SurfaceSlide: a multitouch digital pathology platform

Evaluation of a new technique using artificial intelligence for quantification of plasma cells on CD138 immunohistochemistry

INTRODUCTION

The diagnosis of plasma cell neoplasms depends on the accurate quantification of plasma cells, traditionally done by immunohistochemical CD138 staining of bone marrow biopsies. Currently, there is no fully satisfactory reference method for this quantification. In our previous study, we compared the commonly used overview estimation method (method A) with a novel method for counting plasma cells in three representative areas (method B). Results showed comparable concordance parameters between the two methods. In this follow-up study, we compared the previously evaluated methods with a digital analysis method (method C) that uses artificial intelligence in open-source software, QuPath.

METHODS

Archived CD138 immunohistochemically stained trephine sections of bone marrow samples used in our previous study were used (n = 33). Reviewers selected three representative areas on each sample by taking images with a light microscope and camera. Digital analysis was performed using the positive cell detection function in QuPath. The entire process was repeated by each reviewer to test intraobserver concordance (concordance correlation coefficient [CCC]) in addition to interobserver concordance (intraclass correlation coefficient [ICC]).

RESULTS

Intraobserver concordance of method C showed strong agreement for all reviewers with the lowest CCC = 0.854. Interobserver concordance for method C using ICC was 0.909 and 0.949. This showed high interobserver agreement with significant differences between method C and previously assessed method A (ICC = 0.793 and 0.713) and method B (ICC = 0.657 and 0.658).

CONCLUSION

We were able to successfully count CD138-positive plasma cells in bone marrow biopsies using artificial intelligence. This method is superior to both manual counting and overview estimation, regardless of tumour load.

Classification of breast tumors by using a novel approach based on deep learning methods and feature selection

PURPOSE

Cancer is one of the most insidious diseases that the most important factor in overcoming the cancer is early diagnosis and detection. The histo-pathological images are used to determine whether the tissue is cancerous and the type of cancer. As the result of examination on tissue images by the expert personnel, the cancer type, and stage of the tissue can be determined. However, this situation can cause both time and energy loss as well as personnel-related inspection errors. By the increased usage of computer-based decision methods in the last decades, it would be more efficient and accurate to detect and classify the cancerous tissues with computer-aided systems.

METHODS

As classical image processing methods were used for cancer-type detection in early studies, advanced deep learning methods based on recurrent neural networks and convolutional neural networks have been used more recently. In this paper, popular deep learning methods such as ResNet-50, GoogLeNet, InceptionV3, and MobilNetV2 are employed by implementing novel feature selection method in order to classify cancer type on a local binary class dataset and multi-class BACH dataset.

RESULTS

The classification performance of the proposed feature selection implemented deep learning methods follows as for the local binary class dataset 98.89% and 92.17% for BACH dataset which is much better than most of the obtained results in literature.

CONCLUSION

The obtained findings on both datasets indicates that the proposed methods can detect and classify the cancerous type of a tissue with high accuracy and efficiency.

Comparison of muscle activity while using different input devices in digital pathology

INTRODUCTION

The high prevalence of musculoskeletal disorders in pathologists, together with the current trend towards the digitization of pathology, prompted us to study the different types of input devices employed during the revision of whole slide images, in order to investigate the pattern and extent of muscle activity involved in their use.

MATERIAL AND METHODS

A comparative study was made of 10 input devices (conventional and vertical mouse, three trackballs, the Ergopointer™, the Rollermouse™, an optical pen mouse, a touchpad, and the Leap Motion™). Six medical students performed a standardized circuit using a Fitts' Law based tissue array, digitized. The electrical activity of seven upper limb muscles (adductor pollicis, extensor pollicis longus, extensor digitorum, flexor digitorum, middle deltoid, upper trapezius, and middle trapezius) was measured using surface electromyography.

RESULTS

Statistically significant differences in the overall electrical activity among the different input devices, both absolute values in mV as well as normalized values to the upper limb at rest, were observed (p<0.001); the Rollermouse™ (0.1027mV; 139%), Logitech M570 trackball (0.1053mV; 145%), Ergopointer™ (0.1151mV; 167%), conventional mouse (0.1251mV; 191%), and vertical mouse (0.1312mV; 205%) required less activity, while the optical pen mouse (0.1717mV; 299%), Leap Motion™ (0.1803mV; 319%), Expert Mouse trackball (0.1845mV; 329%), EIGIIS trackball (0.2442mV; 468%) and the touchpad (0.2560mV; 496%) required greater muscle mobilization.

CONCLUSION

We designed a system based on Fitts' Law to compare input devices in digital pathology. Variability between compared devices and muscle activity was found. Long-term use could result in different muscular fatigue patterns. Even though the selection of an input device is a matter of personal preference, its impact on ergonomics should be considered.

Whole Slide Imaging (WSI) in Pathology: Current Perspectives and Future Directions

Whole slide imaging (WSI), ever since its first introduction about two decades ago, has been validated for a number of applications in the field of pathology. The recent approval of US FDA to a WSI system for use in primary surgical pathology diagnosis has opened avenues for wider acceptance and application of this technology in routine practice. The ongoing technological advances in digital scanners, image visualization methods, and the integration of artificial intelligence-derived algorithms with these systems provide opportunities of its newer applications. Its benefits are innumerable such as ease of access through internet, avoidance of physical storage space, and no risk of deterioration of staining quality or breakage of slides to name a few. Various barriers such as the high cost, technical glitches, and professional hesitation to adopt a new technology have hindered its use in pathology. This review article summarizes the technical aspects of WSI, its applications in diagnostic pathology, training, and research along with future perspectives. It highlights the benefits, limitations, and challenges delaying the use of this technology in routine practice. The review is targeted at students, residents, and budding pathologists to better acquaint them with the key aspects of state-of-the-art technology and enable them to implement WSI judiciously.

Head-tracking as an interface device for image control in digital pathology: a comparative study

BACKGROUND

Inasmuch as the conventional mouse is not an ideal input device for digital pathology, the aim of this study was to evaluate alternative systems with the goal of identifying a natural user interface (NUI) for controlling whole slide images (WSI).

DESIGN

Four pathologists evaluated three webcam-based, head-tracking mouse emulators: Enable Viacam (eViacam, CREA Software), Nouse (JLG Health Solutions Inc), and Camera Mouse (CM Solutions Inc). Twenty WSI dermatopathological cases were randomly selected and examined with Image Viewer (Ventana, AZ, USA). The NASA-TLX was used to rate the perceived workload of using these systems and time was recorded. In addition, a satisfaction survey was used.

RESULTS

The mean total time needed for diagnosis with Camera Mouse, eViacam, and Nouse was 18'57", 19'37" and 22'32", respectively (57/59/68seconds per case, respectively). The NASA-TLX workload score, where lower scores are better, was 42.1 for eViacam, 53.3 for Nouse and 60.62 for Camera Mouse. This correlated with the pathologists' degree of satisfaction on a scale of 1-5: 3.4 for eViacam, 3 for Nouse, and 2 for Camera Mouse (p<0.05).

CONCLUSIONS

Head-tracking systems enable pathologists to control the computer cursor and virtual slides without their hands using only a webcam as an input device. - Of the three software solutions examined, eViacam seems to be the best of those evaluated in this study, followed by Nouse and, finally, Camera Mouse. - Further studies integrating other systems should be performed in conjunction with software developments to identify the ideal device for digital pathology.

[The application of the Multi-Touch pad for the evaluation of the fine motor activity of the wrist]

AIM

The objective of the present study was to elaborate the method for the evaluation of the fine motor activity of the wrist in the patients presenting with wrist movement disorders resulting from central hemiparesis and to demonstratee the reliability of such method through the calculation of the standard error of measurements and minimal the detectable change (MDC95%).

MATERIAL AND METHODS

The study population was comprised of 42 patients who had undergone ischaemic stroke and suffered from the impairment of the upper limb functions . The deficit of the fine motor skills was estimated with the use of the original multi-touch diagnostic technique. The results of the assessment were compared with those of the measurement of upper limb motor activity based on the validated scales, such as the Fugl-Meyer Assessment (FMA) scale and the Nine Hole Peg Test (PHT).

RESULTS

The study with the application of the multi-touch method for diagnostics of the fine motor skills has demonstrated the high internal consistency of the measurements, with the Cronbach's Alpha Reliability Coefficient amounting to 0.98. The re-test reliability was high, with the ICC=0.98 (95% CI 0.97-0.99). The Spearman rank-order correlation with the locomotion scale estimates gave evidence of the good associative links, with the Fugl-Meyer Assessment scale correlation coefficient making 0.55-0.66 and the Nine Hole Peg Test findings being -0.7. The Minimal Detectable Change (MDC95%) for the multi-touch method was found to be 12.67%.

CONCLUSION

The objective diagnostics of the fine motor skill disturbances with the use of the original multi-touch method has demonstrated its high reliability and a high degree of correlation with the estimates obtained with the application of the modern validated scales in the patients who had undergone ischaemic stroke. Therefore, this method can be recommended for clinical use.

Performance of residents using digital images versus glass slides on certification examination in anatomical pathology: a mixed methods pilot study

BACKGROUND

It is anticipated that many licensing examination centres for pathology will begin fully digitizing the certification examinations. The objective of our study was to test the feasibility of a fully digital examination and to assess the needs, concerns and expectations of pathology residents in moving from a glass slide-based examination to a fully digital examination.

METHODS

We conducted a mixed methods study that compared, after randomization, the performance of senior residents (postgraduate years 4 and 5) in 7 accredited anatomical pathology training programs across Canada on a pathology examination using either glass slides or digital whole-slide scanned images of the slides. The pilot examination was followed by a post-test survey. In addition, pathology residents from all levels of training were invited to participate in an online survey.

RESULTS

A total of 100 residents participated in the pilot examination; 49 were given glass slides instead of digital images. We found no significant difference in examination results between the 2 groups of residents (estimated marginal mean 8.23/12, 95% confidence interval [CI] 7.72-8.87, for glass slides; 7.84/12, 95% CI 7.28-8.41, for digital slides). In the post-test survey, most of the respondents expressed concerns with the digital examination, including slowly functioning software, blurring and poor detail of images, particularly nuclear features. All of the respondents of the general survey (n = 179) agreed that additional training was required if the examination were to become fully digital.

INTERPRETATION

Although the performance of residents completing pathology examinations with glass slides was comparable to that of residents using digital images, our study showed that residents were not comfortable with the digital technology, especially given their current level of exposure to it. Additional training may be needed before implementing a fully digital examination, with consideration for a gradual transition.

Whole slide image cytometry: a novel method to detect abnormal DNA content in Barrett's esophagus

Barrett's esophagus (BE) is a precursor of esophageal adenocarcinoma (EAC). Both low-grade dysplasia (LGD) and high-grade dysplasia (HGD) are associated with an increased risk of progression to EAC. However, histological interpretation and grading of dysplasia (particularly LGD) is subjective and poorly reproducible. This study has combined whole slide imaging with DNA image cytometry to provide a novel method for the detection of abnormal DNA content through image analysis of tissue sections. A total of 20 cases were evaluated, including 8 negative for dysplasia (NFD), 6 LGD, and 6 HGD. Feulgen-stained esophageal sections were scanned in their entirety. Barrett's mucosa was interactively chosen for automatic nuclei segmentation where irrelevant cell types were ignored. The combined DNA content histogram for all nuclei within selected image regions was then obtained. In addition, three histogram measurements were computed, including xER-5C, 2cDI, and DNA-MG. Visual evaluation suggested the shape of DNA content histograms from NFD, LGD, and HGD cases exhibiting identifiable differences. The histogram measurements, xER-5C, 2cDI, and DNA-MG, were shown to be effective in differentiating metaplastic from dysplastic cases with statistical significance. Moreover, they also successfully separated NFD, LGD, and HGD patients with statistical significance. Whole slide image cytometry is a novel and effective method for the detection of abnormal DNA content in BE. Compared with histological review, it is more objective. Compared with flow cytometry and cytology-preparation image cytometry, it is low cost, simple to use, only requires a single 1 μm section, and facilitates selection of tissue and topographical correlation. Whole slide image cytometry can detect differences in DNA content between NFD, LGD, and HGD patients in this cross-sectional study. Abnormal DNA content detection by whole slide image cytometry is a promising biomarker of progression that could affect future diagnostics in BE.

Whole slide images for primary diagnostics of urinary system pathology: a feasibility study

INTRODUCTION

During the last decade, whole slide images (WSI) have been used in many areas of pathology such as teaching, research, digital archiving, teleconsultation and quality assurance testing. However, WSI have as yet not much been used for upfront diagnostics because of the lack of validation studies.

OBJECTIVES

The aim of this study was to test the feasibility of WSI for primary diagnosis of urinary tract pathology.

MATERIALS AND METHODS

100 consecutive urinary tract biopsies and resections which had been diagnosed conventionally between the years 2008-2009 were scanned at 20× magnification, and rediagnosed by two pathologists on WSI, having the original clinical information available, but blinded to the original diagnoses. Original and WSI diagnoses were compared and classified as concordant, slightly discordant (without clinical consequences) and discordant.

RESULTS

Original and WSI based rediagnosis were concordant in 87% of the cases. Original and WSI diagnosis were slightly discordant in 8% of cases. Major discrepancies with clinical or prognostic implications were founded in only 5 cases. However, for 6 out of the 13 discrepancies, WSI based diagnoses were considered to be better than the original diagnoses.

CONCLUSION

Primary diagnostics of urinary tract specimens can be reliably done on WSI. Further improvements of image resolution may help to increase diagnostic accuracy and WSI acceptance in routine pathology.

Screening and dotting virtual slides: A new challenge for cytotechnologists

Digital images are increasingly being used in cytopathology. Whole-slide imaging (WSI) is a digital imaging modality that uses computerized technology to scan and convert entire cytology glass slides into digital images that can be viewed on a digital display using the image viewer software. Digital image acquisition of cytology glass slides has improved significantly over the years due to the use of liquid-based preparations and advances in WSI scanning technology such as automatic multipoint pre-scan focus technology or z-stack scanning technology. Screening cytotechnologists are responsible for every cell that is present on an imaged slide. One of the challenges users have to overcome is to establish a technique to review systematically the entire imaged slide and to dot selected abnormal or significant findings. The scope of this article is to review the current user interface technology available for virtual slide navigation when screening digital slides in cytology. WSI scanner vendors provide tools, built into the image viewer software that allow for a more systematic navigation of the virtual slides, such as auto-panning, keyboard-controlled slide navigation and track map. Annotation tools can improve communication between the screener and the final reviewer or can be used for education. The tracking functionality allows recording of the WSI navigation process and provides a mechanism for confirmation of slide coverage by the screening cytotechnologist as well as a useful tool for quality assurance. As the WSI technology matures, additional features and tools to support navigation of a cytology virtual slide are anticipated.

Virtual microscopy and digital pathology in training and education

Traditionally, education and training in pathology has been delivered using textbooks, glass slides and conventional microscopy. Over the last two decades, the number of web-based pathology resources has expanded dramatically with centralized pathological resources being delivered to many students simultaneously. Recently, whole slide imaging technology allows glass slides to be scanned and viewed on a computer screen via dedicated software. This technology is referred to as virtual microscopy and has created enormous opportunities in pathological training and education. Students are able to learn key histopathological skills, e.g. to identify areas of diagnostic relevance from an entire slide, via a web-based computer environment. Students no longer need to be in the same room as the slides. New human-computer interfaces are also being developed using more natural touch technology to enhance the manipulation of digitized slides. Several major initiatives are also underway introducing online competency and diagnostic decision analysis using virtual microscopy and have important future roles in accreditation and recertification. Finally, researchers are investigating how pathological decision-making is achieved using virtual microscopy and modern eye-tracking devices. Virtual microscopy and digital pathology will continue to improve how pathology training and education is delivered.