping to identify and measure any performance differences between the two smear types.

TBDx™ processing has been completed in Lima. The culture tests have been completed and the data are being collected and analyzed by the FIND staff, for each type of smear. All results will be compared against culture, the gold standard, and each case seen by TBDx™ will have a corresponding molecular test, and a routine microscopy read.

Today, TBDx™ is processing cases in Ho Chi Minh City and should finish in the first week or two in April. The results can be tabulated and compared quickly as the culture tests for each specimen have been completed. Both evaluations use exactly the same testing protocol so all results will be compared against culture, and will include direct and concentrated smears, and routine microscopy and molecular testing.

It is our understanding that FIND intends to complete all of the analysis for internal presentation in May.

Final Comments

In the weeks ahead we will release additional performance results as they become publicly available. Each of these evaluations are independent of the company. We provide the technology, but the study, it’s funding and the data with all of its written analyses, belong to the sponsoring organizations or to the journal publisher. For example, we have known the details behind the South Africa evaluation, but have only released what has been made available to the public so far. When the published article appears, and is posted on the blog, you will see a great deal more details and you may notice that APVS is not among the cited authors, appropriately so.

We genuinely appreciate your patience with the process. These efforts involve talented and dedicated scientists at work, focused on the fair and accurate evaluation of new diagnostic technologies that may lead to earlier disease detection and better health outcomes. Truly the emphasis always remains on precise and accurate analysis.

Posted in Corporate, Healthcare, TB | Tagged , , , , , , , , ,